First Comm
This commit is contained in:
parent
51b0446d22
commit
3437822c54
1
.gitattributes
vendored
Normal file
1
.gitattributes
vendored
Normal file
@ -0,0 +1 @@
|
||||
* text=crlf
|
||||
278
.gitignore
vendored
Normal file
278
.gitignore
vendored
Normal file
@ -0,0 +1,278 @@
|
||||
|
||||
# Created by https://www.toptal.com/developers/gitignore/api/python,pycharm+all
|
||||
# Edit at https://www.toptal.com/developers/gitignore?templates=python,pycharm+all
|
||||
|
||||
### PyCharm+all ###
|
||||
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
|
||||
# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
|
||||
|
||||
# User-specific stuff
|
||||
.idea/**/workspace.xml
|
||||
.idea/**/tasks.xml
|
||||
.idea/**/usage.statistics.xml
|
||||
.idea/**/dictionaries
|
||||
.idea/**/shelf
|
||||
|
||||
# AWS User-specific
|
||||
.idea/**/aws.xml
|
||||
|
||||
# Generated files
|
||||
.idea/**/contentModel.xml
|
||||
|
||||
# Sensitive or high-churn files
|
||||
.idea/**/dataSources/
|
||||
.idea/**/dataSources.ids
|
||||
.idea/**/dataSources.local.xml
|
||||
.idea/**/sqlDataSources.xml
|
||||
.idea/**/dynamic.xml
|
||||
.idea/**/uiDesigner.xml
|
||||
.idea/**/dbnavigator.xml
|
||||
|
||||
# Gradle
|
||||
.idea/**/gradle.xml
|
||||
.idea/**/libraries
|
||||
|
||||
# Gradle and Maven with auto-import
|
||||
# When using Gradle or Maven with auto-import, you should exclude module files,
|
||||
# since they will be recreated, and may cause churn. Uncomment if using
|
||||
# auto-import.
|
||||
# .idea/artifacts
|
||||
# .idea/compiler.xml
|
||||
# .idea/jarRepositories.xml
|
||||
# .idea/modules.xml
|
||||
# .idea/*.iml
|
||||
# .idea/modules
|
||||
# *.iml
|
||||
# *.ipr
|
||||
|
||||
# CMake
|
||||
cmake-build-*/
|
||||
|
||||
# Mongo Explorer plugin
|
||||
.idea/**/mongoSettings.xml
|
||||
|
||||
# File-based project format
|
||||
*.iws
|
||||
|
||||
# IntelliJ
|
||||
out/
|
||||
|
||||
# mpeltonen/sbt-idea plugin
|
||||
.idea_modules/
|
||||
|
||||
# JIRA plugin
|
||||
atlassian-ide-plugin.xml
|
||||
|
||||
# Cursive Clojure plugin
|
||||
.idea/replstate.xml
|
||||
|
||||
# SonarLint plugin
|
||||
.idea/sonarlint/
|
||||
|
||||
# Crashlytics plugin (for Android Studio and IntelliJ)
|
||||
com_crashlytics_export_strings.xml
|
||||
crashlytics.properties
|
||||
crashlytics-build.properties
|
||||
fabric.properties
|
||||
|
||||
# Editor-based Rest Client
|
||||
.idea/httpRequests
|
||||
|
||||
# Android studio 3.1+ serialized cache file
|
||||
.idea/caches/build_file_checksums.ser
|
||||
|
||||
### PyCharm+all Patch ###
|
||||
# Ignores the whole .idea folder and all .iml files
|
||||
# See https://github.com/joeblau/gitignore.io/issues/186 and https://github.com/joeblau/gitignore.io/issues/360
|
||||
|
||||
.idea/*
|
||||
|
||||
# Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023
|
||||
|
||||
*.iml
|
||||
modules.xml
|
||||
.idea/misc.xml
|
||||
*.ipr
|
||||
|
||||
# Sonarlint plugin
|
||||
.idea/sonarlint
|
||||
|
||||
### Python ###
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
cover/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
.pybuilder/
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
# For a library or package, you might want to ignore these files since the code is
|
||||
# intended to run in multiple environments; otherwise, check them in:
|
||||
# .python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# poetry
|
||||
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
||||
#poetry.lock
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
# pytype static type analyzer
|
||||
.pytype/
|
||||
|
||||
# Cython debug symbols
|
||||
cython_debug/
|
||||
|
||||
# PyCharm
|
||||
# JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
|
||||
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
||||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
|
||||
### VisualStudioCode ###
|
||||
.vscode/*
|
||||
!.vscode/settings.json
|
||||
!.vscode/tasks.json
|
||||
!.vscode/launch.json
|
||||
!.vscode/extensions.json
|
||||
!.vscode/*.code-snippets
|
||||
|
||||
# Local History for Visual Studio Code
|
||||
.history/
|
||||
|
||||
# Built Visual Studio Code Extensions
|
||||
*.vsix
|
||||
|
||||
### VisualStudioCode Patch ###
|
||||
# Ignore all local history of files
|
||||
.history
|
||||
.ionide
|
||||
|
||||
# End of https://www.toptal.com/developers/gitignore/api/python,pycharm+all
|
||||
|
||||
# JS
|
||||
node_modules/
|
||||
|
||||
test.csv
|
||||
1719
FINAL_USO.csv
Normal file
1719
FINAL_USO.csv
Normal file
File diff suppressed because it is too large
Load Diff
2601
Forbes Billionaires.csv
Normal file
2601
Forbes Billionaires.csv
Normal file
File diff suppressed because it is too large
Load Diff
836
Lab2.ipynb
Normal file
836
Lab2.ipynb
Normal file
@ -0,0 +1,836 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Лабораторная работа 2.\n",
|
||||
"\n",
|
||||
"### Первый набор данных. Цены на золото (14 вариант).\n",
|
||||
"### Второй набор данных. Продажи домов (6 вариант).\n",
|
||||
"### Третий набор данных. Данные о миллионерах (19 вариант)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Проблемная область 14 варианта.\n",
|
||||
" - Проблемная область описания относится к финансовой аналитике и прогнозированию цен активов, в частности, к регрессионному анализу цен на золото.\n",
|
||||
"# Проблемная область 6 варианта.\n",
|
||||
" - Проблемная область в данном случае связана с регрессией в области анализа цен на недвижимость\n",
|
||||
"# Проблемная область 19 варианта.\n",
|
||||
" - Анализ и прогнозирование богатства, документальное подтверждение и составление рейтингов состоятельных людей."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"df_house = pd.read_csv('kc_house_data.csv')\n",
|
||||
"\n",
|
||||
"df_house.head()\n",
|
||||
"df_house.info()\n",
|
||||
"\n",
|
||||
"# Устранение проблемы пропущенных данных\n",
|
||||
"# Преобразование столбца 'your_column' из float в int\n",
|
||||
"df_house[\"floors\"] = df_house[\"floors\"].astype(int)\n",
|
||||
"\n",
|
||||
"# Сохранение измененного DataFrame обратно в CSV\n",
|
||||
"df_house.to_csv(\"houses.csv\", index=False)\n",
|
||||
"# Удаление строк с полностью пустыми значениями\n",
|
||||
"df_cleaned = df_house.dropna(how=\"all\", inplace=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from src.utils import split_stratified_into_train_val_test\n",
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"df_house = pd.read_csv(\"houses.csv\")\n",
|
||||
"display(df_house.floors.value_counts())\n",
|
||||
"display()\n",
|
||||
"\n",
|
||||
"data = df_house[[\"bedrooms\", \"floors\", \"condition\"]].copy()\n",
|
||||
"\n",
|
||||
"df_train, df_val, df_test, y_train, y_val, y_test = (\n",
|
||||
" split_stratified_into_train_val_test(\n",
|
||||
" data,\n",
|
||||
" stratify_colname=\"floors\",\n",
|
||||
" frac_train=0.60,\n",
|
||||
" frac_val=0.20,\n",
|
||||
" frac_test=0.20,\n",
|
||||
" )\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка: \", df_train.shape)\n",
|
||||
"display(df_train.floors.value_counts())\n",
|
||||
"\n",
|
||||
"display(\"Контрольная выборка: \", df_val.shape)\n",
|
||||
"display(df_val.floors.value_counts())\n",
|
||||
"\n",
|
||||
"display(\"Тестовая выборка: \", df_test.shape)\n",
|
||||
"display(df_test.floors.value_counts())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from imblearn.over_sampling import ADASYN\n",
|
||||
"\n",
|
||||
"ada = ADASYN()\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка: \", df_train.shape)\n",
|
||||
"display(df_train.floors.value_counts())\n",
|
||||
"\n",
|
||||
"X_resampled, y_resampled = ada.fit_resample(df_train, df_train[\"floors\"]) # type: ignore\n",
|
||||
"df_train_adasyn = pd.DataFrame(X_resampled)\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка после oversampling: \", df_train_adasyn.shape)\n",
|
||||
"display(df_train_adasyn.floors.value_counts())\n",
|
||||
"\n",
|
||||
"df_train_adasyn"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Пример бизнес целей для 6 варианта.\n",
|
||||
" - Ценообразование и прогнозирование цен на недвижимость. Эффект: Упрощение процесса оценки для риэлторов, улучшение точности ценообразования.\n",
|
||||
"\n",
|
||||
" Техническая цель: Построить модель машинного обучения для прогнозирования стоимости недвижимости.\n",
|
||||
" Вход:\n",
|
||||
"\n",
|
||||
" Количество спален (bedrooms)\n",
|
||||
" Количество ванных комнат (bathrooms)\n",
|
||||
" Площадь жилого пространства (sqft_living)\n",
|
||||
" Площадь участка (sqft_lot)\n",
|
||||
" Год постройки (yr_built)\n",
|
||||
" Рейтинг дома (grade)\n",
|
||||
" Вид, состояние, близость к воде (view, condition, waterfront)\n",
|
||||
" Почтовый индекс и координаты (zipcode, lat, long)\n",
|
||||
" Целевой признак:\n",
|
||||
"\n",
|
||||
" Цена недвижимости (price).\n",
|
||||
"\n",
|
||||
" - Идентификация перспективных районов. Эффект: Помощь инвесторам в выборе объектов для вложений.\n",
|
||||
"\n",
|
||||
" Техническая цель: Анализ динамики цен недвижимости по районам для выявления быстро растущих районов.\n",
|
||||
" Вход:\n",
|
||||
"\n",
|
||||
" Средняя цена домов в почтовом индексе за предыдущие годы.\n",
|
||||
" Координаты домов (lat, long).\n",
|
||||
" Число продаж в каждом районе за период.\n",
|
||||
" Целевой признак:\n",
|
||||
"\n",
|
||||
" Рост средней цены домов в районе.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"### 6.Определить проблемы выбранных наборов данных: зашумленность, смещение, актуальность, выбросы, просачивание данных.\n",
|
||||
"#### 1.1. Зашумленность данных\n",
|
||||
" Возможные ошибки ввода: некорректные значения площади или количества комнат (например, площадь 0, количество комнат слишком велико).\n",
|
||||
" Сильная корреляция признаков: например, площадь дома и количество комнат могут дублировать информацию.\n",
|
||||
"#### 1.2. Смещение данных\n",
|
||||
" Набор данных может не охватывать все районы и типы недвижимости, например, роскошные или дешевые дома могут быть представлены неравномерно.\n",
|
||||
" Временная зависимость: если данные устарели (например, цены из старого периода), это может привести к смещению в прогнозах.\n",
|
||||
"#### 1.3. Актуальность данных\n",
|
||||
" Если рынок недвижимости изменился (например, после 2020 года из-за пандемии), старые данные могут быть малоактуальны для современных прогнозов.\n",
|
||||
"#### 1.4. Выбросы\n",
|
||||
" Очень высокие или низкие цены (например, элитная недвижимость или заброшенные дома).\n",
|
||||
" Аномальные значения площади (например, слишком большие или маленькие площади).\n",
|
||||
"#### 1.5. Просачивание данных (Data Leakage)\n",
|
||||
" Если в модели используются признаки, которые недоступны на момент прогноза (например, цена или площадь после ремонта), это приведет к завышенной точности модели.\n",
|
||||
"\n",
|
||||
"### 7.Привести примеры решения обнаруженных проблем для каждого набора данных.\n",
|
||||
"\n",
|
||||
"#### 1.1. Зашумленность данных\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Проверка данных на наличие некорректных значений:\n",
|
||||
" Исключить записи с площадью 0 или нереалистично большими значениями.\n",
|
||||
" Проверить диапазон значений для числовых признаков (например, количество комнат не превышает разумных пределов).\n",
|
||||
" Удаление или сглаживание дублирующихся признаков:\n",
|
||||
" Если два признака, например, sqft_living и sqft_living15, имеют очень высокую корреляцию, можно исключить один из них.\n",
|
||||
"#### 1.2. Смещение данных\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Применение стратифицированного отбора данных, чтобы обеспечить равномерное покрытие различных типов недвижимости (дешевые, средние, элитные дома).\n",
|
||||
" Актуализация данных: объединение с дополнительными источниками, которые отражают текущие цены.\n",
|
||||
"#### 1.3. Актуальность данных\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Удаление устаревших записей (например, с датой продажи старше 10 лет).\n",
|
||||
" Добавление новых данных о ценах и характеристиках недвижимости для текущего рынка.\n",
|
||||
"#### 1.4. Выбросы\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Использование статистических методов (например, межквартильный размах) для выявления выбросов:\n",
|
||||
" Исключение аномально высоких или низких цен.\n",
|
||||
" Логическая проверка площадей и количества этажей.\n",
|
||||
"#### 1.5. Просачивание данных\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Исключение признаков, которые невозможно знать в момент прогноза (например, год реновации, если он произошел после продажи).\n",
|
||||
" Разделение данных на тренировочный и тестовый наборы с учетом временного разрыва.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"### 8.Оценить качество каждого набора данных: информативность, степень покрытия, соответствие реальным данным, согласованность меток.\n",
|
||||
"\n",
|
||||
"#### 1.1. Информативность\n",
|
||||
" Положительные стороны:\n",
|
||||
" Набор включает множество характеристик недвижимости (размеры, состояние, год постройки, координаты), что позволяет решать широкий спектр задач (прогнозирование цены, классификация).\n",
|
||||
" Ограничения:\n",
|
||||
" Некоторые признаки, такие как yr_renovated, имеют много нулевых значений, что может снижать информативность.\n",
|
||||
" Почтовый индекс (zipcode) предоставляет лишь ограниченную информацию о районе.\n",
|
||||
"#### 1.2. Степень покрытия\n",
|
||||
" Положительные стороны:\n",
|
||||
" Набор охватывает более 21 000 объектов недвижимости, что достаточно для генерализации моделей.\n",
|
||||
" Ограничения:\n",
|
||||
" Данные представлены только для одного региона (вероятно, Сиэтл или его окрестности), что ограничивает применение моделей для других территорий.\n",
|
||||
"#### 1.3. Соответствие реальным данным\n",
|
||||
" Положительные стороны:\n",
|
||||
" Данные хорошо описывают основные характеристики недвижимости, которые действительно влияют на цены.\n",
|
||||
" Ограничения:\n",
|
||||
" Устаревшие записи (например, дома, проданные более 10 лет назад) могут не отражать текущие рыночные тенденции.\n",
|
||||
"#### 1.4. Согласованность меток\n",
|
||||
" Положительные стороны:\n",
|
||||
" Основной целевой признак (price) представлен четко и корректно.\n",
|
||||
" Ограничения:\n",
|
||||
" Возможны редкие выбросы или ошибки в данных о цене (например, нереалистично высокая или низкая стоимость)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"df = pd.read_csv('Forbes Billionaires.csv')\n",
|
||||
"\n",
|
||||
"df.head()\n",
|
||||
"df.info()\n",
|
||||
"\n",
|
||||
"# Устранение проблемы пропущенных данных, а именно - замена на const.\n",
|
||||
"df['AgeFillNA'] = df['Age'].fillna(50)\n",
|
||||
"\n",
|
||||
"# Разделение столбца Networth на 3 группы\n",
|
||||
"df[\"Networth_Group\"] = pd.qcut(df[\"Networth\"], q=3, labels=[1, 2, 3])\n",
|
||||
"df"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from src.utils import split_stratified_into_train_val_test\n",
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"display(df.Networth_Group.value_counts())\n",
|
||||
"display()\n",
|
||||
"\n",
|
||||
"data = df[[\"Networth_Group\", \"Networth\", \"AgeFillNA\"]].copy()\n",
|
||||
"\n",
|
||||
"df_train, df_val, df_test, y_train, y_val, y_test = (\n",
|
||||
" split_stratified_into_train_val_test(\n",
|
||||
" data,\n",
|
||||
" stratify_colname=\"Networth_Group\",\n",
|
||||
" frac_train=0.60,\n",
|
||||
" frac_val=0.20,\n",
|
||||
" frac_test=0.20,\n",
|
||||
" )\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка: \", df_train.shape)\n",
|
||||
"display(df_train.Networth_Group.value_counts())\n",
|
||||
"\n",
|
||||
"display(\"Контрольная выборка: \", df_val.shape)\n",
|
||||
"display(df_val.Networth_Group.value_counts())\n",
|
||||
"\n",
|
||||
"display(\"Тестовая выборка: \", df_test.shape)\n",
|
||||
"display(df_test.Networth_Group.value_counts())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from imblearn.over_sampling import ADASYN\n",
|
||||
"\n",
|
||||
"ada = ADASYN()\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка: \", df_train.shape)\n",
|
||||
"display(df_train.Networth_Group.value_counts())\n",
|
||||
"\n",
|
||||
"X_resampled, y_resampled = ada.fit_resample(df_train, df_train[\"Networth_Group\"]) # type: ignore\n",
|
||||
"df_train_adasyn = pd.DataFrame(X_resampled)\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка после oversampling: \", df_train_adasyn.shape)\n",
|
||||
"display(df_train_adasyn.Networth_Group.value_counts())\n",
|
||||
"\n",
|
||||
"df_train_adasyn"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"В данном примере мы можем видеть достаточную сбалансированность (или же распределение почти равно, метод ADASYN не смог создать новые примеры, как так это не нужно). Это произошло из за дорабатывания исходного файла, так как на стандартном - выполнить данное задание не представляется возможным."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Пример бизнес цели для 19 варианта\n",
|
||||
" - Анализ целевой аудитории для элитных товаров и услуг. Эффект: Повышение доходов за счёт фокусировки на платежеспособных клиентах.\n",
|
||||
" - Определение перспективных индустрий для инвестиций. Эффект: Увеличение доходности инвестиций за счёт выбора наиболее прибыльных секторов.\n",
|
||||
"\n",
|
||||
"### 6.Определить проблемы выбранных наборов данных: зашумленность, смещение, актуальность, выбросы, просачивание данных.\n",
|
||||
"\n",
|
||||
"Проблемы и их решения:\n",
|
||||
"1. Зашумленность данных\n",
|
||||
" Проблема: Возможны дублирующиеся или некорректные записи (например, одинаковые имена с разными рангами).\n",
|
||||
" Решение: Проверить и удалить дубликаты, если они есть.\n",
|
||||
"2. Смещение данных\n",
|
||||
" Проблема: Набор может быть смещен в сторону представителей более крупных стран или популярных отраслей.\n",
|
||||
" Решение: Провести анализ распределения по странам и индустриям, а также сбалансировать данные для более равномерного анализа.\n",
|
||||
"3. Актуальность данных\n",
|
||||
" Проблема: Устаревшие данные могут не отражать текущее состояние богатства.\n",
|
||||
" Решение: Проверить год публикации данных и, если необходимо, дополнить их более актуальной информацией.\n",
|
||||
"4. Выбросы\n",
|
||||
" Проблема: Возможны выбросы в данных состояния (например, ошибки ввода).\n",
|
||||
" Решение: Проверить распределение состояния (например, с помощью диаграммы размаха) и устранить аномалии.\n",
|
||||
"5. Просачивание данных\n",
|
||||
" Проблема: Если использовать ранги или источники состояния для предсказания состояний, это может привести к неправильной интерпретации.\n",
|
||||
" Решение: Исключить признаки, которые содержат информацию о целевой переменной.\n",
|
||||
"\n",
|
||||
"### 8.Оценить качество каждого набора данных: информативность, степень покрытия, соответствие реальным данным, согласованность меток.\n",
|
||||
"\n",
|
||||
"1. Информативность\n",
|
||||
" Положительные стороны:\n",
|
||||
" Набор данных предоставляет ключевые параметры: состояние, возраст, страна, индустрия и источник дохода.\n",
|
||||
" Полезен для анализа распределения богатства по странам, индустриям и возрастным группам.\n",
|
||||
" Ограничения:\n",
|
||||
" Возможно, не хватает дополнительных параметров (например, гендер или тренды изменения состояния).\n",
|
||||
"2. Степень покрытия\n",
|
||||
" Положительные стороны:\n",
|
||||
" Набор включает информацию о 2600 миллиардерах, что является большим объемом для глобального анализа.\n",
|
||||
" Ограничения:\n",
|
||||
" Отсутствие данных о миллиардерах из менее известных стран или отраслей может снижать репрезентативность.\n",
|
||||
"3. Соответствие реальным данным\n",
|
||||
" Положительные стороны:\n",
|
||||
" Данные соответствуют информации из открытых источников (Forbes).\n",
|
||||
" Ограничения:\n",
|
||||
" Актуальность данных зависит от года публикации (нужно уточнить).\n",
|
||||
"4. Согласованность меток\n",
|
||||
" Положительные стороны:\n",
|
||||
" Столбцы (Rank, Networth, Country, Industry) логически согласованы и не содержат явных ошибок.\n",
|
||||
" Ограничения:\n",
|
||||
" Возможны дублирующиеся записи или опечатки в текстовых данных (например, в именах или странах)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"df = pd.read_csv('FINAL_USO.csv')\n",
|
||||
"df.head()\n",
|
||||
"df.info()\n",
|
||||
"\n",
|
||||
"# Устранение проблемы пропущенных данных - медианное значение.\n",
|
||||
"median_value = df['DJ_high'].median()\n",
|
||||
"df['DJ_high'].fillna(median_value, inplace=True)\n",
|
||||
"\n",
|
||||
"df\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"PLT_Trend\n",
|
||||
"0 886\n",
|
||||
"1 832\n",
|
||||
"Name: count, dtype: int64"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Обучающая выборка: '"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(1030, 3)"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"PLT_Trend\n",
|
||||
"0 531\n",
|
||||
"1 499\n",
|
||||
"Name: count, dtype: int64"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Контрольная выборка: '"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(344, 3)"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"PLT_Trend\n",
|
||||
"0 177\n",
|
||||
"1 167\n",
|
||||
"Name: count, dtype: int64"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Тестовая выборка: '"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(344, 3)"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"PLT_Trend\n",
|
||||
"0 178\n",
|
||||
"1 166\n",
|
||||
"Name: count, dtype: int64"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from src.utils import split_stratified_into_train_val_test\n",
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"display(df.PLT_Trend.value_counts())\n",
|
||||
"display()\n",
|
||||
"\n",
|
||||
"data = df[[\"PLT_Trend\", \"High\", \"Low\"]].copy()\n",
|
||||
"\n",
|
||||
"df_train, df_val, df_test, y_train, y_val, y_test = (\n",
|
||||
" split_stratified_into_train_val_test(\n",
|
||||
" data,\n",
|
||||
" stratify_colname=\"PLT_Trend\",\n",
|
||||
" frac_train=0.60,\n",
|
||||
" frac_val=0.20,\n",
|
||||
" frac_test=0.20,\n",
|
||||
" )\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка: \", df_train.shape)\n",
|
||||
"display(df_train.PLT_Trend.value_counts())\n",
|
||||
"\n",
|
||||
"display(\"Контрольная выборка: \", df_val.shape)\n",
|
||||
"display(df_val.PLT_Trend.value_counts())\n",
|
||||
"\n",
|
||||
"display(\"Тестовая выборка: \", df_test.shape)\n",
|
||||
"display(df_test.PLT_Trend.value_counts())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Обучающая выборка: '"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(1030, 3)"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"PLT_Trend\n",
|
||||
"0 531\n",
|
||||
"1 499\n",
|
||||
"Name: count, dtype: int64"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Обучающая выборка после oversampling: '"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(1046, 3)"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"PLT_Trend\n",
|
||||
"0 531\n",
|
||||
"1 515\n",
|
||||
"Name: count, dtype: int64"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div>\n",
|
||||
"<style scoped>\n",
|
||||
" .dataframe tbody tr th:only-of-type {\n",
|
||||
" vertical-align: middle;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe tbody tr th {\n",
|
||||
" vertical-align: top;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe thead th {\n",
|
||||
" text-align: right;\n",
|
||||
" }\n",
|
||||
"</style>\n",
|
||||
"<table border=\"1\" class=\"dataframe\">\n",
|
||||
" <thead>\n",
|
||||
" <tr style=\"text-align: right;\">\n",
|
||||
" <th></th>\n",
|
||||
" <th>PLT_Trend</th>\n",
|
||||
" <th>High</th>\n",
|
||||
" <th>Low</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>0</th>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>118.459999</td>\n",
|
||||
" <td>118.070000</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1</th>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>114.949997</td>\n",
|
||||
" <td>114.410004</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2</th>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>109.769997</td>\n",
|
||||
" <td>108.940002</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3</th>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>126.120003</td>\n",
|
||||
" <td>125.309998</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>4</th>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>122.610001</td>\n",
|
||||
" <td>122.220001</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>...</th>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1041</th>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>135.325901</td>\n",
|
||||
" <td>133.909193</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1042</th>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>136.613181</td>\n",
|
||||
" <td>135.565760</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1043</th>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>136.154196</td>\n",
|
||||
" <td>130.907531</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1044</th>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>153.542436</td>\n",
|
||||
" <td>150.981407</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1045</th>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>136.182537</td>\n",
|
||||
" <td>131.184275</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"<p>1046 rows × 3 columns</p>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" PLT_Trend High Low\n",
|
||||
"0 0 118.459999 118.070000\n",
|
||||
"1 0 114.949997 114.410004\n",
|
||||
"2 0 109.769997 108.940002\n",
|
||||
"3 0 126.120003 125.309998\n",
|
||||
"4 1 122.610001 122.220001\n",
|
||||
"... ... ... ...\n",
|
||||
"1041 1 135.325901 133.909193\n",
|
||||
"1042 1 136.613181 135.565760\n",
|
||||
"1043 1 136.154196 130.907531\n",
|
||||
"1044 1 153.542436 150.981407\n",
|
||||
"1045 1 136.182537 131.184275\n",
|
||||
"\n",
|
||||
"[1046 rows x 3 columns]"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from imblearn.over_sampling import ADASYN\n",
|
||||
"\n",
|
||||
"ada = ADASYN()\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка: \", df_train.shape)\n",
|
||||
"display(df_train.PLT_Trend.value_counts())\n",
|
||||
"\n",
|
||||
"X_resampled, y_resampled = ada.fit_resample(df_train, df_train[\"PLT_Trend\"]) # type: ignore\n",
|
||||
"df_train_adasyn = pd.DataFrame(X_resampled)\n",
|
||||
"\n",
|
||||
"display(\"Обучающая выборка после oversampling: \", df_train_adasyn.shape)\n",
|
||||
"display(df_train_adasyn.PLT_Trend.value_counts())\n",
|
||||
"\n",
|
||||
"df_train_adasyn"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Пример бизнес целей для 14 варианта.\n",
|
||||
" - Оптимизация торговых стратегий. Эффект: Увеличение прибыли трейдеров и инвестиционных фондов.\n",
|
||||
" - Анализ корреляций между рынками. Эффект: Повышение эффективности диверсификации портфеля и управления рисками.\n",
|
||||
"\n",
|
||||
"### 1. Прогнозирование цен на нефть (USO)\n",
|
||||
"Техническая цель: Разработать модель машинного обучения для прогнозирования цены закрытия нефти на следующий день.\n",
|
||||
"\n",
|
||||
"Вход:\n",
|
||||
"\n",
|
||||
"Цены открытия, максимума, минимума, закрытия нефти за последние N дней (USO_Open, USO_High, USO_Low, USO_Close).\n",
|
||||
"Объем торгов нефтью (USO_Volume).\n",
|
||||
"Финансовые индексы (например, SP_Close, DJ_Close, EU_Trend).\n",
|
||||
"Целевой признак:\n",
|
||||
"\n",
|
||||
"Цена закрытия нефти на следующий день (USO_Close).\n",
|
||||
"\n",
|
||||
"### 2. Рекомендации для инвесторов\n",
|
||||
"Техническая цель: Разработать систему рекомендаций, которая советует инвесторам, в какие инструменты вкладывать (нефть, акции, индексы).\n",
|
||||
"\n",
|
||||
"Вход:\n",
|
||||
"\n",
|
||||
"Финансовые показатели (цены открытия, закрытия, объемы торгов для разных инструментов).\n",
|
||||
"Исторические данные о трендах (EU_Trend, USO_Trend).\n",
|
||||
"Предпочтения инвестора (риск, ожидаемая доходность).\n",
|
||||
"Целевой признак:\n",
|
||||
"\n",
|
||||
"Вероятность роста выбранного инструмента в ближайшие дни.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"### 6.Определить проблемы выбранных наборов данных: зашумленность, смещение, актуальность, выбросы, просачивание данных.\n",
|
||||
"\n",
|
||||
"#### 2.1. Зашумленность данных\n",
|
||||
" Наличие мелких колебаний цен, которые не несут значимой информации для долгосрочного прогноза.\n",
|
||||
" Пропуски или дублирование данных в датах или финансовых показателях.\n",
|
||||
"#### 2.2. Смещение данных\n",
|
||||
" Данные могут быть сосредоточены на определенных временных периодах, например, на благоприятных или неблагоприятных для рынка. Это затрудняет генерализацию модели на другие периоды.\n",
|
||||
" Неполное покрытие всех возможных макроэкономических факторов, влияющих на цены (например, влияние геополитических событий).\n",
|
||||
"#### 2.3. Актуальность данных\n",
|
||||
" Финансовые рынки изменяются очень быстро. Если данные устарели, модели, обученные на них, не смогут правильно реагировать на текущую динамику.\n",
|
||||
"#### 2.4. Выбросы\n",
|
||||
" Резкие изменения цен и объемов торгов в периоды нестабильности рынка (например, во время кризисов).\n",
|
||||
" Аномальные тренды в отдельных финансовых инструментах.\n",
|
||||
"#### 2.5. Просачивание данных (Data Leakage)\n",
|
||||
" Использование будущих значений (например, цен закрытия следующего дня) при обучении модели.\n",
|
||||
" Тренды, рассчитанные на основе данных, доступных только после момента прогноза.\n",
|
||||
"\n",
|
||||
"### 7.Привести примеры решения обнаруженных проблем для каждого набора данных.\n",
|
||||
"\n",
|
||||
"#### 2.1. Зашумленность данных\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Применение методов сглаживания временных рядов:\n",
|
||||
" Использование скользящих средних или фильтрации данных для устранения мелких колебаний.\n",
|
||||
" Заполнение пропусков:\n",
|
||||
" Линейная интерполяция или более сложные методы, такие как KNN, для восстановления недостающих значений.\n",
|
||||
"#### 2.2. Смещение данных\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Добавление данных из других периодов (например, кризисных или стабильных) для лучшей генерализации модели.\n",
|
||||
" Балансировка данных: включение записей с различными макроэкономическими условиями (например, с изменениями процентных ставок).\n",
|
||||
"#### 2.3. Актуальность данных\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Постоянное обновление данных за счет регулярной выгрузки актуальных финансовых показателей.\n",
|
||||
" Исключение записей, относящихся к устаревшим периодам, если они не имеют корреляции с текущими тенденциями.\n",
|
||||
"#### 2.4. Выбросы\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Выявление выбросов с помощью методов, таких как Z-оценка или Isolation Forest:\n",
|
||||
" Аномальные объемы торгов или резкие скачки цен можно сгладить или исключить.\n",
|
||||
" Анализ контекста выбросов: если выброс вызван реальным событием (например, кризисом), его нужно сохранить.\n",
|
||||
"#### 2.5. Просачивание данных\n",
|
||||
" Решение:\n",
|
||||
"\n",
|
||||
" Исключение признаков, которые зависят от будущих значений (например, цены закрытия следующего дня).\n",
|
||||
" Формирование тренировочного и тестового наборов с учетом временной последовательности данных (train-test split на основе дат).\n",
|
||||
"\n",
|
||||
"### 8.Оценить качество каждого набора данных: информативность, степень покрытия, соответствие реальным данным, согласованность меток\n",
|
||||
"\n",
|
||||
"#### 2.1. Информативность\n",
|
||||
" Положительные стороны:\n",
|
||||
" Включает широкий спектр финансовых показателей (цены открытия, закрытия, объемы торгов, тренды).\n",
|
||||
" Подходит для временного анализа и прогнозирования.\n",
|
||||
" Ограничения:\n",
|
||||
" Некоторые трендовые и вспомогательные индикаторы не описаны явно, что затрудняет их интерпретацию.\n",
|
||||
"#### 2.2. Степень покрытия\n",
|
||||
" Положительные стороны:\n",
|
||||
" Набор данных включает данные за значительный временной промежуток (1718 записей), что полезно для анализа динамики.\n",
|
||||
" Ограничения:\n",
|
||||
" Возможно, набор данных не охватывает все важные макроэкономические факторы (например, данные о процентных ставках, геополитических событиях).\n",
|
||||
"#### 2.3. Соответствие реальным данным\n",
|
||||
" Положительные стороны:\n",
|
||||
" Цены и объемы торгов являются стандартными финансовыми метриками и, скорее всего, соответствуют реальным данным.\n",
|
||||
" Ограничения:\n",
|
||||
" Актуальность данных может быть ограничена, если набор содержит записи только до определенной даты и не обновляется.\n",
|
||||
"#### 2.4. Согласованность меток\n",
|
||||
" Положительные стороны:\n",
|
||||
" Метки, такие как тренды (Trend) и цены (Close), согласованы с соответствующими временными показателями.\n",
|
||||
" Ограничения:\n",
|
||||
" Если трендовые данные рассчитываются на основе будущих значений, это может привести к ошибкам в анализе."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
455
Lab3.ipynb
Normal file
455
Lab3.ipynb
Normal file
@ -0,0 +1,455 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Лабораторная работа 3."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Определение бизнес и технических целей\n",
|
||||
"1. Прогнозирование цены автомобиля\n",
|
||||
"Бизнес-цель: Оптимизация ценовой политики.\n",
|
||||
"Техническая цель: Построение модели прогнозирования цены.\n",
|
||||
"\n",
|
||||
"Конструирование признаков:\n",
|
||||
"Объем двигателя:\n",
|
||||
"\n",
|
||||
"Извлечь числовую часть из столбца Engine volume (например, 3.5).\n",
|
||||
"Добавить бинарный признак: наличие турбонаддува (Turbo).\n",
|
||||
"Возраст автомобиля:\n",
|
||||
"\n",
|
||||
"Вычислить возраст автомобиля как разницу между текущим годом и Prod. year.\n",
|
||||
"Привод (Drive wheels):\n",
|
||||
"\n",
|
||||
"Закодировать тип привода (например, 4x4, Front, Rear) с помощью One-Hot Encoding.\n",
|
||||
"Категория автомобиля (Category):\n",
|
||||
"\n",
|
||||
"Преобразовать категорию в числовые признаки с помощью One-Hot Encoding.\n",
|
||||
"Технические характеристики:\n",
|
||||
"\n",
|
||||
"Нормализовать числовые параметры, такие как пробег (Mileage) и количество цилиндров (Cylinders).\n",
|
||||
"Состояние интерьера:\n",
|
||||
"\n",
|
||||
"Закодировать признак наличия кожаного салона (Leather interior) как бинарный.\n",
|
||||
"\n",
|
||||
"2. Классификация популярности автомобиля\n",
|
||||
"Бизнес-цель: Изучение предпочтений клиентов.\n",
|
||||
"Техническая цель: Определение популярности автомобилей.\n",
|
||||
"\n",
|
||||
"Конструирование признаков:\n",
|
||||
"Рейтинг безопасности:\n",
|
||||
"\n",
|
||||
"Использовать количество подушек безопасности (Airbags) для создания индикатора безопасности автомобиля.\n",
|
||||
"Тип топлива:\n",
|
||||
"\n",
|
||||
"Закодировать Fuel type как категориальный признак (например, Petrol, Diesel, Hybrid).\n",
|
||||
"Цвет автомобиля:\n",
|
||||
"\n",
|
||||
"Создать признак редкости цвета на основе частоты его встречаемости в данных.\n",
|
||||
"Стоимость обслуживания:\n",
|
||||
"\n",
|
||||
"Преобразовать Levy в числовой признак и обработать пропущенные значения (например, заменить на среднее/медианное значение).\n",
|
||||
"Сегмент рынка:\n",
|
||||
"\n",
|
||||
"Объединить категории автомобилей (например, Jeep, Hatchback) в несколько сегментов (премиум, эконом, компакт).\n",
|
||||
"Особенности привода:\n",
|
||||
"\n",
|
||||
"Создать бинарные признаки, указывающие на тип управления (Left wheel/Right-hand drive)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"((11542, 215), (3847, 215), (3848, 215), (11542,), (3847,), (3848,))"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"data = pd.read_csv(\"car_price_prediction.csv\")\n",
|
||||
"# Preparing the data by removing unnecessary columns and handling categorical data\n",
|
||||
"data_cleaned = data.copy()\n",
|
||||
"\n",
|
||||
"# Converting \"Levy\" and \"Mileage\" to numeric (handling non-numeric values like '-')\n",
|
||||
"data_cleaned[\"Levy\"] = pd.to_numeric(data_cleaned[\"Levy\"], errors=\"coerce\")\n",
|
||||
"data_cleaned[\"Mileage\"] = (\n",
|
||||
" data_cleaned[\"Mileage\"].str.replace(\" km\", \"\").str.replace(\" \", \"\").astype(float)\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Dropping columns that are identifiers or too detailed for prediction (like ID, Model)\n",
|
||||
"data_cleaned = data_cleaned.drop([\"ID\", \"Model\"], axis=1)\n",
|
||||
"\n",
|
||||
"# Encoding categorical columns\n",
|
||||
"categorical_cols = data_cleaned.select_dtypes(include=\"object\").columns\n",
|
||||
"data_encoded = pd.get_dummies(data_cleaned, columns=categorical_cols, drop_first=True)\n",
|
||||
"\n",
|
||||
"# Splitting the data into features (X) and target (y)\n",
|
||||
"X = data_encoded.drop(\"Price\", axis=1)\n",
|
||||
"y = data_encoded[\"Price\"]\n",
|
||||
"\n",
|
||||
"# Splitting into training, validation, and testing datasets\n",
|
||||
"X_train, X_temp, y_train, y_temp = train_test_split(\n",
|
||||
" X, y, test_size=0.4, random_state=42\n",
|
||||
") # 60% training data\n",
|
||||
"X_val, X_test, y_val, y_test = train_test_split(\n",
|
||||
" X_temp, y_temp, test_size=0.5, random_state=42\n",
|
||||
") # 20% validation, 20% testing\n",
|
||||
"\n",
|
||||
"# Displaying the sizes of the datasets\n",
|
||||
"X_train.shape, X_val.shape, X_test.shape, y_train.shape, y_val.shape, y_test.shape"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div>\n",
|
||||
"<style scoped>\n",
|
||||
" .dataframe tbody tr th:only-of-type {\n",
|
||||
" vertical-align: middle;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe tbody tr th {\n",
|
||||
" vertical-align: top;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe thead th {\n",
|
||||
" text-align: right;\n",
|
||||
" }\n",
|
||||
"</style>\n",
|
||||
"<table border=\"1\" class=\"dataframe\">\n",
|
||||
" <thead>\n",
|
||||
" <tr style=\"text-align: right;\">\n",
|
||||
" <th></th>\n",
|
||||
" <th>Price</th>\n",
|
||||
" <th>Levy</th>\n",
|
||||
" <th>Manufacturer</th>\n",
|
||||
" <th>Leather interior</th>\n",
|
||||
" <th>Engine volume</th>\n",
|
||||
" <th>Mileage</th>\n",
|
||||
" <th>Cylinders</th>\n",
|
||||
" <th>Gear box type</th>\n",
|
||||
" <th>Doors</th>\n",
|
||||
" <th>Airbags</th>\n",
|
||||
" <th>...</th>\n",
|
||||
" <th>Fuel type_LPG</th>\n",
|
||||
" <th>Fuel type_Petrol</th>\n",
|
||||
" <th>Fuel type_Plug-in Hybrid</th>\n",
|
||||
" <th>Wheel_Right-hand drive</th>\n",
|
||||
" <th>Car age</th>\n",
|
||||
" <th>Car age bins</th>\n",
|
||||
" <th>Mileage bins</th>\n",
|
||||
" <th>Turbo</th>\n",
|
||||
" <th>Safety rating</th>\n",
|
||||
" <th>Color rarity</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>0</th>\n",
|
||||
" <td>13328</td>\n",
|
||||
" <td>1.065632</td>\n",
|
||||
" <td>LEXUS</td>\n",
|
||||
" <td>Yes</td>\n",
|
||||
" <td>1.357980</td>\n",
|
||||
" <td>-0.027813</td>\n",
|
||||
" <td>1.180937</td>\n",
|
||||
" <td>Automatic</td>\n",
|
||||
" <td>04-May</td>\n",
|
||||
" <td>12</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>15</td>\n",
|
||||
" <td>11-20</td>\n",
|
||||
" <td>High</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>0.750</td>\n",
|
||||
" <td>0.197120</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1</th>\n",
|
||||
" <td>16621</td>\n",
|
||||
" <td>0.240688</td>\n",
|
||||
" <td>CHEVROLET</td>\n",
|
||||
" <td>No</td>\n",
|
||||
" <td>0.788363</td>\n",
|
||||
" <td>-0.027689</td>\n",
|
||||
" <td>1.180937</td>\n",
|
||||
" <td>Tiptronic</td>\n",
|
||||
" <td>04-May</td>\n",
|
||||
" <td>8</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>14</td>\n",
|
||||
" <td>11-20</td>\n",
|
||||
" <td>Very High</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>0.500</td>\n",
|
||||
" <td>0.261631</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2</th>\n",
|
||||
" <td>8467</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>HONDA</td>\n",
|
||||
" <td>No</td>\n",
|
||||
" <td>-1.148338</td>\n",
|
||||
" <td>-0.027524</td>\n",
|
||||
" <td>-0.485866</td>\n",
|
||||
" <td>Variator</td>\n",
|
||||
" <td>04-May</td>\n",
|
||||
" <td>2</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>19</td>\n",
|
||||
" <td>11-20</td>\n",
|
||||
" <td>Very High</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>0.125</td>\n",
|
||||
" <td>0.261631</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3</th>\n",
|
||||
" <td>3607</td>\n",
|
||||
" <td>-0.097084</td>\n",
|
||||
" <td>FORD</td>\n",
|
||||
" <td>Yes</td>\n",
|
||||
" <td>0.218745</td>\n",
|
||||
" <td>-0.028165</td>\n",
|
||||
" <td>-0.485866</td>\n",
|
||||
" <td>Automatic</td>\n",
|
||||
" <td>04-May</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>14</td>\n",
|
||||
" <td>11-20</td>\n",
|
||||
" <td>High</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>0.000</td>\n",
|
||||
" <td>0.233352</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>4</th>\n",
|
||||
" <td>11726</td>\n",
|
||||
" <td>-0.997809</td>\n",
|
||||
" <td>HONDA</td>\n",
|
||||
" <td>Yes</td>\n",
|
||||
" <td>-1.148338</td>\n",
|
||||
" <td>-0.029757</td>\n",
|
||||
" <td>-0.485866</td>\n",
|
||||
" <td>Automatic</td>\n",
|
||||
" <td>04-May</td>\n",
|
||||
" <td>4</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>11</td>\n",
|
||||
" <td>11-20</td>\n",
|
||||
" <td>Medium</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>0.250</td>\n",
|
||||
" <td>0.197120</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"<p>5 rows × 35 columns</p>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" Price Levy Manufacturer Leather interior Engine volume Mileage \\\n",
|
||||
"0 13328 1.065632 LEXUS Yes 1.357980 -0.027813 \n",
|
||||
"1 16621 0.240688 CHEVROLET No 0.788363 -0.027689 \n",
|
||||
"2 8467 NaN HONDA No -1.148338 -0.027524 \n",
|
||||
"3 3607 -0.097084 FORD Yes 0.218745 -0.028165 \n",
|
||||
"4 11726 -0.997809 HONDA Yes -1.148338 -0.029757 \n",
|
||||
"\n",
|
||||
" Cylinders Gear box type Doors Airbags ... Fuel type_LPG \\\n",
|
||||
"0 1.180937 Automatic 04-May 12 ... False \n",
|
||||
"1 1.180937 Tiptronic 04-May 8 ... False \n",
|
||||
"2 -0.485866 Variator 04-May 2 ... False \n",
|
||||
"3 -0.485866 Automatic 04-May 0 ... False \n",
|
||||
"4 -0.485866 Automatic 04-May 4 ... False \n",
|
||||
"\n",
|
||||
" Fuel type_Petrol Fuel type_Plug-in Hybrid Wheel_Right-hand drive \\\n",
|
||||
"0 False False False \n",
|
||||
"1 True False False \n",
|
||||
"2 True False True \n",
|
||||
"3 False False False \n",
|
||||
"4 True False False \n",
|
||||
"\n",
|
||||
" Car age Car age bins Mileage bins Turbo Safety rating Color rarity \n",
|
||||
"0 15 11-20 High 0 0.750 0.197120 \n",
|
||||
"1 14 11-20 Very High 0 0.500 0.261631 \n",
|
||||
"2 19 11-20 Very High 0 0.125 0.261631 \n",
|
||||
"3 14 11-20 High 0 0.000 0.233352 \n",
|
||||
"4 11 11-20 Medium 0 0.250 0.197120 \n",
|
||||
"\n",
|
||||
"[5 rows x 35 columns]"
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"from sklearn.preprocessing import MinMaxScaler, StandardScaler\n",
|
||||
"\n",
|
||||
"# Копия исходного набора данных\n",
|
||||
"features_data = data_cleaned.copy()\n",
|
||||
"\n",
|
||||
"# --- 1. Унитарное кодирование категориальных признаков ---\n",
|
||||
"# Кодирование категориальных переменных\n",
|
||||
"categorical_columns = [\"Drive wheels\", \"Category\", \"Fuel type\", \"Wheel\"]\n",
|
||||
"features_data = pd.get_dummies(\n",
|
||||
" features_data, columns=categorical_columns, drop_first=True\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# --- 2. Дискретизация числовых признаков ---\n",
|
||||
"# Пример: Дискретизация возраста автомобиля\n",
|
||||
"current_year = 2025\n",
|
||||
"features_data[\"Car age\"] = current_year - features_data[\"Prod. year\"]\n",
|
||||
"features_data[\"Car age bins\"] = pd.cut(\n",
|
||||
" features_data[\"Car age\"],\n",
|
||||
" bins=[0, 5, 10, 20, 50],\n",
|
||||
" labels=[\"0-5\", \"6-10\", \"11-20\", \"21+\"],\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Дискретизация пробега\n",
|
||||
"features_data[\"Mileage bins\"] = pd.qcut(\n",
|
||||
" features_data[\"Mileage\"].fillna(0),\n",
|
||||
" q=4,\n",
|
||||
" labels=[\"Low\", \"Medium\", \"High\", \"Very High\"],\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# --- 3. «Ручной» синтез признаков ---\n",
|
||||
"# Индикатор турбонаддува\n",
|
||||
"features_data[\"Turbo\"] = (\n",
|
||||
" features_data[\"Engine volume\"].str.contains(\"Turbo\").astype(int)\n",
|
||||
") # Индикатор турбонаддува\n",
|
||||
"features_data[\"Engine volume\"] = features_data[\"Engine volume\"].str.replace(\n",
|
||||
" \" Turbo\", \"\"\n",
|
||||
") # Убираем текст 'Turbo'\n",
|
||||
"features_data[\"Engine volume\"] = features_data[\"Engine volume\"].astype(\n",
|
||||
" float\n",
|
||||
") # Преобразуем в float\n",
|
||||
"# Рейтинг безопасности\n",
|
||||
"features_data[\"Safety rating\"] = (\n",
|
||||
" features_data[\"Airbags\"] / features_data[\"Airbags\"].max()\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Редкость цвета\n",
|
||||
"color_frequency = features_data[\"Color\"].value_counts(normalize=True)\n",
|
||||
"features_data[\"Color rarity\"] = features_data[\"Color\"].map(color_frequency)\n",
|
||||
"\n",
|
||||
"# --- 4. Масштабирование признаков ---\n",
|
||||
"# Масштабирование числовых признаков с использованием нормализации (Min-Max Scaling)\n",
|
||||
"scaler_minmax = MinMaxScaler()\n",
|
||||
"numerical_features = [\"Mileage\", \"Engine volume\", \"Cylinders\", \"Levy\"]\n",
|
||||
"features_data[numerical_features] = scaler_minmax.fit_transform(\n",
|
||||
" features_data[numerical_features]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Стандартизация (Standard Scaling) для числовых признаков\n",
|
||||
"scaler_standard = StandardScaler()\n",
|
||||
"features_data[numerical_features] = scaler_standard.fit_transform(\n",
|
||||
" features_data[numerical_features]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# --- Удаление ненужных столбцов ---\n",
|
||||
"columns_to_drop = [\"Prod. year\", \"Color\"] # Удаление лишних столбцов\n",
|
||||
"features_data = features_data.drop(columns=columns_to_drop)\n",
|
||||
"\n",
|
||||
"# Просмотр итогового набора данных\n",
|
||||
"features_data.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Оценка набора признаков по следующим критериям: предсказательная способность, скорость вычисления, надежность, корреляция и цельность.\n",
|
||||
"\n",
|
||||
" Предсказательная способность:\n",
|
||||
"1. Код приводит к созданию большого числа новых признаков, что может повысить предсказательную способность модели, если эти признаки действительно значимы для задачи.\n",
|
||||
"Например, создание индикатора турбонаддува, рейтинга безопасности и редкости цвета может улучшить способность модели делать точные предсказания.\n",
|
||||
"Однако важно проверить, что эти признаки не приводят к переобучению.\n",
|
||||
"\n",
|
||||
"2. Скорость вычисления:\n",
|
||||
"Операции, такие как кодирование категориальных признаков, дискретизация и масштабирование, могут замедлить процесс при больших наборах данных.\n",
|
||||
"Особое внимание стоит уделить масштабированию, так как оно требует времени на преобразование значений, особенно если количество числовых признаков велико.\n",
|
||||
"Признаки, полученные в результате ручного синтеза, такие как \"Turbo\", могут быть быстрыми для вычислений, но создание новых бинарных признаков увеличивает размер данных, что может замедлить вычисления.\n",
|
||||
"\n",
|
||||
"3. Надежность:\n",
|
||||
"Признаки, созданные вручную, такие как \"Turbo\" и \"Safety rating\", могут быть более устойчивыми, так как они не зависят от структуры данных, а только от специфической логики.\n",
|
||||
"Однако, например, дискретизация и кодирование категориальных переменных могут изменить поведение модели при изменении данных (например, когда в новых данных появляются новые категории).\n",
|
||||
"\n",
|
||||
"4. Корреляция:\n",
|
||||
"Кодирование категориальных признаков создаст новые столбцы, и важно будет проверить корреляцию между этими новыми признаками, чтобы избежать избыточности.\n",
|
||||
"Признаки, такие как возраст автомобиля и пробег, могут быть взаимосвязаны, что может потребовать дополнительных шагов для уменьшения корреляции (например, PCA или исключение одного из признаков).\n",
|
||||
"\n",
|
||||
"5. Целостность:\n",
|
||||
"Код также не учитывает пропуски в данных (например, в столбцах \"Mileage\" или \"Engine volume\"). Эти пропуски могут повлиять на результат и должны быть обработаны до начала других этапов.\n",
|
||||
"Например, при дискретизации пробега (pd.qcut()) используется .fillna(0), что может быть не оптимальным способом заполнения пропусков, так как это может привести к искажению данных."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
1310
Lab4.ipynb
Normal file
1310
Lab4.ipynb
Normal file
File diff suppressed because it is too large
Load Diff
43
README.md
43
README.md
@ -1,2 +1,43 @@
|
||||
# pred_analytics
|
||||
## Окружение и примеры для выполнения лабораторных работ по дисциплине "Методы ИИ"
|
||||
|
||||
### Python
|
||||
|
||||
Используется Python версии 3.12
|
||||
|
||||
Установщик https://www.python.org/ftp/python/3.12.5/python-3.12.5-amd64.exe
|
||||
|
||||
### Poetry
|
||||
|
||||
Для создания и настройки окружения проекта необходимо установить poetry
|
||||
|
||||
**Для Windows (Powershell)**
|
||||
|
||||
```
|
||||
(Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
|
||||
```
|
||||
|
||||
**Linux, macOS, Windows (WSL)**
|
||||
|
||||
```
|
||||
curl -sSL https://install.python-poetry.org | python3 -
|
||||
```
|
||||
|
||||
**Добавление poetry в PATH**
|
||||
|
||||
1. Открыть настройки переменных среды \
|
||||
\
|
||||
<img src="docs/path1.png" width="300"> \
|
||||
\
|
||||
<img src="docs/path2.png" width="400"> \
|
||||
2. Изменить переменную Path текущего пользователя \
|
||||
\
|
||||
<img src="docs/path3.png" width="500"> \
|
||||
3. Добавление пути `%APPDATA%\Python\Scripts` до исполняемого файла poetry \
|
||||
\
|
||||
<img src="docs/path4.png" width="400">
|
||||
|
||||
### Создание окружения
|
||||
|
||||
```
|
||||
poetry install
|
||||
```
|
||||
|
||||
BIN
assets/lec2-split.png
Normal file
BIN
assets/lec2-split.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 63 KiB |
BIN
assets/quantile.png
Normal file
BIN
assets/quantile.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 111 KiB |
19238
car_price_prediction.csv
Normal file
19238
car_price_prediction.csv
Normal file
File diff suppressed because it is too large
Load Diff
18
data/density/density_test.csv
Normal file
18
data/density/density_test.csv
Normal file
@ -0,0 +1,18 @@
|
||||
T;Al2O3;TiO2;Density
|
||||
30;0;0;1,05696
|
||||
55;0;0;1,04158
|
||||
25;0,05;0;1,08438
|
||||
30;0,05;0;1,08112
|
||||
35;0,05;0;1,07781
|
||||
40;0,05;0;1,07446
|
||||
60;0,05;0;1,06053
|
||||
35;0,3;0;1,17459
|
||||
65;0,3;0;1,14812
|
||||
45;0;0,05;1,07424
|
||||
50;0;0,05;1,07075
|
||||
55;0;0,05;1,06721
|
||||
20;0;0,3;1,22417
|
||||
30;0;0,3;1,2131
|
||||
40;0;0,3;1,20265
|
||||
60;0;0,3;1,18265
|
||||
70;0;0,3;1,17261
|
||||
|
39
data/density/density_train.csv
Normal file
39
data/density/density_train.csv
Normal file
@ -0,0 +1,39 @@
|
||||
T;Al2O3;TiO2;Density
|
||||
20;0;0;1,0625
|
||||
25;0;0;1,05979
|
||||
35;0;0;1,05404
|
||||
40;0;0;1,05103
|
||||
45;0;0;1,04794
|
||||
50;0;0;1,04477
|
||||
60;0;0;1,03826
|
||||
65;0;0;1,03484
|
||||
70;0;0;1,03182
|
||||
20;0,05;0;1,08755
|
||||
45;0,05;0;1,07105
|
||||
50;0,05;0;1,0676
|
||||
55;0,05;0;1,06409
|
||||
65;0,05;0;1,05691
|
||||
70;0,05;0;1,05291
|
||||
20;0,3;0;1,18861
|
||||
25;0,3;0;1,18389
|
||||
30;0,3;0;1,1792
|
||||
40;0,3;0;1,17017
|
||||
45;0,3;0;1,16572
|
||||
50;0,3;0;1,16138
|
||||
55;0,3;0;1,15668
|
||||
60;0,3;0;1,15233
|
||||
70;0,3;0;1,14414
|
||||
20;0;0,05;1,09098
|
||||
25;0;0,05;1,08775
|
||||
30;0;0,05;1,08443
|
||||
35;0;0,05;1,08108
|
||||
40;0;0,05;1,07768
|
||||
60;0;0,05;1,06362
|
||||
65;0;0,05;1,05999
|
||||
70;0;0,05;1,05601
|
||||
25;0;0,3;1,2186
|
||||
35;0;0,3;1,20776
|
||||
45;0;0,3;1,19759
|
||||
50;0;0,3;1,19268
|
||||
55;0;0,3;1,18746
|
||||
65;0;0,3;1,178
|
||||
|
244
data/dollar.csv
Normal file
244
data/dollar.csv
Normal file
@ -0,0 +1,244 @@
|
||||
"my_date","my_value","bullet","bulletClass","label"
|
||||
"28.03.2023","76.5662","","",""
|
||||
"31.03.2023","77.0863","","",""
|
||||
"01.04.2023","77.3233","","",""
|
||||
"04.04.2023","77.9510","","",""
|
||||
"05.04.2023","79.3563","","",""
|
||||
"06.04.2023","79.4961","","",""
|
||||
"07.04.2023","80.6713","","",""
|
||||
"08.04.2023","82.3988","","",""
|
||||
"11.04.2023","81.7441","","",""
|
||||
"12.04.2023","82.1799","","",""
|
||||
"13.04.2023","82.0934","","",""
|
||||
"14.04.2023","81.6758","","",""
|
||||
"15.04.2023","81.5045","","",""
|
||||
"18.04.2023","81.6279","","",""
|
||||
"19.04.2023","81.6028","","",""
|
||||
"20.04.2023","81.6549","","",""
|
||||
"21.04.2023","81.6188","","",""
|
||||
"22.04.2023","81.4863","","",""
|
||||
"25.04.2023","81.2745","","",""
|
||||
"26.04.2023","81.5499","","",""
|
||||
"27.04.2023","81.6274","","",""
|
||||
"28.04.2023","81.5601","","",""
|
||||
"29.04.2023","80.5093","","",""
|
||||
"03.05.2023","79.9609","","",""
|
||||
"04.05.2023","79.3071","","",""
|
||||
"05.05.2023","78.6139","","",""
|
||||
"06.05.2023","76.8207","","",""
|
||||
"11.05.2023","76.6929","","",""
|
||||
"12.05.2023","75.8846","round","min-pulsating-bullet","мин"
|
||||
"13.05.2023","77.2041","","",""
|
||||
"16.05.2023","79.1004","","",""
|
||||
"17.05.2023","79.9798","","",""
|
||||
"18.05.2023","80.7642","","",""
|
||||
"19.05.2023","80.0366","","",""
|
||||
"20.05.2023","79.9093","","",""
|
||||
"23.05.2023","79.9379","","",""
|
||||
"24.05.2023","80.1665","","",""
|
||||
"25.05.2023","79.9669","","",""
|
||||
"26.05.2023","79.9841","","",""
|
||||
"27.05.2023","79.9667","","",""
|
||||
"30.05.2023","80.0555","","",""
|
||||
"31.05.2023","80.6872","","",""
|
||||
"01.06.2023","80.9942","","",""
|
||||
"02.06.2023","80.9657","","",""
|
||||
"03.06.2023","80.8756","","",""
|
||||
"06.06.2023","81.3294","","",""
|
||||
"07.06.2023","81.2502","","",""
|
||||
"08.06.2023","81.4581","","",""
|
||||
"09.06.2023","82.0930","","",""
|
||||
"10.06.2023","82.6417","","",""
|
||||
"14.06.2023","83.6405","","",""
|
||||
"15.06.2023","84.3249","","",""
|
||||
"16.06.2023","83.9611","","",""
|
||||
"17.06.2023","83.6498","","",""
|
||||
"20.06.2023","83.9866","","",""
|
||||
"21.06.2023","84.2336","","",""
|
||||
"22.06.2023","84.2467","","",""
|
||||
"23.06.2023","83.6077","","",""
|
||||
"24.06.2023","84.0793","","",""
|
||||
"27.06.2023","84.6642","","",""
|
||||
"28.06.2023","85.0504","","",""
|
||||
"29.06.2023","85.6192","","",""
|
||||
"30.06.2023","87.0341","","",""
|
||||
"01.07.2023","88.3844","","",""
|
||||
"04.07.2023","89.3255","","",""
|
||||
"05.07.2023","89.5450","","",""
|
||||
"06.07.2023","90.3380","","",""
|
||||
"07.07.2023","92.5695","","",""
|
||||
"08.07.2023","91.6879","","",""
|
||||
"11.07.2023","91.4931","","",""
|
||||
"12.07.2023","90.5045","","",""
|
||||
"13.07.2023","90.6253","","",""
|
||||
"14.07.2023","90.1757","","",""
|
||||
"15.07.2023","90.1190","","",""
|
||||
"18.07.2023","90.4217","","",""
|
||||
"19.07.2023","90.6906","","",""
|
||||
"20.07.2023","91.2046","","",""
|
||||
"21.07.2023","90.8545","","",""
|
||||
"22.07.2023","90.3846","","",""
|
||||
"25.07.2023","90.4890","","",""
|
||||
"26.07.2023","90.0945","","",""
|
||||
"27.07.2023","90.0468","","",""
|
||||
"28.07.2023","90.0225","","",""
|
||||
"29.07.2023","90.9783","","",""
|
||||
"01.08.2023","91.5923","","",""
|
||||
"02.08.2023","91.7755","","",""
|
||||
"03.08.2023","92.8410","","",""
|
||||
"04.08.2023","93.7792","","",""
|
||||
"05.08.2023","94.8076","","",""
|
||||
"08.08.2023","96.5668","","",""
|
||||
"09.08.2023","96.0755","","",""
|
||||
"10.08.2023","97.3999","","",""
|
||||
"11.08.2023","97.2794","","",""
|
||||
"12.08.2023","98.2066","","",""
|
||||
"15.08.2023","101.0399","","",""
|
||||
"16.08.2023","97.4217","","",""
|
||||
"17.08.2023","96.7045","","",""
|
||||
"18.08.2023","93.7460","","",""
|
||||
"19.08.2023","93.4047","","",""
|
||||
"22.08.2023","94.1424","","",""
|
||||
"23.08.2023","94.1185","","",""
|
||||
"24.08.2023","94.4421","","",""
|
||||
"25.08.2023","94.4007","","",""
|
||||
"26.08.2023","94.7117","","",""
|
||||
"29.08.2023","95.4717","","",""
|
||||
"30.08.2023","95.7070","","",""
|
||||
"31.08.2023","95.9283","","",""
|
||||
"01.09.2023","96.3344","","",""
|
||||
"02.09.2023","96.3411","","",""
|
||||
"05.09.2023","96.6199","","",""
|
||||
"06.09.2023","97.5383","","",""
|
||||
"07.09.2023","97.8439","","",""
|
||||
"08.09.2023","98.1961","","",""
|
||||
"09.09.2023","97.9241","","",""
|
||||
"12.09.2023","96.5083","","",""
|
||||
"13.09.2023","94.7035","","",""
|
||||
"14.09.2023","95.9794","","",""
|
||||
"15.09.2023","96.1609","","",""
|
||||
"16.09.2023","96.6338","","",""
|
||||
"19.09.2023","96.6472","","",""
|
||||
"20.09.2023","96.2236","","",""
|
||||
"21.09.2023","96.6172","","",""
|
||||
"22.09.2023","96.0762","","",""
|
||||
"23.09.2023","96.0419","","",""
|
||||
"26.09.2023","96.1456","","",""
|
||||
"27.09.2023","96.2378","","",""
|
||||
"28.09.2023","96.5000","","",""
|
||||
"29.09.2023","97.0018","","",""
|
||||
"30.09.2023","97.4147","","",""
|
||||
"03.10.2023","98.4785","","",""
|
||||
"04.10.2023","99.2677","","",""
|
||||
"05.10.2023","99.4555","","",""
|
||||
"06.10.2023","99.6762","","",""
|
||||
"07.10.2023","100.4911","","",""
|
||||
"10.10.2023","101.3598","round","max-pulsating-bullet","макс"
|
||||
"11.10.2023","99.9349","","",""
|
||||
"12.10.2023","99.9808","","",""
|
||||
"13.10.2023","96.9948","","",""
|
||||
"14.10.2023","97.3075","","",""
|
||||
"17.10.2023","97.2865","","",""
|
||||
"18.10.2023","97.3458","","",""
|
||||
"19.10.2023","97.3724","","",""
|
||||
"20.10.2023","97.3074","","",""
|
||||
"21.10.2023","95.9053","","",""
|
||||
"24.10.2023","94.7081","","",""
|
||||
"25.10.2023","93.5224","","",""
|
||||
"26.10.2023","93.1507","","",""
|
||||
"27.10.2023","93.5616","","",""
|
||||
"28.10.2023","93.2174","","",""
|
||||
"31.10.2023","93.2435","","",""
|
||||
"01.11.2023","92.0226","","",""
|
||||
"02.11.2023","93.2801","","",""
|
||||
"03.11.2023","93.1730","","",""
|
||||
"04.11.2023","93.0351","","",""
|
||||
"08.11.2023","92.4151","","",""
|
||||
"09.11.2023","92.1973","","",""
|
||||
"10.11.2023","91.9266","","",""
|
||||
"11.11.2023","92.0535","","",""
|
||||
"14.11.2023","92.1185","","",""
|
||||
"15.11.2023","91.2570","","",""
|
||||
"16.11.2023","89.4565","","",""
|
||||
"17.11.2023","88.9466","","",""
|
||||
"18.11.2023","89.1237","","",""
|
||||
"21.11.2023","88.4954","","",""
|
||||
"22.11.2023","87.8701","","",""
|
||||
"23.11.2023","88.1648","","",""
|
||||
"24.11.2023","88.1206","","",""
|
||||
"25.11.2023","88.8133","","",""
|
||||
"28.11.2023","88.7045","","",""
|
||||
"29.11.2023","88.6102","","",""
|
||||
"30.11.2023","88.8841","","",""
|
||||
"01.12.2023","88.5819","","",""
|
||||
"02.12.2023","89.7619","","",""
|
||||
"05.12.2023","90.6728","","",""
|
||||
"06.12.2023","91.5823","","",""
|
||||
"07.12.2023","92.7826","","",""
|
||||
"08.12.2023","92.5654","","",""
|
||||
"09.12.2023","91.6402","","",""
|
||||
"12.12.2023","90.9846","","",""
|
||||
"13.12.2023","90.2158","","",""
|
||||
"14.12.2023","89.8926","","",""
|
||||
"15.12.2023","89.6741","","",""
|
||||
"16.12.2023","89.6966","","",""
|
||||
"19.12.2023","90.4162","","",""
|
||||
"20.12.2023","90.0870","","",""
|
||||
"21.12.2023","90.4056","","",""
|
||||
"22.12.2023","91.7062","","",""
|
||||
"23.12.2023","91.9389","","",""
|
||||
"26.12.2023","91.9690","","",""
|
||||
"27.12.2023","91.7069","","",""
|
||||
"28.12.2023","91.7051","","",""
|
||||
"29.12.2023","90.3041","","",""
|
||||
"30.12.2023","89.6883","","",""
|
||||
"10.01.2024","90.4040","","",""
|
||||
"11.01.2024","89.3939","","",""
|
||||
"12.01.2024","88.7818","","",""
|
||||
"13.01.2024","88.1324","","",""
|
||||
"16.01.2024","87.6772","","",""
|
||||
"17.01.2024","87.6457","","",""
|
||||
"18.01.2024","88.3540","","",""
|
||||
"19.01.2024","88.6610","","",""
|
||||
"20.01.2024","88.5896","","",""
|
||||
"23.01.2024","87.9724","","",""
|
||||
"24.01.2024","87.9199","","",""
|
||||
"25.01.2024","88.2829","","",""
|
||||
"26.01.2024","88.6562","","",""
|
||||
"27.01.2024","89.5159","","",""
|
||||
"30.01.2024","89.6090","","",""
|
||||
"31.01.2024","89.2887","","",""
|
||||
"01.02.2024","89.6678","","",""
|
||||
"02.02.2024","90.2299","","",""
|
||||
"03.02.2024","90.6626","","",""
|
||||
"06.02.2024","91.2434","","",""
|
||||
"07.02.2024","90.6842","","",""
|
||||
"08.02.2024","91.1514","","",""
|
||||
"09.02.2024","91.2561","","",""
|
||||
"10.02.2024","90.8901","","",""
|
||||
"13.02.2024","91.0758","","",""
|
||||
"14.02.2024","91.2057","","",""
|
||||
"15.02.2024","91.4316","","",""
|
||||
"16.02.2024","91.8237","","",""
|
||||
"17.02.2024","92.5492","","",""
|
||||
"20.02.2024","92.4102","","",""
|
||||
"21.02.2024","92.3490","","",""
|
||||
"22.02.2024","92.4387","","",""
|
||||
"23.02.2024","92.7519","","",""
|
||||
"27.02.2024","92.6321","","",""
|
||||
"28.02.2024","92.0425","","",""
|
||||
"29.02.2024","91.8692","","",""
|
||||
"01.03.2024","90.8423","","",""
|
||||
"02.03.2024","91.3336","","",""
|
||||
"05.03.2024","91.3534","","",""
|
||||
"06.03.2024","91.1604","","",""
|
||||
"07.03.2024","90.3412","","",""
|
||||
"08.03.2024","90.7493","","",""
|
||||
"12.03.2024","90.6252","","",""
|
||||
"13.03.2024","90.8818","","",""
|
||||
"19.03.2024","91.9829","","",""
|
||||
"20.03.2024","92.2243","","",""
|
||||
"21.03.2024","92.6861","","",""
|
||||
"22.03.2024","91.9499","","",""
|
||||
"23.03.2024","92.6118","","",""
|
||||
"26.03.2024","92.7761","","",""
|
||||
|
101
data/orders/customers.csv
Normal file
101
data/orders/customers.csv
Normal file
@ -0,0 +1,101 @@
|
||||
customer_id,customer_unique_id,customer_zip_code_prefix,customer_city,customer_state
|
||||
41ce2a54c0b03bf3443c3d931a367089,3a653a41f6f9fc3d2a113cf8398680e8,75265,vianopolis,GO
|
||||
7f8c8b9c2ae27bf3300f670c3d478be8,634f09f6075fe9032e6c19609ffe995a,44024,feira de santana,BA
|
||||
569cf68214806a39acc0f39344aea67f,c2551ea089b7ebbc67a2ea8757152514,44380,cruz das almas,BA
|
||||
d3e3b74c766bc6214e0c830b17ee2341,e97109680b052ee858d93a539597bba7,35400,ouro preto,MG
|
||||
d2b091571da224a1b36412c18bc3bbfe,d699688533772c15a061e8ce81cb56df,4001,sao paulo,SP
|
||||
3b6828a50ffe546942b7a473d70ac0fc,ccafc1c3f270410521c3c6f3b249870f,74820,goiania,GO
|
||||
148348ff65384b4249b762579532e248,db979bdfe0bbba29ecd3df3f6c50bea2,87711,paranavai,PR
|
||||
4f28355e5c17a4a42d3ce2439a1d4501,4acce2834231e13b1514915adda5ec2b,21910,rio de janeiro,RJ
|
||||
3187789bec990987628d7a9beb4dd6ac,6087cfc70fd833cf2db637a5e6e9d76b,88780,imbituba,SC
|
||||
8628fac2267e8c8804525da99c10ed0e,7973a6ba9c81ecaeb3d628c33c7c7c48,85555,palmas,PR
|
||||
4fa1cd166fa598be6de80fa84eaade43,68954feaafe4dd638f3bd3e2afa174ec,8473,sao paulo,SP
|
||||
cf8ffeddf027932e51e4eae73b384059,6cbe8a392b76916e84c2faf69d0d0da0,13454,santa barbara d'oeste,SP
|
||||
48558a50a7ba1aab61891936d2ca7681,42f80af2e6c585667e4eb416859ae153,39370,jequitai,MG
|
||||
8b212b9525f9e74e85e37ed6df37693e,f4a7ef6bd931f83d75d83b71c94e90df,13568,sao carlos,SP
|
||||
c77ee2d8ba1614a4d489a44166894938,9c9cef121cb812cb301babddc2d8331e,38067,uberaba,MG
|
||||
be8c14c16a4d47194ccdfe10f1fc5b1a,c86a25b8f5f6c203bb3471553bdc3200,13157,cosmopolis,SP
|
||||
f5618502bee8eafdee72fb6955e2ebdf,fa0ee7ceb94193fb02aa78ce3a55695a,6395,carapicuiba,SP
|
||||
3df704f53d3f1d4818840b34ec672a9f,04cf8185c71090d28baa4407b2e6d600,5271,sao paulo,SP
|
||||
67407057a7d5ee17d1cd09523f484d13,7cfba6e55439cae3fd2479d62fafe67f,22240,rio de janeiro,RJ
|
||||
afb19a4b667cb708caab312757ec3d3f,a7e7b19ff34ab885f7b7331de2417cf3,78043,cuiaba,MT
|
||||
caded193e8e47b8362864762a83db3c5,08fb46d35bb3ab4037202c23592d1259,13215,jundiai,SP
|
||||
241e78de29b3090cfa1b5d73a8130c72,c63e44efa43f3947087aee96b388d949,4658,sao paulo,SP
|
||||
62b423aab58096ca514ba6aa06be2f98,9c9242ad7f1b52d926ea76778e1c0c57,18052,sorocaba,SP
|
||||
494dded5b201313c64ed7f100595b95c,f2a85dec752b8517b5e58a06ff3cd937,20780,rio de janeiro,RJ
|
||||
e28dd4261bed9c7ba89ecaf411b88f7c,b6aa1d5781553afaa244c3e42246d93c,88302,itajai,SC
|
||||
4afc1dcca5fe8926fc97d60a4497f8ab,a464f750556546a0989d9326ec003ccf,8220,sao paulo,SP
|
||||
761df82feda9778854c6dafdaeb567e4,1428917cd397d4f9ac0fde76dd6f2266,69317,boa vista,RR
|
||||
82f0b75bb50fcb30711e5277e36b3983,4a8c8f751984985cd49f74249da95aae,8485,sao paulo,SP
|
||||
f5458ddc3545711efa883dd7ae7c4497,661a5e18a28b34880ccc60112f2b8e8e,62360,ibiapina,CE
|
||||
295ae9b35379e077273387ff64354b6f,f1f4f45c8602d0db1329eed1c8e935d4,19780,quata,SP
|
||||
3a874b4d4c4b6543206ff5d89287f0c3,a25d5f94840d3c6a1a49f271ed83f4ec,21715,rio de janeiro,RJ
|
||||
f54a9f0e6b351c431402b8461ea51999,39382392765b6dc74812866ee5ee92a7,99655,faxinalzinho,RS
|
||||
456dc10730fbdba34615447ea195d643,1974875b4a1d2e2ee6d586e3ba4d7602,5634,sao paulo,SP
|
||||
f178c1827f67a8467b0385b7378d951a,9d9ab3b77f0416765b3fbedf94a942a4,12070,taubate,SP
|
||||
0bf19317b1830a69e55b40710576aa7a,5ddb4fdd9cef2450d17ae20639815885,13218,jundiai,SP
|
||||
8644be24d48806bc3a88fd59fb47ceb1,4ca5f90433afb5493247f0bafb583483,73350,brasilia,DF
|
||||
3391c4bc11a817e7973e498b0b023158,1b542f810484d8c042aed33a7c61a218,4561,sao paulo,SP
|
||||
fee181bf648906d1c57f84f216976286,4754e3b66497719a91b36268ed9c5718,13760,tapiratiba,SP
|
||||
74805bc388861fa350ed2fade8444e0b,5d710d9a48ebb7fe5ffc2940ff29f346,38401,uberlandia,MG
|
||||
6772a0a230a2667d16c3620f000e1348,c7a9a76a4b24a7e7b2caff982409b7ee,58600,santa luzia,PB
|
||||
4632eb5a8f175f6fe020520ae0c678f3,6da92ae920ab16fc4eceb8fcd7bd43ce,8280,sao paulo,SP
|
||||
d9ef95f98d8da3b492bb8c0447910498,a2649503b92028291f011a976619b322,26572,mesquita,RJ
|
||||
059f7fc5719c7da6cbafe370971a8d70,d0ff1a7468fcc46b8fc658ab35d2a12c,13186,hortolandia,SP
|
||||
ddaff536587109b89777e0353215e150,c796780c7daeab9e94cc052b1f103b21,26600,paracambi,RJ
|
||||
dd5095632e3953fc0947b8ab5176b0be,da45a9a1df408c39f013b9b0b505042c,70680,brasilia,DF
|
||||
df9b032b2ad0fd6bf37dfb48e5f83845,410979f3cfd34e467d4fad78bd0f0219,89440,irineopolis,SC
|
||||
684fa6da5134b9e4dab731e00011712d,ddf60e20e6e262e2136801ce5cd628b0,49030,aracaju,SE
|
||||
2b56e94c2f66f2d97cfa63356f69cee8,cc1a30280651daf2d918ed7868575771,95270,flores da cunha,RS
|
||||
9f6618c17568ac301465fe7ad056c674,e3bcfea9bab07b492391664fc1ffc28a,44180,antonio cardoso,BA
|
||||
29cb486c739f9774c8eb542e07b56cd2,2ae3c67452283d5a0d30b32e0d33296e,71505,brasilia,DF
|
||||
5f16605299d698660e0606f7eae2d2f9,92fd8aa5948e20c43a014c44c025c5e1,77480,alvorada,TO
|
||||
f88197465ea7920adcdbec7375364d82,7c142cf63193a1473d2e66489a9ae977,59296,sao goncalo do amarante,RN
|
||||
5dda11942d4f77bee3a46d71e442aec4,6a0e43f0d7e1b5539e4c58a26ebe35da,46740,boninal,BA
|
||||
a90391a47de936d56c66a5366cba1462,32de2a7a93dbfc527b3f584744b9c6ce,37310,bom jardim de minas,MG
|
||||
9916715c2ab6ee1710c9c32f0a534ad2,bf0303939d54b8df5da4762bbaab1955,22631,rio de janeiro,RJ
|
||||
636e15840ab051faa13d3f781b6e4233,65e5aaf9f721945f29cdba45c206cb83,14090,ribeirao preto,SP
|
||||
8ab97904e6daea8866dbdbc4fb7aad2c,72632f0f9dd73dfee390c9b22eb56dd6,9195,santo andre,SP
|
||||
388025bec8128ff20ec1a316ed4dcf02,f9effeed3df9ae063a58c0759b96f8b2,85804,cascavel,PR
|
||||
c7340080e394356141681bd4c9b8fe31,3e4fd73f1e86b135b9b121d6abbe9597,19400,presidente venceslau,SP
|
||||
503740e9ca751ccdda7ba28e9ab8f608,80bb27c7c16e8f973207a5086ab329e2,86320,congonhinhas,PR
|
||||
816f8653d5361cbf94e58c33f2502a5c,37363700139c1aef873bbcd916e57dfd,5778,sao paulo,SP
|
||||
9ef432eb6251297304e76186b10a928d,7c396fd4830fd04220f754e42b4e5bff,3149,sao paulo,SP
|
||||
68451b39b1314302c08c65a29f1140fc,781ae350edb16842380e81d7c7feb431,20740,rio de janeiro,RJ
|
||||
b673f0597cb0c4d12778f731045f361a,04e495a3f45df8b41be2e934bbc16961,94055,gravatai,RS
|
||||
3a897024068ed42a183de61d5727d866,adeefbe14d26d3bf90facfeaae35d605,4845,sao paulo,SP
|
||||
52142aa69d8d0e1247ab0cada0f76023,a6fefcd9f434474cf6fcd8ed1102fd63,55540,palmares,PE
|
||||
55e6b290205c84ddd23ddf5eb134efd4,7f2eb9cf900070f2e7a7f0e95719f85b,13145,paulinia,SP
|
||||
ed0271e0b7da060a393796590e7b737a,36edbb3fb164b1f16485364b6fb04c73,98900,santa rosa,RS
|
||||
a9d37ddc8ba4d9f6dbac7d8ec378cc95,3c0402bcc3ec3b33fc4430eb6c08720a,89225,joinville,SC
|
||||
b0830fb4747a6c6d20dea0b8c802d7ef,af07308b275d755c9edb36a90c618231,47813,barreiras,BA
|
||||
bb2f5e670f7155dc622c57e4b31d0a69,31b8fa2573bde01af4737e8ed29c348b,2346,sao paulo,SP
|
||||
756fb9391752dad934e0fe3733378e57,394b2ce444baae9ae609f5d32000de0f,47850,luis eduardo magalhaes,BA
|
||||
5bb39c890c91b1d26801aa19a9336eac,a71cac9f356cfeb9db35061020806212,2407,sao paulo,SP
|
||||
7e20bf5ca92da68200643bda76c504c6,576ea0cab426cd8a00fad9a9c90a4494,41213,salvador,BA
|
||||
2a1dfb647f32f4390e7b857c67458536,5f7d7732b351ce851a158528581af05f,54330,jaboatao dos guararapes,PE
|
||||
cce89a605105b148387c52e286ac8335,bd13608b9c6033892ce62269b50a0afc,9182,santo andre,SP
|
||||
738b086814c6fcc74b8cc583f8516ee3,6e26bbeaa107ec34112c64e1ee31c0f5,21381,rio de janeiro,RJ
|
||||
81e08b08e5ed4472008030d70327c71f,0e764fc1a13e47e900c3d59a989753e8,36045,juiz de fora,MG
|
||||
911e4c37f5cafe1604fe6767034bf1ae,51838d41add414a0b1b989b7d251d9ee,13068,campinas,SP
|
||||
f26a435864aebedff7f7c84f82ee229f,bb4d84a2b45b22ed710ac8c0dec63d1a,8552,poa,SP
|
||||
9bdf08b4b3b52b5526ff42d37d47f222,932afa1e708222e5821dac9cd5db4cae,26525,nilopolis,RJ
|
||||
64fb950e760ec8b0db79154a1fa9c1bf,b11b7871c2b8be2d11fab954f58542f2,18017,sorocaba,SP
|
||||
bf141bf67fbe428d558bcf0e018eab60,c756e1910755edd88c00ac3f46baba4b,31255,belo horizonte,MG
|
||||
3135962ee745ef39b85576df7ddbaa99,00b2ca23369b68c4d4105ecea9c0cb93,62970,alto santo,CE
|
||||
1833a0540067becaf59368fe4cd4303a,ca73adc05ad5d0d880de79b5ea3253b3,4053,sao paulo,SP
|
||||
7f2178c5d771e17f507d3c1637339298,12e7a2c201751ddc979e7a45cef500f3,1038,sao paulo,SP
|
||||
c622b892a190735ef81c0087973fa16d,439ced9aafa171a1ac88efa951c7db0a,85618,flor da serra do sul,PR
|
||||
79183cd650e2bb0d475b0067d45946ac,c77154776ead8e798c2d684205938f71,90620,porto alegre,RS
|
||||
332df68ccac2f2f7d9e11299188f8bce,bb7ef994cc22b1fc694ac59fb377b824,39135,presidente kubitschek,MG
|
||||
a166da34890074091a942054b36e4265,451e48381edab7f1f6dbfa6d728616ff,89070,blumenau,SC
|
||||
f5afca14dfa9dc64251cf2b45c54c363,38cad70d154a4dcc42b598d5c01f7ef1,25211,duque de caxias,RJ
|
||||
31ad1d1b63eb9962463f764d4e6e0c9d,299905e3934e9e181bfb2e164dd4b4f8,18075,sorocaba,SP
|
||||
7711cf624183d843aafe81855097bc37,782987b81c92239d922aa49d6bd4200b,4278,sao paulo,SP
|
||||
72ae281627a6102d9b3718528b420f8a,b8df986511d928829c3192c2ed081eba,3323,sao paulo,SP
|
||||
12fd2740039676063a874b9567dfa651,372e0fc66eacb8698e4f9997d366d961,12230,sao jose dos campos,SP
|
||||
19402a48fe860416adf93348aba37740,e2dfa3127fedbbca9707b36304996dab,4812,sao paulo,SP
|
||||
9b18f3fc296990b97854e351334a32f6,b2cac0b16835dabf811b204127f58afa,6330,carapicuiba,SP
|
||||
05e996469a2bf9559c7122b87e156724,5229b8e4d7d2b9b676c2083c17b1ecd0,93180,portao,RS
|
||||
2932d241d1f31e6df6c701d52370ae02,f7603d34c795584792a484186233e6e5,3942,sao paulo,SP
|
||||
93ada7a24817edda9f4ab998fa823d16,cd148470c375939669971e8a032b16b4,14091,ribeirao preto,SP
|
||||
|
116
data/orders/order_items.csv
Normal file
116
data/orders/order_items.csv
Normal file
@ -0,0 +1,116 @@
|
||||
order_id,order_item_id,product_id,seller_id,shipping_limit_date,price,freight_value
|
||||
0a4a2fccb27bd83a892fa503987a595b,1,f7d7b5c58704fb359a74580622800051,4a3ca9315b744ce9f8e9374361493884,2017-04-28 20:55:09,38.5,24.84
|
||||
0e782c3705510e717d28907746cbda82,1,79da264732f717f10ebf5d102aa6c32a,562fc2f2c2863ab7e79a9e4388a58a14,2018-05-07 08:52:58,29.99,7.39
|
||||
10c320f977c6a18f91b2d14be13128c6,1,b3be1f83cef05668c25e134852d44545,3b15288545f8928d3e65a8f949a28291,2017-05-16 21:02:45,110.99,21.27
|
||||
116f0b09343b49556bbad5f35bee0cdf,1,a47295965bd091207681b541b26e40a5,ea8482cd71df3c1969d7b9473ff13abc,2018-01-02 23:50:22,27.99,15.1
|
||||
136cce7faa42fdb2cefd53fdc79a6098,1,a1804276d9941ac0733cfd409f5206eb,dc8798cbf453b7e0f98745e396cc5616,2017-04-19 13:25:17,49.9,16.05
|
||||
138849fd84dff2fb4ca70a0a34c4aa1c,1,304fad8dc4d2012dc4062839972f2d96,6860153b69cc696d5dcfe1cdaaafcf62,2018-02-08 02:53:07,39.47,13.37
|
||||
1790eea0b567cf50911c057cf20f90f9,1,2d8f2be4f08788ee3bf5356af2b2ee6c,d91fb3b7d041e83b64a00a3edfb37e4f,2018-04-22 22:10:26,186.9,38.0
|
||||
1e7aff52cdbb2451ace09d0f848c3699,1,8c591ab0ca519558779df02023177f44,a1043bafd471dff536d0c462352beb48,2017-05-25 19:05:17,119.99,34.2
|
||||
203096f03d82e0dffbc41ebc2e2bcfb7,1,5ac9d9e379c606e36a8094a6046f75dc,633ecdf879b94b5337cca303328e4a25,2017-09-25 04:04:09,109.9,8.96
|
||||
20e0101b20700188cadb288126949685,1,64d0feb1bcf9c7fe7b5dad3271c10910,e5a38146df062edaf55c38afa99e42dc,2018-01-26 19:36:35,89.18,16.38
|
||||
23f553848a03aaab35bb3f9f87725125,1,cac9e5692471a0700418aa3400b9b2b1,36890be00bbfc1cdb9a4a38a6af05a69,2018-06-15 09:31:23,99.2,18.57
|
||||
25f4376934e13d3508486352e11a5db0,1,aca2eb7d00ea1a7b8ebd4e68314663af,955fee9216a65b617aa5c0531780ce60,2018-05-22 01:17:39,69.9,12.43
|
||||
2711a938db643b3f0b62ee2c8a2784aa,1,ad1128daf194f4b6ac4256e16233497c,1ca7077d890b907f89be8c954a02686a,2017-12-29 02:15:31,45.0,14.1
|
||||
2807d0e504d6d4894d41672727bc139f,1,6893767814d1ac82a81bcd365e1cc918,8b321bb669392f5163d04c59e235e066,2018-02-08 20:50:22,9.5,7.78
|
||||
2ce1ad82022c1ba30c2079502ac725aa,1,f35927953ed82e19d06ad3aac2f06353,669ae81880e08f269a64487cfb287169,2017-08-17 04:15:29,115.0,15.56
|
||||
2edfd6d1f0b4cd0db4bf37b1b224d855,1,30469bb5ea377eae7121981e2f0778e4,80e6699fe29150b372a0c8a1ebf7dcc8,2017-06-21 03:05:45,113.0,28.15
|
||||
34513ce0c4fab462a55830c0989c7edb,1,f7e0fa615b386bc9a8b9eb52bc1fff76,87142160b41353c4e5fca2360caf6f92,2017-07-19 20:10:08,98.0,16.13
|
||||
3bc77ce8be27211bac313c2daa402d1a,1,f497ba62f1d6b4f6a3a3266fa8623ad3,6df688df543f90e9b38f4319e75a9d88,2017-04-12 22:50:24,58.2,8.78
|
||||
403b97836b0c04a622354cf531062e5f,1,638bbb2a5e4f360b71f332ddfebfd672,c4af86330efa7a2620772227d2d670c9,2018-01-12 19:09:04,1299.0,77.45
|
||||
40c5e18f7d112b59b3e5113a59a905b3,1,595fac2a385ac33a80bd5114aec74eb8,ef0ace09169ac090589d85746e3e036f,2018-06-15 10:58:32,119.9,8.78
|
||||
41bb5cee06dbf170878a9ef93ac7e7f5,1,43ee88561093499d9e571d4db5f20b79,23613d49c3ac2bd302259e55c06c050c,2018-05-28 08:52:24,10.9,12.79
|
||||
432aaf21d85167c2c86ec9448c4e42cc,1,72d3bf1d3a790f8874096fcf860e3eff,0bae85eb84b9fb3bd773911e89288d54,2018-03-07 15:10:47,38.25,16.11
|
||||
434d158e96bdd6972ad6e6d73ddcfd22,1,c7df652246ed7b3300aaf46960c141e4,a5cba26a62b8b4d0145b68b841e62e7f,2018-06-13 03:35:15,445.0,63.17
|
||||
47770eb9100c2d0c44946d9cf07ec65d,1,aa4383b373c6aca5d8797843e5594415,4869f7a5dfa277a7dca6462dcf3b52b2,2018-08-13 08:55:23,159.9,19.22
|
||||
47aa4816b27ba60ec948cd019cc1afc1,1,1501b0033c68a37fa9560033a440e529,33cbbec1e7e1044aaf11d152172c776f,2018-06-29 03:31:40,53.44,18.47
|
||||
53cdb2fc8bc7dce0b6741e2150273451,1,595fac2a385ac33a80bd5114aec74eb8,289cdb325fb7e7f891c38608bf9e0962,2018-07-30 03:24:27,118.7,22.76
|
||||
5820a1100976432c7968a52da59e9364,1,1deda1acffb44ed38494667d7e49a9f3,f52c2422904463fdd7741f99045fecb6,2018-07-31 11:44:19,33.9,18.34
|
||||
5acce57f8d9dfd55fa48e212a641a69d,1,0cd9f302c8a5b076ffa5c3567c6705fd,85d9eb9ddc5d00ca9336a2219c97bb13,2017-08-08 02:56:02,27.9,15.1
|
||||
5ff96c15d0b717ac6ad1f3d77225a350,1,10adb53d8faa890ca7c2f0cbcb68d777,1900267e848ceeba8fa32d80c1a5f5a8,2018-07-27 17:55:14,19.9,12.8
|
||||
60550084e6b4c0cb89a87df1f3e5ebd9,1,9b37a918bcf2c8e1064e867cf1df4637,f27e33c6d29b5138fa9967bcd445b6d5,2018-03-01 02:10:52,39.9,26.89
|
||||
634e8f4c0f6744a626f77f39770ac6aa,1,69d980b4120a76616d7b237d731d6156,744dac408745240a2c2528fb1b6028f3,2017-08-15 18:45:18,219.0,15.28
|
||||
641fb0752bf5b5940c376b3a8bb9dc52,1,60184212dae4e6b0da32bf54271a8c4a,b33e7c55446eabf8fe1a42d037ac7d6d,2017-12-21 00:14:55,369.0,17.33
|
||||
6514b8ad8028c9f2cc2374ded245783f,1,4520766ec412348b8d4caa5e8a18c464,16090f2ca825584b5a147ab24aa30c86,2017-05-22 13:22:11,59.99,15.17
|
||||
66e4624ae69e7dc89bd50222b59f581f,1,b37b72d5a56f887725c2862184b8cab8,db4350fd57ae30082dec7acbaacc17f9,2018-03-15 15:30:45,22.99,22.85
|
||||
66e4624ae69e7dc89bd50222b59f581f,2,b37b72d5a56f887725c2862184b8cab8,db4350fd57ae30082dec7acbaacc17f9,2018-03-15 15:30:45,22.99,22.85
|
||||
686541986ecfb7d9296eb67719973bf0,1,3014e35fd70fce29095ced5cdc89f4ce,5656537e588803a555b8eb41f07a944b,2018-02-15 13:35:31,24.89,15.1
|
||||
688052146432ef8253587b930b01a06d,1,d1c427060a0f73f6b889a5c7c61f2ac4,a1043bafd471dff536d0c462352beb48,2018-04-26 09:31:11,119.0,24.97
|
||||
688052146432ef8253587b930b01a06d,2,db56f6d2b04c89eae4daba188842fd7b,2a84855fd20af891be03bc5924d2b453,2018-04-26 09:31:11,199.0,3.12
|
||||
68873cf91053cd11e6b49a766db5af1a,1,15a9e834e89eab39d973492882c658d6,a673821011d0cec28146ea42f5ab767f,2017-12-07 02:51:18,79.9,11.76
|
||||
68e48e68da1f50f7c5838ea75e3a20dd,1,a659cb33082b851fb87a33af8f0fff29,817245bcc3badd82bbd222e0366951a6,2018-06-22 17:00:57,84.9,13.25
|
||||
68e48e68da1f50f7c5838ea75e3a20dd,2,a659cb33082b851fb87a33af8f0fff29,817245bcc3badd82bbd222e0366951a6,2018-06-22 17:00:57,84.9,13.25
|
||||
68e48e68da1f50f7c5838ea75e3a20dd,3,a659cb33082b851fb87a33af8f0fff29,817245bcc3badd82bbd222e0366951a6,2018-06-22 17:00:57,84.9,13.25
|
||||
68e48e68da1f50f7c5838ea75e3a20dd,4,a659cb33082b851fb87a33af8f0fff29,817245bcc3badd82bbd222e0366951a6,2018-06-22 17:00:57,84.9,13.25
|
||||
6a0a8bfbbe700284feb0845d95e0867f,1,f8a8f05a35976a91aed5cccc3992c357,4a3ca9315b744ce9f8e9374361493884,2017-11-28 11:46:50,83.9,17.84
|
||||
6abaad69b8b349c3a529b4b91ce18e46,1,3dd6c9d499e7c311a29e08afe1fd8fc6,537eb890efff034a88679788b647c564,2018-02-21 09:47:59,42.9,14.1
|
||||
6b860b35691d486e45dc98e3514ec5f6,1,c827fb43ad0fb8708f34c2911fdc164b,76d5af76d0271110f9af36c92573f765,2017-12-14 02:49:54,544.0,30.36
|
||||
6d25592267349b322799e2beb687871e,1,c3ba4e8d3cb30049213b682e751e9d00,6560211a19b47992c3666cc44a7e94c0,2018-08-30 04:10:18,93.0,7.91
|
||||
6d25592267349b322799e2beb687871e,2,c3ba4e8d3cb30049213b682e751e9d00,6560211a19b47992c3666cc44a7e94c0,2018-08-30 04:10:18,93.0,7.91
|
||||
6ea2f835b4556291ffdc53fa0b3b95e8,1,be021417a6acb56b9b50d3fd2714baa8,f5f46307a4d15880ca14fab4ad9dfc9b,2017-11-30 00:21:09,339.0,17.12
|
||||
6ebaec694d7025e2ad4a05dba887c032,1,e251ebd2858be1aa7d9b2087a6992580,001cca7ae9ae17fb1caed9dfb1094831,2017-05-24 14:05:17,139.0,14.72
|
||||
7206b86ea789983f7a273ea7fa0bc2a8,1,9a469eaf45dfbc43d39ba1977a3c07af,d2374cbcbb3ca4ab1086534108cc3ab7,2018-03-30 17:27:57,36.9,12.79
|
||||
734e7d1bbaeb2ff82521ca0fe6fb6f79,1,278b3c6462e86b4556b99989513ddf73,d1ef48b38baca7e831711c4a0aeb398f,2018-06-13 08:31:12,29.99,13.47
|
||||
76c6e866289321a7c93b82b54852dc33,1,ac1789e492dcd698c5c10b97a671243a,63b9ae557efed31d1f7687917d248a8d,2017-01-27 18:29:09,19.9,16.05
|
||||
77e9941864fc840be8e4b1ba5347c0f7,1,a01d1cbb398e386a4a8f8364401a7584,d566c37fa119d5e66c4e9052e83ee4ea,2018-08-07 09:10:14,65.9,37.37
|
||||
82566a660a982b15fb86e904c8d32918,1,72a97c271b2e429974398f46b93ae530,094ced053e257ae8cae57205592d6712,2018-06-18 03:13:12,31.9,18.23
|
||||
82bce245b1c9148f8d19a55b9ff70644,1,a5a0e71a81ae65aa335e71c06261e260,c8417879a15366a17c30af34c798c332,2017-04-27 05:15:56,38.0,15.56
|
||||
82bce245b1c9148f8d19a55b9ff70644,2,a5a0e71a81ae65aa335e71c06261e260,c8417879a15366a17c30af34c798c332,2017-04-27 05:15:56,38.0,15.56
|
||||
82bce245b1c9148f8d19a55b9ff70644,3,a5a0e71a81ae65aa335e71c06261e260,c8417879a15366a17c30af34c798c332,2017-04-27 05:15:56,38.0,15.56
|
||||
82bce245b1c9148f8d19a55b9ff70644,4,a5a0e71a81ae65aa335e71c06261e260,c8417879a15366a17c30af34c798c332,2017-04-27 05:15:56,38.0,15.56
|
||||
82bce245b1c9148f8d19a55b9ff70644,5,a5a0e71a81ae65aa335e71c06261e260,c8417879a15366a17c30af34c798c332,2017-04-27 05:15:56,38.0,15.56
|
||||
83018ec114eee8641c97e08f7b4e926f,1,c35498fbb4358837ae16850f50c3fd22,70a12e78e608ac31179aea7f8422044b,2017-11-01 16:07:35,76.0,16.97
|
||||
8447ff843b2616c50c0ced28ab1dae03,1,7a10781637204d8d10485c71a6108a2e,4869f7a5dfa277a7dca6462dcf3b52b2,2017-12-29 02:37:45,219.9,18.79
|
||||
8563039e855156e48fccee4d611a3196,1,bff2010b28e8fbcff5a9db9d3fea5ac4,955fee9216a65b617aa5c0531780ce60,2018-02-22 15:15:34,78.0,28.95
|
||||
85ce859fd6dc634de8d2f1e290444043,1,cce679660c66e6fbd5c8091dfd29e9cd,d2374cbcbb3ca4ab1086534108cc3ab7,2017-11-29 00:14:22,17.9,11.85
|
||||
86f21bf63784876b9fd6d35f46581d72,1,5526b1ae9ab2688cf600783cece249df,0b90b6df587eb83608a64ea8b390cf07,2018-04-23 22:49:32,98.44,22.4
|
||||
8f06cc6465925031568537b815f1198d,1,12087840651e83b48206b82c213b76fd,5b925e1d006e9476d738aa200751b73b,2017-11-21 11:46:42,299.0,18.34
|
||||
91b2a010e1e45e6ba3d133fa997597be,1,ba74c6b75d2ad7503175809688d5a03c,7d13fca15225358621be4086e1eb0964,2018-05-09 12:55:01,178.99,13.69
|
||||
948097deef559c742e7ce321e5e58919,1,cd935d283d47f1050c505e1c39c48b67,a3a38f4affed601eb87a97788c949667,2017-08-10 17:25:11,69.9,25.77
|
||||
949d5b44dbf5de918fe9c16f97b45f8a,1,d0b61bfb1de832b15ba9d266ca96e5b0,66922902710d126a0e7d26b0e3805106,2017-11-23 19:45:59,45.0,27.2
|
||||
95266dbfb7e20354baba07964dac78d5,1,bb7181410b4e02f93f3697f765db53c7,855668e0971d4dfd7bef1b6a4133b41b,2018-01-26 08:07:31,129.99,57.58
|
||||
974c1993ab8024d3ed16229183c2308d,1,5e2ba75ad255ff60b1c76c5bf526ae9b,f84a00e60c73a49e7e851c9bdca3a5bb,2017-02-24 11:45:39,69.9,14.66
|
||||
989225ba6d0ebd5873335f7e01de2ae7,1,6b64362e89896be7589621df54be089e,77530e9772f57a62c906e1c21538ab82,2017-12-20 13:54:13,49.0,14.1
|
||||
9defaf92cff22420e4e8ef7784815a55,1,cf944645d4ff2a3eed3ae17f641ea861,a6fe7de3d16f6149ffe280349a8535a0,2018-05-23 13:30:30,49.9,12.79
|
||||
9faeb9b2746b9d7526aef5acb08e2aa0,1,f48eb5c2fde13ca63664f0bb05f55346,f7ba60f8c3f99e7ee4042fdef03b70c4,2018-07-30 14:55:10,60.0,15.52
|
||||
9faeb9b2746b9d7526aef5acb08e2aa0,2,f48eb5c2fde13ca63664f0bb05f55346,f7ba60f8c3f99e7ee4042fdef03b70c4,2018-07-30 14:55:10,60.0,15.52
|
||||
a4591c265e18cb1dcee52889e2d8acc3,1,060cb19345d90064d1015407193c233d,8581055ce74af1daba164fdbd55a40de,2017-07-13 22:10:13,147.9,27.36
|
||||
a685d016c8a26f71a0bb67821070e398,1,ebd7c847c1e1cb69ec374ae0ebee1f4c,391fc6631aebcf3004804e51b40bcf1e,2017-03-17 18:14:36,84.9,14.36
|
||||
a6aeb116d2cb5013eb8a94585b71ffef,1,163e6400e6dadd0fe04775c5e9331fda,855668e0971d4dfd7bef1b6a4133b41b,2017-09-19 14:44:39,50.0,9.34
|
||||
a910f58086d58b3ae6f37aa712d377b9,1,75d6b6963340c6063f7f4cfcccfe6a30,cc419e0650a3c5ba77189a1882b7556a,2017-09-22 09:35:18,56.99,15.84
|
||||
a910f58086d58b3ae6f37aa712d377b9,2,75d6b6963340c6063f7f4cfcccfe6a30,cc419e0650a3c5ba77189a1882b7556a,2017-09-22 09:35:18,56.99,15.84
|
||||
acce194856392f074dbf9dada14d8d82,1,d70f38e7f79c630f8ea00c993897042c,977f9f63dd360c2a32ece2f93ad6d306,2018-06-13 00:35:10,90.9,48.64
|
||||
acce194856392f074dbf9dada14d8d82,2,9451e630d725c4bb7a5a206b48b99486,d673a59aac7a70d8b01e6902bf090a11,2018-06-13 00:35:10,39.5,48.64
|
||||
ad21c59c0840e6cb83a9ceb5573f8159,1,65266b2da20d04dbe00c5c2d3bb7859e,2c9e548be18521d1c43cde1c582c6de8,2018-02-19 20:31:37,19.9,8.72
|
||||
b276e4f8c0fb86bd82fce576f21713e0,1,c6c1f263e076bd9c1f1640250a5d0c29,fe2032dab1a61af8794248c8196565c9,2018-08-02 23:45:15,179.0,9.41
|
||||
b52cc4919de82b4d696a4380d10804a3,1,7564c1759c04fc0a38f2aa84f7a370ee,6860153b69cc696d5dcfe1cdaaafcf62,2018-06-19 02:30:26,42.99,12.03
|
||||
b8801cccd8068de30112e4f49903d74a,1,154e7e31ebfa092203795c972e5804a6,cc419e0650a3c5ba77189a1882b7556a,2017-08-08 03:25:08,19.99,7.78
|
||||
bd4bd0194d6d29f83b8557d4b89b572a,1,7f457254a89d62960399e075711b3deb,ea8482cd71df3c1969d7b9473ff13abc,2018-08-02 03:50:24,24.99,12.84
|
||||
cadbb3657dac2dbbd5b84b12e7b78aad,1,9d2ff462feaaf88912539b8647e17ab4,00fc707aaaad2d31347cf883cd2dfe10,2018-03-13 02:48:54,394.9,14.89
|
||||
ccbabeb0b02433bd0fcbac46e70339f2,1,89321f94e35fc6d7903d36f74e351d40,16090f2ca825584b5a147ab24aa30c86,2018-02-27 03:31:34,27.9,15.1
|
||||
d17dc4a904426827ca80f2ccb3a6be56,1,ba4bfbf74dbe7ab37e263b9326da0523,f8db351d8c4c4c22c6835c19a46f01b0,2017-05-18 20:42:45,36.9,17.92
|
||||
d22e9fa5731b9e30e8b27afcdc2f8563,1,f410090aec61f7c73748ca894286edcd,980640c45d7a4635885491d077167e4d,2018-08-07 23:35:13,99.0,22.62
|
||||
d3d6788577c9592da441752e8a1dd5e3,1,7c1bd920dbdf22470b68bde975dd3ccf,cc419e0650a3c5ba77189a1882b7556a,2017-09-27 07:55:14,58.99,17.66
|
||||
d887b52c6516beb39e8cd44a5f8b60f7,1,39a9942865c056ed2006a5e8c11d9537,ba5daa4041e1f15cdf34b76e3e18a450,2018-02-08 12:50:30,84.9,15.35
|
||||
dcb36b511fcac050b97cd5c05de84dc3,1,009c09f439988bc06a93d6b8186dce73,89a51f50b8095ea78d5768f34c13a76f,2018-06-18 18:59:02,132.4,14.05
|
||||
dd78f560c270f1909639c11b925620ea,1,00baba5b58e274d0332a0c8a0a66f877,d3f39f05462b79a4562d35893a28f159,2018-03-16 02:30:56,47.9,12.79
|
||||
e425680f760cbc130be3e53a9773c584,1,9ecadb84c81da840dbf3564378b586e9,1025f0e2d44d7041d6cf58b6550e0bfa,2017-09-08 08:30:17,38.4,11.85
|
||||
e481f51cbdc54678b7cc49136f2d6af7,1,87285b34884572647811a353c7ac498a,3504c0cb71d7fa48d967e0e4c94d59d9,2017-10-06 11:07:15,29.99,8.72
|
||||
e4de6d53ecff736bc68804b0b6e9f635,1,90b58782fdd04cb829667fcc41fb65f5,7c67e1448b00f6e969d365cea6b010ab,2017-10-27 03:49:34,179.99,51.13
|
||||
e69bfb5eb88e0ed6a785585b27e16dbf,1,9a78fb9862b10749a117f7fc3c31f051,7c67e1448b00f6e969d365cea6b010ab,2017-08-11 12:05:32,149.99,19.77
|
||||
e6ce16cb79ec1d90b1da9085a6118aeb,1,08574b074924071f4e201e151b152b4e,001cca7ae9ae17fb1caed9dfb1094831,2017-05-22 19:50:18,99.0,30.53
|
||||
e6ce16cb79ec1d90b1da9085a6118aeb,2,08574b074924071f4e201e151b152b4e,001cca7ae9ae17fb1caed9dfb1094831,2017-05-22 19:50:18,99.0,30.53
|
||||
ec341c54a5ebf8ee0a67a8632aa7579b,1,22f5b63060a1185e5ec7721efd622321,4c8b8048e33af2bf94f2eb547746a916,2017-08-31 17:04:12,14.82,15.1
|
||||
ecab90c9933c58908d3d6add7c6f5ae3,1,c0db539123a403f670c50237d970b215,f7720c4fa8e3aba4546301ab80ea1f1b,2018-03-01 14:28:03,30.1,33.24
|
||||
ee64d42b8cf066f35eac1cf57de1aa85,1,c50ca07e9e4db9ea5011f06802c0aea0,e9779976487b77c6d4ac45f75ec7afe9,2018-06-13 04:30:33,14.49,7.87
|
||||
f169bd689fb8b32ccd62df9050aebc0b,1,20a8603c265d777e25da064113d556f5,e70053bf73d1b5863932e53a9fa47496,2018-04-29 23:31:10,759.0,13.08
|
||||
f271576bed568e896f99eb710cd3a6f8,1,d457916b4fdc60154ed93b5dd3e6fd69,76d64c4aca3a7baf218bf93ef7fa768d,2018-01-11 21:51:28,329.9,82.48
|
||||
f271576bed568e896f99eb710cd3a6f8,2,d457916b4fdc60154ed93b5dd3e6fd69,76d64c4aca3a7baf218bf93ef7fa768d,2018-01-11 21:51:28,329.9,82.48
|
||||
f346ad4ee8f630e5e4ddaf862a34e6dd,1,4ce99ff9dcb7821acd8e599d5d4a6531,70125af26c2d6d4ef401a1d02ae7701f,2018-08-07 13:24:34,39.9,13.76
|
||||
f3e7c359154d965827355f39d6b1fdac,1,e99d69efe684efaa643f99805f7c81bc,55c26bcb609f480eb7868594245febb5,2018-08-14 03:24:51,89.9,14.21
|
||||
f70a0aff17df5a6cdd9a7196128bd354,1,cafd558df4c3c9d1c338ba6930ea9a62,5dceca129747e92ff8ef7a997dc4f8ca,2017-08-17 02:45:24,279.0,34.19
|
||||
f7959f8385f34c4f645327465a1c9fc4,1,c1234c80dafde7ef3311b3eabd5069ed,dc4a0fc896dc34b0d5bfec8438291c80,2017-04-11 08:05:08,17.9,10.96
|
||||
f848643eec1d69395095eb3840d2051e,1,2b4609f8948be18874494203496bc318,cc419e0650a3c5ba77189a1882b7556a,2018-03-23 09:09:31,79.99,8.91
|
||||
fa516182d28f96f5f5c651026b0749ee,1,e932008cf0ea7c93a077dd8d7e5f49eb,fcdd820084f17e9982427971e4e9d47f,2018-04-19 13:30:02,190.0,19.41
|
||||
fbf9ac61453ac646ce8ad9783d7d0af6,1,7b717060aa783eb7f23a747a3a733dd7,c0563dd588b775f2e37747ef6ad6c92c,2018-02-28 02:30:44,109.9,15.53
|
||||
fdf128b3630c21adc9ca4fb8a51b68ec,1,89321f94e35fc6d7903d36f74e351d40,16090f2ca825584b5a147ab24aa30c86,2018-07-18 14:31:10,27.9,18.3
|
||||
|
101
data/orders/orders.csv
Normal file
101
data/orders/orders.csv
Normal file
@ -0,0 +1,101 @@
|
||||
order_id,customer_id,order_status,order_purchase_timestamp,order_approved_at,order_delivered_carrier_date,order_delivered_customer_date,order_estimated_delivery_date
|
||||
e481f51cbdc54678b7cc49136f2d6af7,9ef432eb6251297304e76186b10a928d,delivered,2017-10-02 10:56:33,2017-10-02 11:07:15,2017-10-04 19:55:00,2017-10-10 21:25:13,2017-10-18 00:00:00
|
||||
53cdb2fc8bc7dce0b6741e2150273451,b0830fb4747a6c6d20dea0b8c802d7ef,delivered,2018-07-24 20:41:37,2018-07-26 03:24:27,2018-07-26 14:31:00,2018-08-07 15:27:45,2018-08-13 00:00:00
|
||||
47770eb9100c2d0c44946d9cf07ec65d,41ce2a54c0b03bf3443c3d931a367089,delivered,2018-08-08 08:38:49,2018-08-08 08:55:23,2018-08-08 13:50:00,2018-08-17 18:06:29,2018-09-04 00:00:00
|
||||
949d5b44dbf5de918fe9c16f97b45f8a,f88197465ea7920adcdbec7375364d82,delivered,2017-11-18 19:28:06,2017-11-18 19:45:59,2017-11-22 13:39:59,2017-12-02 00:28:42,2017-12-15 00:00:00
|
||||
ad21c59c0840e6cb83a9ceb5573f8159,8ab97904e6daea8866dbdbc4fb7aad2c,delivered,2018-02-13 21:18:39,2018-02-13 22:20:29,2018-02-14 19:46:34,2018-02-16 18:17:02,2018-02-26 00:00:00
|
||||
a4591c265e18cb1dcee52889e2d8acc3,503740e9ca751ccdda7ba28e9ab8f608,delivered,2017-07-09 21:57:05,2017-07-09 22:10:13,2017-07-11 14:58:04,2017-07-26 10:57:55,2017-08-01 00:00:00
|
||||
136cce7faa42fdb2cefd53fdc79a6098,ed0271e0b7da060a393796590e7b737a,invoiced,2017-04-11 12:22:08,2017-04-13 13:25:17,,,2017-05-09 00:00:00
|
||||
6514b8ad8028c9f2cc2374ded245783f,9bdf08b4b3b52b5526ff42d37d47f222,delivered,2017-05-16 13:10:30,2017-05-16 13:22:11,2017-05-22 10:07:46,2017-05-26 12:55:51,2017-06-07 00:00:00
|
||||
76c6e866289321a7c93b82b54852dc33,f54a9f0e6b351c431402b8461ea51999,delivered,2017-01-23 18:29:09,2017-01-25 02:50:47,2017-01-26 14:16:31,2017-02-02 14:08:10,2017-03-06 00:00:00
|
||||
e69bfb5eb88e0ed6a785585b27e16dbf,31ad1d1b63eb9962463f764d4e6e0c9d,delivered,2017-07-29 11:55:02,2017-07-29 12:05:32,2017-08-10 19:45:24,2017-08-16 17:14:30,2017-08-23 00:00:00
|
||||
e6ce16cb79ec1d90b1da9085a6118aeb,494dded5b201313c64ed7f100595b95c,delivered,2017-05-16 19:41:10,2017-05-16 19:50:18,2017-05-18 11:40:40,2017-05-29 11:18:31,2017-06-07 00:00:00
|
||||
34513ce0c4fab462a55830c0989c7edb,7711cf624183d843aafe81855097bc37,delivered,2017-07-13 19:58:11,2017-07-13 20:10:08,2017-07-14 18:43:29,2017-07-19 14:04:48,2017-08-08 00:00:00
|
||||
82566a660a982b15fb86e904c8d32918,d3e3b74c766bc6214e0c830b17ee2341,delivered,2018-06-07 10:06:19,2018-06-09 03:13:12,2018-06-11 13:29:00,2018-06-19 12:05:52,2018-07-18 00:00:00
|
||||
5ff96c15d0b717ac6ad1f3d77225a350,19402a48fe860416adf93348aba37740,delivered,2018-07-25 17:44:10,2018-07-25 17:55:14,2018-07-26 13:16:00,2018-07-30 15:52:25,2018-08-08 00:00:00
|
||||
432aaf21d85167c2c86ec9448c4e42cc,3df704f53d3f1d4818840b34ec672a9f,delivered,2018-03-01 14:14:28,2018-03-01 15:10:47,2018-03-02 21:09:20,2018-03-12 23:36:26,2018-03-21 00:00:00
|
||||
dcb36b511fcac050b97cd5c05de84dc3,3b6828a50ffe546942b7a473d70ac0fc,delivered,2018-06-07 19:03:12,2018-06-12 23:31:02,2018-06-11 14:54:00,2018-06-21 15:34:32,2018-07-04 00:00:00
|
||||
403b97836b0c04a622354cf531062e5f,738b086814c6fcc74b8cc583f8516ee3,delivered,2018-01-02 19:00:43,2018-01-02 19:09:04,2018-01-03 18:19:09,2018-01-20 01:38:59,2018-02-06 00:00:00
|
||||
116f0b09343b49556bbad5f35bee0cdf,3187789bec990987628d7a9beb4dd6ac,delivered,2017-12-26 23:41:31,2017-12-26 23:50:22,2017-12-28 18:33:05,2018-01-08 22:36:36,2018-01-29 00:00:00
|
||||
85ce859fd6dc634de8d2f1e290444043,059f7fc5719c7da6cbafe370971a8d70,delivered,2017-11-21 00:03:41,2017-11-21 00:14:22,2017-11-23 21:32:26,2017-11-27 18:28:00,2017-12-11 00:00:00
|
||||
83018ec114eee8641c97e08f7b4e926f,7f8c8b9c2ae27bf3300f670c3d478be8,delivered,2017-10-26 15:54:26,2017-10-26 16:08:14,2017-10-26 21:46:53,2017-11-08 22:22:00,2017-11-23 00:00:00
|
||||
203096f03d82e0dffbc41ebc2e2bcfb7,d2b091571da224a1b36412c18bc3bbfe,delivered,2017-09-18 14:31:30,2017-09-19 04:04:09,2017-10-06 17:50:03,2017-10-09 22:23:46,2017-09-28 00:00:00
|
||||
f848643eec1d69395095eb3840d2051e,4fa1cd166fa598be6de80fa84eaade43,delivered,2018-03-15 08:52:40,2018-03-15 09:09:31,2018-03-15 19:52:48,2018-03-19 18:08:32,2018-03-29 00:00:00
|
||||
2807d0e504d6d4894d41672727bc139f,72ae281627a6102d9b3718528b420f8a,delivered,2018-02-03 20:37:35,2018-02-03 20:50:22,2018-02-05 22:37:28,2018-02-08 16:13:46,2018-02-21 00:00:00
|
||||
95266dbfb7e20354baba07964dac78d5,a166da34890074091a942054b36e4265,delivered,2018-01-08 07:55:29,2018-01-08 08:07:31,2018-01-24 23:16:37,2018-01-26 17:32:38,2018-02-21 00:00:00
|
||||
f3e7c359154d965827355f39d6b1fdac,62b423aab58096ca514ba6aa06be2f98,delivered,2018-08-09 11:44:40,2018-08-10 03:24:51,2018-08-10 12:29:00,2018-08-13 18:24:27,2018-08-17 00:00:00
|
||||
fbf9ac61453ac646ce8ad9783d7d0af6,3a874b4d4c4b6543206ff5d89287f0c3,delivered,2018-02-20 23:46:53,2018-02-22 02:30:46,2018-02-26 22:25:22,2018-03-21 22:03:54,2018-03-12 00:00:00
|
||||
acce194856392f074dbf9dada14d8d82,7e20bf5ca92da68200643bda76c504c6,delivered,2018-06-04 00:00:13,2018-06-05 00:35:10,2018-06-05 13:24:00,2018-06-16 15:20:55,2018-07-18 00:00:00
|
||||
dd78f560c270f1909639c11b925620ea,8b212b9525f9e74e85e37ed6df37693e,delivered,2018-03-12 01:50:26,2018-03-12 03:28:34,2018-03-12 21:06:37,2018-03-21 14:41:50,2018-03-28 00:00:00
|
||||
91b2a010e1e45e6ba3d133fa997597be,cce89a605105b148387c52e286ac8335,delivered,2018-05-02 11:45:38,2018-05-03 12:55:01,2018-05-10 16:16:00,2018-05-16 20:56:24,2018-05-23 00:00:00
|
||||
ecab90c9933c58908d3d6add7c6f5ae3,761df82feda9778854c6dafdaeb567e4,delivered,2018-02-25 13:50:30,2018-02-25 14:47:35,2018-02-26 22:28:50,2018-03-27 23:29:14,2018-04-13 00:00:00
|
||||
f70a0aff17df5a6cdd9a7196128bd354,456dc10730fbdba34615447ea195d643,delivered,2017-08-10 11:58:33,2017-08-12 02:45:24,2017-08-17 15:35:07,2017-08-18 14:28:02,2017-08-23 00:00:00
|
||||
1790eea0b567cf50911c057cf20f90f9,52142aa69d8d0e1247ab0cada0f76023,delivered,2018-04-16 21:15:39,2018-04-16 22:10:26,2018-04-18 13:05:09,2018-05-05 12:28:34,2018-05-15 00:00:00
|
||||
989225ba6d0ebd5873335f7e01de2ae7,816f8653d5361cbf94e58c33f2502a5c,delivered,2017-12-12 13:56:04,2017-12-14 13:54:13,2017-12-16 00:18:57,2018-01-03 18:03:36,2018-01-08 00:00:00
|
||||
d887b52c6516beb39e8cd44a5f8b60f7,d9ef95f98d8da3b492bb8c0447910498,delivered,2018-02-03 12:38:58,2018-02-03 12:50:30,2018-02-05 21:26:53,2018-02-22 00:07:55,2018-03-07 00:00:00
|
||||
b276e4f8c0fb86bd82fce576f21713e0,cf8ffeddf027932e51e4eae73b384059,delivered,2018-07-29 23:34:51,2018-07-29 23:45:15,2018-07-30 14:43:00,2018-07-31 22:48:50,2018-08-06 00:00:00
|
||||
8563039e855156e48fccee4d611a3196,5f16605299d698660e0606f7eae2d2f9,delivered,2018-02-17 15:59:46,2018-02-17 16:15:34,2018-02-20 23:03:56,2018-03-20 00:59:25,2018-03-20 00:00:00
|
||||
60550084e6b4c0cb89a87df1f3e5ebd9,f5458ddc3545711efa883dd7ae7c4497,delivered,2018-02-21 18:15:12,2018-02-23 02:10:52,2018-02-27 18:52:09,2018-03-13 23:58:43,2018-03-29 00:00:00
|
||||
5acce57f8d9dfd55fa48e212a641a69d,295ae9b35379e077273387ff64354b6f,delivered,2017-07-31 21:37:10,2017-08-02 02:56:02,2017-08-03 18:32:48,2017-08-08 21:24:41,2017-08-22 00:00:00
|
||||
434d158e96bdd6972ad6e6d73ddcfd22,2a1dfb647f32f4390e7b857c67458536,delivered,2018-06-01 12:23:13,2018-06-05 03:35:15,2018-06-08 11:49:00,2018-06-18 21:32:52,2018-07-17 00:00:00
|
||||
7206b86ea789983f7a273ea7fa0bc2a8,3391c4bc11a817e7973e498b0b023158,delivered,2018-03-26 17:12:18,2018-03-26 17:28:27,2018-03-28 17:22:53,2018-04-05 22:11:18,2018-04-12 00:00:00
|
||||
1e7aff52cdbb2451ace09d0f848c3699,ddaff536587109b89777e0353215e150,delivered,2017-05-19 18:53:40,2017-05-19 19:05:17,2017-05-22 10:16:07,2017-05-31 13:58:46,2017-06-12 00:00:00
|
||||
6ea2f835b4556291ffdc53fa0b3b95e8,c7340080e394356141681bd4c9b8fe31,delivered,2017-11-24 21:27:48,2017-11-25 00:21:09,2017-12-13 21:14:05,2017-12-28 18:59:23,2017-12-21 00:00:00
|
||||
948097deef559c742e7ce321e5e58919,8644be24d48806bc3a88fd59fb47ceb1,delivered,2017-08-04 17:10:39,2017-08-04 17:25:11,2017-08-07 17:52:01,2017-08-12 14:08:40,2017-09-01 00:00:00
|
||||
d22e9fa5731b9e30e8b27afcdc2f8563,756fb9391752dad934e0fe3733378e57,delivered,2018-08-04 23:25:30,2018-08-04 23:35:13,2018-08-06 15:03:00,2018-08-13 23:34:42,2018-09-13 00:00:00
|
||||
ee64d42b8cf066f35eac1cf57de1aa85,caded193e8e47b8362864762a83db3c5,shipped,2018-06-04 16:44:48,2018-06-05 04:31:18,2018-06-05 14:32:00,,2018-06-28 00:00:00
|
||||
6ebaec694d7025e2ad4a05dba887c032,4f28355e5c17a4a42d3ce2439a1d4501,delivered,2017-05-18 13:55:47,2017-05-18 14:05:17,2017-05-19 12:01:38,2017-05-29 12:47:20,2017-06-09 00:00:00
|
||||
d17dc4a904426827ca80f2ccb3a6be56,569cf68214806a39acc0f39344aea67f,delivered,2017-05-14 20:28:25,2017-05-14 20:42:45,2017-05-16 08:17:46,2017-05-25 09:14:31,2017-06-12 00:00:00
|
||||
25f4376934e13d3508486352e11a5db0,12fd2740039676063a874b9567dfa651,delivered,2018-05-17 16:59:11,2018-05-18 01:17:39,2018-05-18 13:02:00,2018-05-21 15:22:11,2018-05-25 00:00:00
|
||||
5820a1100976432c7968a52da59e9364,2b56e94c2f66f2d97cfa63356f69cee8,delivered,2018-07-29 11:24:17,2018-07-29 11:44:19,2018-07-30 13:47:00,2018-08-02 22:09:11,2018-08-13 00:00:00
|
||||
2ce1ad82022c1ba30c2079502ac725aa,7f2178c5d771e17f507d3c1637339298,delivered,2017-08-09 20:19:05,2017-08-11 04:15:29,2017-08-11 17:52:32,2017-08-16 17:16:44,2017-08-31 00:00:00
|
||||
138849fd84dff2fb4ca70a0a34c4aa1c,9b18f3fc296990b97854e351334a32f6,delivered,2018-02-01 14:02:19,2018-02-03 02:53:07,2018-02-06 19:13:26,2018-02-14 13:41:59,2018-02-23 00:00:00
|
||||
47aa4816b27ba60ec948cd019cc1afc1,148348ff65384b4249b762579532e248,delivered,2018-06-26 13:42:52,2018-06-27 08:35:32,2018-06-27 13:20:00,2018-07-03 18:37:46,2018-07-20 00:00:00
|
||||
9faeb9b2746b9d7526aef5acb08e2aa0,79183cd650e2bb0d475b0067d45946ac,delivered,2018-07-26 14:39:59,2018-07-26 14:55:10,2018-07-27 12:04:00,2018-07-31 22:26:55,2018-08-16 00:00:00
|
||||
641fb0752bf5b5940c376b3a8bb9dc52,f5afca14dfa9dc64251cf2b45c54c363,delivered,2017-12-15 00:06:10,2017-12-15 00:14:55,2017-12-19 01:58:00,2018-01-03 15:09:32,2018-01-16 00:00:00
|
||||
e425680f760cbc130be3e53a9773c584,f178c1827f67a8467b0385b7378d951a,delivered,2017-08-31 08:15:24,2017-08-31 08:30:17,2017-08-31 20:06:14,2017-09-04 20:59:55,2017-09-20 00:00:00
|
||||
40c5e18f7d112b59b3e5113a59a905b3,67407057a7d5ee17d1cd09523f484d13,delivered,2018-06-11 10:25:52,2018-06-11 10:58:32,2018-06-14 13:03:00,2018-06-19 00:31:13,2018-07-16 00:00:00
|
||||
734e7d1bbaeb2ff82521ca0fe6fb6f79,2932d241d1f31e6df6c701d52370ae02,delivered,2018-06-11 08:18:19,2018-06-11 08:31:50,2018-06-11 14:54:00,2018-06-14 21:32:21,2018-07-05 00:00:00
|
||||
66e4624ae69e7dc89bd50222b59f581f,684fa6da5134b9e4dab731e00011712d,delivered,2018-03-09 14:50:15,2018-03-09 15:40:39,2018-03-15 00:31:19,2018-04-03 13:28:46,2018-04-02 00:00:00
|
||||
a685d016c8a26f71a0bb67821070e398,911e4c37f5cafe1604fe6767034bf1ae,delivered,2017-03-13 18:14:36,2017-03-13 18:14:36,2017-03-22 14:03:09,2017-04-06 13:37:16,2017-03-30 00:00:00
|
||||
2edfd6d1f0b4cd0db4bf37b1b224d855,241e78de29b3090cfa1b5d73a8130c72,delivered,2017-06-13 21:11:26,2017-06-15 03:05:45,2017-06-16 14:55:37,2017-06-19 18:51:28,2017-07-06 00:00:00
|
||||
68873cf91053cd11e6b49a766db5af1a,4632eb5a8f175f6fe020520ae0c678f3,delivered,2017-11-30 22:02:15,2017-12-02 02:51:18,2017-12-04 22:07:01,2017-12-05 20:28:40,2017-12-18 00:00:00
|
||||
f346ad4ee8f630e5e4ddaf862a34e6dd,dd5095632e3953fc0947b8ab5176b0be,delivered,2018-08-05 13:09:48,2018-08-05 13:24:34,2018-08-06 13:41:00,2018-08-10 18:35:40,2018-08-15 00:00:00
|
||||
8f06cc6465925031568537b815f1198d,9916715c2ab6ee1710c9c32f0a534ad2,delivered,2017-11-15 11:31:41,2017-11-15 11:46:42,2017-11-16 22:03:00,2017-11-22 22:41:07,2017-12-05 00:00:00
|
||||
ccbabeb0b02433bd0fcbac46e70339f2,c77ee2d8ba1614a4d489a44166894938,delivered,2018-02-19 20:31:09,2018-02-21 06:15:25,2018-02-22 21:04:23,2018-03-09 22:22:25,2018-03-13 00:00:00
|
||||
688052146432ef8253587b930b01a06d,81e08b08e5ed4472008030d70327c71f,delivered,2018-04-22 08:48:13,2018-04-24 18:25:22,2018-04-23 19:19:14,2018-04-24 19:31:58,2018-05-15 00:00:00
|
||||
f271576bed568e896f99eb710cd3a6f8,5dda11942d4f77bee3a46d71e442aec4,delivered,2018-01-07 21:44:54,2018-01-07 21:51:28,2018-01-10 21:56:09,2018-01-17 20:26:31,2018-02-14 00:00:00
|
||||
686541986ecfb7d9296eb67719973bf0,74805bc388861fa350ed2fade8444e0b,delivered,2018-02-10 13:26:59,2018-02-10 13:35:31,2018-02-14 20:47:38,2018-02-20 22:13:08,2018-03-12 00:00:00
|
||||
68e48e68da1f50f7c5838ea75e3a20dd,4afc1dcca5fe8926fc97d60a4497f8ab,delivered,2018-06-18 16:02:23,2018-06-18 17:00:57,2018-06-19 15:55:00,2018-06-22 21:18:51,2018-07-13 00:00:00
|
||||
b52cc4919de82b4d696a4380d10804a3,be8c14c16a4d47194ccdfe10f1fc5b1a,delivered,2018-06-13 13:47:39,2018-06-15 02:37:29,2018-06-15 14:22:00,2018-06-18 22:32:44,2018-06-26 00:00:00
|
||||
fdf128b3630c21adc9ca4fb8a51b68ec,a9d37ddc8ba4d9f6dbac7d8ec378cc95,delivered,2018-07-15 08:33:19,2018-07-16 14:31:10,2018-07-17 15:33:00,2018-07-24 16:41:18,2018-08-02 00:00:00
|
||||
a6aeb116d2cb5013eb8a94585b71ffef,bb2f5e670f7155dc622c57e4b31d0a69,delivered,2017-09-13 14:27:11,2017-09-13 14:44:39,2017-09-15 18:42:29,2017-09-16 15:40:08,2017-09-25 00:00:00
|
||||
fa516182d28f96f5f5c651026b0749ee,55e6b290205c84ddd23ddf5eb134efd4,delivered,2018-04-13 08:44:17,2018-04-13 13:30:02,2018-04-13 22:19:21,2018-04-19 20:41:45,2018-05-08 00:00:00
|
||||
6abaad69b8b349c3a529b4b91ce18e46,f5618502bee8eafdee72fb6955e2ebdf,delivered,2018-02-15 10:33:30,2018-02-15 10:47:59,2018-02-20 14:15:09,2018-02-24 19:15:56,2018-03-07 00:00:00
|
||||
974c1993ab8024d3ed16229183c2308d,a90391a47de936d56c66a5366cba1462,delivered,2017-02-20 11:45:39,2017-02-22 03:10:20,2017-02-23 06:47:35,2017-03-09 14:27:58,2017-03-21 00:00:00
|
||||
82bce245b1c9148f8d19a55b9ff70644,388025bec8128ff20ec1a316ed4dcf02,delivered,2017-04-20 17:15:46,2017-04-21 05:15:56,2017-04-24 09:34:13,2017-05-10 09:17:55,2017-05-12 00:00:00
|
||||
a910f58086d58b3ae6f37aa712d377b9,afb19a4b667cb708caab312757ec3d3f,delivered,2017-09-15 09:19:48,2017-09-15 09:35:18,2017-09-18 18:20:00,2017-09-25 20:14:48,2017-10-11 00:00:00
|
||||
bd4bd0194d6d29f83b8557d4b89b572a,636e15840ab051faa13d3f781b6e4233,delivered,2018-07-28 16:52:55,2018-07-31 03:50:24,2018-08-01 16:01:00,2018-08-06 18:44:46,2018-08-08 00:00:00
|
||||
634e8f4c0f6744a626f77f39770ac6aa,05e996469a2bf9559c7122b87e156724,delivered,2017-08-09 18:32:47,2017-08-09 18:45:18,2017-08-10 20:21:53,2017-08-16 18:17:54,2017-08-31 00:00:00
|
||||
6d25592267349b322799e2beb687871e,5bb39c890c91b1d26801aa19a9336eac,delivered,2018-08-26 22:04:34,2018-08-28 04:10:18,2018-08-28 12:56:00,2018-08-29 12:40:53,2018-08-30 00:00:00
|
||||
b8801cccd8068de30112e4f49903d74a,f26a435864aebedff7f7c84f82ee229f,delivered,2017-07-30 03:06:35,2017-07-30 03:25:08,2017-07-31 16:42:54,2017-08-01 14:27:31,2017-08-16 00:00:00
|
||||
2711a938db643b3f0b62ee2c8a2784aa,29cb486c739f9774c8eb542e07b56cd2,delivered,2017-12-22 00:17:37,2017-12-23 02:15:31,2017-12-27 19:54:46,2018-01-09 19:52:32,2018-01-19 00:00:00
|
||||
3bc77ce8be27211bac313c2daa402d1a,bf141bf67fbe428d558bcf0e018eab60,delivered,2017-04-06 22:39:29,2017-04-06 22:50:24,2017-04-07 14:54:18,2017-04-11 12:31:36,2017-04-27 00:00:00
|
||||
10c320f977c6a18f91b2d14be13128c6,b673f0597cb0c4d12778f731045f361a,delivered,2017-05-09 20:48:59,2017-05-09 21:02:45,2017-05-10 11:22:15,2017-05-18 13:22:35,2017-06-01 00:00:00
|
||||
0a4a2fccb27bd83a892fa503987a595b,6772a0a230a2667d16c3620f000e1348,delivered,2017-04-20 20:42:44,2017-04-20 20:55:09,2017-04-25 08:23:08,2017-05-11 13:07:46,2017-05-25 00:00:00
|
||||
e4de6d53ecff736bc68804b0b6e9f635,9f6618c17568ac301465fe7ad056c674,delivered,2017-10-16 14:56:50,2017-10-17 03:49:34,2017-10-27 22:14:21,2017-11-08 21:25:24,2017-11-21 00:00:00
|
||||
6b860b35691d486e45dc98e3514ec5f6,fee181bf648906d1c57f84f216976286,delivered,2017-12-08 09:42:43,2017-12-09 02:49:54,2017-12-11 15:19:04,2017-12-19 18:43:35,2018-01-03 00:00:00
|
||||
ec341c54a5ebf8ee0a67a8632aa7579b,df9b032b2ad0fd6bf37dfb48e5f83845,delivered,2017-08-26 16:53:30,2017-08-27 17:04:12,2017-08-30 13:26:32,2017-09-08 20:39:56,2017-09-21 00:00:00
|
||||
cadbb3657dac2dbbd5b84b12e7b78aad,93ada7a24817edda9f4ab998fa823d16,delivered,2018-02-27 12:55:42,2018-03-01 02:48:54,2018-03-03 02:27:03,2018-03-16 14:59:01,2018-03-29 00:00:00
|
||||
9defaf92cff22420e4e8ef7784815a55,64fb950e760ec8b0db79154a1fa9c1bf,delivered,2018-05-11 13:10:51,2018-05-11 13:36:50,2018-05-16 14:43:00,2018-05-21 16:09:55,2018-06-05 00:00:00
|
||||
20e0101b20700188cadb288126949685,48558a50a7ba1aab61891936d2ca7681,delivered,2018-01-22 19:22:22,2018-01-22 19:36:35,2018-01-24 23:32:21,2018-02-15 20:08:15,2018-02-19 00:00:00
|
||||
0e782c3705510e717d28907746cbda82,3a897024068ed42a183de61d5727d866,delivered,2018-05-01 08:12:37,2018-05-01 08:52:58,2018-05-02 19:01:00,2018-05-04 14:02:26,2018-05-16 00:00:00
|
||||
d3d6788577c9592da441752e8a1dd5e3,8628fac2267e8c8804525da99c10ed0e,delivered,2017-09-19 22:17:15,2017-09-20 07:55:14,2017-09-22 17:23:09,2017-10-10 18:43:53,2017-10-13 00:00:00
|
||||
86f21bf63784876b9fd6d35f46581d72,332df68ccac2f2f7d9e11299188f8bce,delivered,2018-04-11 22:32:31,2018-04-11 22:49:32,2018-04-14 00:02:39,2018-04-27 23:14:42,2018-05-21 00:00:00
|
||||
8447ff843b2616c50c0ced28ab1dae03,e28dd4261bed9c7ba89ecaf411b88f7c,delivered,2017-12-20 23:45:07,2017-12-22 02:37:45,2017-12-23 13:10:45,2018-01-09 18:14:02,2018-01-22 00:00:00
|
||||
f169bd689fb8b32ccd62df9050aebc0b,82f0b75bb50fcb30711e5277e36b3983,delivered,2018-04-22 23:23:18,2018-04-24 19:24:14,2018-04-27 13:46:00,2018-04-30 17:57:25,2018-05-07 00:00:00
|
||||
77e9941864fc840be8e4b1ba5347c0f7,3135962ee745ef39b85576df7ddbaa99,delivered,2018-08-03 08:59:39,2018-08-03 09:31:36,2018-08-03 10:10:00,2018-08-17 00:49:41,2018-08-27 00:00:00
|
||||
41bb5cee06dbf170878a9ef93ac7e7f5,1833a0540067becaf59368fe4cd4303a,delivered,2018-05-14 08:35:33,2018-05-14 08:52:24,2018-05-16 14:46:00,2018-05-18 14:48:38,2018-06-08 00:00:00
|
||||
6a0a8bfbbe700284feb0845d95e0867f,68451b39b1314302c08c65a29f1140fc,delivered,2017-11-22 11:32:22,2017-11-22 11:46:50,2017-11-27 13:39:35,2017-12-28 19:43:00,2017-12-11 00:00:00
|
||||
f7959f8385f34c4f645327465a1c9fc4,0bf19317b1830a69e55b40710576aa7a,delivered,2017-03-30 07:50:33,2017-03-30 08:05:08,2017-03-30 10:55:54,2017-04-10 02:59:52,2017-04-26 00:00:00
|
||||
23f553848a03aaab35bb3f9f87725125,c622b892a190735ef81c0087973fa16d,delivered,2018-06-05 09:10:34,2018-06-05 09:32:22,2018-06-06 15:37:00,2018-06-18 12:36:54,2018-07-23 00:00:00
|
||||
|
101
data/orders/products.csv
Normal file
101
data/orders/products.csv
Normal file
@ -0,0 +1,101 @@
|
||||
product_id,product_category_name,product_name_lenght,product_description_lenght,product_photos_qty,product_weight_g,product_length_cm,product_height_cm,product_width_cm
|
||||
278b3c6462e86b4556b99989513ddf73,eletroportateis,58.0,587.0,3.0,350.0,20.0,20.0,20.0
|
||||
3014e35fd70fce29095ced5cdc89f4ce,telefonia,51.0,244.0,1.0,125.0,17.0,10.0,14.0
|
||||
15a9e834e89eab39d973492882c658d6,cama_mesa_banho,52.0,530.0,6.0,949.0,30.0,20.0,26.0
|
||||
db56f6d2b04c89eae4daba188842fd7b,malas_acessorios,56.0,450.0,3.0,12450.0,40.0,25.0,57.0
|
||||
154e7e31ebfa092203795c972e5804a6,beleza_saude,48.0,575.0,1.0,100.0,20.0,15.0,15.0
|
||||
20a8603c265d777e25da064113d556f5,telefonia,59.0,474.0,3.0,475.0,17.0,14.0,14.0
|
||||
87285b34884572647811a353c7ac498a,utilidades_domesticas,40.0,268.0,4.0,500.0,19.0,8.0,13.0
|
||||
7c1bd920dbdf22470b68bde975dd3ccf,beleza_saude,59.0,492.0,2.0,200.0,22.0,10.0,18.0
|
||||
b37b72d5a56f887725c2862184b8cab8,telefonia,59.0,566.0,1.0,150.0,19.0,4.0,11.0
|
||||
ac1789e492dcd698c5c10b97a671243a,moveis_decoracao,41.0,432.0,2.0,300.0,35.0,35.0,15.0
|
||||
f410090aec61f7c73748ca894286edcd,papelaria,60.0,1847.0,3.0,450.0,35.0,50.0,12.0
|
||||
e251ebd2858be1aa7d9b2087a6992580,ferramentas_jardim,34.0,511.0,4.0,8875.0,40.0,14.0,43.0
|
||||
1501b0033c68a37fa9560033a440e529,eletroportateis,58.0,1160.0,6.0,410.0,24.0,22.0,17.0
|
||||
43ee88561093499d9e571d4db5f20b79,moveis_decoracao,39.0,161.0,3.0,200.0,20.0,20.0,20.0
|
||||
f8a8f05a35976a91aed5cccc3992c357,moveis_decoracao,63.0,418.0,1.0,1500.0,45.0,15.0,35.0
|
||||
7564c1759c04fc0a38f2aa84f7a370ee,construcao_ferramentas_construcao,59.0,2432.0,3.0,1200.0,16.0,11.0,11.0
|
||||
ebd7c847c1e1cb69ec374ae0ebee1f4c,moveis_decoracao,50.0,228.0,3.0,1200.0,40.0,15.0,30.0
|
||||
2b4609f8948be18874494203496bc318,beleza_saude,59.0,492.0,3.0,250.0,22.0,10.0,18.0
|
||||
c7df652246ed7b3300aaf46960c141e4,beleza_saude,28.0,1455.0,1.0,683.0,29.0,15.0,22.0
|
||||
2d8f2be4f08788ee3bf5356af2b2ee6c,climatizacao,52.0,331.0,4.0,100.0,27.0,13.0,17.0
|
||||
f7d7b5c58704fb359a74580622800051,cama_mesa_banho,53.0,223.0,1.0,950.0,45.0,15.0,35.0
|
||||
304fad8dc4d2012dc4062839972f2d96,construcao_ferramentas_construcao,59.0,1775.0,2.0,1700.0,16.0,11.0,11.0
|
||||
60184212dae4e6b0da32bf54271a8c4a,relogios_presentes,59.0,476.0,2.0,394.0,17.0,11.0,14.0
|
||||
d1c427060a0f73f6b889a5c7c61f2ac4,informatica_acessorios,59.0,1893.0,1.0,6550.0,20.0,20.0,20.0
|
||||
cf944645d4ff2a3eed3ae17f641ea861,fashion_underwear_e_moda_praia,52.0,579.0,1.0,450.0,42.0,4.0,14.0
|
||||
6893767814d1ac82a81bcd365e1cc918,eletronicos,26.0,511.0,1.0,200.0,25.0,7.0,16.0
|
||||
d70f38e7f79c630f8ea00c993897042c,bebes,53.0,233.0,1.0,10950.0,41.0,40.0,40.0
|
||||
4520766ec412348b8d4caa5e8a18c464,automotivo,59.0,956.0,1.0,50.0,16.0,16.0,17.0
|
||||
5ac9d9e379c606e36a8094a6046f75dc,beleza_saude,46.0,2345.0,6.0,525.0,21.0,16.0,13.0
|
||||
9d2ff462feaaf88912539b8647e17ab4,informatica_acessorios,42.0,315.0,1.0,813.0,32.0,16.0,16.0
|
||||
72d3bf1d3a790f8874096fcf860e3eff,brinquedos,57.0,341.0,2.0,583.0,20.0,21.0,20.0
|
||||
64d0feb1bcf9c7fe7b5dad3271c10910,moveis_decoracao,58.0,696.0,7.0,750.0,25.0,15.0,35.0
|
||||
08574b074924071f4e201e151b152b4e,ferramentas_jardim,36.0,450.0,1.0,9000.0,42.0,12.0,39.0
|
||||
30469bb5ea377eae7121981e2f0778e4,esporte_lazer,57.0,574.0,4.0,5950.0,20.0,30.0,80.0
|
||||
9b37a918bcf2c8e1064e867cf1df4637,eletronicos,57.0,1710.0,6.0,1207.0,20.0,10.0,20.0
|
||||
65266b2da20d04dbe00c5c2d3bb7859e,papelaria,38.0,316.0,4.0,250.0,51.0,15.0,15.0
|
||||
00baba5b58e274d0332a0c8a0a66f877,perfumaria,27.0,406.0,4.0,200.0,18.0,7.0,12.0
|
||||
aa4383b373c6aca5d8797843e5594415,automotivo,46.0,232.0,1.0,420.0,24.0,19.0,21.0
|
||||
f497ba62f1d6b4f6a3a3266fa8623ad3,beleza_saude,45.0,1276.0,1.0,83.0,13.0,8.0,12.0
|
||||
a5a0e71a81ae65aa335e71c06261e260,utilidades_domesticas,57.0,698.0,3.0,705.0,34.0,22.0,28.0
|
||||
c0db539123a403f670c50237d970b215,ferramentas_jardim,56.0,1313.0,2.0,850.0,20.0,20.0,20.0
|
||||
aca2eb7d00ea1a7b8ebd4e68314663af,moveis_decoracao,44.0,903.0,6.0,2600.0,50.0,10.0,30.0
|
||||
c6c1f263e076bd9c1f1640250a5d0c29,perfumaria,32.0,102.0,1.0,425.0,24.0,12.0,16.0
|
||||
6b64362e89896be7589621df54be089e,moveis_decoracao,57.0,2435.0,2.0,3000.0,69.0,11.0,11.0
|
||||
f7e0fa615b386bc9a8b9eb52bc1fff76,informatica_acessorios,59.0,2574.0,1.0,325.0,21.0,21.0,21.0
|
||||
7a10781637204d8d10485c71a6108a2e,relogios_presentes,42.0,236.0,1.0,342.0,18.0,13.0,15.0
|
||||
9451e630d725c4bb7a5a206b48b99486,bebes,52.0,300.0,1.0,350.0,31.0,10.0,12.0
|
||||
ba4bfbf74dbe7ab37e263b9326da0523,esporte_lazer,60.0,521.0,1.0,650.0,24.0,10.0,20.0
|
||||
90b58782fdd04cb829667fcc41fb65f5,moveis_escritorio,34.0,794.0,1.0,7417.0,102.0,46.0,11.0
|
||||
79da264732f717f10ebf5d102aa6c32a,telefonia,59.0,675.0,5.0,150.0,17.0,8.0,14.0
|
||||
c827fb43ad0fb8708f34c2911fdc164b,esporte_lazer,53.0,699.0,1.0,10600.0,26.0,30.0,26.0
|
||||
ba74c6b75d2ad7503175809688d5a03c,relogios_presentes,59.0,1088.0,2.0,292.0,17.0,8.0,12.0
|
||||
c1234c80dafde7ef3311b3eabd5069ed,cama_mesa_banho,55.0,122.0,1.0,300.0,20.0,2.0,15.0
|
||||
5e2ba75ad255ff60b1c76c5bf526ae9b,beleza_saude,47.0,1346.0,2.0,500.0,20.0,8.0,20.0
|
||||
ad1128daf194f4b6ac4256e16233497c,telefonia,32.0,580.0,2.0,100.0,16.0,3.0,11.0
|
||||
163e6400e6dadd0fe04775c5e9331fda,bebes,29.0,462.0,1.0,500.0,47.0,10.0,36.0
|
||||
009c09f439988bc06a93d6b8186dce73,perfumaria,39.0,991.0,3.0,150.0,20.0,20.0,20.0
|
||||
7b717060aa783eb7f23a747a3a733dd7,cool_stuff,46.0,595.0,2.0,500.0,16.0,12.0,22.0
|
||||
9ecadb84c81da840dbf3564378b586e9,moveis_decoracao,41.0,789.0,1.0,950.0,20.0,35.0,20.0
|
||||
060cb19345d90064d1015407193c233d,automotivo,49.0,608.0,1.0,7150.0,65.0,10.0,65.0
|
||||
7f457254a89d62960399e075711b3deb,automotivo,60.0,558.0,6.0,300.0,17.0,4.0,12.0
|
||||
72a97c271b2e429974398f46b93ae530,perfumaria,59.0,685.0,1.0,450.0,16.0,17.0,16.0
|
||||
a47295965bd091207681b541b26e40a5,telefonia,60.0,818.0,6.0,300.0,17.0,4.0,12.0
|
||||
bb7181410b4e02f93f3697f765db53c7,bebes,36.0,1058.0,1.0,14950.0,77.0,20.0,53.0
|
||||
595fac2a385ac33a80bd5114aec74eb8,perfumaria,29.0,178.0,1.0,400.0,19.0,13.0,19.0
|
||||
22f5b63060a1185e5ec7721efd622321,cama_mesa_banho,32.0,606.0,2.0,400.0,90.0,6.0,12.0
|
||||
bff2010b28e8fbcff5a9db9d3fea5ac4,ferramentas_jardim,58.0,769.0,6.0,850.0,90.0,20.0,20.0
|
||||
c35498fbb4358837ae16850f50c3fd22,telefonia,59.0,973.0,1.0,325.0,19.0,8.0,22.0
|
||||
4ce99ff9dcb7821acd8e599d5d4a6531,esporte_lazer,51.0,192.0,2.0,450.0,35.0,10.0,11.0
|
||||
b3be1f83cef05668c25e134852d44545,cama_mesa_banho,52.0,413.0,1.0,1750.0,42.0,11.0,36.0
|
||||
c3ba4e8d3cb30049213b682e751e9d00,relogios_presentes,58.0,737.0,3.0,350.0,16.0,2.0,20.0
|
||||
a1804276d9941ac0733cfd409f5206eb,,,,,600.0,35.0,35.0,15.0
|
||||
cafd558df4c3c9d1c338ba6930ea9a62,bebes,45.0,1009.0,1.0,16450.0,44.0,70.0,32.0
|
||||
d457916b4fdc60154ed93b5dd3e6fd69,construcao_ferramentas_construcao,57.0,424.0,1.0,10000.0,30.0,20.0,30.0
|
||||
638bbb2a5e4f360b71f332ddfebfd672,construcao_ferramentas_construcao,38.0,143.0,2.0,20850.0,100.0,25.0,50.0
|
||||
75d6b6963340c6063f7f4cfcccfe6a30,perfumaria,51.0,999.0,2.0,400.0,18.0,11.0,20.0
|
||||
a659cb33082b851fb87a33af8f0fff29,automotivo,60.0,380.0,1.0,150.0,16.0,6.0,11.0
|
||||
e932008cf0ea7c93a077dd8d7e5f49eb,climatizacao,60.0,3270.0,4.0,7350.0,105.0,10.0,40.0
|
||||
89321f94e35fc6d7903d36f74e351d40,alimentos,59.0,982.0,1.0,150.0,17.0,13.0,13.0
|
||||
0cd9f302c8a5b076ffa5c3567c6705fd,informatica_acessorios,22.0,716.0,2.0,200.0,36.0,2.0,28.0
|
||||
c50ca07e9e4db9ea5011f06802c0aea0,beleza_saude,59.0,1782.0,1.0,125.0,25.0,14.0,18.0
|
||||
e99d69efe684efaa643f99805f7c81bc,papelaria,56.0,115.0,1.0,600.0,33.0,13.0,25.0
|
||||
be021417a6acb56b9b50d3fd2714baa8,utilidades_domesticas,48.0,664.0,6.0,14300.0,38.0,34.0,34.0
|
||||
cce679660c66e6fbd5c8091dfd29e9cd,cama_mesa_banho,43.0,125.0,1.0,250.0,40.0,4.0,30.0
|
||||
3dd6c9d499e7c311a29e08afe1fd8fc6,cool_stuff,60.0,396.0,4.0,250.0,19.0,12.0,12.0
|
||||
9a469eaf45dfbc43d39ba1977a3c07af,cama_mesa_banho,44.0,192.0,1.0,700.0,40.0,4.0,30.0
|
||||
cac9e5692471a0700418aa3400b9b2b1,bebes,57.0,2440.0,1.0,375.0,29.0,14.0,20.0
|
||||
5526b1ae9ab2688cf600783cece249df,informatica_acessorios,49.0,385.0,1.0,200.0,16.0,16.0,16.0
|
||||
9a78fb9862b10749a117f7fc3c31f051,moveis_escritorio,45.0,527.0,1.0,9750.0,42.0,41.0,42.0
|
||||
1deda1acffb44ed38494667d7e49a9f3,esporte_lazer,53.0,891.0,2.0,1150.0,27.0,12.0,17.0
|
||||
10adb53d8faa890ca7c2f0cbcb68d777,cama_mesa_banho,52.0,155.0,1.0,200.0,16.0,10.0,16.0
|
||||
d0b61bfb1de832b15ba9d266ca96e5b0,pet_shop,59.0,468.0,3.0,450.0,30.0,10.0,20.0
|
||||
8c591ab0ca519558779df02023177f44,ferramentas_jardim,47.0,1893.0,1.0,6050.0,20.0,20.0,20.0
|
||||
cd935d283d47f1050c505e1c39c48b67,esporte_lazer,32.0,658.0,5.0,281.0,30.0,14.0,25.0
|
||||
a01d1cbb398e386a4a8f8364401a7584,esporte_lazer,58.0,757.0,2.0,500.0,50.0,5.0,30.0
|
||||
12087840651e83b48206b82c213b76fd,esporte_lazer,27.0,521.0,1.0,1813.0,30.0,13.0,28.0
|
||||
f48eb5c2fde13ca63664f0bb05f55346,esporte_lazer,60.0,1153.0,2.0,100.0,20.0,11.0,11.0
|
||||
69d980b4120a76616d7b237d731d6156,relogios_presentes,60.0,1362.0,3.0,600.0,16.0,11.0,12.0
|
||||
39a9942865c056ed2006a5e8c11d9537,brinquedos,47.0,556.0,5.0,800.0,37.0,14.0,37.0
|
||||
f35927953ed82e19d06ad3aac2f06353,livros_interesse_geral,39.0,724.0,1.0,450.0,20.0,20.0,20.0
|
||||
|
88
data/orders/sellers.csv
Normal file
88
data/orders/sellers.csv
Normal file
@ -0,0 +1,88 @@
|
||||
seller_id,seller_zip_code_prefix,seller_city,seller_state
|
||||
669ae81880e08f269a64487cfb287169,89160,rio do sul,SC
|
||||
817245bcc3badd82bbd222e0366951a6,17056,bauru,SP
|
||||
7d13fca15225358621be4086e1eb0964,14050,ribeirao preto,SP
|
||||
a3a38f4affed601eb87a97788c949667,89204,joinville,SC
|
||||
744dac408745240a2c2528fb1b6028f3,83408,colombo,PR
|
||||
8b321bb669392f5163d04c59e235e066,1212,sao paulo,SP
|
||||
76d64c4aca3a7baf218bf93ef7fa768d,80215,curitiba,PR
|
||||
537eb890efff034a88679788b647c564,20270,rio de janeiro,RJ
|
||||
955fee9216a65b617aa5c0531780ce60,4782,sao paulo,SP
|
||||
ba5daa4041e1f15cdf34b76e3e18a450,4363,sao paulo,SP
|
||||
d3f39f05462b79a4562d35893a28f159,13730,mococa,SP
|
||||
d1ef48b38baca7e831711c4a0aeb398f,86800,apucarana,PR
|
||||
f7ba60f8c3f99e7ee4042fdef03b70c4,9628,sao bernardo do campo,SP
|
||||
f84a00e60c73a49e7e851c9bdca3a5bb,20756,rio de janeiro,RJ
|
||||
e5a38146df062edaf55c38afa99e42dc,1233,sao paulo,SP
|
||||
ef0ace09169ac090589d85746e3e036f,24451,sao goncalo,RJ
|
||||
87142160b41353c4e5fca2360caf6f92,90230,porto alegre,RS
|
||||
289cdb325fb7e7f891c38608bf9e0962,31570,belo horizonte,SP
|
||||
3504c0cb71d7fa48d967e0e4c94d59d9,9350,maua,SP
|
||||
23613d49c3ac2bd302259e55c06c050c,13660,porto ferreira,SP
|
||||
391fc6631aebcf3004804e51b40bcf1e,14940,ibitinga,SP
|
||||
33cbbec1e7e1044aaf11d152172c776f,95705,bento goncalves,RS
|
||||
e9779976487b77c6d4ac45f75ec7afe9,11701,praia grande,SP
|
||||
db4350fd57ae30082dec7acbaacc17f9,3126,sao paulo,SP
|
||||
70125af26c2d6d4ef401a1d02ae7701f,74435,goiania,GO
|
||||
6560211a19b47992c3666cc44a7e94c0,5849,sao paulo,SP
|
||||
0b90b6df587eb83608a64ea8b390cf07,87025,maringa,PR
|
||||
55c26bcb609f480eb7868594245febb5,14910,tabatinga,SP
|
||||
6df688df543f90e9b38f4319e75a9d88,31230,belo horizonte,MG
|
||||
d673a59aac7a70d8b01e6902bf090a11,14940,ibitinga,SP
|
||||
f52c2422904463fdd7741f99045fecb6,9230,santo andre/sao paulo,SP
|
||||
ea8482cd71df3c1969d7b9473ff13abc,4160,sao paulo,SP
|
||||
5b925e1d006e9476d738aa200751b73b,4567,sao paulo,SP
|
||||
fe2032dab1a61af8794248c8196565c9,13030,campinas,SP
|
||||
2a84855fd20af891be03bc5924d2b453,30111,belo horizonte,MG
|
||||
c4af86330efa7a2620772227d2d670c9,8840,mogi das cruzes,SP
|
||||
001cca7ae9ae17fb1caed9dfb1094831,29156,cariacica,ES
|
||||
d91fb3b7d041e83b64a00a3edfb37e4f,11704,praia grande,SP
|
||||
e70053bf73d1b5863932e53a9fa47496,5059,sao paulo,SP
|
||||
7c67e1448b00f6e969d365cea6b010ab,8577,itaquaquecetuba,SP
|
||||
980640c45d7a4635885491d077167e4d,13501,rio claro,SP
|
||||
d2374cbcbb3ca4ab1086534108cc3ab7,14940,ibitinga,SP
|
||||
0bae85eb84b9fb3bd773911e89288d54,88301,itajai,SP
|
||||
6860153b69cc696d5dcfe1cdaaafcf62,13360,capivari,SP
|
||||
76d5af76d0271110f9af36c92573f765,3194,sao paulo,SP
|
||||
cc419e0650a3c5ba77189a1882b7556a,9015,santo andre,SP
|
||||
977f9f63dd360c2a32ece2f93ad6d306,14910,tabatinga,SP
|
||||
2c9e548be18521d1c43cde1c582c6de8,8752,mogi das cruzes,SP
|
||||
855668e0971d4dfd7bef1b6a4133b41b,13257,itatiba,SP
|
||||
77530e9772f57a62c906e1c21538ab82,80310,curitiba,PR
|
||||
f7720c4fa8e3aba4546301ab80ea1f1b,81350,curitiba,PR
|
||||
8581055ce74af1daba164fdbd55a40de,7112,guarulhos,SP
|
||||
c8417879a15366a17c30af34c798c332,4445,sao paulo,SP
|
||||
16090f2ca825584b5a147ab24aa30c86,12940,atibaia,SP
|
||||
4c8b8048e33af2bf94f2eb547746a916,14940,ibitinga,SP
|
||||
00fc707aaaad2d31347cf883cd2dfe10,87025,maringa,PR
|
||||
562fc2f2c2863ab7e79a9e4388a58a14,13070,campinas,SP
|
||||
85d9eb9ddc5d00ca9336a2219c97bb13,31255,belo horizonte,MG
|
||||
a673821011d0cec28146ea42f5ab767f,3809,sao paulo,SP
|
||||
dc4a0fc896dc34b0d5bfec8438291c80,14940,ibitinga,SP
|
||||
a6fe7de3d16f6149ffe280349a8535a0,14401,franca,SP
|
||||
f5f46307a4d15880ca14fab4ad9dfc9b,89165,rio do sul,SC
|
||||
fcdd820084f17e9982427971e4e9d47f,14075,ribeirao preto,SP
|
||||
36890be00bbfc1cdb9a4a38a6af05a69,6040,osasco,SP
|
||||
f27e33c6d29b5138fa9967bcd445b6d5,4273,sao paulo,SP
|
||||
c0563dd588b775f2e37747ef6ad6c92c,9220,santo andre,SP
|
||||
633ecdf879b94b5337cca303328e4a25,4438,sao paulo,SP
|
||||
80e6699fe29150b372a0c8a1ebf7dcc8,83323,pinhais,PR
|
||||
5656537e588803a555b8eb41f07a944b,72015,brasilia,DF
|
||||
5dceca129747e92ff8ef7a997dc4f8ca,13450,santa barbara d´oeste,SP
|
||||
dc8798cbf453b7e0f98745e396cc5616,5455,sao paulo,SP
|
||||
4a3ca9315b744ce9f8e9374361493884,14940,ibitinga,SP
|
||||
b33e7c55446eabf8fe1a42d037ac7d6d,14850,pradopolis,SP
|
||||
3b15288545f8928d3e65a8f949a28291,14940,ibitinga,SP
|
||||
4869f7a5dfa277a7dca6462dcf3b52b2,14840,guariba,SP
|
||||
094ced053e257ae8cae57205592d6712,14095,ribeirao preto,SP
|
||||
a5cba26a62b8b4d0145b68b841e62e7f,87303,campo mourao,PR
|
||||
1025f0e2d44d7041d6cf58b6550e0bfa,3204,sao paulo,SP
|
||||
a1043bafd471dff536d0c462352beb48,37175,ilicinea,MG
|
||||
f8db351d8c4c4c22c6835c19a46f01b0,13324,salto,SP
|
||||
1ca7077d890b907f89be8c954a02686a,6506,santana de parnaiba,SP
|
||||
89a51f50b8095ea78d5768f34c13a76f,71931,brasilia,DF
|
||||
d566c37fa119d5e66c4e9052e83ee4ea,4131,sao paulo,SP
|
||||
70a12e78e608ac31179aea7f8422044b,12327,jacarei,SP
|
||||
66922902710d126a0e7d26b0e3805106,31842,belo horizonte,MG
|
||||
1900267e848ceeba8fa32d80c1a5f5a8,14940,ibitinga,SP
|
||||
63b9ae557efed31d1f7687917d248a8d,13720,sao jose do rio pardo,SP
|
||||
|
892
data/titanic.csv
Normal file
892
data/titanic.csv
Normal file
@ -0,0 +1,892 @@
|
||||
PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked
|
||||
1,0,3,"Braund, Mr. Owen Harris",male,22,1,0,A/5 21171,7.25,,S
|
||||
2,1,1,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",female,38,1,0,PC 17599,71.2833,C85,C
|
||||
3,1,3,"Heikkinen, Miss. Laina",female,26,0,0,STON/O2. 3101282,7.925,,S
|
||||
4,1,1,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",female,35,1,0,113803,53.1,C123,S
|
||||
5,0,3,"Allen, Mr. William Henry",male,35,0,0,373450,8.05,,S
|
||||
6,0,3,"Moran, Mr. James",male,,0,0,330877,8.4583,,Q
|
||||
7,0,1,"McCarthy, Mr. Timothy J",male,54,0,0,17463,51.8625,E46,S
|
||||
8,0,3,"Palsson, Master. Gosta Leonard",male,2,3,1,349909,21.075,,S
|
||||
9,1,3,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",female,27,0,2,347742,11.1333,,S
|
||||
10,1,2,"Nasser, Mrs. Nicholas (Adele Achem)",female,14,1,0,237736,30.0708,,C
|
||||
11,1,3,"Sandstrom, Miss. Marguerite Rut",female,4,1,1,PP 9549,16.7,G6,S
|
||||
12,1,1,"Bonnell, Miss. Elizabeth",female,58,0,0,113783,26.55,C103,S
|
||||
13,0,3,"Saundercock, Mr. William Henry",male,20,0,0,A/5. 2151,8.05,,S
|
||||
14,0,3,"Andersson, Mr. Anders Johan",male,39,1,5,347082,31.275,,S
|
||||
15,0,3,"Vestrom, Miss. Hulda Amanda Adolfina",female,14,0,0,350406,7.8542,,S
|
||||
16,1,2,"Hewlett, Mrs. (Mary D Kingcome) ",female,55,0,0,248706,16,,S
|
||||
17,0,3,"Rice, Master. Eugene",male,2,4,1,382652,29.125,,Q
|
||||
18,1,2,"Williams, Mr. Charles Eugene",male,,0,0,244373,13,,S
|
||||
19,0,3,"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)",female,31,1,0,345763,18,,S
|
||||
20,1,3,"Masselmani, Mrs. Fatima",female,,0,0,2649,7.225,,C
|
||||
21,0,2,"Fynney, Mr. Joseph J",male,35,0,0,239865,26,,S
|
||||
22,1,2,"Beesley, Mr. Lawrence",male,34,0,0,248698,13,D56,S
|
||||
23,1,3,"McGowan, Miss. Anna ""Annie""",female,15,0,0,330923,8.0292,,Q
|
||||
24,1,1,"Sloper, Mr. William Thompson",male,28,0,0,113788,35.5,A6,S
|
||||
25,0,3,"Palsson, Miss. Torborg Danira",female,8,3,1,349909,21.075,,S
|
||||
26,1,3,"Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)",female,38,1,5,347077,31.3875,,S
|
||||
27,0,3,"Emir, Mr. Farred Chehab",male,,0,0,2631,7.225,,C
|
||||
28,0,1,"Fortune, Mr. Charles Alexander",male,19,3,2,19950,263,C23 C25 C27,S
|
||||
29,1,3,"O'Dwyer, Miss. Ellen ""Nellie""",female,,0,0,330959,7.8792,,Q
|
||||
30,0,3,"Todoroff, Mr. Lalio",male,,0,0,349216,7.8958,,S
|
||||
31,0,1,"Uruchurtu, Don. Manuel E",male,40,0,0,PC 17601,27.7208,,C
|
||||
32,1,1,"Spencer, Mrs. William Augustus (Marie Eugenie)",female,,1,0,PC 17569,146.5208,B78,C
|
||||
33,1,3,"Glynn, Miss. Mary Agatha",female,,0,0,335677,7.75,,Q
|
||||
34,0,2,"Wheadon, Mr. Edward H",male,66,0,0,C.A. 24579,10.5,,S
|
||||
35,0,1,"Meyer, Mr. Edgar Joseph",male,28,1,0,PC 17604,82.1708,,C
|
||||
36,0,1,"Holverson, Mr. Alexander Oskar",male,42,1,0,113789,52,,S
|
||||
37,1,3,"Mamee, Mr. Hanna",male,,0,0,2677,7.2292,,C
|
||||
38,0,3,"Cann, Mr. Ernest Charles",male,21,0,0,A./5. 2152,8.05,,S
|
||||
39,0,3,"Vander Planke, Miss. Augusta Maria",female,18,2,0,345764,18,,S
|
||||
40,1,3,"Nicola-Yarred, Miss. Jamila",female,14,1,0,2651,11.2417,,C
|
||||
41,0,3,"Ahlin, Mrs. Johan (Johanna Persdotter Larsson)",female,40,1,0,7546,9.475,,S
|
||||
42,0,2,"Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)",female,27,1,0,11668,21,,S
|
||||
43,0,3,"Kraeff, Mr. Theodor",male,,0,0,349253,7.8958,,C
|
||||
44,1,2,"Laroche, Miss. Simonne Marie Anne Andree",female,3,1,2,SC/Paris 2123,41.5792,,C
|
||||
45,1,3,"Devaney, Miss. Margaret Delia",female,19,0,0,330958,7.8792,,Q
|
||||
46,0,3,"Rogers, Mr. William John",male,,0,0,S.C./A.4. 23567,8.05,,S
|
||||
47,0,3,"Lennon, Mr. Denis",male,,1,0,370371,15.5,,Q
|
||||
48,1,3,"O'Driscoll, Miss. Bridget",female,,0,0,14311,7.75,,Q
|
||||
49,0,3,"Samaan, Mr. Youssef",male,,2,0,2662,21.6792,,C
|
||||
50,0,3,"Arnold-Franchi, Mrs. Josef (Josefine Franchi)",female,18,1,0,349237,17.8,,S
|
||||
51,0,3,"Panula, Master. Juha Niilo",male,7,4,1,3101295,39.6875,,S
|
||||
52,0,3,"Nosworthy, Mr. Richard Cater",male,21,0,0,A/4. 39886,7.8,,S
|
||||
53,1,1,"Harper, Mrs. Henry Sleeper (Myna Haxtun)",female,49,1,0,PC 17572,76.7292,D33,C
|
||||
54,1,2,"Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)",female,29,1,0,2926,26,,S
|
||||
55,0,1,"Ostby, Mr. Engelhart Cornelius",male,65,0,1,113509,61.9792,B30,C
|
||||
56,1,1,"Woolner, Mr. Hugh",male,,0,0,19947,35.5,C52,S
|
||||
57,1,2,"Rugg, Miss. Emily",female,21,0,0,C.A. 31026,10.5,,S
|
||||
58,0,3,"Novel, Mr. Mansouer",male,28.5,0,0,2697,7.2292,,C
|
||||
59,1,2,"West, Miss. Constance Mirium",female,5,1,2,C.A. 34651,27.75,,S
|
||||
60,0,3,"Goodwin, Master. William Frederick",male,11,5,2,CA 2144,46.9,,S
|
||||
61,0,3,"Sirayanian, Mr. Orsen",male,22,0,0,2669,7.2292,,C
|
||||
62,1,1,"Icard, Miss. Amelie",female,38,0,0,113572,80,B28,
|
||||
63,0,1,"Harris, Mr. Henry Birkhardt",male,45,1,0,36973,83.475,C83,S
|
||||
64,0,3,"Skoog, Master. Harald",male,4,3,2,347088,27.9,,S
|
||||
65,0,1,"Stewart, Mr. Albert A",male,,0,0,PC 17605,27.7208,,C
|
||||
66,1,3,"Moubarek, Master. Gerios",male,,1,1,2661,15.2458,,C
|
||||
67,1,2,"Nye, Mrs. (Elizabeth Ramell)",female,29,0,0,C.A. 29395,10.5,F33,S
|
||||
68,0,3,"Crease, Mr. Ernest James",male,19,0,0,S.P. 3464,8.1583,,S
|
||||
69,1,3,"Andersson, Miss. Erna Alexandra",female,17,4,2,3101281,7.925,,S
|
||||
70,0,3,"Kink, Mr. Vincenz",male,26,2,0,315151,8.6625,,S
|
||||
71,0,2,"Jenkin, Mr. Stephen Curnow",male,32,0,0,C.A. 33111,10.5,,S
|
||||
72,0,3,"Goodwin, Miss. Lillian Amy",female,16,5,2,CA 2144,46.9,,S
|
||||
73,0,2,"Hood, Mr. Ambrose Jr",male,21,0,0,S.O.C. 14879,73.5,,S
|
||||
74,0,3,"Chronopoulos, Mr. Apostolos",male,26,1,0,2680,14.4542,,C
|
||||
75,1,3,"Bing, Mr. Lee",male,32,0,0,1601,56.4958,,S
|
||||
76,0,3,"Moen, Mr. Sigurd Hansen",male,25,0,0,348123,7.65,F G73,S
|
||||
77,0,3,"Staneff, Mr. Ivan",male,,0,0,349208,7.8958,,S
|
||||
78,0,3,"Moutal, Mr. Rahamin Haim",male,,0,0,374746,8.05,,S
|
||||
79,1,2,"Caldwell, Master. Alden Gates",male,0.83,0,2,248738,29,,S
|
||||
80,1,3,"Dowdell, Miss. Elizabeth",female,30,0,0,364516,12.475,,S
|
||||
81,0,3,"Waelens, Mr. Achille",male,22,0,0,345767,9,,S
|
||||
82,1,3,"Sheerlinck, Mr. Jan Baptist",male,29,0,0,345779,9.5,,S
|
||||
83,1,3,"McDermott, Miss. Brigdet Delia",female,,0,0,330932,7.7875,,Q
|
||||
84,0,1,"Carrau, Mr. Francisco M",male,28,0,0,113059,47.1,,S
|
||||
85,1,2,"Ilett, Miss. Bertha",female,17,0,0,SO/C 14885,10.5,,S
|
||||
86,1,3,"Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)",female,33,3,0,3101278,15.85,,S
|
||||
87,0,3,"Ford, Mr. William Neal",male,16,1,3,W./C. 6608,34.375,,S
|
||||
88,0,3,"Slocovski, Mr. Selman Francis",male,,0,0,SOTON/OQ 392086,8.05,,S
|
||||
89,1,1,"Fortune, Miss. Mabel Helen",female,23,3,2,19950,263,C23 C25 C27,S
|
||||
90,0,3,"Celotti, Mr. Francesco",male,24,0,0,343275,8.05,,S
|
||||
91,0,3,"Christmann, Mr. Emil",male,29,0,0,343276,8.05,,S
|
||||
92,0,3,"Andreasson, Mr. Paul Edvin",male,20,0,0,347466,7.8542,,S
|
||||
93,0,1,"Chaffee, Mr. Herbert Fuller",male,46,1,0,W.E.P. 5734,61.175,E31,S
|
||||
94,0,3,"Dean, Mr. Bertram Frank",male,26,1,2,C.A. 2315,20.575,,S
|
||||
95,0,3,"Coxon, Mr. Daniel",male,59,0,0,364500,7.25,,S
|
||||
96,0,3,"Shorney, Mr. Charles Joseph",male,,0,0,374910,8.05,,S
|
||||
97,0,1,"Goldschmidt, Mr. George B",male,71,0,0,PC 17754,34.6542,A5,C
|
||||
98,1,1,"Greenfield, Mr. William Bertram",male,23,0,1,PC 17759,63.3583,D10 D12,C
|
||||
99,1,2,"Doling, Mrs. John T (Ada Julia Bone)",female,34,0,1,231919,23,,S
|
||||
100,0,2,"Kantor, Mr. Sinai",male,34,1,0,244367,26,,S
|
||||
101,0,3,"Petranec, Miss. Matilda",female,28,0,0,349245,7.8958,,S
|
||||
102,0,3,"Petroff, Mr. Pastcho (""Pentcho"")",male,,0,0,349215,7.8958,,S
|
||||
103,0,1,"White, Mr. Richard Frasar",male,21,0,1,35281,77.2875,D26,S
|
||||
104,0,3,"Johansson, Mr. Gustaf Joel",male,33,0,0,7540,8.6542,,S
|
||||
105,0,3,"Gustafsson, Mr. Anders Vilhelm",male,37,2,0,3101276,7.925,,S
|
||||
106,0,3,"Mionoff, Mr. Stoytcho",male,28,0,0,349207,7.8958,,S
|
||||
107,1,3,"Salkjelsvik, Miss. Anna Kristine",female,21,0,0,343120,7.65,,S
|
||||
108,1,3,"Moss, Mr. Albert Johan",male,,0,0,312991,7.775,,S
|
||||
109,0,3,"Rekic, Mr. Tido",male,38,0,0,349249,7.8958,,S
|
||||
110,1,3,"Moran, Miss. Bertha",female,,1,0,371110,24.15,,Q
|
||||
111,0,1,"Porter, Mr. Walter Chamberlain",male,47,0,0,110465,52,C110,S
|
||||
112,0,3,"Zabour, Miss. Hileni",female,14.5,1,0,2665,14.4542,,C
|
||||
113,0,3,"Barton, Mr. David John",male,22,0,0,324669,8.05,,S
|
||||
114,0,3,"Jussila, Miss. Katriina",female,20,1,0,4136,9.825,,S
|
||||
115,0,3,"Attalah, Miss. Malake",female,17,0,0,2627,14.4583,,C
|
||||
116,0,3,"Pekoniemi, Mr. Edvard",male,21,0,0,STON/O 2. 3101294,7.925,,S
|
||||
117,0,3,"Connors, Mr. Patrick",male,70.5,0,0,370369,7.75,,Q
|
||||
118,0,2,"Turpin, Mr. William John Robert",male,29,1,0,11668,21,,S
|
||||
119,0,1,"Baxter, Mr. Quigg Edmond",male,24,0,1,PC 17558,247.5208,B58 B60,C
|
||||
120,0,3,"Andersson, Miss. Ellis Anna Maria",female,2,4,2,347082,31.275,,S
|
||||
121,0,2,"Hickman, Mr. Stanley George",male,21,2,0,S.O.C. 14879,73.5,,S
|
||||
122,0,3,"Moore, Mr. Leonard Charles",male,,0,0,A4. 54510,8.05,,S
|
||||
123,0,2,"Nasser, Mr. Nicholas",male,32.5,1,0,237736,30.0708,,C
|
||||
124,1,2,"Webber, Miss. Susan",female,32.5,0,0,27267,13,E101,S
|
||||
125,0,1,"White, Mr. Percival Wayland",male,54,0,1,35281,77.2875,D26,S
|
||||
126,1,3,"Nicola-Yarred, Master. Elias",male,12,1,0,2651,11.2417,,C
|
||||
127,0,3,"McMahon, Mr. Martin",male,,0,0,370372,7.75,,Q
|
||||
128,1,3,"Madsen, Mr. Fridtjof Arne",male,24,0,0,C 17369,7.1417,,S
|
||||
129,1,3,"Peter, Miss. Anna",female,,1,1,2668,22.3583,F E69,C
|
||||
130,0,3,"Ekstrom, Mr. Johan",male,45,0,0,347061,6.975,,S
|
||||
131,0,3,"Drazenoic, Mr. Jozef",male,33,0,0,349241,7.8958,,C
|
||||
132,0,3,"Coelho, Mr. Domingos Fernandeo",male,20,0,0,SOTON/O.Q. 3101307,7.05,,S
|
||||
133,0,3,"Robins, Mrs. Alexander A (Grace Charity Laury)",female,47,1,0,A/5. 3337,14.5,,S
|
||||
134,1,2,"Weisz, Mrs. Leopold (Mathilde Francoise Pede)",female,29,1,0,228414,26,,S
|
||||
135,0,2,"Sobey, Mr. Samuel James Hayden",male,25,0,0,C.A. 29178,13,,S
|
||||
136,0,2,"Richard, Mr. Emile",male,23,0,0,SC/PARIS 2133,15.0458,,C
|
||||
137,1,1,"Newsom, Miss. Helen Monypeny",female,19,0,2,11752,26.2833,D47,S
|
||||
138,0,1,"Futrelle, Mr. Jacques Heath",male,37,1,0,113803,53.1,C123,S
|
||||
139,0,3,"Osen, Mr. Olaf Elon",male,16,0,0,7534,9.2167,,S
|
||||
140,0,1,"Giglio, Mr. Victor",male,24,0,0,PC 17593,79.2,B86,C
|
||||
141,0,3,"Boulos, Mrs. Joseph (Sultana)",female,,0,2,2678,15.2458,,C
|
||||
142,1,3,"Nysten, Miss. Anna Sofia",female,22,0,0,347081,7.75,,S
|
||||
143,1,3,"Hakkarainen, Mrs. Pekka Pietari (Elin Matilda Dolck)",female,24,1,0,STON/O2. 3101279,15.85,,S
|
||||
144,0,3,"Burke, Mr. Jeremiah",male,19,0,0,365222,6.75,,Q
|
||||
145,0,2,"Andrew, Mr. Edgardo Samuel",male,18,0,0,231945,11.5,,S
|
||||
146,0,2,"Nicholls, Mr. Joseph Charles",male,19,1,1,C.A. 33112,36.75,,S
|
||||
147,1,3,"Andersson, Mr. August Edvard (""Wennerstrom"")",male,27,0,0,350043,7.7958,,S
|
||||
148,0,3,"Ford, Miss. Robina Maggie ""Ruby""",female,9,2,2,W./C. 6608,34.375,,S
|
||||
149,0,2,"Navratil, Mr. Michel (""Louis M Hoffman"")",male,36.5,0,2,230080,26,F2,S
|
||||
150,0,2,"Byles, Rev. Thomas Roussel Davids",male,42,0,0,244310,13,,S
|
||||
151,0,2,"Bateman, Rev. Robert James",male,51,0,0,S.O.P. 1166,12.525,,S
|
||||
152,1,1,"Pears, Mrs. Thomas (Edith Wearne)",female,22,1,0,113776,66.6,C2,S
|
||||
153,0,3,"Meo, Mr. Alfonzo",male,55.5,0,0,A.5. 11206,8.05,,S
|
||||
154,0,3,"van Billiard, Mr. Austin Blyler",male,40.5,0,2,A/5. 851,14.5,,S
|
||||
155,0,3,"Olsen, Mr. Ole Martin",male,,0,0,Fa 265302,7.3125,,S
|
||||
156,0,1,"Williams, Mr. Charles Duane",male,51,0,1,PC 17597,61.3792,,C
|
||||
157,1,3,"Gilnagh, Miss. Katherine ""Katie""",female,16,0,0,35851,7.7333,,Q
|
||||
158,0,3,"Corn, Mr. Harry",male,30,0,0,SOTON/OQ 392090,8.05,,S
|
||||
159,0,3,"Smiljanic, Mr. Mile",male,,0,0,315037,8.6625,,S
|
||||
160,0,3,"Sage, Master. Thomas Henry",male,,8,2,CA. 2343,69.55,,S
|
||||
161,0,3,"Cribb, Mr. John Hatfield",male,44,0,1,371362,16.1,,S
|
||||
162,1,2,"Watt, Mrs. James (Elizabeth ""Bessie"" Inglis Milne)",female,40,0,0,C.A. 33595,15.75,,S
|
||||
163,0,3,"Bengtsson, Mr. John Viktor",male,26,0,0,347068,7.775,,S
|
||||
164,0,3,"Calic, Mr. Jovo",male,17,0,0,315093,8.6625,,S
|
||||
165,0,3,"Panula, Master. Eino Viljami",male,1,4,1,3101295,39.6875,,S
|
||||
166,1,3,"Goldsmith, Master. Frank John William ""Frankie""",male,9,0,2,363291,20.525,,S
|
||||
167,1,1,"Chibnall, Mrs. (Edith Martha Bowerman)",female,,0,1,113505,55,E33,S
|
||||
168,0,3,"Skoog, Mrs. William (Anna Bernhardina Karlsson)",female,45,1,4,347088,27.9,,S
|
||||
169,0,1,"Baumann, Mr. John D",male,,0,0,PC 17318,25.925,,S
|
||||
170,0,3,"Ling, Mr. Lee",male,28,0,0,1601,56.4958,,S
|
||||
171,0,1,"Van der hoef, Mr. Wyckoff",male,61,0,0,111240,33.5,B19,S
|
||||
172,0,3,"Rice, Master. Arthur",male,4,4,1,382652,29.125,,Q
|
||||
173,1,3,"Johnson, Miss. Eleanor Ileen",female,1,1,1,347742,11.1333,,S
|
||||
174,0,3,"Sivola, Mr. Antti Wilhelm",male,21,0,0,STON/O 2. 3101280,7.925,,S
|
||||
175,0,1,"Smith, Mr. James Clinch",male,56,0,0,17764,30.6958,A7,C
|
||||
176,0,3,"Klasen, Mr. Klas Albin",male,18,1,1,350404,7.8542,,S
|
||||
177,0,3,"Lefebre, Master. Henry Forbes",male,,3,1,4133,25.4667,,S
|
||||
178,0,1,"Isham, Miss. Ann Elizabeth",female,50,0,0,PC 17595,28.7125,C49,C
|
||||
179,0,2,"Hale, Mr. Reginald",male,30,0,0,250653,13,,S
|
||||
180,0,3,"Leonard, Mr. Lionel",male,36,0,0,LINE,0,,S
|
||||
181,0,3,"Sage, Miss. Constance Gladys",female,,8,2,CA. 2343,69.55,,S
|
||||
182,0,2,"Pernot, Mr. Rene",male,,0,0,SC/PARIS 2131,15.05,,C
|
||||
183,0,3,"Asplund, Master. Clarence Gustaf Hugo",male,9,4,2,347077,31.3875,,S
|
||||
184,1,2,"Becker, Master. Richard F",male,1,2,1,230136,39,F4,S
|
||||
185,1,3,"Kink-Heilmann, Miss. Luise Gretchen",female,4,0,2,315153,22.025,,S
|
||||
186,0,1,"Rood, Mr. Hugh Roscoe",male,,0,0,113767,50,A32,S
|
||||
187,1,3,"O'Brien, Mrs. Thomas (Johanna ""Hannah"" Godfrey)",female,,1,0,370365,15.5,,Q
|
||||
188,1,1,"Romaine, Mr. Charles Hallace (""Mr C Rolmane"")",male,45,0,0,111428,26.55,,S
|
||||
189,0,3,"Bourke, Mr. John",male,40,1,1,364849,15.5,,Q
|
||||
190,0,3,"Turcin, Mr. Stjepan",male,36,0,0,349247,7.8958,,S
|
||||
191,1,2,"Pinsky, Mrs. (Rosa)",female,32,0,0,234604,13,,S
|
||||
192,0,2,"Carbines, Mr. William",male,19,0,0,28424,13,,S
|
||||
193,1,3,"Andersen-Jensen, Miss. Carla Christine Nielsine",female,19,1,0,350046,7.8542,,S
|
||||
194,1,2,"Navratil, Master. Michel M",male,3,1,1,230080,26,F2,S
|
||||
195,1,1,"Brown, Mrs. James Joseph (Margaret Tobin)",female,44,0,0,PC 17610,27.7208,B4,C
|
||||
196,1,1,"Lurette, Miss. Elise",female,58,0,0,PC 17569,146.5208,B80,C
|
||||
197,0,3,"Mernagh, Mr. Robert",male,,0,0,368703,7.75,,Q
|
||||
198,0,3,"Olsen, Mr. Karl Siegwart Andreas",male,42,0,1,4579,8.4042,,S
|
||||
199,1,3,"Madigan, Miss. Margaret ""Maggie""",female,,0,0,370370,7.75,,Q
|
||||
200,0,2,"Yrois, Miss. Henriette (""Mrs Harbeck"")",female,24,0,0,248747,13,,S
|
||||
201,0,3,"Vande Walle, Mr. Nestor Cyriel",male,28,0,0,345770,9.5,,S
|
||||
202,0,3,"Sage, Mr. Frederick",male,,8,2,CA. 2343,69.55,,S
|
||||
203,0,3,"Johanson, Mr. Jakob Alfred",male,34,0,0,3101264,6.4958,,S
|
||||
204,0,3,"Youseff, Mr. Gerious",male,45.5,0,0,2628,7.225,,C
|
||||
205,1,3,"Cohen, Mr. Gurshon ""Gus""",male,18,0,0,A/5 3540,8.05,,S
|
||||
206,0,3,"Strom, Miss. Telma Matilda",female,2,0,1,347054,10.4625,G6,S
|
||||
207,0,3,"Backstrom, Mr. Karl Alfred",male,32,1,0,3101278,15.85,,S
|
||||
208,1,3,"Albimona, Mr. Nassef Cassem",male,26,0,0,2699,18.7875,,C
|
||||
209,1,3,"Carr, Miss. Helen ""Ellen""",female,16,0,0,367231,7.75,,Q
|
||||
210,1,1,"Blank, Mr. Henry",male,40,0,0,112277,31,A31,C
|
||||
211,0,3,"Ali, Mr. Ahmed",male,24,0,0,SOTON/O.Q. 3101311,7.05,,S
|
||||
212,1,2,"Cameron, Miss. Clear Annie",female,35,0,0,F.C.C. 13528,21,,S
|
||||
213,0,3,"Perkin, Mr. John Henry",male,22,0,0,A/5 21174,7.25,,S
|
||||
214,0,2,"Givard, Mr. Hans Kristensen",male,30,0,0,250646,13,,S
|
||||
215,0,3,"Kiernan, Mr. Philip",male,,1,0,367229,7.75,,Q
|
||||
216,1,1,"Newell, Miss. Madeleine",female,31,1,0,35273,113.275,D36,C
|
||||
217,1,3,"Honkanen, Miss. Eliina",female,27,0,0,STON/O2. 3101283,7.925,,S
|
||||
218,0,2,"Jacobsohn, Mr. Sidney Samuel",male,42,1,0,243847,27,,S
|
||||
219,1,1,"Bazzani, Miss. Albina",female,32,0,0,11813,76.2917,D15,C
|
||||
220,0,2,"Harris, Mr. Walter",male,30,0,0,W/C 14208,10.5,,S
|
||||
221,1,3,"Sunderland, Mr. Victor Francis",male,16,0,0,SOTON/OQ 392089,8.05,,S
|
||||
222,0,2,"Bracken, Mr. James H",male,27,0,0,220367,13,,S
|
||||
223,0,3,"Green, Mr. George Henry",male,51,0,0,21440,8.05,,S
|
||||
224,0,3,"Nenkoff, Mr. Christo",male,,0,0,349234,7.8958,,S
|
||||
225,1,1,"Hoyt, Mr. Frederick Maxfield",male,38,1,0,19943,90,C93,S
|
||||
226,0,3,"Berglund, Mr. Karl Ivar Sven",male,22,0,0,PP 4348,9.35,,S
|
||||
227,1,2,"Mellors, Mr. William John",male,19,0,0,SW/PP 751,10.5,,S
|
||||
228,0,3,"Lovell, Mr. John Hall (""Henry"")",male,20.5,0,0,A/5 21173,7.25,,S
|
||||
229,0,2,"Fahlstrom, Mr. Arne Jonas",male,18,0,0,236171,13,,S
|
||||
230,0,3,"Lefebre, Miss. Mathilde",female,,3,1,4133,25.4667,,S
|
||||
231,1,1,"Harris, Mrs. Henry Birkhardt (Irene Wallach)",female,35,1,0,36973,83.475,C83,S
|
||||
232,0,3,"Larsson, Mr. Bengt Edvin",male,29,0,0,347067,7.775,,S
|
||||
233,0,2,"Sjostedt, Mr. Ernst Adolf",male,59,0,0,237442,13.5,,S
|
||||
234,1,3,"Asplund, Miss. Lillian Gertrud",female,5,4,2,347077,31.3875,,S
|
||||
235,0,2,"Leyson, Mr. Robert William Norman",male,24,0,0,C.A. 29566,10.5,,S
|
||||
236,0,3,"Harknett, Miss. Alice Phoebe",female,,0,0,W./C. 6609,7.55,,S
|
||||
237,0,2,"Hold, Mr. Stephen",male,44,1,0,26707,26,,S
|
||||
238,1,2,"Collyer, Miss. Marjorie ""Lottie""",female,8,0,2,C.A. 31921,26.25,,S
|
||||
239,0,2,"Pengelly, Mr. Frederick William",male,19,0,0,28665,10.5,,S
|
||||
240,0,2,"Hunt, Mr. George Henry",male,33,0,0,SCO/W 1585,12.275,,S
|
||||
241,0,3,"Zabour, Miss. Thamine",female,,1,0,2665,14.4542,,C
|
||||
242,1,3,"Murphy, Miss. Katherine ""Kate""",female,,1,0,367230,15.5,,Q
|
||||
243,0,2,"Coleridge, Mr. Reginald Charles",male,29,0,0,W./C. 14263,10.5,,S
|
||||
244,0,3,"Maenpaa, Mr. Matti Alexanteri",male,22,0,0,STON/O 2. 3101275,7.125,,S
|
||||
245,0,3,"Attalah, Mr. Sleiman",male,30,0,0,2694,7.225,,C
|
||||
246,0,1,"Minahan, Dr. William Edward",male,44,2,0,19928,90,C78,Q
|
||||
247,0,3,"Lindahl, Miss. Agda Thorilda Viktoria",female,25,0,0,347071,7.775,,S
|
||||
248,1,2,"Hamalainen, Mrs. William (Anna)",female,24,0,2,250649,14.5,,S
|
||||
249,1,1,"Beckwith, Mr. Richard Leonard",male,37,1,1,11751,52.5542,D35,S
|
||||
250,0,2,"Carter, Rev. Ernest Courtenay",male,54,1,0,244252,26,,S
|
||||
251,0,3,"Reed, Mr. James George",male,,0,0,362316,7.25,,S
|
||||
252,0,3,"Strom, Mrs. Wilhelm (Elna Matilda Persson)",female,29,1,1,347054,10.4625,G6,S
|
||||
253,0,1,"Stead, Mr. William Thomas",male,62,0,0,113514,26.55,C87,S
|
||||
254,0,3,"Lobb, Mr. William Arthur",male,30,1,0,A/5. 3336,16.1,,S
|
||||
255,0,3,"Rosblom, Mrs. Viktor (Helena Wilhelmina)",female,41,0,2,370129,20.2125,,S
|
||||
256,1,3,"Touma, Mrs. Darwis (Hanne Youssef Razi)",female,29,0,2,2650,15.2458,,C
|
||||
257,1,1,"Thorne, Mrs. Gertrude Maybelle",female,,0,0,PC 17585,79.2,,C
|
||||
258,1,1,"Cherry, Miss. Gladys",female,30,0,0,110152,86.5,B77,S
|
||||
259,1,1,"Ward, Miss. Anna",female,35,0,0,PC 17755,512.3292,,C
|
||||
260,1,2,"Parrish, Mrs. (Lutie Davis)",female,50,0,1,230433,26,,S
|
||||
261,0,3,"Smith, Mr. Thomas",male,,0,0,384461,7.75,,Q
|
||||
262,1,3,"Asplund, Master. Edvin Rojj Felix",male,3,4,2,347077,31.3875,,S
|
||||
263,0,1,"Taussig, Mr. Emil",male,52,1,1,110413,79.65,E67,S
|
||||
264,0,1,"Harrison, Mr. William",male,40,0,0,112059,0,B94,S
|
||||
265,0,3,"Henry, Miss. Delia",female,,0,0,382649,7.75,,Q
|
||||
266,0,2,"Reeves, Mr. David",male,36,0,0,C.A. 17248,10.5,,S
|
||||
267,0,3,"Panula, Mr. Ernesti Arvid",male,16,4,1,3101295,39.6875,,S
|
||||
268,1,3,"Persson, Mr. Ernst Ulrik",male,25,1,0,347083,7.775,,S
|
||||
269,1,1,"Graham, Mrs. William Thompson (Edith Junkins)",female,58,0,1,PC 17582,153.4625,C125,S
|
||||
270,1,1,"Bissette, Miss. Amelia",female,35,0,0,PC 17760,135.6333,C99,S
|
||||
271,0,1,"Cairns, Mr. Alexander",male,,0,0,113798,31,,S
|
||||
272,1,3,"Tornquist, Mr. William Henry",male,25,0,0,LINE,0,,S
|
||||
273,1,2,"Mellinger, Mrs. (Elizabeth Anne Maidment)",female,41,0,1,250644,19.5,,S
|
||||
274,0,1,"Natsch, Mr. Charles H",male,37,0,1,PC 17596,29.7,C118,C
|
||||
275,1,3,"Healy, Miss. Hanora ""Nora""",female,,0,0,370375,7.75,,Q
|
||||
276,1,1,"Andrews, Miss. Kornelia Theodosia",female,63,1,0,13502,77.9583,D7,S
|
||||
277,0,3,"Lindblom, Miss. Augusta Charlotta",female,45,0,0,347073,7.75,,S
|
||||
278,0,2,"Parkes, Mr. Francis ""Frank""",male,,0,0,239853,0,,S
|
||||
279,0,3,"Rice, Master. Eric",male,7,4,1,382652,29.125,,Q
|
||||
280,1,3,"Abbott, Mrs. Stanton (Rosa Hunt)",female,35,1,1,C.A. 2673,20.25,,S
|
||||
281,0,3,"Duane, Mr. Frank",male,65,0,0,336439,7.75,,Q
|
||||
282,0,3,"Olsson, Mr. Nils Johan Goransson",male,28,0,0,347464,7.8542,,S
|
||||
283,0,3,"de Pelsmaeker, Mr. Alfons",male,16,0,0,345778,9.5,,S
|
||||
284,1,3,"Dorking, Mr. Edward Arthur",male,19,0,0,A/5. 10482,8.05,,S
|
||||
285,0,1,"Smith, Mr. Richard William",male,,0,0,113056,26,A19,S
|
||||
286,0,3,"Stankovic, Mr. Ivan",male,33,0,0,349239,8.6625,,C
|
||||
287,1,3,"de Mulder, Mr. Theodore",male,30,0,0,345774,9.5,,S
|
||||
288,0,3,"Naidenoff, Mr. Penko",male,22,0,0,349206,7.8958,,S
|
||||
289,1,2,"Hosono, Mr. Masabumi",male,42,0,0,237798,13,,S
|
||||
290,1,3,"Connolly, Miss. Kate",female,22,0,0,370373,7.75,,Q
|
||||
291,1,1,"Barber, Miss. Ellen ""Nellie""",female,26,0,0,19877,78.85,,S
|
||||
292,1,1,"Bishop, Mrs. Dickinson H (Helen Walton)",female,19,1,0,11967,91.0792,B49,C
|
||||
293,0,2,"Levy, Mr. Rene Jacques",male,36,0,0,SC/Paris 2163,12.875,D,C
|
||||
294,0,3,"Haas, Miss. Aloisia",female,24,0,0,349236,8.85,,S
|
||||
295,0,3,"Mineff, Mr. Ivan",male,24,0,0,349233,7.8958,,S
|
||||
296,0,1,"Lewy, Mr. Ervin G",male,,0,0,PC 17612,27.7208,,C
|
||||
297,0,3,"Hanna, Mr. Mansour",male,23.5,0,0,2693,7.2292,,C
|
||||
298,0,1,"Allison, Miss. Helen Loraine",female,2,1,2,113781,151.55,C22 C26,S
|
||||
299,1,1,"Saalfeld, Mr. Adolphe",male,,0,0,19988,30.5,C106,S
|
||||
300,1,1,"Baxter, Mrs. James (Helene DeLaudeniere Chaput)",female,50,0,1,PC 17558,247.5208,B58 B60,C
|
||||
301,1,3,"Kelly, Miss. Anna Katherine ""Annie Kate""",female,,0,0,9234,7.75,,Q
|
||||
302,1,3,"McCoy, Mr. Bernard",male,,2,0,367226,23.25,,Q
|
||||
303,0,3,"Johnson, Mr. William Cahoone Jr",male,19,0,0,LINE,0,,S
|
||||
304,1,2,"Keane, Miss. Nora A",female,,0,0,226593,12.35,E101,Q
|
||||
305,0,3,"Williams, Mr. Howard Hugh ""Harry""",male,,0,0,A/5 2466,8.05,,S
|
||||
306,1,1,"Allison, Master. Hudson Trevor",male,0.92,1,2,113781,151.55,C22 C26,S
|
||||
307,1,1,"Fleming, Miss. Margaret",female,,0,0,17421,110.8833,,C
|
||||
308,1,1,"Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo)",female,17,1,0,PC 17758,108.9,C65,C
|
||||
309,0,2,"Abelson, Mr. Samuel",male,30,1,0,P/PP 3381,24,,C
|
||||
310,1,1,"Francatelli, Miss. Laura Mabel",female,30,0,0,PC 17485,56.9292,E36,C
|
||||
311,1,1,"Hays, Miss. Margaret Bechstein",female,24,0,0,11767,83.1583,C54,C
|
||||
312,1,1,"Ryerson, Miss. Emily Borie",female,18,2,2,PC 17608,262.375,B57 B59 B63 B66,C
|
||||
313,0,2,"Lahtinen, Mrs. William (Anna Sylfven)",female,26,1,1,250651,26,,S
|
||||
314,0,3,"Hendekovic, Mr. Ignjac",male,28,0,0,349243,7.8958,,S
|
||||
315,0,2,"Hart, Mr. Benjamin",male,43,1,1,F.C.C. 13529,26.25,,S
|
||||
316,1,3,"Nilsson, Miss. Helmina Josefina",female,26,0,0,347470,7.8542,,S
|
||||
317,1,2,"Kantor, Mrs. Sinai (Miriam Sternin)",female,24,1,0,244367,26,,S
|
||||
318,0,2,"Moraweck, Dr. Ernest",male,54,0,0,29011,14,,S
|
||||
319,1,1,"Wick, Miss. Mary Natalie",female,31,0,2,36928,164.8667,C7,S
|
||||
320,1,1,"Spedden, Mrs. Frederic Oakley (Margaretta Corning Stone)",female,40,1,1,16966,134.5,E34,C
|
||||
321,0,3,"Dennis, Mr. Samuel",male,22,0,0,A/5 21172,7.25,,S
|
||||
322,0,3,"Danoff, Mr. Yoto",male,27,0,0,349219,7.8958,,S
|
||||
323,1,2,"Slayter, Miss. Hilda Mary",female,30,0,0,234818,12.35,,Q
|
||||
324,1,2,"Caldwell, Mrs. Albert Francis (Sylvia Mae Harbaugh)",female,22,1,1,248738,29,,S
|
||||
325,0,3,"Sage, Mr. George John Jr",male,,8,2,CA. 2343,69.55,,S
|
||||
326,1,1,"Young, Miss. Marie Grice",female,36,0,0,PC 17760,135.6333,C32,C
|
||||
327,0,3,"Nysveen, Mr. Johan Hansen",male,61,0,0,345364,6.2375,,S
|
||||
328,1,2,"Ball, Mrs. (Ada E Hall)",female,36,0,0,28551,13,D,S
|
||||
329,1,3,"Goldsmith, Mrs. Frank John (Emily Alice Brown)",female,31,1,1,363291,20.525,,S
|
||||
330,1,1,"Hippach, Miss. Jean Gertrude",female,16,0,1,111361,57.9792,B18,C
|
||||
331,1,3,"McCoy, Miss. Agnes",female,,2,0,367226,23.25,,Q
|
||||
332,0,1,"Partner, Mr. Austen",male,45.5,0,0,113043,28.5,C124,S
|
||||
333,0,1,"Graham, Mr. George Edward",male,38,0,1,PC 17582,153.4625,C91,S
|
||||
334,0,3,"Vander Planke, Mr. Leo Edmondus",male,16,2,0,345764,18,,S
|
||||
335,1,1,"Frauenthal, Mrs. Henry William (Clara Heinsheimer)",female,,1,0,PC 17611,133.65,,S
|
||||
336,0,3,"Denkoff, Mr. Mitto",male,,0,0,349225,7.8958,,S
|
||||
337,0,1,"Pears, Mr. Thomas Clinton",male,29,1,0,113776,66.6,C2,S
|
||||
338,1,1,"Burns, Miss. Elizabeth Margaret",female,41,0,0,16966,134.5,E40,C
|
||||
339,1,3,"Dahl, Mr. Karl Edwart",male,45,0,0,7598,8.05,,S
|
||||
340,0,1,"Blackwell, Mr. Stephen Weart",male,45,0,0,113784,35.5,T,S
|
||||
341,1,2,"Navratil, Master. Edmond Roger",male,2,1,1,230080,26,F2,S
|
||||
342,1,1,"Fortune, Miss. Alice Elizabeth",female,24,3,2,19950,263,C23 C25 C27,S
|
||||
343,0,2,"Collander, Mr. Erik Gustaf",male,28,0,0,248740,13,,S
|
||||
344,0,2,"Sedgwick, Mr. Charles Frederick Waddington",male,25,0,0,244361,13,,S
|
||||
345,0,2,"Fox, Mr. Stanley Hubert",male,36,0,0,229236,13,,S
|
||||
346,1,2,"Brown, Miss. Amelia ""Mildred""",female,24,0,0,248733,13,F33,S
|
||||
347,1,2,"Smith, Miss. Marion Elsie",female,40,0,0,31418,13,,S
|
||||
348,1,3,"Davison, Mrs. Thomas Henry (Mary E Finck)",female,,1,0,386525,16.1,,S
|
||||
349,1,3,"Coutts, Master. William Loch ""William""",male,3,1,1,C.A. 37671,15.9,,S
|
||||
350,0,3,"Dimic, Mr. Jovan",male,42,0,0,315088,8.6625,,S
|
||||
351,0,3,"Odahl, Mr. Nils Martin",male,23,0,0,7267,9.225,,S
|
||||
352,0,1,"Williams-Lambert, Mr. Fletcher Fellows",male,,0,0,113510,35,C128,S
|
||||
353,0,3,"Elias, Mr. Tannous",male,15,1,1,2695,7.2292,,C
|
||||
354,0,3,"Arnold-Franchi, Mr. Josef",male,25,1,0,349237,17.8,,S
|
||||
355,0,3,"Yousif, Mr. Wazli",male,,0,0,2647,7.225,,C
|
||||
356,0,3,"Vanden Steen, Mr. Leo Peter",male,28,0,0,345783,9.5,,S
|
||||
357,1,1,"Bowerman, Miss. Elsie Edith",female,22,0,1,113505,55,E33,S
|
||||
358,0,2,"Funk, Miss. Annie Clemmer",female,38,0,0,237671,13,,S
|
||||
359,1,3,"McGovern, Miss. Mary",female,,0,0,330931,7.8792,,Q
|
||||
360,1,3,"Mockler, Miss. Helen Mary ""Ellie""",female,,0,0,330980,7.8792,,Q
|
||||
361,0,3,"Skoog, Mr. Wilhelm",male,40,1,4,347088,27.9,,S
|
||||
362,0,2,"del Carlo, Mr. Sebastiano",male,29,1,0,SC/PARIS 2167,27.7208,,C
|
||||
363,0,3,"Barbara, Mrs. (Catherine David)",female,45,0,1,2691,14.4542,,C
|
||||
364,0,3,"Asim, Mr. Adola",male,35,0,0,SOTON/O.Q. 3101310,7.05,,S
|
||||
365,0,3,"O'Brien, Mr. Thomas",male,,1,0,370365,15.5,,Q
|
||||
366,0,3,"Adahl, Mr. Mauritz Nils Martin",male,30,0,0,C 7076,7.25,,S
|
||||
367,1,1,"Warren, Mrs. Frank Manley (Anna Sophia Atkinson)",female,60,1,0,110813,75.25,D37,C
|
||||
368,1,3,"Moussa, Mrs. (Mantoura Boulos)",female,,0,0,2626,7.2292,,C
|
||||
369,1,3,"Jermyn, Miss. Annie",female,,0,0,14313,7.75,,Q
|
||||
370,1,1,"Aubart, Mme. Leontine Pauline",female,24,0,0,PC 17477,69.3,B35,C
|
||||
371,1,1,"Harder, Mr. George Achilles",male,25,1,0,11765,55.4417,E50,C
|
||||
372,0,3,"Wiklund, Mr. Jakob Alfred",male,18,1,0,3101267,6.4958,,S
|
||||
373,0,3,"Beavan, Mr. William Thomas",male,19,0,0,323951,8.05,,S
|
||||
374,0,1,"Ringhini, Mr. Sante",male,22,0,0,PC 17760,135.6333,,C
|
||||
375,0,3,"Palsson, Miss. Stina Viola",female,3,3,1,349909,21.075,,S
|
||||
376,1,1,"Meyer, Mrs. Edgar Joseph (Leila Saks)",female,,1,0,PC 17604,82.1708,,C
|
||||
377,1,3,"Landergren, Miss. Aurora Adelia",female,22,0,0,C 7077,7.25,,S
|
||||
378,0,1,"Widener, Mr. Harry Elkins",male,27,0,2,113503,211.5,C82,C
|
||||
379,0,3,"Betros, Mr. Tannous",male,20,0,0,2648,4.0125,,C
|
||||
380,0,3,"Gustafsson, Mr. Karl Gideon",male,19,0,0,347069,7.775,,S
|
||||
381,1,1,"Bidois, Miss. Rosalie",female,42,0,0,PC 17757,227.525,,C
|
||||
382,1,3,"Nakid, Miss. Maria (""Mary"")",female,1,0,2,2653,15.7417,,C
|
||||
383,0,3,"Tikkanen, Mr. Juho",male,32,0,0,STON/O 2. 3101293,7.925,,S
|
||||
384,1,1,"Holverson, Mrs. Alexander Oskar (Mary Aline Towner)",female,35,1,0,113789,52,,S
|
||||
385,0,3,"Plotcharsky, Mr. Vasil",male,,0,0,349227,7.8958,,S
|
||||
386,0,2,"Davies, Mr. Charles Henry",male,18,0,0,S.O.C. 14879,73.5,,S
|
||||
387,0,3,"Goodwin, Master. Sidney Leonard",male,1,5,2,CA 2144,46.9,,S
|
||||
388,1,2,"Buss, Miss. Kate",female,36,0,0,27849,13,,S
|
||||
389,0,3,"Sadlier, Mr. Matthew",male,,0,0,367655,7.7292,,Q
|
||||
390,1,2,"Lehmann, Miss. Bertha",female,17,0,0,SC 1748,12,,C
|
||||
391,1,1,"Carter, Mr. William Ernest",male,36,1,2,113760,120,B96 B98,S
|
||||
392,1,3,"Jansson, Mr. Carl Olof",male,21,0,0,350034,7.7958,,S
|
||||
393,0,3,"Gustafsson, Mr. Johan Birger",male,28,2,0,3101277,7.925,,S
|
||||
394,1,1,"Newell, Miss. Marjorie",female,23,1,0,35273,113.275,D36,C
|
||||
395,1,3,"Sandstrom, Mrs. Hjalmar (Agnes Charlotta Bengtsson)",female,24,0,2,PP 9549,16.7,G6,S
|
||||
396,0,3,"Johansson, Mr. Erik",male,22,0,0,350052,7.7958,,S
|
||||
397,0,3,"Olsson, Miss. Elina",female,31,0,0,350407,7.8542,,S
|
||||
398,0,2,"McKane, Mr. Peter David",male,46,0,0,28403,26,,S
|
||||
399,0,2,"Pain, Dr. Alfred",male,23,0,0,244278,10.5,,S
|
||||
400,1,2,"Trout, Mrs. William H (Jessie L)",female,28,0,0,240929,12.65,,S
|
||||
401,1,3,"Niskanen, Mr. Juha",male,39,0,0,STON/O 2. 3101289,7.925,,S
|
||||
402,0,3,"Adams, Mr. John",male,26,0,0,341826,8.05,,S
|
||||
403,0,3,"Jussila, Miss. Mari Aina",female,21,1,0,4137,9.825,,S
|
||||
404,0,3,"Hakkarainen, Mr. Pekka Pietari",male,28,1,0,STON/O2. 3101279,15.85,,S
|
||||
405,0,3,"Oreskovic, Miss. Marija",female,20,0,0,315096,8.6625,,S
|
||||
406,0,2,"Gale, Mr. Shadrach",male,34,1,0,28664,21,,S
|
||||
407,0,3,"Widegren, Mr. Carl/Charles Peter",male,51,0,0,347064,7.75,,S
|
||||
408,1,2,"Richards, Master. William Rowe",male,3,1,1,29106,18.75,,S
|
||||
409,0,3,"Birkeland, Mr. Hans Martin Monsen",male,21,0,0,312992,7.775,,S
|
||||
410,0,3,"Lefebre, Miss. Ida",female,,3,1,4133,25.4667,,S
|
||||
411,0,3,"Sdycoff, Mr. Todor",male,,0,0,349222,7.8958,,S
|
||||
412,0,3,"Hart, Mr. Henry",male,,0,0,394140,6.8583,,Q
|
||||
413,1,1,"Minahan, Miss. Daisy E",female,33,1,0,19928,90,C78,Q
|
||||
414,0,2,"Cunningham, Mr. Alfred Fleming",male,,0,0,239853,0,,S
|
||||
415,1,3,"Sundman, Mr. Johan Julian",male,44,0,0,STON/O 2. 3101269,7.925,,S
|
||||
416,0,3,"Meek, Mrs. Thomas (Annie Louise Rowley)",female,,0,0,343095,8.05,,S
|
||||
417,1,2,"Drew, Mrs. James Vivian (Lulu Thorne Christian)",female,34,1,1,28220,32.5,,S
|
||||
418,1,2,"Silven, Miss. Lyyli Karoliina",female,18,0,2,250652,13,,S
|
||||
419,0,2,"Matthews, Mr. William John",male,30,0,0,28228,13,,S
|
||||
420,0,3,"Van Impe, Miss. Catharina",female,10,0,2,345773,24.15,,S
|
||||
421,0,3,"Gheorgheff, Mr. Stanio",male,,0,0,349254,7.8958,,C
|
||||
422,0,3,"Charters, Mr. David",male,21,0,0,A/5. 13032,7.7333,,Q
|
||||
423,0,3,"Zimmerman, Mr. Leo",male,29,0,0,315082,7.875,,S
|
||||
424,0,3,"Danbom, Mrs. Ernst Gilbert (Anna Sigrid Maria Brogren)",female,28,1,1,347080,14.4,,S
|
||||
425,0,3,"Rosblom, Mr. Viktor Richard",male,18,1,1,370129,20.2125,,S
|
||||
426,0,3,"Wiseman, Mr. Phillippe",male,,0,0,A/4. 34244,7.25,,S
|
||||
427,1,2,"Clarke, Mrs. Charles V (Ada Maria Winfield)",female,28,1,0,2003,26,,S
|
||||
428,1,2,"Phillips, Miss. Kate Florence (""Mrs Kate Louise Phillips Marshall"")",female,19,0,0,250655,26,,S
|
||||
429,0,3,"Flynn, Mr. James",male,,0,0,364851,7.75,,Q
|
||||
430,1,3,"Pickard, Mr. Berk (Berk Trembisky)",male,32,0,0,SOTON/O.Q. 392078,8.05,E10,S
|
||||
431,1,1,"Bjornstrom-Steffansson, Mr. Mauritz Hakan",male,28,0,0,110564,26.55,C52,S
|
||||
432,1,3,"Thorneycroft, Mrs. Percival (Florence Kate White)",female,,1,0,376564,16.1,,S
|
||||
433,1,2,"Louch, Mrs. Charles Alexander (Alice Adelaide Slow)",female,42,1,0,SC/AH 3085,26,,S
|
||||
434,0,3,"Kallio, Mr. Nikolai Erland",male,17,0,0,STON/O 2. 3101274,7.125,,S
|
||||
435,0,1,"Silvey, Mr. William Baird",male,50,1,0,13507,55.9,E44,S
|
||||
436,1,1,"Carter, Miss. Lucile Polk",female,14,1,2,113760,120,B96 B98,S
|
||||
437,0,3,"Ford, Miss. Doolina Margaret ""Daisy""",female,21,2,2,W./C. 6608,34.375,,S
|
||||
438,1,2,"Richards, Mrs. Sidney (Emily Hocking)",female,24,2,3,29106,18.75,,S
|
||||
439,0,1,"Fortune, Mr. Mark",male,64,1,4,19950,263,C23 C25 C27,S
|
||||
440,0,2,"Kvillner, Mr. Johan Henrik Johannesson",male,31,0,0,C.A. 18723,10.5,,S
|
||||
441,1,2,"Hart, Mrs. Benjamin (Esther Ada Bloomfield)",female,45,1,1,F.C.C. 13529,26.25,,S
|
||||
442,0,3,"Hampe, Mr. Leon",male,20,0,0,345769,9.5,,S
|
||||
443,0,3,"Petterson, Mr. Johan Emil",male,25,1,0,347076,7.775,,S
|
||||
444,1,2,"Reynaldo, Ms. Encarnacion",female,28,0,0,230434,13,,S
|
||||
445,1,3,"Johannesen-Bratthammer, Mr. Bernt",male,,0,0,65306,8.1125,,S
|
||||
446,1,1,"Dodge, Master. Washington",male,4,0,2,33638,81.8583,A34,S
|
||||
447,1,2,"Mellinger, Miss. Madeleine Violet",female,13,0,1,250644,19.5,,S
|
||||
448,1,1,"Seward, Mr. Frederic Kimber",male,34,0,0,113794,26.55,,S
|
||||
449,1,3,"Baclini, Miss. Marie Catherine",female,5,2,1,2666,19.2583,,C
|
||||
450,1,1,"Peuchen, Major. Arthur Godfrey",male,52,0,0,113786,30.5,C104,S
|
||||
451,0,2,"West, Mr. Edwy Arthur",male,36,1,2,C.A. 34651,27.75,,S
|
||||
452,0,3,"Hagland, Mr. Ingvald Olai Olsen",male,,1,0,65303,19.9667,,S
|
||||
453,0,1,"Foreman, Mr. Benjamin Laventall",male,30,0,0,113051,27.75,C111,C
|
||||
454,1,1,"Goldenberg, Mr. Samuel L",male,49,1,0,17453,89.1042,C92,C
|
||||
455,0,3,"Peduzzi, Mr. Joseph",male,,0,0,A/5 2817,8.05,,S
|
||||
456,1,3,"Jalsevac, Mr. Ivan",male,29,0,0,349240,7.8958,,C
|
||||
457,0,1,"Millet, Mr. Francis Davis",male,65,0,0,13509,26.55,E38,S
|
||||
458,1,1,"Kenyon, Mrs. Frederick R (Marion)",female,,1,0,17464,51.8625,D21,S
|
||||
459,1,2,"Toomey, Miss. Ellen",female,50,0,0,F.C.C. 13531,10.5,,S
|
||||
460,0,3,"O'Connor, Mr. Maurice",male,,0,0,371060,7.75,,Q
|
||||
461,1,1,"Anderson, Mr. Harry",male,48,0,0,19952,26.55,E12,S
|
||||
462,0,3,"Morley, Mr. William",male,34,0,0,364506,8.05,,S
|
||||
463,0,1,"Gee, Mr. Arthur H",male,47,0,0,111320,38.5,E63,S
|
||||
464,0,2,"Milling, Mr. Jacob Christian",male,48,0,0,234360,13,,S
|
||||
465,0,3,"Maisner, Mr. Simon",male,,0,0,A/S 2816,8.05,,S
|
||||
466,0,3,"Goncalves, Mr. Manuel Estanslas",male,38,0,0,SOTON/O.Q. 3101306,7.05,,S
|
||||
467,0,2,"Campbell, Mr. William",male,,0,0,239853,0,,S
|
||||
468,0,1,"Smart, Mr. John Montgomery",male,56,0,0,113792,26.55,,S
|
||||
469,0,3,"Scanlan, Mr. James",male,,0,0,36209,7.725,,Q
|
||||
470,1,3,"Baclini, Miss. Helene Barbara",female,0.75,2,1,2666,19.2583,,C
|
||||
471,0,3,"Keefe, Mr. Arthur",male,,0,0,323592,7.25,,S
|
||||
472,0,3,"Cacic, Mr. Luka",male,38,0,0,315089,8.6625,,S
|
||||
473,1,2,"West, Mrs. Edwy Arthur (Ada Mary Worth)",female,33,1,2,C.A. 34651,27.75,,S
|
||||
474,1,2,"Jerwan, Mrs. Amin S (Marie Marthe Thuillard)",female,23,0,0,SC/AH Basle 541,13.7917,D,C
|
||||
475,0,3,"Strandberg, Miss. Ida Sofia",female,22,0,0,7553,9.8375,,S
|
||||
476,0,1,"Clifford, Mr. George Quincy",male,,0,0,110465,52,A14,S
|
||||
477,0,2,"Renouf, Mr. Peter Henry",male,34,1,0,31027,21,,S
|
||||
478,0,3,"Braund, Mr. Lewis Richard",male,29,1,0,3460,7.0458,,S
|
||||
479,0,3,"Karlsson, Mr. Nils August",male,22,0,0,350060,7.5208,,S
|
||||
480,1,3,"Hirvonen, Miss. Hildur E",female,2,0,1,3101298,12.2875,,S
|
||||
481,0,3,"Goodwin, Master. Harold Victor",male,9,5,2,CA 2144,46.9,,S
|
||||
482,0,2,"Frost, Mr. Anthony Wood ""Archie""",male,,0,0,239854,0,,S
|
||||
483,0,3,"Rouse, Mr. Richard Henry",male,50,0,0,A/5 3594,8.05,,S
|
||||
484,1,3,"Turkula, Mrs. (Hedwig)",female,63,0,0,4134,9.5875,,S
|
||||
485,1,1,"Bishop, Mr. Dickinson H",male,25,1,0,11967,91.0792,B49,C
|
||||
486,0,3,"Lefebre, Miss. Jeannie",female,,3,1,4133,25.4667,,S
|
||||
487,1,1,"Hoyt, Mrs. Frederick Maxfield (Jane Anne Forby)",female,35,1,0,19943,90,C93,S
|
||||
488,0,1,"Kent, Mr. Edward Austin",male,58,0,0,11771,29.7,B37,C
|
||||
489,0,3,"Somerton, Mr. Francis William",male,30,0,0,A.5. 18509,8.05,,S
|
||||
490,1,3,"Coutts, Master. Eden Leslie ""Neville""",male,9,1,1,C.A. 37671,15.9,,S
|
||||
491,0,3,"Hagland, Mr. Konrad Mathias Reiersen",male,,1,0,65304,19.9667,,S
|
||||
492,0,3,"Windelov, Mr. Einar",male,21,0,0,SOTON/OQ 3101317,7.25,,S
|
||||
493,0,1,"Molson, Mr. Harry Markland",male,55,0,0,113787,30.5,C30,S
|
||||
494,0,1,"Artagaveytia, Mr. Ramon",male,71,0,0,PC 17609,49.5042,,C
|
||||
495,0,3,"Stanley, Mr. Edward Roland",male,21,0,0,A/4 45380,8.05,,S
|
||||
496,0,3,"Yousseff, Mr. Gerious",male,,0,0,2627,14.4583,,C
|
||||
497,1,1,"Eustis, Miss. Elizabeth Mussey",female,54,1,0,36947,78.2667,D20,C
|
||||
498,0,3,"Shellard, Mr. Frederick William",male,,0,0,C.A. 6212,15.1,,S
|
||||
499,0,1,"Allison, Mrs. Hudson J C (Bessie Waldo Daniels)",female,25,1,2,113781,151.55,C22 C26,S
|
||||
500,0,3,"Svensson, Mr. Olof",male,24,0,0,350035,7.7958,,S
|
||||
501,0,3,"Calic, Mr. Petar",male,17,0,0,315086,8.6625,,S
|
||||
502,0,3,"Canavan, Miss. Mary",female,21,0,0,364846,7.75,,Q
|
||||
503,0,3,"O'Sullivan, Miss. Bridget Mary",female,,0,0,330909,7.6292,,Q
|
||||
504,0,3,"Laitinen, Miss. Kristina Sofia",female,37,0,0,4135,9.5875,,S
|
||||
505,1,1,"Maioni, Miss. Roberta",female,16,0,0,110152,86.5,B79,S
|
||||
506,0,1,"Penasco y Castellana, Mr. Victor de Satode",male,18,1,0,PC 17758,108.9,C65,C
|
||||
507,1,2,"Quick, Mrs. Frederick Charles (Jane Richards)",female,33,0,2,26360,26,,S
|
||||
508,1,1,"Bradley, Mr. George (""George Arthur Brayton"")",male,,0,0,111427,26.55,,S
|
||||
509,0,3,"Olsen, Mr. Henry Margido",male,28,0,0,C 4001,22.525,,S
|
||||
510,1,3,"Lang, Mr. Fang",male,26,0,0,1601,56.4958,,S
|
||||
511,1,3,"Daly, Mr. Eugene Patrick",male,29,0,0,382651,7.75,,Q
|
||||
512,0,3,"Webber, Mr. James",male,,0,0,SOTON/OQ 3101316,8.05,,S
|
||||
513,1,1,"McGough, Mr. James Robert",male,36,0,0,PC 17473,26.2875,E25,S
|
||||
514,1,1,"Rothschild, Mrs. Martin (Elizabeth L. Barrett)",female,54,1,0,PC 17603,59.4,,C
|
||||
515,0,3,"Coleff, Mr. Satio",male,24,0,0,349209,7.4958,,S
|
||||
516,0,1,"Walker, Mr. William Anderson",male,47,0,0,36967,34.0208,D46,S
|
||||
517,1,2,"Lemore, Mrs. (Amelia Milley)",female,34,0,0,C.A. 34260,10.5,F33,S
|
||||
518,0,3,"Ryan, Mr. Patrick",male,,0,0,371110,24.15,,Q
|
||||
519,1,2,"Angle, Mrs. William A (Florence ""Mary"" Agnes Hughes)",female,36,1,0,226875,26,,S
|
||||
520,0,3,"Pavlovic, Mr. Stefo",male,32,0,0,349242,7.8958,,S
|
||||
521,1,1,"Perreault, Miss. Anne",female,30,0,0,12749,93.5,B73,S
|
||||
522,0,3,"Vovk, Mr. Janko",male,22,0,0,349252,7.8958,,S
|
||||
523,0,3,"Lahoud, Mr. Sarkis",male,,0,0,2624,7.225,,C
|
||||
524,1,1,"Hippach, Mrs. Louis Albert (Ida Sophia Fischer)",female,44,0,1,111361,57.9792,B18,C
|
||||
525,0,3,"Kassem, Mr. Fared",male,,0,0,2700,7.2292,,C
|
||||
526,0,3,"Farrell, Mr. James",male,40.5,0,0,367232,7.75,,Q
|
||||
527,1,2,"Ridsdale, Miss. Lucy",female,50,0,0,W./C. 14258,10.5,,S
|
||||
528,0,1,"Farthing, Mr. John",male,,0,0,PC 17483,221.7792,C95,S
|
||||
529,0,3,"Salonen, Mr. Johan Werner",male,39,0,0,3101296,7.925,,S
|
||||
530,0,2,"Hocking, Mr. Richard George",male,23,2,1,29104,11.5,,S
|
||||
531,1,2,"Quick, Miss. Phyllis May",female,2,1,1,26360,26,,S
|
||||
532,0,3,"Toufik, Mr. Nakli",male,,0,0,2641,7.2292,,C
|
||||
533,0,3,"Elias, Mr. Joseph Jr",male,17,1,1,2690,7.2292,,C
|
||||
534,1,3,"Peter, Mrs. Catherine (Catherine Rizk)",female,,0,2,2668,22.3583,,C
|
||||
535,0,3,"Cacic, Miss. Marija",female,30,0,0,315084,8.6625,,S
|
||||
536,1,2,"Hart, Miss. Eva Miriam",female,7,0,2,F.C.C. 13529,26.25,,S
|
||||
537,0,1,"Butt, Major. Archibald Willingham",male,45,0,0,113050,26.55,B38,S
|
||||
538,1,1,"LeRoy, Miss. Bertha",female,30,0,0,PC 17761,106.425,,C
|
||||
539,0,3,"Risien, Mr. Samuel Beard",male,,0,0,364498,14.5,,S
|
||||
540,1,1,"Frolicher, Miss. Hedwig Margaritha",female,22,0,2,13568,49.5,B39,C
|
||||
541,1,1,"Crosby, Miss. Harriet R",female,36,0,2,WE/P 5735,71,B22,S
|
||||
542,0,3,"Andersson, Miss. Ingeborg Constanzia",female,9,4,2,347082,31.275,,S
|
||||
543,0,3,"Andersson, Miss. Sigrid Elisabeth",female,11,4,2,347082,31.275,,S
|
||||
544,1,2,"Beane, Mr. Edward",male,32,1,0,2908,26,,S
|
||||
545,0,1,"Douglas, Mr. Walter Donald",male,50,1,0,PC 17761,106.425,C86,C
|
||||
546,0,1,"Nicholson, Mr. Arthur Ernest",male,64,0,0,693,26,,S
|
||||
547,1,2,"Beane, Mrs. Edward (Ethel Clarke)",female,19,1,0,2908,26,,S
|
||||
548,1,2,"Padro y Manent, Mr. Julian",male,,0,0,SC/PARIS 2146,13.8625,,C
|
||||
549,0,3,"Goldsmith, Mr. Frank John",male,33,1,1,363291,20.525,,S
|
||||
550,1,2,"Davies, Master. John Morgan Jr",male,8,1,1,C.A. 33112,36.75,,S
|
||||
551,1,1,"Thayer, Mr. John Borland Jr",male,17,0,2,17421,110.8833,C70,C
|
||||
552,0,2,"Sharp, Mr. Percival James R",male,27,0,0,244358,26,,S
|
||||
553,0,3,"O'Brien, Mr. Timothy",male,,0,0,330979,7.8292,,Q
|
||||
554,1,3,"Leeni, Mr. Fahim (""Philip Zenni"")",male,22,0,0,2620,7.225,,C
|
||||
555,1,3,"Ohman, Miss. Velin",female,22,0,0,347085,7.775,,S
|
||||
556,0,1,"Wright, Mr. George",male,62,0,0,113807,26.55,,S
|
||||
557,1,1,"Duff Gordon, Lady. (Lucille Christiana Sutherland) (""Mrs Morgan"")",female,48,1,0,11755,39.6,A16,C
|
||||
558,0,1,"Robbins, Mr. Victor",male,,0,0,PC 17757,227.525,,C
|
||||
559,1,1,"Taussig, Mrs. Emil (Tillie Mandelbaum)",female,39,1,1,110413,79.65,E67,S
|
||||
560,1,3,"de Messemaeker, Mrs. Guillaume Joseph (Emma)",female,36,1,0,345572,17.4,,S
|
||||
561,0,3,"Morrow, Mr. Thomas Rowan",male,,0,0,372622,7.75,,Q
|
||||
562,0,3,"Sivic, Mr. Husein",male,40,0,0,349251,7.8958,,S
|
||||
563,0,2,"Norman, Mr. Robert Douglas",male,28,0,0,218629,13.5,,S
|
||||
564,0,3,"Simmons, Mr. John",male,,0,0,SOTON/OQ 392082,8.05,,S
|
||||
565,0,3,"Meanwell, Miss. (Marion Ogden)",female,,0,0,SOTON/O.Q. 392087,8.05,,S
|
||||
566,0,3,"Davies, Mr. Alfred J",male,24,2,0,A/4 48871,24.15,,S
|
||||
567,0,3,"Stoytcheff, Mr. Ilia",male,19,0,0,349205,7.8958,,S
|
||||
568,0,3,"Palsson, Mrs. Nils (Alma Cornelia Berglund)",female,29,0,4,349909,21.075,,S
|
||||
569,0,3,"Doharr, Mr. Tannous",male,,0,0,2686,7.2292,,C
|
||||
570,1,3,"Jonsson, Mr. Carl",male,32,0,0,350417,7.8542,,S
|
||||
571,1,2,"Harris, Mr. George",male,62,0,0,S.W./PP 752,10.5,,S
|
||||
572,1,1,"Appleton, Mrs. Edward Dale (Charlotte Lamson)",female,53,2,0,11769,51.4792,C101,S
|
||||
573,1,1,"Flynn, Mr. John Irwin (""Irving"")",male,36,0,0,PC 17474,26.3875,E25,S
|
||||
574,1,3,"Kelly, Miss. Mary",female,,0,0,14312,7.75,,Q
|
||||
575,0,3,"Rush, Mr. Alfred George John",male,16,0,0,A/4. 20589,8.05,,S
|
||||
576,0,3,"Patchett, Mr. George",male,19,0,0,358585,14.5,,S
|
||||
577,1,2,"Garside, Miss. Ethel",female,34,0,0,243880,13,,S
|
||||
578,1,1,"Silvey, Mrs. William Baird (Alice Munger)",female,39,1,0,13507,55.9,E44,S
|
||||
579,0,3,"Caram, Mrs. Joseph (Maria Elias)",female,,1,0,2689,14.4583,,C
|
||||
580,1,3,"Jussila, Mr. Eiriik",male,32,0,0,STON/O 2. 3101286,7.925,,S
|
||||
581,1,2,"Christy, Miss. Julie Rachel",female,25,1,1,237789,30,,S
|
||||
582,1,1,"Thayer, Mrs. John Borland (Marian Longstreth Morris)",female,39,1,1,17421,110.8833,C68,C
|
||||
583,0,2,"Downton, Mr. William James",male,54,0,0,28403,26,,S
|
||||
584,0,1,"Ross, Mr. John Hugo",male,36,0,0,13049,40.125,A10,C
|
||||
585,0,3,"Paulner, Mr. Uscher",male,,0,0,3411,8.7125,,C
|
||||
586,1,1,"Taussig, Miss. Ruth",female,18,0,2,110413,79.65,E68,S
|
||||
587,0,2,"Jarvis, Mr. John Denzil",male,47,0,0,237565,15,,S
|
||||
588,1,1,"Frolicher-Stehli, Mr. Maxmillian",male,60,1,1,13567,79.2,B41,C
|
||||
589,0,3,"Gilinski, Mr. Eliezer",male,22,0,0,14973,8.05,,S
|
||||
590,0,3,"Murdlin, Mr. Joseph",male,,0,0,A./5. 3235,8.05,,S
|
||||
591,0,3,"Rintamaki, Mr. Matti",male,35,0,0,STON/O 2. 3101273,7.125,,S
|
||||
592,1,1,"Stephenson, Mrs. Walter Bertram (Martha Eustis)",female,52,1,0,36947,78.2667,D20,C
|
||||
593,0,3,"Elsbury, Mr. William James",male,47,0,0,A/5 3902,7.25,,S
|
||||
594,0,3,"Bourke, Miss. Mary",female,,0,2,364848,7.75,,Q
|
||||
595,0,2,"Chapman, Mr. John Henry",male,37,1,0,SC/AH 29037,26,,S
|
||||
596,0,3,"Van Impe, Mr. Jean Baptiste",male,36,1,1,345773,24.15,,S
|
||||
597,1,2,"Leitch, Miss. Jessie Wills",female,,0,0,248727,33,,S
|
||||
598,0,3,"Johnson, Mr. Alfred",male,49,0,0,LINE,0,,S
|
||||
599,0,3,"Boulos, Mr. Hanna",male,,0,0,2664,7.225,,C
|
||||
600,1,1,"Duff Gordon, Sir. Cosmo Edmund (""Mr Morgan"")",male,49,1,0,PC 17485,56.9292,A20,C
|
||||
601,1,2,"Jacobsohn, Mrs. Sidney Samuel (Amy Frances Christy)",female,24,2,1,243847,27,,S
|
||||
602,0,3,"Slabenoff, Mr. Petco",male,,0,0,349214,7.8958,,S
|
||||
603,0,1,"Harrington, Mr. Charles H",male,,0,0,113796,42.4,,S
|
||||
604,0,3,"Torber, Mr. Ernst William",male,44,0,0,364511,8.05,,S
|
||||
605,1,1,"Homer, Mr. Harry (""Mr E Haven"")",male,35,0,0,111426,26.55,,C
|
||||
606,0,3,"Lindell, Mr. Edvard Bengtsson",male,36,1,0,349910,15.55,,S
|
||||
607,0,3,"Karaic, Mr. Milan",male,30,0,0,349246,7.8958,,S
|
||||
608,1,1,"Daniel, Mr. Robert Williams",male,27,0,0,113804,30.5,,S
|
||||
609,1,2,"Laroche, Mrs. Joseph (Juliette Marie Louise Lafargue)",female,22,1,2,SC/Paris 2123,41.5792,,C
|
||||
610,1,1,"Shutes, Miss. Elizabeth W",female,40,0,0,PC 17582,153.4625,C125,S
|
||||
611,0,3,"Andersson, Mrs. Anders Johan (Alfrida Konstantia Brogren)",female,39,1,5,347082,31.275,,S
|
||||
612,0,3,"Jardin, Mr. Jose Neto",male,,0,0,SOTON/O.Q. 3101305,7.05,,S
|
||||
613,1,3,"Murphy, Miss. Margaret Jane",female,,1,0,367230,15.5,,Q
|
||||
614,0,3,"Horgan, Mr. John",male,,0,0,370377,7.75,,Q
|
||||
615,0,3,"Brocklebank, Mr. William Alfred",male,35,0,0,364512,8.05,,S
|
||||
616,1,2,"Herman, Miss. Alice",female,24,1,2,220845,65,,S
|
||||
617,0,3,"Danbom, Mr. Ernst Gilbert",male,34,1,1,347080,14.4,,S
|
||||
618,0,3,"Lobb, Mrs. William Arthur (Cordelia K Stanlick)",female,26,1,0,A/5. 3336,16.1,,S
|
||||
619,1,2,"Becker, Miss. Marion Louise",female,4,2,1,230136,39,F4,S
|
||||
620,0,2,"Gavey, Mr. Lawrence",male,26,0,0,31028,10.5,,S
|
||||
621,0,3,"Yasbeck, Mr. Antoni",male,27,1,0,2659,14.4542,,C
|
||||
622,1,1,"Kimball, Mr. Edwin Nelson Jr",male,42,1,0,11753,52.5542,D19,S
|
||||
623,1,3,"Nakid, Mr. Sahid",male,20,1,1,2653,15.7417,,C
|
||||
624,0,3,"Hansen, Mr. Henry Damsgaard",male,21,0,0,350029,7.8542,,S
|
||||
625,0,3,"Bowen, Mr. David John ""Dai""",male,21,0,0,54636,16.1,,S
|
||||
626,0,1,"Sutton, Mr. Frederick",male,61,0,0,36963,32.3208,D50,S
|
||||
627,0,2,"Kirkland, Rev. Charles Leonard",male,57,0,0,219533,12.35,,Q
|
||||
628,1,1,"Longley, Miss. Gretchen Fiske",female,21,0,0,13502,77.9583,D9,S
|
||||
629,0,3,"Bostandyeff, Mr. Guentcho",male,26,0,0,349224,7.8958,,S
|
||||
630,0,3,"O'Connell, Mr. Patrick D",male,,0,0,334912,7.7333,,Q
|
||||
631,1,1,"Barkworth, Mr. Algernon Henry Wilson",male,80,0,0,27042,30,A23,S
|
||||
632,0,3,"Lundahl, Mr. Johan Svensson",male,51,0,0,347743,7.0542,,S
|
||||
633,1,1,"Stahelin-Maeglin, Dr. Max",male,32,0,0,13214,30.5,B50,C
|
||||
634,0,1,"Parr, Mr. William Henry Marsh",male,,0,0,112052,0,,S
|
||||
635,0,3,"Skoog, Miss. Mabel",female,9,3,2,347088,27.9,,S
|
||||
636,1,2,"Davis, Miss. Mary",female,28,0,0,237668,13,,S
|
||||
637,0,3,"Leinonen, Mr. Antti Gustaf",male,32,0,0,STON/O 2. 3101292,7.925,,S
|
||||
638,0,2,"Collyer, Mr. Harvey",male,31,1,1,C.A. 31921,26.25,,S
|
||||
639,0,3,"Panula, Mrs. Juha (Maria Emilia Ojala)",female,41,0,5,3101295,39.6875,,S
|
||||
640,0,3,"Thorneycroft, Mr. Percival",male,,1,0,376564,16.1,,S
|
||||
641,0,3,"Jensen, Mr. Hans Peder",male,20,0,0,350050,7.8542,,S
|
||||
642,1,1,"Sagesser, Mlle. Emma",female,24,0,0,PC 17477,69.3,B35,C
|
||||
643,0,3,"Skoog, Miss. Margit Elizabeth",female,2,3,2,347088,27.9,,S
|
||||
644,1,3,"Foo, Mr. Choong",male,,0,0,1601,56.4958,,S
|
||||
645,1,3,"Baclini, Miss. Eugenie",female,0.75,2,1,2666,19.2583,,C
|
||||
646,1,1,"Harper, Mr. Henry Sleeper",male,48,1,0,PC 17572,76.7292,D33,C
|
||||
647,0,3,"Cor, Mr. Liudevit",male,19,0,0,349231,7.8958,,S
|
||||
648,1,1,"Simonius-Blumer, Col. Oberst Alfons",male,56,0,0,13213,35.5,A26,C
|
||||
649,0,3,"Willey, Mr. Edward",male,,0,0,S.O./P.P. 751,7.55,,S
|
||||
650,1,3,"Stanley, Miss. Amy Zillah Elsie",female,23,0,0,CA. 2314,7.55,,S
|
||||
651,0,3,"Mitkoff, Mr. Mito",male,,0,0,349221,7.8958,,S
|
||||
652,1,2,"Doling, Miss. Elsie",female,18,0,1,231919,23,,S
|
||||
653,0,3,"Kalvik, Mr. Johannes Halvorsen",male,21,0,0,8475,8.4333,,S
|
||||
654,1,3,"O'Leary, Miss. Hanora ""Norah""",female,,0,0,330919,7.8292,,Q
|
||||
655,0,3,"Hegarty, Miss. Hanora ""Nora""",female,18,0,0,365226,6.75,,Q
|
||||
656,0,2,"Hickman, Mr. Leonard Mark",male,24,2,0,S.O.C. 14879,73.5,,S
|
||||
657,0,3,"Radeff, Mr. Alexander",male,,0,0,349223,7.8958,,S
|
||||
658,0,3,"Bourke, Mrs. John (Catherine)",female,32,1,1,364849,15.5,,Q
|
||||
659,0,2,"Eitemiller, Mr. George Floyd",male,23,0,0,29751,13,,S
|
||||
660,0,1,"Newell, Mr. Arthur Webster",male,58,0,2,35273,113.275,D48,C
|
||||
661,1,1,"Frauenthal, Dr. Henry William",male,50,2,0,PC 17611,133.65,,S
|
||||
662,0,3,"Badt, Mr. Mohamed",male,40,0,0,2623,7.225,,C
|
||||
663,0,1,"Colley, Mr. Edward Pomeroy",male,47,0,0,5727,25.5875,E58,S
|
||||
664,0,3,"Coleff, Mr. Peju",male,36,0,0,349210,7.4958,,S
|
||||
665,1,3,"Lindqvist, Mr. Eino William",male,20,1,0,STON/O 2. 3101285,7.925,,S
|
||||
666,0,2,"Hickman, Mr. Lewis",male,32,2,0,S.O.C. 14879,73.5,,S
|
||||
667,0,2,"Butler, Mr. Reginald Fenton",male,25,0,0,234686,13,,S
|
||||
668,0,3,"Rommetvedt, Mr. Knud Paust",male,,0,0,312993,7.775,,S
|
||||
669,0,3,"Cook, Mr. Jacob",male,43,0,0,A/5 3536,8.05,,S
|
||||
670,1,1,"Taylor, Mrs. Elmer Zebley (Juliet Cummins Wright)",female,,1,0,19996,52,C126,S
|
||||
671,1,2,"Brown, Mrs. Thomas William Solomon (Elizabeth Catherine Ford)",female,40,1,1,29750,39,,S
|
||||
672,0,1,"Davidson, Mr. Thornton",male,31,1,0,F.C. 12750,52,B71,S
|
||||
673,0,2,"Mitchell, Mr. Henry Michael",male,70,0,0,C.A. 24580,10.5,,S
|
||||
674,1,2,"Wilhelms, Mr. Charles",male,31,0,0,244270,13,,S
|
||||
675,0,2,"Watson, Mr. Ennis Hastings",male,,0,0,239856,0,,S
|
||||
676,0,3,"Edvardsson, Mr. Gustaf Hjalmar",male,18,0,0,349912,7.775,,S
|
||||
677,0,3,"Sawyer, Mr. Frederick Charles",male,24.5,0,0,342826,8.05,,S
|
||||
678,1,3,"Turja, Miss. Anna Sofia",female,18,0,0,4138,9.8417,,S
|
||||
679,0,3,"Goodwin, Mrs. Frederick (Augusta Tyler)",female,43,1,6,CA 2144,46.9,,S
|
||||
680,1,1,"Cardeza, Mr. Thomas Drake Martinez",male,36,0,1,PC 17755,512.3292,B51 B53 B55,C
|
||||
681,0,3,"Peters, Miss. Katie",female,,0,0,330935,8.1375,,Q
|
||||
682,1,1,"Hassab, Mr. Hammad",male,27,0,0,PC 17572,76.7292,D49,C
|
||||
683,0,3,"Olsvigen, Mr. Thor Anderson",male,20,0,0,6563,9.225,,S
|
||||
684,0,3,"Goodwin, Mr. Charles Edward",male,14,5,2,CA 2144,46.9,,S
|
||||
685,0,2,"Brown, Mr. Thomas William Solomon",male,60,1,1,29750,39,,S
|
||||
686,0,2,"Laroche, Mr. Joseph Philippe Lemercier",male,25,1,2,SC/Paris 2123,41.5792,,C
|
||||
687,0,3,"Panula, Mr. Jaako Arnold",male,14,4,1,3101295,39.6875,,S
|
||||
688,0,3,"Dakic, Mr. Branko",male,19,0,0,349228,10.1708,,S
|
||||
689,0,3,"Fischer, Mr. Eberhard Thelander",male,18,0,0,350036,7.7958,,S
|
||||
690,1,1,"Madill, Miss. Georgette Alexandra",female,15,0,1,24160,211.3375,B5,S
|
||||
691,1,1,"Dick, Mr. Albert Adrian",male,31,1,0,17474,57,B20,S
|
||||
692,1,3,"Karun, Miss. Manca",female,4,0,1,349256,13.4167,,C
|
||||
693,1,3,"Lam, Mr. Ali",male,,0,0,1601,56.4958,,S
|
||||
694,0,3,"Saad, Mr. Khalil",male,25,0,0,2672,7.225,,C
|
||||
695,0,1,"Weir, Col. John",male,60,0,0,113800,26.55,,S
|
||||
696,0,2,"Chapman, Mr. Charles Henry",male,52,0,0,248731,13.5,,S
|
||||
697,0,3,"Kelly, Mr. James",male,44,0,0,363592,8.05,,S
|
||||
698,1,3,"Mullens, Miss. Katherine ""Katie""",female,,0,0,35852,7.7333,,Q
|
||||
699,0,1,"Thayer, Mr. John Borland",male,49,1,1,17421,110.8833,C68,C
|
||||
700,0,3,"Humblen, Mr. Adolf Mathias Nicolai Olsen",male,42,0,0,348121,7.65,F G63,S
|
||||
701,1,1,"Astor, Mrs. John Jacob (Madeleine Talmadge Force)",female,18,1,0,PC 17757,227.525,C62 C64,C
|
||||
702,1,1,"Silverthorne, Mr. Spencer Victor",male,35,0,0,PC 17475,26.2875,E24,S
|
||||
703,0,3,"Barbara, Miss. Saiide",female,18,0,1,2691,14.4542,,C
|
||||
704,0,3,"Gallagher, Mr. Martin",male,25,0,0,36864,7.7417,,Q
|
||||
705,0,3,"Hansen, Mr. Henrik Juul",male,26,1,0,350025,7.8542,,S
|
||||
706,0,2,"Morley, Mr. Henry Samuel (""Mr Henry Marshall"")",male,39,0,0,250655,26,,S
|
||||
707,1,2,"Kelly, Mrs. Florence ""Fannie""",female,45,0,0,223596,13.5,,S
|
||||
708,1,1,"Calderhead, Mr. Edward Pennington",male,42,0,0,PC 17476,26.2875,E24,S
|
||||
709,1,1,"Cleaver, Miss. Alice",female,22,0,0,113781,151.55,,S
|
||||
710,1,3,"Moubarek, Master. Halim Gonios (""William George"")",male,,1,1,2661,15.2458,,C
|
||||
711,1,1,"Mayne, Mlle. Berthe Antonine (""Mrs de Villiers"")",female,24,0,0,PC 17482,49.5042,C90,C
|
||||
712,0,1,"Klaber, Mr. Herman",male,,0,0,113028,26.55,C124,S
|
||||
713,1,1,"Taylor, Mr. Elmer Zebley",male,48,1,0,19996,52,C126,S
|
||||
714,0,3,"Larsson, Mr. August Viktor",male,29,0,0,7545,9.4833,,S
|
||||
715,0,2,"Greenberg, Mr. Samuel",male,52,0,0,250647,13,,S
|
||||
716,0,3,"Soholt, Mr. Peter Andreas Lauritz Andersen",male,19,0,0,348124,7.65,F G73,S
|
||||
717,1,1,"Endres, Miss. Caroline Louise",female,38,0,0,PC 17757,227.525,C45,C
|
||||
718,1,2,"Troutt, Miss. Edwina Celia ""Winnie""",female,27,0,0,34218,10.5,E101,S
|
||||
719,0,3,"McEvoy, Mr. Michael",male,,0,0,36568,15.5,,Q
|
||||
720,0,3,"Johnson, Mr. Malkolm Joackim",male,33,0,0,347062,7.775,,S
|
||||
721,1,2,"Harper, Miss. Annie Jessie ""Nina""",female,6,0,1,248727,33,,S
|
||||
722,0,3,"Jensen, Mr. Svend Lauritz",male,17,1,0,350048,7.0542,,S
|
||||
723,0,2,"Gillespie, Mr. William Henry",male,34,0,0,12233,13,,S
|
||||
724,0,2,"Hodges, Mr. Henry Price",male,50,0,0,250643,13,,S
|
||||
725,1,1,"Chambers, Mr. Norman Campbell",male,27,1,0,113806,53.1,E8,S
|
||||
726,0,3,"Oreskovic, Mr. Luka",male,20,0,0,315094,8.6625,,S
|
||||
727,1,2,"Renouf, Mrs. Peter Henry (Lillian Jefferys)",female,30,3,0,31027,21,,S
|
||||
728,1,3,"Mannion, Miss. Margareth",female,,0,0,36866,7.7375,,Q
|
||||
729,0,2,"Bryhl, Mr. Kurt Arnold Gottfrid",male,25,1,0,236853,26,,S
|
||||
730,0,3,"Ilmakangas, Miss. Pieta Sofia",female,25,1,0,STON/O2. 3101271,7.925,,S
|
||||
731,1,1,"Allen, Miss. Elisabeth Walton",female,29,0,0,24160,211.3375,B5,S
|
||||
732,0,3,"Hassan, Mr. Houssein G N",male,11,0,0,2699,18.7875,,C
|
||||
733,0,2,"Knight, Mr. Robert J",male,,0,0,239855,0,,S
|
||||
734,0,2,"Berriman, Mr. William John",male,23,0,0,28425,13,,S
|
||||
735,0,2,"Troupiansky, Mr. Moses Aaron",male,23,0,0,233639,13,,S
|
||||
736,0,3,"Williams, Mr. Leslie",male,28.5,0,0,54636,16.1,,S
|
||||
737,0,3,"Ford, Mrs. Edward (Margaret Ann Watson)",female,48,1,3,W./C. 6608,34.375,,S
|
||||
738,1,1,"Lesurer, Mr. Gustave J",male,35,0,0,PC 17755,512.3292,B101,C
|
||||
739,0,3,"Ivanoff, Mr. Kanio",male,,0,0,349201,7.8958,,S
|
||||
740,0,3,"Nankoff, Mr. Minko",male,,0,0,349218,7.8958,,S
|
||||
741,1,1,"Hawksford, Mr. Walter James",male,,0,0,16988,30,D45,S
|
||||
742,0,1,"Cavendish, Mr. Tyrell William",male,36,1,0,19877,78.85,C46,S
|
||||
743,1,1,"Ryerson, Miss. Susan Parker ""Suzette""",female,21,2,2,PC 17608,262.375,B57 B59 B63 B66,C
|
||||
744,0,3,"McNamee, Mr. Neal",male,24,1,0,376566,16.1,,S
|
||||
745,1,3,"Stranden, Mr. Juho",male,31,0,0,STON/O 2. 3101288,7.925,,S
|
||||
746,0,1,"Crosby, Capt. Edward Gifford",male,70,1,1,WE/P 5735,71,B22,S
|
||||
747,0,3,"Abbott, Mr. Rossmore Edward",male,16,1,1,C.A. 2673,20.25,,S
|
||||
748,1,2,"Sinkkonen, Miss. Anna",female,30,0,0,250648,13,,S
|
||||
749,0,1,"Marvin, Mr. Daniel Warner",male,19,1,0,113773,53.1,D30,S
|
||||
750,0,3,"Connaghton, Mr. Michael",male,31,0,0,335097,7.75,,Q
|
||||
751,1,2,"Wells, Miss. Joan",female,4,1,1,29103,23,,S
|
||||
752,1,3,"Moor, Master. Meier",male,6,0,1,392096,12.475,E121,S
|
||||
753,0,3,"Vande Velde, Mr. Johannes Joseph",male,33,0,0,345780,9.5,,S
|
||||
754,0,3,"Jonkoff, Mr. Lalio",male,23,0,0,349204,7.8958,,S
|
||||
755,1,2,"Herman, Mrs. Samuel (Jane Laver)",female,48,1,2,220845,65,,S
|
||||
756,1,2,"Hamalainen, Master. Viljo",male,0.67,1,1,250649,14.5,,S
|
||||
757,0,3,"Carlsson, Mr. August Sigfrid",male,28,0,0,350042,7.7958,,S
|
||||
758,0,2,"Bailey, Mr. Percy Andrew",male,18,0,0,29108,11.5,,S
|
||||
759,0,3,"Theobald, Mr. Thomas Leonard",male,34,0,0,363294,8.05,,S
|
||||
760,1,1,"Rothes, the Countess. of (Lucy Noel Martha Dyer-Edwards)",female,33,0,0,110152,86.5,B77,S
|
||||
761,0,3,"Garfirth, Mr. John",male,,0,0,358585,14.5,,S
|
||||
762,0,3,"Nirva, Mr. Iisakki Antino Aijo",male,41,0,0,SOTON/O2 3101272,7.125,,S
|
||||
763,1,3,"Barah, Mr. Hanna Assi",male,20,0,0,2663,7.2292,,C
|
||||
764,1,1,"Carter, Mrs. William Ernest (Lucile Polk)",female,36,1,2,113760,120,B96 B98,S
|
||||
765,0,3,"Eklund, Mr. Hans Linus",male,16,0,0,347074,7.775,,S
|
||||
766,1,1,"Hogeboom, Mrs. John C (Anna Andrews)",female,51,1,0,13502,77.9583,D11,S
|
||||
767,0,1,"Brewe, Dr. Arthur Jackson",male,,0,0,112379,39.6,,C
|
||||
768,0,3,"Mangan, Miss. Mary",female,30.5,0,0,364850,7.75,,Q
|
||||
769,0,3,"Moran, Mr. Daniel J",male,,1,0,371110,24.15,,Q
|
||||
770,0,3,"Gronnestad, Mr. Daniel Danielsen",male,32,0,0,8471,8.3625,,S
|
||||
771,0,3,"Lievens, Mr. Rene Aime",male,24,0,0,345781,9.5,,S
|
||||
772,0,3,"Jensen, Mr. Niels Peder",male,48,0,0,350047,7.8542,,S
|
||||
773,0,2,"Mack, Mrs. (Mary)",female,57,0,0,S.O./P.P. 3,10.5,E77,S
|
||||
774,0,3,"Elias, Mr. Dibo",male,,0,0,2674,7.225,,C
|
||||
775,1,2,"Hocking, Mrs. Elizabeth (Eliza Needs)",female,54,1,3,29105,23,,S
|
||||
776,0,3,"Myhrman, Mr. Pehr Fabian Oliver Malkolm",male,18,0,0,347078,7.75,,S
|
||||
777,0,3,"Tobin, Mr. Roger",male,,0,0,383121,7.75,F38,Q
|
||||
778,1,3,"Emanuel, Miss. Virginia Ethel",female,5,0,0,364516,12.475,,S
|
||||
779,0,3,"Kilgannon, Mr. Thomas J",male,,0,0,36865,7.7375,,Q
|
||||
780,1,1,"Robert, Mrs. Edward Scott (Elisabeth Walton McMillan)",female,43,0,1,24160,211.3375,B3,S
|
||||
781,1,3,"Ayoub, Miss. Banoura",female,13,0,0,2687,7.2292,,C
|
||||
782,1,1,"Dick, Mrs. Albert Adrian (Vera Gillespie)",female,17,1,0,17474,57,B20,S
|
||||
783,0,1,"Long, Mr. Milton Clyde",male,29,0,0,113501,30,D6,S
|
||||
784,0,3,"Johnston, Mr. Andrew G",male,,1,2,W./C. 6607,23.45,,S
|
||||
785,0,3,"Ali, Mr. William",male,25,0,0,SOTON/O.Q. 3101312,7.05,,S
|
||||
786,0,3,"Harmer, Mr. Abraham (David Lishin)",male,25,0,0,374887,7.25,,S
|
||||
787,1,3,"Sjoblom, Miss. Anna Sofia",female,18,0,0,3101265,7.4958,,S
|
||||
788,0,3,"Rice, Master. George Hugh",male,8,4,1,382652,29.125,,Q
|
||||
789,1,3,"Dean, Master. Bertram Vere",male,1,1,2,C.A. 2315,20.575,,S
|
||||
790,0,1,"Guggenheim, Mr. Benjamin",male,46,0,0,PC 17593,79.2,B82 B84,C
|
||||
791,0,3,"Keane, Mr. Andrew ""Andy""",male,,0,0,12460,7.75,,Q
|
||||
792,0,2,"Gaskell, Mr. Alfred",male,16,0,0,239865,26,,S
|
||||
793,0,3,"Sage, Miss. Stella Anna",female,,8,2,CA. 2343,69.55,,S
|
||||
794,0,1,"Hoyt, Mr. William Fisher",male,,0,0,PC 17600,30.6958,,C
|
||||
795,0,3,"Dantcheff, Mr. Ristiu",male,25,0,0,349203,7.8958,,S
|
||||
796,0,2,"Otter, Mr. Richard",male,39,0,0,28213,13,,S
|
||||
797,1,1,"Leader, Dr. Alice (Farnham)",female,49,0,0,17465,25.9292,D17,S
|
||||
798,1,3,"Osman, Mrs. Mara",female,31,0,0,349244,8.6833,,S
|
||||
799,0,3,"Ibrahim Shawah, Mr. Yousseff",male,30,0,0,2685,7.2292,,C
|
||||
800,0,3,"Van Impe, Mrs. Jean Baptiste (Rosalie Paula Govaert)",female,30,1,1,345773,24.15,,S
|
||||
801,0,2,"Ponesell, Mr. Martin",male,34,0,0,250647,13,,S
|
||||
802,1,2,"Collyer, Mrs. Harvey (Charlotte Annie Tate)",female,31,1,1,C.A. 31921,26.25,,S
|
||||
803,1,1,"Carter, Master. William Thornton II",male,11,1,2,113760,120,B96 B98,S
|
||||
804,1,3,"Thomas, Master. Assad Alexander",male,0.42,0,1,2625,8.5167,,C
|
||||
805,1,3,"Hedman, Mr. Oskar Arvid",male,27,0,0,347089,6.975,,S
|
||||
806,0,3,"Johansson, Mr. Karl Johan",male,31,0,0,347063,7.775,,S
|
||||
807,0,1,"Andrews, Mr. Thomas Jr",male,39,0,0,112050,0,A36,S
|
||||
808,0,3,"Pettersson, Miss. Ellen Natalia",female,18,0,0,347087,7.775,,S
|
||||
809,0,2,"Meyer, Mr. August",male,39,0,0,248723,13,,S
|
||||
810,1,1,"Chambers, Mrs. Norman Campbell (Bertha Griggs)",female,33,1,0,113806,53.1,E8,S
|
||||
811,0,3,"Alexander, Mr. William",male,26,0,0,3474,7.8875,,S
|
||||
812,0,3,"Lester, Mr. James",male,39,0,0,A/4 48871,24.15,,S
|
||||
813,0,2,"Slemen, Mr. Richard James",male,35,0,0,28206,10.5,,S
|
||||
814,0,3,"Andersson, Miss. Ebba Iris Alfrida",female,6,4,2,347082,31.275,,S
|
||||
815,0,3,"Tomlin, Mr. Ernest Portage",male,30.5,0,0,364499,8.05,,S
|
||||
816,0,1,"Fry, Mr. Richard",male,,0,0,112058,0,B102,S
|
||||
817,0,3,"Heininen, Miss. Wendla Maria",female,23,0,0,STON/O2. 3101290,7.925,,S
|
||||
818,0,2,"Mallet, Mr. Albert",male,31,1,1,S.C./PARIS 2079,37.0042,,C
|
||||
819,0,3,"Holm, Mr. John Fredrik Alexander",male,43,0,0,C 7075,6.45,,S
|
||||
820,0,3,"Skoog, Master. Karl Thorsten",male,10,3,2,347088,27.9,,S
|
||||
821,1,1,"Hays, Mrs. Charles Melville (Clara Jennings Gregg)",female,52,1,1,12749,93.5,B69,S
|
||||
822,1,3,"Lulic, Mr. Nikola",male,27,0,0,315098,8.6625,,S
|
||||
823,0,1,"Reuchlin, Jonkheer. John George",male,38,0,0,19972,0,,S
|
||||
824,1,3,"Moor, Mrs. (Beila)",female,27,0,1,392096,12.475,E121,S
|
||||
825,0,3,"Panula, Master. Urho Abraham",male,2,4,1,3101295,39.6875,,S
|
||||
826,0,3,"Flynn, Mr. John",male,,0,0,368323,6.95,,Q
|
||||
827,0,3,"Lam, Mr. Len",male,,0,0,1601,56.4958,,S
|
||||
828,1,2,"Mallet, Master. Andre",male,1,0,2,S.C./PARIS 2079,37.0042,,C
|
||||
829,1,3,"McCormack, Mr. Thomas Joseph",male,,0,0,367228,7.75,,Q
|
||||
830,1,1,"Stone, Mrs. George Nelson (Martha Evelyn)",female,62,0,0,113572,80,B28,
|
||||
831,1,3,"Yasbeck, Mrs. Antoni (Selini Alexander)",female,15,1,0,2659,14.4542,,C
|
||||
832,1,2,"Richards, Master. George Sibley",male,0.83,1,1,29106,18.75,,S
|
||||
833,0,3,"Saad, Mr. Amin",male,,0,0,2671,7.2292,,C
|
||||
834,0,3,"Augustsson, Mr. Albert",male,23,0,0,347468,7.8542,,S
|
||||
835,0,3,"Allum, Mr. Owen George",male,18,0,0,2223,8.3,,S
|
||||
836,1,1,"Compton, Miss. Sara Rebecca",female,39,1,1,PC 17756,83.1583,E49,C
|
||||
837,0,3,"Pasic, Mr. Jakob",male,21,0,0,315097,8.6625,,S
|
||||
838,0,3,"Sirota, Mr. Maurice",male,,0,0,392092,8.05,,S
|
||||
839,1,3,"Chip, Mr. Chang",male,32,0,0,1601,56.4958,,S
|
||||
840,1,1,"Marechal, Mr. Pierre",male,,0,0,11774,29.7,C47,C
|
||||
841,0,3,"Alhomaki, Mr. Ilmari Rudolf",male,20,0,0,SOTON/O2 3101287,7.925,,S
|
||||
842,0,2,"Mudd, Mr. Thomas Charles",male,16,0,0,S.O./P.P. 3,10.5,,S
|
||||
843,1,1,"Serepeca, Miss. Augusta",female,30,0,0,113798,31,,C
|
||||
844,0,3,"Lemberopolous, Mr. Peter L",male,34.5,0,0,2683,6.4375,,C
|
||||
845,0,3,"Culumovic, Mr. Jeso",male,17,0,0,315090,8.6625,,S
|
||||
846,0,3,"Abbing, Mr. Anthony",male,42,0,0,C.A. 5547,7.55,,S
|
||||
847,0,3,"Sage, Mr. Douglas Bullen",male,,8,2,CA. 2343,69.55,,S
|
||||
848,0,3,"Markoff, Mr. Marin",male,35,0,0,349213,7.8958,,C
|
||||
849,0,2,"Harper, Rev. John",male,28,0,1,248727,33,,S
|
||||
850,1,1,"Goldenberg, Mrs. Samuel L (Edwiga Grabowska)",female,,1,0,17453,89.1042,C92,C
|
||||
851,0,3,"Andersson, Master. Sigvard Harald Elias",male,4,4,2,347082,31.275,,S
|
||||
852,0,3,"Svensson, Mr. Johan",male,74,0,0,347060,7.775,,S
|
||||
853,0,3,"Boulos, Miss. Nourelain",female,9,1,1,2678,15.2458,,C
|
||||
854,1,1,"Lines, Miss. Mary Conover",female,16,0,1,PC 17592,39.4,D28,S
|
||||
855,0,2,"Carter, Mrs. Ernest Courtenay (Lilian Hughes)",female,44,1,0,244252,26,,S
|
||||
856,1,3,"Aks, Mrs. Sam (Leah Rosen)",female,18,0,1,392091,9.35,,S
|
||||
857,1,1,"Wick, Mrs. George Dennick (Mary Hitchcock)",female,45,1,1,36928,164.8667,,S
|
||||
858,1,1,"Daly, Mr. Peter Denis ",male,51,0,0,113055,26.55,E17,S
|
||||
859,1,3,"Baclini, Mrs. Solomon (Latifa Qurban)",female,24,0,3,2666,19.2583,,C
|
||||
860,0,3,"Razi, Mr. Raihed",male,,0,0,2629,7.2292,,C
|
||||
861,0,3,"Hansen, Mr. Claus Peter",male,41,2,0,350026,14.1083,,S
|
||||
862,0,2,"Giles, Mr. Frederick Edward",male,21,1,0,28134,11.5,,S
|
||||
863,1,1,"Swift, Mrs. Frederick Joel (Margaret Welles Barron)",female,48,0,0,17466,25.9292,D17,S
|
||||
864,0,3,"Sage, Miss. Dorothy Edith ""Dolly""",female,,8,2,CA. 2343,69.55,,S
|
||||
865,0,2,"Gill, Mr. John William",male,24,0,0,233866,13,,S
|
||||
866,1,2,"Bystrom, Mrs. (Karolina)",female,42,0,0,236852,13,,S
|
||||
867,1,2,"Duran y More, Miss. Asuncion",female,27,1,0,SC/PARIS 2149,13.8583,,C
|
||||
868,0,1,"Roebling, Mr. Washington Augustus II",male,31,0,0,PC 17590,50.4958,A24,S
|
||||
869,0,3,"van Melkebeke, Mr. Philemon",male,,0,0,345777,9.5,,S
|
||||
870,1,3,"Johnson, Master. Harold Theodor",male,4,1,1,347742,11.1333,,S
|
||||
871,0,3,"Balkic, Mr. Cerin",male,26,0,0,349248,7.8958,,S
|
||||
872,1,1,"Beckwith, Mrs. Richard Leonard (Sallie Monypeny)",female,47,1,1,11751,52.5542,D35,S
|
||||
873,0,1,"Carlsson, Mr. Frans Olof",male,33,0,0,695,5,B51 B53 B55,S
|
||||
874,0,3,"Vander Cruyssen, Mr. Victor",male,47,0,0,345765,9,,S
|
||||
875,1,2,"Abelson, Mrs. Samuel (Hannah Wizosky)",female,28,1,0,P/PP 3381,24,,C
|
||||
876,1,3,"Najib, Miss. Adele Kiamie ""Jane""",female,15,0,0,2667,7.225,,C
|
||||
877,0,3,"Gustafsson, Mr. Alfred Ossian",male,20,0,0,7534,9.8458,,S
|
||||
878,0,3,"Petroff, Mr. Nedelio",male,19,0,0,349212,7.8958,,S
|
||||
879,0,3,"Laleff, Mr. Kristo",male,,0,0,349217,7.8958,,S
|
||||
880,1,1,"Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)",female,56,0,1,11767,83.1583,C50,C
|
||||
881,1,2,"Shelley, Mrs. William (Imanita Parrish Hall)",female,25,0,1,230433,26,,S
|
||||
882,0,3,"Markun, Mr. Johann",male,33,0,0,349257,7.8958,,S
|
||||
883,0,3,"Dahlberg, Miss. Gerda Ulrika",female,22,0,0,7552,10.5167,,S
|
||||
884,0,2,"Banfield, Mr. Frederick James",male,28,0,0,C.A./SOTON 34068,10.5,,S
|
||||
885,0,3,"Sutehall, Mr. Henry Jr",male,25,0,0,SOTON/OQ 392076,7.05,,S
|
||||
886,0,3,"Rice, Mrs. William (Margaret Norton)",female,39,0,5,382652,29.125,,Q
|
||||
887,0,2,"Montvila, Rev. Juozas",male,27,0,0,211536,13,,S
|
||||
888,1,1,"Graham, Miss. Margaret Edith",female,19,0,0,112053,30,B42,S
|
||||
889,0,3,"Johnston, Miss. Catherine Helen ""Carrie""",female,,1,2,W./C. 6607,23.45,,S
|
||||
890,1,1,"Behr, Mr. Karl Howell",male,26,0,0,111369,30,C148,C
|
||||
891,0,3,"Dooley, Mr. Patrick",male,32,0,0,370376,7.75,,Q
|
||||
|
BIN
docs/path1.png
Normal file
BIN
docs/path1.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 22 KiB |
BIN
docs/path2.png
Normal file
BIN
docs/path2.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 74 KiB |
BIN
docs/path3.png
Normal file
BIN
docs/path3.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 129 KiB |
BIN
docs/path4.png
Normal file
BIN
docs/path4.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 38 KiB |
21614
houses.csv
Normal file
21614
houses.csv
Normal file
File diff suppressed because it is too large
Load Diff
21614
kc_house_data.csv
Normal file
21614
kc_house_data.csv
Normal file
File diff suppressed because it is too large
Load Diff
358
lab1.ipynb
Normal file
358
lab1.ipynb
Normal file
File diff suppressed because one or more lines are too long
713
lec1.ipynb
Normal file
713
lec1.ipynb
Normal file
File diff suppressed because one or more lines are too long
1017
lec2.ipynb
Normal file
1017
lec2.ipynb
Normal file
File diff suppressed because it is too large
Load Diff
4278
lec3.ipynb
Normal file
4278
lec3.ipynb
Normal file
File diff suppressed because one or more lines are too long
4367
lec4.ipynb
Normal file
4367
lec4.ipynb
Normal file
File diff suppressed because one or more lines are too long
1175
lec5.ipynb
Normal file
1175
lec5.ipynb
Normal file
File diff suppressed because one or more lines are too long
3061
poetry.lock
generated
Normal file
3061
poetry.lock
generated
Normal file
File diff suppressed because it is too large
Load Diff
2
poetry.toml
Normal file
2
poetry.toml
Normal file
@ -0,0 +1,2 @@
|
||||
[virtualenvs]
|
||||
in-project = true
|
||||
21
pyproject.toml
Normal file
21
pyproject.toml
Normal file
@ -0,0 +1,21 @@
|
||||
[tool.poetry]
|
||||
name = "mai"
|
||||
version = "1.0.0"
|
||||
description = "MAI Examples"
|
||||
authors = ["Aleksey Filippov <al.filippov@ulstu.ru>"]
|
||||
readme = "readme.md"
|
||||
package-mode = false
|
||||
|
||||
[tool.poetry.dependencies]
|
||||
python = "^3.12"
|
||||
jupyter = "^1.1.1"
|
||||
numpy = "^2.1.0"
|
||||
pandas = "^2.2.2"
|
||||
matplotlib = "^3.9.2"
|
||||
imbalanced-learn = "^0.12.3"
|
||||
featuretools = "^1.31.0"
|
||||
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
100
src/clusters.py
Normal file
100
src/clusters.py
Normal file
@ -0,0 +1,100 @@
|
||||
import math
|
||||
from typing import Dict, List, Tuple
|
||||
|
||||
import numpy as np
|
||||
from pandas import DataFrame
|
||||
from sklearn import cluster
|
||||
from sklearn.metrics import silhouette_samples, silhouette_score
|
||||
|
||||
|
||||
def run_agglomerative(
|
||||
df: DataFrame, num_clusters: int | None = 2
|
||||
) -> cluster.AgglomerativeClustering:
|
||||
agglomerative = cluster.AgglomerativeClustering(
|
||||
n_clusters=num_clusters,
|
||||
compute_distances=True,
|
||||
)
|
||||
return agglomerative.fit(df)
|
||||
|
||||
|
||||
def get_linkage_matrix(model: cluster.AgglomerativeClustering) -> np.ndarray:
|
||||
counts = np.zeros(model.children_.shape[0]) # type: ignore
|
||||
n_samples = len(model.labels_)
|
||||
for i, merge in enumerate(model.children_): # type: ignore
|
||||
current_count = 0
|
||||
for child_idx in merge:
|
||||
if child_idx < n_samples:
|
||||
current_count += 1
|
||||
else:
|
||||
current_count += counts[child_idx - n_samples]
|
||||
counts[i] = current_count
|
||||
|
||||
return np.column_stack([model.children_, model.distances_, counts]).astype(float)
|
||||
|
||||
|
||||
def print_cluster_result(
|
||||
df: DataFrame, clusters_num: int, labels: np.ndarray, separator: str = ", "
|
||||
):
|
||||
for cluster_id in range(clusters_num):
|
||||
cluster_indices = np.where(labels == cluster_id)[0]
|
||||
print(f"Cluster {cluster_id + 1} ({len(cluster_indices)}):")
|
||||
rules = [str(df.index[idx]) for idx in cluster_indices]
|
||||
print(separator.join(rules))
|
||||
print("")
|
||||
print("--------")
|
||||
|
||||
|
||||
def run_kmeans(
|
||||
df: DataFrame, num_clusters: int, random_state: int
|
||||
) -> Tuple[np.ndarray, np.ndarray]:
|
||||
kmeans = cluster.KMeans(n_clusters=num_clusters, random_state=random_state)
|
||||
labels = kmeans.fit_predict(df)
|
||||
return labels, kmeans.cluster_centers_
|
||||
|
||||
|
||||
def fit_kmeans(
|
||||
reduced_data: np.ndarray, num_clusters: int, random_state: int
|
||||
) -> cluster.KMeans:
|
||||
kmeans = cluster.KMeans(n_clusters=num_clusters, random_state=random_state)
|
||||
kmeans.fit(reduced_data)
|
||||
return kmeans
|
||||
|
||||
|
||||
def _get_kmeans_range(
|
||||
df: DataFrame | np.ndarray, random_state: int
|
||||
) -> Tuple[List, range]:
|
||||
max_clusters = int(math.sqrt(len(df)))
|
||||
clusters_range = range(2, max_clusters + 1)
|
||||
kmeans_per_k = [
|
||||
cluster.KMeans(n_clusters=k, random_state=random_state).fit(df)
|
||||
for k in clusters_range
|
||||
]
|
||||
return kmeans_per_k, clusters_range
|
||||
|
||||
|
||||
def get_clusters_inertia(df: DataFrame, random_state: int) -> Tuple[List, range]:
|
||||
kmeans_per_k, clusters_range = _get_kmeans_range(df, random_state)
|
||||
return [model.inertia_ for model in kmeans_per_k], clusters_range
|
||||
|
||||
|
||||
def get_clusters_silhouette_scores(
|
||||
df: DataFrame, random_state: int
|
||||
) -> Tuple[List, range]:
|
||||
kmeans_per_k, clusters_range = _get_kmeans_range(df, random_state)
|
||||
return [
|
||||
float(silhouette_score(df, model.labels_)) for model in kmeans_per_k
|
||||
], clusters_range
|
||||
|
||||
|
||||
def get_clusters_silhouettes(df: np.ndarray, random_state: int) -> Dict:
|
||||
kmeans_per_k, _ = _get_kmeans_range(df, random_state)
|
||||
clusters_silhouettes: Dict = {}
|
||||
for model in kmeans_per_k:
|
||||
silhouette_value = silhouette_score(df, model.labels_)
|
||||
sample_silhouette_values = silhouette_samples(df, model.labels_)
|
||||
clusters_silhouettes[model.n_clusters] = (
|
||||
silhouette_value,
|
||||
sample_silhouette_values,
|
||||
model,
|
||||
)
|
||||
return clusters_silhouettes
|
||||
27
src/transformers.py
Normal file
27
src/transformers.py
Normal file
@ -0,0 +1,27 @@
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
from sklearn.base import BaseEstimator, TransformerMixin
|
||||
|
||||
|
||||
class TitanicFeatures(BaseEstimator, TransformerMixin):
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
def fit(self, X, y=None):
|
||||
return self
|
||||
|
||||
def transform(self, X, y=None):
|
||||
def get_title(name) -> str:
|
||||
return name.split(",")[1].split(".")[0].strip()
|
||||
|
||||
def get_cabin_type(cabin) -> str:
|
||||
if pd.isna(cabin):
|
||||
return "unknown"
|
||||
return cabin[0]
|
||||
|
||||
X["Is_married"] = [1 if get_title(name) == "Mrs" else 0 for name in X["Name"]]
|
||||
X["Cabin_type"] = [get_cabin_type(cabin) for cabin in X["Cabin"]]
|
||||
return X
|
||||
|
||||
def get_feature_names_out(self, features_in):
|
||||
return np.append(features_in, ["Is_married", "Cabin_type"], axis=0)
|
||||
138
src/utils.py
Normal file
138
src/utils.py
Normal file
@ -0,0 +1,138 @@
|
||||
import math
|
||||
from typing import Dict, Tuple
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
from pandas import DataFrame
|
||||
from sklearn import metrics
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.pipeline import Pipeline
|
||||
|
||||
|
||||
def split_stratified_into_train_val_test(
|
||||
df_input,
|
||||
stratify_colname="y",
|
||||
frac_train=0.6,
|
||||
frac_val=0.15,
|
||||
frac_test=0.25,
|
||||
random_state=None,
|
||||
) -> Tuple[DataFrame, DataFrame, DataFrame, DataFrame, DataFrame, DataFrame]:
|
||||
"""
|
||||
Splits a Pandas dataframe into three subsets (train, val, and test)
|
||||
following fractional ratios provided by the user, where each subset is
|
||||
stratified by the values in a specific column (that is, each subset has
|
||||
the same relative frequency of the values in the column). It performs this
|
||||
splitting by running train_test_split() twice.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
df_input : Pandas dataframe
|
||||
Input dataframe to be split.
|
||||
stratify_colname : str
|
||||
The name of the column that will be used for stratification. Usually
|
||||
this column would be for the label.
|
||||
frac_train : float
|
||||
frac_val : float
|
||||
frac_test : float
|
||||
The ratios with which the dataframe will be split into train, val, and
|
||||
test data. The values should be expressed as float fractions and should
|
||||
sum to 1.0.
|
||||
random_state : int, None, or RandomStateInstance
|
||||
Value to be passed to train_test_split().
|
||||
|
||||
Returns
|
||||
-------
|
||||
df_train, df_val, df_test :
|
||||
Dataframes containing the three splits.
|
||||
"""
|
||||
|
||||
if frac_train + frac_val + frac_test != 1.0:
|
||||
raise ValueError(
|
||||
"fractions %f, %f, %f do not add up to 1.0"
|
||||
% (frac_train, frac_val, frac_test)
|
||||
)
|
||||
|
||||
if stratify_colname not in df_input.columns:
|
||||
raise ValueError("%s is not a column in the dataframe" % (stratify_colname))
|
||||
|
||||
X = df_input # Contains all columns.
|
||||
y = df_input[
|
||||
[stratify_colname]
|
||||
] # Dataframe of just the column on which to stratify.
|
||||
|
||||
# Split original dataframe into train and temp dataframes.
|
||||
df_train, df_temp, y_train, y_temp = train_test_split(
|
||||
X, y, stratify=y, test_size=(1.0 - frac_train), random_state=random_state
|
||||
)
|
||||
|
||||
if frac_val <= 0:
|
||||
assert len(df_input) == len(df_train) + len(df_temp)
|
||||
return df_train, pd.DataFrame(), df_temp, y_train, pd.DataFrame(), y_temp
|
||||
|
||||
# Split the temp dataframe into val and test dataframes.
|
||||
relative_frac_test = frac_test / (frac_val + frac_test)
|
||||
df_val, df_test, y_val, y_test = train_test_split(
|
||||
df_temp,
|
||||
y_temp,
|
||||
stratify=y_temp,
|
||||
test_size=relative_frac_test,
|
||||
random_state=random_state,
|
||||
)
|
||||
|
||||
assert len(df_input) == len(df_train) + len(df_val) + len(df_test)
|
||||
return df_train, df_val, df_test, y_train, y_val, y_test
|
||||
|
||||
|
||||
def run_classification(
|
||||
model: Pipeline,
|
||||
X_train: DataFrame,
|
||||
X_test: DataFrame,
|
||||
y_train: DataFrame,
|
||||
y_test: DataFrame,
|
||||
) -> Dict:
|
||||
result = {}
|
||||
y_train_predict = model.predict(X_train)
|
||||
y_test_probs = model.predict_proba(X_test)[:, 1]
|
||||
y_test_predict = np.where(y_test_probs > 0.5, 1, 0)
|
||||
|
||||
result["pipeline"] = model
|
||||
result["probs"] = y_test_probs
|
||||
result["preds"] = y_test_predict
|
||||
|
||||
result["Precision_train"] = metrics.precision_score(y_train, y_train_predict)
|
||||
result["Precision_test"] = metrics.precision_score(y_test, y_test_predict)
|
||||
result["Recall_train"] = metrics.recall_score(y_train, y_train_predict)
|
||||
result["Recall_test"] = metrics.recall_score(y_test, y_test_predict)
|
||||
result["Accuracy_train"] = metrics.accuracy_score(y_train, y_train_predict)
|
||||
result["Accuracy_test"] = metrics.accuracy_score(y_test, y_test_predict)
|
||||
result["ROC_AUC_test"] = metrics.roc_auc_score(y_test, y_test_probs)
|
||||
result["F1_train"] = metrics.f1_score(y_train, y_train_predict)
|
||||
result["F1_test"] = metrics.f1_score(y_test, y_test_predict)
|
||||
result["MCC_test"] = metrics.matthews_corrcoef(y_test, y_test_predict)
|
||||
result["Cohen_kappa_test"] = metrics.cohen_kappa_score(y_test, y_test_predict)
|
||||
result["Confusion_matrix"] = metrics.confusion_matrix(y_test, y_test_predict)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def run_regression(
|
||||
model: Pipeline,
|
||||
X_train: DataFrame,
|
||||
X_test: DataFrame,
|
||||
y_train: DataFrame,
|
||||
y_test: DataFrame,
|
||||
) -> Dict:
|
||||
result = {}
|
||||
y_train_pred = model.predict(X_train.values)
|
||||
y_test_pred = model.predict(X_test.values)
|
||||
|
||||
result["fitted"] = model
|
||||
result["train_preds"] = y_train_pred
|
||||
result["preds"] = y_test_pred
|
||||
|
||||
result["RMSE_train"] = math.sqrt(metrics.mean_squared_error(y_train, y_train_pred))
|
||||
result["RMSE_test"] = math.sqrt(metrics.mean_squared_error(y_test, y_test_pred))
|
||||
result["RMAE_test"] = math.sqrt(metrics.mean_absolute_error(y_test, y_test_pred))
|
||||
result["R2_test"] = metrics.r2_score(y_test, y_test_pred)
|
||||
|
||||
return result
|
||||
242
src/visual.py
Normal file
242
src/visual.py
Normal file
@ -0,0 +1,242 @@
|
||||
from typing import Any, Dict, List
|
||||
|
||||
import matplotlib.cm as cm
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
from pandas import DataFrame
|
||||
from scipy.cluster import hierarchy
|
||||
from sklearn.cluster import KMeans
|
||||
|
||||
|
||||
def draw_data_2d(
|
||||
df: DataFrame,
|
||||
col1: int,
|
||||
col2: int,
|
||||
y: List | None = None,
|
||||
classes: List | None = None,
|
||||
subplot: Any | None = None,
|
||||
):
|
||||
ax = None
|
||||
if subplot is None:
|
||||
_, ax = plt.subplots()
|
||||
else:
|
||||
ax = subplot
|
||||
scatter = ax.scatter(df[df.columns[col1]], df[df.columns[col2]], c=y)
|
||||
ax.set(xlabel=df.columns[col1], ylabel=df.columns[col2])
|
||||
if classes is not None:
|
||||
ax.legend(
|
||||
scatter.legend_elements()[0], classes, loc="lower right", title="Classes"
|
||||
)
|
||||
|
||||
|
||||
def draw_dendrogram(linkage_matrix: np.ndarray):
|
||||
hierarchy.dendrogram(linkage_matrix, truncate_mode="level", p=3)
|
||||
|
||||
|
||||
def draw_cluster_results(
|
||||
df: DataFrame,
|
||||
col1: int,
|
||||
col2: int,
|
||||
labels: np.ndarray,
|
||||
cluster_centers: np.ndarray,
|
||||
subplot: Any | None = None,
|
||||
):
|
||||
ax = None
|
||||
if subplot is None:
|
||||
ax = plt
|
||||
else:
|
||||
ax = subplot
|
||||
|
||||
centroids = cluster_centers
|
||||
u_labels = np.unique(labels)
|
||||
|
||||
for i in u_labels:
|
||||
ax.scatter(
|
||||
df[labels == i][df.columns[col1]],
|
||||
df[labels == i][df.columns[col2]],
|
||||
label=i,
|
||||
)
|
||||
|
||||
ax.scatter(centroids[:, col1], centroids[:, col2], s=80, color="k")
|
||||
|
||||
|
||||
def draw_clusters(reduced_data: np.ndarray, kmeans: KMeans):
|
||||
h = 0.02
|
||||
|
||||
x_min, x_max = reduced_data[:, 0].min() - 1, reduced_data[:, 0].max() + 1
|
||||
y_min, y_max = reduced_data[:, 1].min() - 1, reduced_data[:, 1].max() + 1
|
||||
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
|
||||
|
||||
Z = kmeans.predict(np.c_[xx.ravel(), yy.ravel()])
|
||||
|
||||
Z = Z.reshape(xx.shape)
|
||||
plt.figure(1)
|
||||
plt.clf()
|
||||
plt.imshow(
|
||||
Z,
|
||||
interpolation="nearest",
|
||||
extent=(xx.min(), xx.max(), yy.min(), yy.max()),
|
||||
cmap=plt.cm.Paired, # type: ignore
|
||||
aspect="auto",
|
||||
origin="lower",
|
||||
)
|
||||
|
||||
plt.plot(reduced_data[:, 0], reduced_data[:, 1], "k.", markersize=2)
|
||||
centroids = kmeans.cluster_centers_
|
||||
plt.scatter(
|
||||
centroids[:, 0],
|
||||
centroids[:, 1],
|
||||
marker="x",
|
||||
s=169,
|
||||
linewidths=3,
|
||||
color="w",
|
||||
zorder=10,
|
||||
)
|
||||
plt.title(
|
||||
"K-means clustering (PCA-reduced data)\n"
|
||||
"Centroids are marked with white cross"
|
||||
)
|
||||
plt.xlim(x_min, x_max)
|
||||
plt.ylim(y_min, y_max)
|
||||
plt.xticks(())
|
||||
plt.yticks(())
|
||||
|
||||
|
||||
def _draw_cluster_scores(
|
||||
data: List,
|
||||
clusters_range: range,
|
||||
score_name: str,
|
||||
title: str,
|
||||
):
|
||||
plt.figure(figsize=(8, 5))
|
||||
plt.plot(clusters_range, data, "bo-")
|
||||
plt.xlabel("$k$", fontsize=8)
|
||||
plt.ylabel(score_name, fontsize=8)
|
||||
plt.title(title)
|
||||
|
||||
|
||||
def draw_elbow_diagram(inertias: List, clusters_range: range):
|
||||
_draw_cluster_scores(inertias, clusters_range, "Inertia", "The Elbow Diagram")
|
||||
|
||||
|
||||
def draw_silhouettes_diagram(silhouette: List, clusters_range: range):
|
||||
_draw_cluster_scores(
|
||||
silhouette, clusters_range, "Silhouette score", "The Silhouette score"
|
||||
)
|
||||
|
||||
|
||||
def _draw_silhouette(
|
||||
ax: Any,
|
||||
reduced_data: np.ndarray,
|
||||
n_clusters: int,
|
||||
silhouette_avg: float,
|
||||
sample_silhouette_values: List,
|
||||
cluster_labels: List,
|
||||
):
|
||||
ax.set_xlim([-0.1, 1])
|
||||
ax.set_ylim([0, len(reduced_data) + (n_clusters + 1) * 10])
|
||||
|
||||
y_lower = 10
|
||||
for i in range(n_clusters):
|
||||
ith_cluster_silhouette_values = sample_silhouette_values[cluster_labels == i]
|
||||
|
||||
ith_cluster_silhouette_values.sort()
|
||||
|
||||
size_cluster_i = ith_cluster_silhouette_values.shape[0]
|
||||
y_upper = y_lower + size_cluster_i
|
||||
|
||||
color = cm.nipy_spectral(float(i) / n_clusters) # type: ignore
|
||||
ax.fill_betweenx(
|
||||
np.arange(y_lower, y_upper),
|
||||
0,
|
||||
ith_cluster_silhouette_values,
|
||||
facecolor=color,
|
||||
edgecolor=color,
|
||||
alpha=0.7,
|
||||
)
|
||||
|
||||
ax.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
|
||||
|
||||
y_lower = y_upper + 10 # 10 for the 0 samples
|
||||
|
||||
ax.set_title("The silhouette plot for the various clusters.")
|
||||
ax.set_xlabel("The silhouette coefficient values")
|
||||
ax.set_ylabel("Cluster label")
|
||||
|
||||
ax.axvline(x=silhouette_avg, color="red", linestyle="--")
|
||||
|
||||
ax.set_yticks([])
|
||||
ax.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])
|
||||
|
||||
|
||||
def _draw_cluster_data(
|
||||
ax: Any,
|
||||
reduced_data: np.ndarray,
|
||||
n_clusters: int,
|
||||
cluster_labels: np.ndarray,
|
||||
cluster_centers: np.ndarray,
|
||||
):
|
||||
colors = cm.nipy_spectral(cluster_labels.astype(float) / n_clusters) # type: ignore
|
||||
ax.scatter(
|
||||
reduced_data[:, 0],
|
||||
reduced_data[:, 1],
|
||||
marker=".",
|
||||
s=30,
|
||||
lw=0,
|
||||
alpha=0.7,
|
||||
c=colors,
|
||||
edgecolor="k",
|
||||
)
|
||||
|
||||
ax.scatter(
|
||||
cluster_centers[:, 0],
|
||||
cluster_centers[:, 1],
|
||||
marker="o",
|
||||
c="white",
|
||||
alpha=1,
|
||||
s=200,
|
||||
edgecolor="k",
|
||||
)
|
||||
|
||||
for i, c in enumerate(cluster_centers):
|
||||
ax.scatter(c[0], c[1], marker="$%d$" % i, alpha=1, s=50, edgecolor="k")
|
||||
|
||||
ax.set_title("The visualization of the clustered data.")
|
||||
ax.set_xlabel("Feature space for the 1st feature")
|
||||
ax.set_ylabel("Feature space for the 2nd feature")
|
||||
|
||||
|
||||
def draw_silhouettes(reduced_data: np.ndarray, silhouettes: Dict):
|
||||
for key, value in silhouettes.items():
|
||||
fig, (ax1, ax2) = plt.subplots(1, 2)
|
||||
fig.set_size_inches(18, 7)
|
||||
|
||||
n_clusters = key
|
||||
silhouette_avg = value[0]
|
||||
sample_silhouette_values = value[1]
|
||||
cluster_labels = value[2].labels_
|
||||
cluster_centers = value[2].cluster_centers_
|
||||
|
||||
_draw_silhouette(
|
||||
ax1,
|
||||
reduced_data,
|
||||
n_clusters,
|
||||
silhouette_avg,
|
||||
sample_silhouette_values,
|
||||
cluster_labels,
|
||||
)
|
||||
|
||||
_draw_cluster_data(
|
||||
ax2,
|
||||
reduced_data,
|
||||
n_clusters,
|
||||
cluster_labels,
|
||||
cluster_centers,
|
||||
)
|
||||
|
||||
plt.suptitle(
|
||||
"Silhouette analysis for KMeans clustering on sample data with n_clusters = %d"
|
||||
% n_clusters,
|
||||
fontsize=14,
|
||||
fontweight="bold",
|
||||
)
|
||||
Loading…
x
Reference in New Issue
Block a user