Lab3 done

2024-10-23 13:43:55 +04:00 · 2024-10-23 13:43:55 +04:00 · 01c27ac023
commit 01c27ac023
parent 3720eb2ec7
6 changed files with 3596 additions and 9 deletions
--- a/data/countries-continents-capitals.csv
+++ b/data/countries-continents-capitals.csv
@ -1,4 +1,4 @@
-Country/Territory,Capital,Continent
+Country,Capital,Continent
 Afghanistan,Kabul,Asia
 Albania,Tirana,Europe
 Algeria,Algiers,Africa
@ -6,7 +6,7 @@ American Samoa,Pago Pago,Oceania
 Andorra,Andorra la Vella,Europe
 Angola,Luanda,Africa
 Anguilla,The Valley,North America
-Antigua and Barbuda,Saint Johnƒ??s,North America
+Antigua and Barbuda,Saint John<EFBFBD>??s,North America
 Argentina,Buenos Aires,South America
 Armenia,Yerevan,Asia
 Aruba,Oranjestad,North America
@ -80,7 +80,7 @@ Greece,Athens,Europe
 Greenland,Nuuk,North America
 Grenada,Saint George's,North America
 Guadeloupe,Basse-Terre,North America
-Guam,Hag?<3F>t?ña,Oceania
+Guam,Hag?<3F>t?<EFBFBD>a,Oceania
 Guatemala,Guatemala City,North America
 Guernsey,Saint Peter Port,Europe
 Guinea,Conakry,Africa
@ -180,7 +180,7 @@ Saint Pierre and Miquelon,Saint-Pierre,North America
 Saint Vincent and the Grenadines,Kingstown,North America
 Samoa,Apia,Oceania
 San Marino,San Marino,Europe
-Sao Tome and Principe,S?œo Tom??,Africa
+Sao Tome and Principe,S?<EFBFBD>o Tom??,Africa
 Saudi Arabia,Riyadh,Asia
 Senegal,Dakar,Africa
 Serbia,Belgrade,Europe
@ -209,7 +209,7 @@ Thailand,Bangkok,Asia
 Timor-Leste,Dili,Asia
 Togo,Lom??,Africa
 Tokelau,Nukunonu,Oceania
-Tonga,Nukuƒ??alofa,Oceania
+Tonga,Nuku<EFBFBD>??alofa,Oceania
 Trinidad and Tobago,Port-of-Spain,North America
 Tunisia,Tunis,Africa
 Turkey,Ankara,Asia
@ -229,7 +229,7 @@ Vatican City,Vatican City,Europe
 Venezuela,Caracas,South America
 Vietnam,Hanoi,Asia
 Wallis and Futuna,Mata-Utu,Oceania
-Western Sahara,El Aai?§n,Africa
+Western Sahara,El Aai?<EFBFBD>n,Africa
 Yemen,Sanaa,Asia
 Zambia,Lusaka,Africa
 Zimbabwe,Harare,Africa
--- a/data/world-population-by-country-2020.csv
+++ b/data/world-population-by-country-2020.csv
@ -1,4 +1,4 @@
-no,Country (or dependency),Population 2020,Yearly Change,Net Change,Density  (P/Km²),Land Area (Km²),Migrants (net),Fert. Rate,Med. Age,Urban Pop %,World Share
+no,Country,Population2020,Yearly,NetChange,Density,LandArea,Migrants,FertRate,MedAge,UrbanPop,WorldShare
 1,China,"1,439,323,776",0.39%,"5,540,090",153,"9,388,211","-348,399",1.7,38,61%,18.47%
 2,India,"1,380,004,385",0.99%,"13,586,631",464,"2,973,190","-532,687",2.2,28,35%,17.70%
 3,United States,"331,002,651",0.59%,"1,937,734",36,"9,147,420","954,806",1.8,38,83%,4.25%
--- a/data/world-population-forcast-2020-2050.csv
+++ b/data/world-population-forcast-2020-2050.csv
@ -1,4 +1,4 @@
-Year,Population,Yearly %,Yearly,Median,Fertility,Density
+Year,Population,YearlyPer,Yearly,Median,Fertility,Density
 2020,"7,794,798,739",1.10%,"83,000,320",31,2.47,52
 2025,"8,184,437,460",0.98%,"77,927,744",32,2.54,55
 2030,"8,548,487,400",0.87%,"72,809,988",33,2.62,57
--- a/lec3.ipynb
+++ b/lec3.ipynb
--- a/poetry.lock
+++ b/poetry.lock
@ -467,6 +467,17 @@ files = [
 [package.dependencies]
 colorama = {version = "*", markers = "platform_system == \"Windows\""}

+[[package]]
+name = "cloudpickle"
+version = "3.1.0"
+description = "Pickler class to extend the standard pickle.Pickler functionality"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "cloudpickle-3.1.0-py3-none-any.whl", hash = "sha256:fe11acda67f61aaaec473e3afe030feb131d78a43461b718185363384f1ba12e"},
+    {file = "cloudpickle-3.1.0.tar.gz", hash = "sha256:81a929b6e3c7335c863c771d673d105f02efdb89dfaba0c90495d1c64796601b"},
+]
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
@ -675,6 +686,41 @@ files = [
 [package.extras]
 devel = ["colorama", "json-spec", "jsonschema", "pylint", "pytest", "pytest-benchmark", "pytest-cache", "validictory"]

+[[package]]
+name = "featuretools"
+version = "1.31.0"
+description = "a framework for automated feature engineering"
+optional = false
+python-versions = "<4,>=3.9"
+files = [
+    {file = "featuretools-1.31.0-py3-none-any.whl", hash = "sha256:87c94e9ae959c89acd83da96bd2583f3ef0f6daaa9639cbb6e46dbde2c742a18"},
+    {file = "featuretools-1.31.0.tar.gz", hash = "sha256:01bfb17fcc1715b4c3623c7bc94a8982122c4a0fa03350ed478601bb81f90155"},
+]
+
+[package.dependencies]
+cloudpickle = ">=1.5.0"
+holidays = ">=0.17"
+numpy = ">=1.25.0"
+packaging = ">=20.0"
+pandas = ">=2.0.0"
+psutil = ">=5.7.0"
+scipy = ">=1.10.0"
+tqdm = ">=4.66.3"
+woodwork = ">=0.28.0"
+
+[package.extras]
+autonormalize = ["autonormalize (>=2.0.1)"]
+complete = ["featuretools[dask,nlp,premium]"]
+dask = ["dask[dataframe] (>=2023.2.0)", "distributed (>=2023.2.0)"]
+dev = ["black[jupyter] (>=23.1.0)", "featuretools[dask,docs,test]", "pre-commit (>=2.20.0)", "ruff (>=0.1.6)"]
+docs = ["Sphinx (==5.1.1)", "autonormalize (>=2.0.1)", "click (>=7.0.0)", "featuretools[dask,test]", "ipython (==8.4.0)", "jupyter (==1.0.0)", "jupyter-client (>=8.0.2)", "matplotlib (==3.7.2)", "myst-parser (==0.18.0)", "nbconvert (==6.5.0)", "nbsphinx (==0.8.9)", "pydata-sphinx-theme (==0.9.0)", "sphinx-copybutton (==0.5.0)", "sphinx-inline-tabs (==2022.1.2b11)"]
+nlp = ["nlp-primitives (>=2.12.0)"]
+premium = ["premium-primitives (>=0.0.3)"]
+sklearn = ["featuretools-sklearn-transformer (>=1.0.0)"]
+sql = ["featuretools-sql (>=0.0.1)", "psycopg2-binary (>=2.9.3)"]
+test = ["boto3 (>=1.34.32)", "composeml (>=0.8.0)", "graphviz (>=0.8.4)", "moto[all] (>=5.0.0)", "pip (>=23.3.0)", "pyarrow (>=14.0.1)", "pympler (>=0.8)", "pytest (>=7.1.2)", "pytest-cov (>=3.0.0)", "pytest-timeout (>=2.1.0)", "pytest-xdist (>=2.5.0)", "smart-open (>=5.0.0)", "urllib3 (>=1.26.18)"]
+tsfresh = ["featuretools-tsfresh-primitives (>=1.0.0)"]
+
 [[package]]
 name = "flask"
 version = "3.0.3"
@ -833,6 +879,20 @@ files = [
    {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
 ]

+[[package]]
+name = "holidays"
+version = "0.59"
+description = "World Holidays Framework"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "holidays-0.59-py3-none-any.whl", hash = "sha256:4576ec7aaad7cd66463236c110bcbd533ac7e739e0e9d3cbeccf8107384a8a92"},
+    {file = "holidays-0.59.tar.gz", hash = "sha256:c5cd2e1c0c27a64217b10faf2e8fcc224f5bb64087b56b70c6aff21f6379e6e4"},
+]
+
+[package.dependencies]
+python-dateutil = "*"
+
 [[package]]
 name = "httpcore"
 version = "1.0.5"
@ -914,6 +974,25 @@ examples = ["keras (>=2.4.3)", "matplotlib (>=3.1.2)", "pandas (>=1.0.5)", "seab
 optional = ["keras (>=2.4.3)", "pandas (>=1.0.5)", "tensorflow (>=2.4.3)"]
 tests = ["black (>=23.3.0)", "flake8 (>=3.8.2)", "keras (>=2.4.3)", "mypy (>=1.3.0)", "pandas (>=1.0.5)", "pytest (>=5.0.1)", "pytest-cov (>=2.9.0)", "tensorflow (>=2.4.3)"]

+[[package]]
+name = "importlib-resources"
+version = "6.4.5"
+description = "Read resources from Python packages"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "importlib_resources-6.4.5-py3-none-any.whl", hash = "sha256:ac29d5f956f01d5e4bb63102a5a19957f1b9175e45649977264a1416783bb717"},
+    {file = "importlib_resources-6.4.5.tar.gz", hash = "sha256:980862a1d16c9e147a59603677fa2aa5fd82b87f223b6cb870695bcfce830065"},
+]
+
+[package.extras]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
+cover = ["pytest-cov"]
+doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+enabler = ["pytest-enabler (>=2.2)"]
+test = ["jaraco.test (>=5.4)", "pytest (>=6,!=8.1.*)", "zipp (>=3.17)"]
+type = ["pytest-mypy"]
+
 [[package]]
 name = "ipykernel"
 version = "6.29.5"
@ -2708,6 +2787,11 @@ files = [
    {file = "scikit_learn-1.5.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f60021ec1574e56632be2a36b946f8143bf4e5e6af4a06d85281adc22938e0dd"},
    {file = "scikit_learn-1.5.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:394397841449853c2290a32050382edaec3da89e35b3e03d6cc966aebc6a8ae6"},
    {file = "scikit_learn-1.5.2-cp312-cp312-win_amd64.whl", hash = "sha256:57cc1786cfd6bd118220a92ede80270132aa353647684efa385a74244a41e3b1"},
+    {file = "scikit_learn-1.5.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e9a702e2de732bbb20d3bad29ebd77fc05a6b427dc49964300340e4c9328b3f5"},
+    {file = "scikit_learn-1.5.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:b0768ad641981f5d3a198430a1d31c3e044ed2e8a6f22166b4d546a5116d7908"},
+    {file = "scikit_learn-1.5.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:178ddd0a5cb0044464fc1bfc4cca5b1833bfc7bb022d70b05db8530da4bb3dd3"},
+    {file = "scikit_learn-1.5.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f7284ade780084d94505632241bf78c44ab3b6f1e8ccab3d2af58e0e950f9c12"},
+    {file = "scikit_learn-1.5.2-cp313-cp313-win_amd64.whl", hash = "sha256:b7b0f9a0b1040830d38c39b91b3a44e1b643f4b36e36567b80b7c6bd2202a27f"},
    {file = "scikit_learn-1.5.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:757c7d514ddb00ae249832fe87100d9c73c6ea91423802872d9e74970a0e40b9"},
    {file = "scikit_learn-1.5.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:52788f48b5d8bca5c0736c175fa6bdaab2ef00a8f536cda698db61bd89c551c1"},
    {file = "scikit_learn-1.5.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:643964678f4b5fbdc95cbf8aec638acc7aa70f5f79ee2cdad1eec3df4ba6ead8"},
@ -2939,6 +3023,26 @@ files = [
    {file = "tornado-6.4.1.tar.gz", hash = "sha256:92d3ab53183d8c50f8204a51e6f91d18a15d5ef261e84d452800d4ff6fc504e9"},
 ]

+[[package]]
+name = "tqdm"
+version = "4.66.5"
+description = "Fast, Extensible Progress Meter"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tqdm-4.66.5-py3-none-any.whl", hash = "sha256:90279a3770753eafc9194a0364852159802111925aa30eb3f9d85b0e805ac7cd"},
+    {file = "tqdm-4.66.5.tar.gz", hash = "sha256:e1020aef2e5096702d8a025ac7d16b1577279c9d63f8375b63083e9a5f0fcbad"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"]
+notebook = ["ipywidgets (>=6)"]
+slack = ["slack-sdk"]
+telegram = ["requests"]
+
 [[package]]
 name = "traitlets"
 version = "5.14.3"
@ -3110,7 +3214,33 @@ files = [
    {file = "widgetsnbextension-4.0.13.tar.gz", hash = "sha256:ffcb67bc9febd10234a362795f643927f4e0c05d9342c727b65d2384f8feacb6"},
 ]

+[[package]]
+name = "woodwork"
+version = "0.31.0"
+description = "a data typing library for machine learning"
+optional = false
+python-versions = "<4,>=3.9"
+files = [
+    {file = "woodwork-0.31.0-py3-none-any.whl", hash = "sha256:5cb3370553b5f466f8c8599b1bf559584dc0b798cc1f2da26bbd7029d256c6f9"},
+    {file = "woodwork-0.31.0.tar.gz", hash = "sha256:6ef82af1d5b6525b02efe6417c574c810cfdcc606cb266bd0d7fb17a1d066b67"},
+]
+
+[package.dependencies]
+importlib-resources = ">=5.10.0"
+numpy = ">=1.25.0"
+pandas = ">=2.0.0"
+python-dateutil = ">=2.8.2"
+scikit-learn = ">=1.1.0"
+scipy = ">=1.10.0"
+
+[package.extras]
+complete = ["woodwork[updater]"]
+dev = ["click (>=8.1.7)", "pre-commit (>=2.20.0)", "ruff (>=0.1.6)", "woodwork[docs,test]"]
+docs = ["Sphinx (==5.1.1)", "ipython (==8.4.0)", "jupyter (==1.0.0)", "myst-parser (==0.18.0)", "nbconvert (==6.5.0)", "nbsphinx (==0.8.9)", "pyarrow (>=14.0.1)", "pydata-sphinx-theme (==0.9.0)", "sphinx-copybutton (==0.5.0)", "sphinx-inline-tabs (==2022.1.2b11)"]
+test = ["boto3 (>=1.34.32)", "moto[all] (>=5.0.0)", "pyarrow (>=14.0.1)", "pytest (>=7.0.1)", "pytest-cov (>=2.10.1)", "pytest-xdist (>=2.1.0)", "smart-open (>=5.0.0)"]
+updater = ["alteryx-open-src-update-checker (>=3.1.0)"]
+
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.12"
-content-hash = "a7e3d516bde2d6e4173d8a9770fb5337a0c806dadaeda355084b262c1995f7ea"
+content-hash = "09433ce7624fd6af995c85e9e980c57cd417491975e280f0a844931df35e5085"
--- a/pyproject.toml
+++ b/pyproject.toml
@ -17,8 +17,12 @@ apiflask = "^2.2.0"
 flask-cors = "^5.0.0"
 scikit-learn = "^1.5.2"
 imbalanced-learn = "^0.12.3"
+featuretools = "^1.31.0"


+[tool.poetry.group.dev.dependencies]
+ipykernel = "^6.29.5"
+
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"