{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index(['Rank ', 'Name', 'Networth', 'Age', 'Country', 'Source', 'Industry'], dtype='object')\n" ] } ], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "df = pd.read_csv(\"C://Users//annal//aim//static//csv//Forbes_Billionaires.csv\")\n", "print(df.columns)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Определим бизнес цели:\n", "## 1- Прогнозирование состояния миллиардера(регрессия)\n", "## 2- Прогнозирование возраста миллиардера(классификация)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Проверим данные на пустые значения" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Rank 0\n", "Name 0\n", "Networth 0\n", "Age 0\n", "Country 0\n", "Source 0\n", "Industry 0\n", "dtype: int64\n", "\n", "Rank False\n", "Name False\n", "Networth False\n", "Age False\n", "Country False\n", "Source False\n", "Industry False\n", "dtype: bool\n", "\n" ] } ], "source": [ "print(df.isnull().sum())\n", "\n", "print()\n", "\n", "# Есть ли пустые значения признаков\n", "print(df.isnull().any())\n", "\n", "print()\n", "\n", "# Процент пустых значений признаков\n", "for i in df.columns:\n", " null_rate = df[i].isnull().sum() / len(df) * 100\n", " if null_rate > 0:\n", " print(f\"{i} процент пустых значений: %{null_rate:.2f}\")" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Collecting Jinja2\n", " Downloading jinja2-3.1.4-py3-none-any.whl.metadata (2.6 kB)\n", "Collecting MarkupSafe>=2.0 (from Jinja2)\n", " Downloading MarkupSafe-3.0.2-cp312-cp312-win_amd64.whl.metadata (4.1 kB)\n", "Downloading jinja2-3.1.4-py3-none-any.whl (133 kB)\n", "Downloading MarkupSafe-3.0.2-cp312-cp312-win_amd64.whl (15 kB)\n", "Installing collected packages: MarkupSafe, Jinja2\n", "Successfully installed Jinja2-3.1.4 MarkupSafe-3.0.2\n", "Note: you may need to restart the kernel to use updated packages.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n", "[notice] A new release of pip is available: 24.2 -> 24.3.1\n", "[notice] To update, run: python.exe -m pip install --upgrade pip\n" ] } ], "source": [ "pip install Jinja2" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Задача регрессии" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Создадим выборки" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "from sklearn.model_selection import train_test_split\n", "df = pd.read_csv(\"C://Users//annal//aim//static//csv//Forbes_Billionaires.csv\")\n", "X = df.drop(columns=['Networth','Rank ', 'Name']) # Признаки\n", "y = df['Networth'] # Целевая переменная для регрессии\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Формирование конвейера для классификации данных\n", "## preprocessing_num -- конвейер для обработки числовых данных: заполнение пропущенных значений и стандартизация\n", "## preprocessing_cat -- конвейер для обработки категориальных данных: заполнение пропущенных данных и унитарное кодирование\n", "## features_preprocessing -- трансформер для предобработки признаков\n", "## features_engineering -- трансформер для конструирования признаков\n", "## drop_columns -- трансформер для удаления колонок\n", "## pipeline_end -- основной конвейер предобработки данных и конструирования признаков" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
prepocessing_num__Ageprepocessing_cat__Country_Argentinaprepocessing_cat__Country_Australiaprepocessing_cat__Country_Austriaprepocessing_cat__Country_Barbadosprepocessing_cat__Country_Belgiumprepocessing_cat__Country_Belizeprepocessing_cat__Country_Brazilprepocessing_cat__Country_Bulgariaprepocessing_cat__Country_Canada...prepocessing_cat__Industry_Logisticsprepocessing_cat__Industry_Manufacturingprepocessing_cat__Industry_Media & Entertainmentprepocessing_cat__Industry_Metals & Miningprepocessing_cat__Industry_Real Estateprepocessing_cat__Industry_Serviceprepocessing_cat__Industry_Sportsprepocessing_cat__Industry_Technologyprepocessing_cat__Industry_Telecomprepocessing_cat__Industry_diversified
582-0.1099340.00.00.00.00.00.00.00.00.0...0.00.00.00.01.00.00.00.00.00.0
481.0790790.00.00.00.00.00.00.00.00.0...0.01.00.00.00.00.00.00.00.00.0
17721.0047660.01.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
964-0.4071870.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
22131.3020190.00.00.00.00.00.01.00.00.0...0.00.00.00.00.00.00.00.00.00.0
..................................................................
16381.2277060.00.00.00.00.00.00.00.00.0...0.01.00.00.00.00.00.00.00.00.0
10950.8561390.00.00.00.00.00.01.00.00.0...0.00.00.00.00.00.00.00.00.00.0
11300.7818260.00.00.00.00.00.00.00.00.0...0.00.00.00.01.00.00.00.00.00.0
12940.3359460.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
8600.5588860.00.00.00.00.00.00.00.00.0...0.01.00.00.00.00.00.00.00.00.0
\n", "

2080 rows × 855 columns

\n", "
" ], "text/plain": [ " prepocessing_num__Age prepocessing_cat__Country_Argentina \\\n", "582 -0.109934 0.0 \n", "48 1.079079 0.0 \n", "1772 1.004766 0.0 \n", "964 -0.407187 0.0 \n", "2213 1.302019 0.0 \n", "... ... ... \n", "1638 1.227706 0.0 \n", "1095 0.856139 0.0 \n", "1130 0.781826 0.0 \n", "1294 0.335946 0.0 \n", "860 0.558886 0.0 \n", "\n", " prepocessing_cat__Country_Australia prepocessing_cat__Country_Austria \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 1.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 0.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 0.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " prepocessing_cat__Country_Barbados prepocessing_cat__Country_Belgium \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 0.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 0.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 0.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " prepocessing_cat__Country_Belize prepocessing_cat__Country_Brazil \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 0.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 1.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 1.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " prepocessing_cat__Country_Bulgaria prepocessing_cat__Country_Canada \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 0.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 0.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 0.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " ... prepocessing_cat__Industry_Logistics \\\n", "582 ... 0.0 \n", "48 ... 0.0 \n", "1772 ... 0.0 \n", "964 ... 0.0 \n", "2213 ... 0.0 \n", "... ... ... \n", "1638 ... 0.0 \n", "1095 ... 0.0 \n", "1130 ... 0.0 \n", "1294 ... 0.0 \n", "860 ... 0.0 \n", "\n", " prepocessing_cat__Industry_Manufacturing \\\n", "582 0.0 \n", "48 1.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 1.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 1.0 \n", "\n", " prepocessing_cat__Industry_Media & Entertainment \\\n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_Metals & Mining \\\n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_Real Estate \\\n", "582 1.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 1.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_Service prepocessing_cat__Industry_Sports \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 0.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 0.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 0.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " prepocessing_cat__Industry_Technology \\\n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_Telecom \\\n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_diversified \n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", "[2080 rows x 855 columns]" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.compose import ColumnTransformer\n", "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n", "from sklearn.impute import SimpleImputer\n", "from sklearn.pipeline import Pipeline\n", "import pandas as pd\n", "\n", "# Исправляем ColumnTransformer с сохранением имен колонок\n", "columns_to_drop = []\n", "\n", "num_columns = [\n", " column\n", " for column in X_train.columns\n", " if column not in columns_to_drop and X_train[column].dtype != \"object\"\n", "]\n", "cat_columns = [\n", " column\n", " for column in X_train.columns\n", " if column not in columns_to_drop and X_train[column].dtype == \"object\"\n", "]\n", "\n", "# Предобработка числовых данных\n", "num_imputer = SimpleImputer(strategy=\"median\")\n", "num_scaler = StandardScaler()\n", "preprocessing_num = Pipeline(\n", " [\n", " (\"imputer\", num_imputer),\n", " (\"scaler\", num_scaler),\n", " ]\n", ")\n", "\n", "# Предобработка категориальных данных\n", "cat_imputer = SimpleImputer(strategy=\"constant\", fill_value=\"unknown\")\n", "cat_encoder = OneHotEncoder(handle_unknown=\"ignore\", sparse_output=False, drop=\"first\")\n", "preprocessing_cat = Pipeline(\n", " [\n", " (\"imputer\", cat_imputer),\n", " (\"encoder\", cat_encoder),\n", " ]\n", ")\n", "\n", "# Общая предобработка признаков\n", "features_preprocessing = ColumnTransformer(\n", " verbose_feature_names_out=True, # Сохраняем имена колонок\n", " transformers=[\n", " (\"prepocessing_num\", preprocessing_num, num_columns),\n", " (\"prepocessing_cat\", preprocessing_cat, cat_columns),\n", " ],\n", " remainder=\"drop\" # Убираем неиспользуемые столбцы\n", ")\n", "\n", "# Итоговый конвейер\n", "pipeline_end = Pipeline(\n", " [\n", " (\"features_preprocessing\", features_preprocessing),\n", " ]\n", ")\n", "\n", "# Преобразуем данные\n", "preprocessing_result = pipeline_end.fit_transform(X_train)\n", "\n", "# Создаем DataFrame с правильными именами колонок\n", "preprocessed_df = pd.DataFrame(\n", " preprocessing_result,\n", " columns=pipeline_end.get_feature_names_out(),\n", " index=X_train.index, # Сохраняем индексы\n", ")\n", "\n", "preprocessed_df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Формирование набора моделей\n", "## LinearRegression -- логистическая регрессия\n", "## RandomForestRegressor -- метод случайного леса (набор деревьев решений)\n", "## GradientBoostingRegressor -- метод градиентного бустинга (набор деревьев решений)\n", "# Обучение этих моделей с применением RandomizedSearchCV(для подбора гиперпараметров)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training LinearRegression...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:320: UserWarning: The total space of parameters 1 is smaller than n_iter=10. Running 1 iterations. For exhaustive searches, use GridSearchCV.\n", " warnings.warn(\n", "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:242: UserWarning: Found unknown categories in columns [0, 1] during transform. These unknown categories will be encoded as all zeros\n", " warnings.warn(\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Training RandomForestRegressor...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:242: UserWarning: Found unknown categories in columns [0, 1] during transform. These unknown categories will be encoded as all zeros\n", " warnings.warn(\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Training GradientBoostingRegressor...\n", "\n", "Model: LinearRegression\n", "Best Params: {}\n", "MAE: 18059903.80176681\n", "RMSE: 411829080.6584508\n", "R2: -7135788186375614.0\n", "\n", "Model: RandomForestRegressor\n", "Best Params: {'model__n_estimators': 40, 'model__max_depth': 10}\n", "MAE: 3.454630023161808\n", "RMSE: 7.755775760541111\n", "R2: -1.530803448377045\n", "\n", "Model: GradientBoostingRegressor\n", "Best Params: {'model__n_estimators': 100, 'model__max_depth': 4, 'model__learning_rate': 0.4}\n", "MAE: 3.585784679817764\n", "RMSE: 10.312249036012052\n", "R2: -3.474193004771121\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:242: UserWarning: Found unknown categories in columns [0, 1] during transform. These unknown categories will be encoded as all zeros\n", " warnings.warn(\n" ] } ], "source": [ "import numpy as np\n", "from sklearn.linear_model import LinearRegression\n", "from sklearn.ensemble import RandomForestRegressor\n", "from sklearn.ensemble import GradientBoostingRegressor\n", "from sklearn.model_selection import GridSearchCV, RandomizedSearchCV\n", "from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score\n", "import matplotlib.pyplot as plt\n", "\n", "random_state = 42\n", "\n", "# Модели и параметры\n", "models_regression = {\n", " \"LinearRegression\": LinearRegression(),\n", " \"RandomForestRegressor\": RandomForestRegressor(random_state=random_state),\n", " \"GradientBoostingRegressor\": GradientBoostingRegressor(random_state=random_state)\n", "}\n", "\n", "param_grids_regression = {\n", " \"LinearRegression\": {},\n", " \"RandomForestRegressor\": {\n", " 'model__n_estimators': [10, 20, 30, 40, 50, 100, 150, 200, 250, 500],\n", " 'model__max_depth': [None, 2, 3, 4, 5, 6, 7, 8, 9 ,10],\n", " },\n", " \"GradientBoostingRegressor\": {\n", " 'model__n_estimators': [10, 20, 30, 40, 50, 100, 150, 200, 250, 500],\n", " 'model__learning_rate': [0.01, 0.1, 0.2, 0.3, 0.4, 0.5],\n", " 'model__max_depth': [2, 3, 4, 5, 6, 7, 8, 9 ,10]\n", " }\n", "}\n", "\n", "# Результаты\n", "results_regression = {}\n", "\n", "# Перебор моделей\n", "for name, model in models_regression.items():\n", " print(f\"Training {name}...\")\n", " pipeline = Pipeline(steps=[\n", " ('features_preprocessing', features_preprocessing),\n", " ('model', model)\n", " ])\n", " param_grid = param_grids_regression[name]\n", " grid_search = RandomizedSearchCV(pipeline, param_grid, cv=5, scoring='neg_mean_absolute_error', n_jobs=-1)\n", " grid_search.fit(X_train, y_train)\n", "\n", " # Лучшая модель\n", " best_model = grid_search.best_estimator_\n", " y_pred = best_model.predict(X_test)\n", "\n", " # Метрики\n", " mae = mean_absolute_error(y_test, y_pred)\n", " rmse = np.sqrt(mean_squared_error(y_test, y_pred))\n", " r2 = r2_score(y_test, y_pred)\n", "\n", " # Сохранение результатов\n", " results_regression[name] = {\n", " \"Best Params\": grid_search.best_params_,\n", " \"MAE\": mae,\n", " \"RMSE\": rmse,\n", " \"R2\": r2\n", " }\n", "\n", "# Печать результатов\n", "for name, metrics in results_regression.items():\n", " print(f\"\\nModel: {name}\")\n", " for metric, value in metrics.items():\n", " print(f\"{metric}: {value}\")" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 MAERMSER2
RandomForestRegressor3.4546307.755776-1.530803
GradientBoostingRegressor3.58578510.312249-3.474193
LinearRegression18059903.801767411829080.658451-7135788186375614.000000
\n" ], "text/plain": [ "" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Импортируем pandas для работы с таблицами\n", "import pandas as pd\n", "\n", "# Формируем таблицу метрик\n", "reg_metrics = pd.DataFrame.from_dict(results_regression, orient=\"index\")[\n", " [\"MAE\", \"RMSE\", \"R2\"]\n", "]\n", "\n", "# Визуализация результатов с помощью стилизации\n", "styled_metrics = (\n", " reg_metrics.sort_values(by=\"RMSE\")\n", " .style.background_gradient(cmap=\"viridis\", low=1, high=0.3, subset=[\"RMSE\", \"MAE\"])\n", " .background_gradient(cmap=\"plasma\", low=0.3, high=1, subset=[\"R2\"])\n", ")\n", "\n", "styled_metrics" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Шикарный вывод: по стране, возрасту, сфере деятельности и источнику доходов невозможно предсказать состояние человека. Значит ли это, что кто угодно, где угодно, и в чём угодно может добиться успеха?" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Классификация" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Категоризируем колонку возраста миллиардеров" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Rank Name Networth Country \\\n", "0 1 Elon Musk 219.0 United States \n", "1 2 Jeff Bezos 171.0 United States \n", "2 3 Bernard Arnault & family 158.0 France \n", "3 4 Bill Gates 129.0 United States \n", "4 5 Warren Buffett 118.0 United States \n", "\n", " Source Industry Age_category \n", "0 Tesla, SpaceX Automotive 50-60 \n", "1 Amazon Technology 50-60 \n", "2 LVMH Fashion & Retail 70-80 \n", "3 Microsoft Technology 60-70 \n", "4 Berkshire Hathaway Finance & Investments 80+ \n" ] } ], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "df = pd.read_csv(\"C://Users//annal//aim//static//csv//Forbes_Billionaires.csv\")\n", "\n", "bins = [0, 30, 40, 50, 60, 70, 80, 101] # границы для возрастных категорий\n", "labels = ['Under 30', '30-40', '40-50', '50-60', '60-70', '70-80', '80+'] # метки для категорий\n", "\n", "df[\"Age_category\"] = pd.cut(df['Age'], bins=bins, labels=labels, right=False)\n", "# Удаляем оригинальные колонки 'country', 'industry' и 'source' из исходного DataFrame\n", "df.drop(columns=['Age'], inplace=True)\n", "\n", "# Просмотр результата\n", "print(df.head())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Создадим выборки" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "X = df.drop(columns=['Age_category','Rank ', 'Name']) # Признаки\n", "# Целевая переменная для классификации\n", "y_class = df['Age_category'] \n", "\n", "# Разделение данных\n", "X_train_clf, X_test_clf, y_train_clf, y_test_clf = train_test_split(X, y_class, test_size=0.2, random_state=42)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Вновь запустим конвейер" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
prepocessing_num__Networthprepocessing_cat__Country_Argentinaprepocessing_cat__Country_Australiaprepocessing_cat__Country_Austriaprepocessing_cat__Country_Barbadosprepocessing_cat__Country_Belgiumprepocessing_cat__Country_Belizeprepocessing_cat__Country_Brazilprepocessing_cat__Country_Bulgariaprepocessing_cat__Country_Canada...prepocessing_cat__Industry_Logisticsprepocessing_cat__Industry_Manufacturingprepocessing_cat__Industry_Media & Entertainmentprepocessing_cat__Industry_Metals & Miningprepocessing_cat__Industry_Real Estateprepocessing_cat__Industry_Serviceprepocessing_cat__Industry_Sportsprepocessing_cat__Industry_Technologyprepocessing_cat__Industry_Telecomprepocessing_cat__Industry_diversified
582-0.0136060.00.00.00.00.00.00.00.00.0...0.00.00.00.01.00.00.00.00.00.0
481.9940830.00.00.00.00.00.00.00.00.0...0.01.00.00.00.00.00.00.00.00.0
1772-0.2881620.01.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
964-0.1594640.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
2213-0.3224810.00.00.00.00.00.01.00.00.0...0.00.00.00.00.00.00.00.00.00.0
..................................................................
1638-0.2710020.00.00.00.00.00.00.00.00.0...0.01.00.00.00.00.00.00.00.00.0
1095-0.1937830.00.00.00.00.00.01.00.00.0...0.00.00.00.00.00.00.00.00.00.0
1130-0.1937830.00.00.00.00.00.00.00.00.0...0.00.00.00.01.00.00.00.00.00.0
1294-0.2281030.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
860-0.1337240.00.00.00.00.00.00.00.00.0...0.01.00.00.00.00.00.00.00.00.0
\n", "

2080 rows × 855 columns

\n", "
" ], "text/plain": [ " prepocessing_num__Networth prepocessing_cat__Country_Argentina \\\n", "582 -0.013606 0.0 \n", "48 1.994083 0.0 \n", "1772 -0.288162 0.0 \n", "964 -0.159464 0.0 \n", "2213 -0.322481 0.0 \n", "... ... ... \n", "1638 -0.271002 0.0 \n", "1095 -0.193783 0.0 \n", "1130 -0.193783 0.0 \n", "1294 -0.228103 0.0 \n", "860 -0.133724 0.0 \n", "\n", " prepocessing_cat__Country_Australia prepocessing_cat__Country_Austria \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 1.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 0.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 0.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " prepocessing_cat__Country_Barbados prepocessing_cat__Country_Belgium \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 0.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 0.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 0.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " prepocessing_cat__Country_Belize prepocessing_cat__Country_Brazil \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 0.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 1.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 1.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " prepocessing_cat__Country_Bulgaria prepocessing_cat__Country_Canada \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 0.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 0.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 0.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " ... prepocessing_cat__Industry_Logistics \\\n", "582 ... 0.0 \n", "48 ... 0.0 \n", "1772 ... 0.0 \n", "964 ... 0.0 \n", "2213 ... 0.0 \n", "... ... ... \n", "1638 ... 0.0 \n", "1095 ... 0.0 \n", "1130 ... 0.0 \n", "1294 ... 0.0 \n", "860 ... 0.0 \n", "\n", " prepocessing_cat__Industry_Manufacturing \\\n", "582 0.0 \n", "48 1.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 1.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 1.0 \n", "\n", " prepocessing_cat__Industry_Media & Entertainment \\\n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_Metals & Mining \\\n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_Real Estate \\\n", "582 1.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 1.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_Service prepocessing_cat__Industry_Sports \\\n", "582 0.0 0.0 \n", "48 0.0 0.0 \n", "1772 0.0 0.0 \n", "964 0.0 0.0 \n", "2213 0.0 0.0 \n", "... ... ... \n", "1638 0.0 0.0 \n", "1095 0.0 0.0 \n", "1130 0.0 0.0 \n", "1294 0.0 0.0 \n", "860 0.0 0.0 \n", "\n", " prepocessing_cat__Industry_Technology \\\n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_Telecom \\\n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", " prepocessing_cat__Industry_diversified \n", "582 0.0 \n", "48 0.0 \n", "1772 0.0 \n", "964 0.0 \n", "2213 0.0 \n", "... ... \n", "1638 0.0 \n", "1095 0.0 \n", "1130 0.0 \n", "1294 0.0 \n", "860 0.0 \n", "\n", "[2080 rows x 855 columns]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.compose import ColumnTransformer\n", "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n", "from sklearn.impute import SimpleImputer\n", "from sklearn.pipeline import Pipeline\n", "import pandas as pd\n", "\n", "# Исправляем ColumnTransformer с сохранением имен колонок\n", "columns_to_drop = []\n", "\n", "num_columns = [\n", " column\n", " for column in X_train_clf.columns\n", " if column not in columns_to_drop and X_train_clf[column].dtype != \"object\"\n", "]\n", "cat_columns = [\n", " column\n", " for column in X_train_clf.columns\n", " if column not in columns_to_drop and X_train_clf[column].dtype == \"object\"\n", "]\n", "\n", "# Предобработка числовых данных\n", "num_imputer = SimpleImputer(strategy=\"median\")\n", "num_scaler = StandardScaler()\n", "preprocessing_num = Pipeline(\n", " [\n", " (\"imputer\", num_imputer),\n", " (\"scaler\", num_scaler),\n", " ]\n", ")\n", "\n", "# Предобработка категориальных данных\n", "cat_imputer = SimpleImputer(strategy=\"constant\", fill_value=\"unknown\")\n", "cat_encoder = OneHotEncoder(handle_unknown=\"ignore\", sparse_output=False, drop=\"first\")\n", "preprocessing_cat = Pipeline(\n", " [\n", " (\"imputer\", cat_imputer),\n", " (\"encoder\", cat_encoder),\n", " ]\n", ")\n", "\n", "# Общая предобработка признаков\n", "features_preprocessing = ColumnTransformer(\n", " verbose_feature_names_out=True, # Сохраняем имена колонок\n", " transformers=[\n", " (\"prepocessing_num\", preprocessing_num, num_columns),\n", " (\"prepocessing_cat\", preprocessing_cat, cat_columns),\n", " ],\n", " remainder=\"drop\" # Убираем неиспользуемые столбцы\n", ")\n", "\n", "# Итоговый конвейер\n", "pipeline_end = Pipeline(\n", " [\n", " (\"features_preprocessing\", features_preprocessing),\n", " ]\n", ")\n", "\n", "# Преобразуем данные\n", "preprocessing_result = pipeline_end.fit_transform(X_train_clf)\n", "\n", "# Создаем DataFrame с правильными именами колонок\n", "preprocessed_df = pd.DataFrame(\n", " preprocessing_result,\n", " columns=pipeline_end.get_feature_names_out(),\n", " index=X_train_clf.index, # Сохраняем индексы\n", ")\n", "\n", "preprocessed_df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Формирование набора моделей\n", "## LogisticRegression -- логистическая регрессия\n", "## RandomForestClassifier -- метод случайного леса (набор деревьев решений)\n", "## KNN -- k-ближайших соседей\n", "# Обучение этих моделей с применением RandomizedSearchCV(для подбора гиперпараметров)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training LogisticRegression...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:320: UserWarning: The total space of parameters 3 is smaller than n_iter=10. Running 3 iterations. For exhaustive searches, use GridSearchCV.\n", " warnings.warn(\n", "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:1103: UserWarning: One or more of the test scores are non-finite: [nan nan nan]\n", " warnings.warn(\n", "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:242: UserWarning: Found unknown categories in columns [0, 1] during transform. These unknown categories will be encoded as all zeros\n", " warnings.warn(\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Training RandomForestClassifier...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:1103: UserWarning: One or more of the test scores are non-finite: [nan nan nan nan nan nan nan nan nan nan]\n", " warnings.warn(\n", "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:242: UserWarning: Found unknown categories in columns [0, 1] during transform. These unknown categories will be encoded as all zeros\n", " warnings.warn(\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Training KNN...\n", "\n", "Model: LogisticRegression\n", "Best Params: {'model__C': 0.1}\n", "Accuracy: 0.3903846153846154\n", "F1 Score: 0.20313635491500218\n", "Confusion_matrix: [[ 0 1 2 6 1 0 0]\n", " [ 0 1 27 18 7 0 0]\n", " [ 0 1 82 35 13 3 0]\n", " [ 0 1 45 80 34 4 0]\n", " [ 0 0 15 51 37 4 0]\n", " [ 0 0 5 28 14 3 0]\n", " [ 0 0 0 2 0 0 0]]\n", "\n", "Model: RandomForestClassifier\n", "Best Params: {'model__n_estimators': 200, 'model__max_features': 'sqrt', 'model__max_depth': 7, 'model__criterion': 'gini', 'model__class_weight': 'balanced'}\n", "Accuracy: 0.29615384615384616\n", "F1 Score: 0.23917948939202166\n", "Confusion_matrix: [[ 2 3 1 1 0 1 2]\n", " [ 1 21 11 4 2 14 0]\n", " [ 1 18 65 7 12 31 0]\n", " [ 2 23 35 12 20 70 2]\n", " [ 1 4 12 3 20 65 2]\n", " [ 0 5 1 5 5 34 0]\n", " [ 1 0 0 1 0 0 0]]\n", "\n", "Model: KNN\n", "Best Params: {'model__weights': 'uniform', 'model__n_neighbors': 3}\n", "Accuracy: 0.32884615384615384\n", "F1 Score: 0.23870853259159636\n", "Confusion_matrix: [[ 3 0 4 2 1 0 0]\n", " [ 4 19 13 10 6 1 0]\n", " [ 8 14 65 27 15 5 0]\n", " [ 9 14 49 53 29 10 0]\n", " [ 8 8 28 25 24 14 0]\n", " [ 0 4 9 18 12 7 0]\n", " [ 1 0 0 1 0 0 0]]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\numpy\\ma\\core.py:2881: RuntimeWarning: invalid value encountered in cast\n", " _data = np.array(data, dtype=dtype, copy=copy,\n", "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:1103: UserWarning: One or more of the test scores are non-finite: [nan nan nan nan nan nan nan nan nan nan]\n", " warnings.warn(\n", "c:\\Users\\annal\\aim\\.venv\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:242: UserWarning: Found unknown categories in columns [0, 1] during transform. These unknown categories will be encoded as all zeros\n", " warnings.warn(\n" ] } ], "source": [ "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.neighbors import KNeighborsClassifier\n", "from sklearn.model_selection import GridSearchCV, RandomizedSearchCV\n", "from sklearn.metrics import accuracy_score, confusion_matrix, f1_score\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.pipeline import Pipeline\n", "\n", "\n", "# Модели и параметры\n", "models_classification = {\n", " \"LogisticRegression\": LogisticRegression(max_iter=1000),\n", " \"RandomForestClassifier\": RandomForestClassifier(random_state=42),\n", " \"KNN\": KNeighborsClassifier()\n", "}\n", "\n", "param_grids_classification = {\n", " \"LogisticRegression\": {\n", " 'model__C': [0.1, 1, 10]\n", " },\n", " \"RandomForestClassifier\": {\n", " \"model__n_estimators\": [10, 20, 30, 40, 50, 100, 150, 200, 250, 500],\n", " \"model__max_features\": [\"sqrt\", \"log2\", 2],\n", " \"model__max_depth\": [2, 3, 4, 5, 6, 7, 8, 9 ,10, 20],\n", " \"model__criterion\": [\"gini\", \"entropy\", \"log_loss\"],\n", " \"model__class_weight\": [\"balanced\"]\n", " },\n", " \"KNN\": {\n", " 'model__n_neighbors': [3, 5, 7, 9, 11],\n", " 'model__weights': ['uniform', 'distance']\n", " }\n", "}\n", "\n", "# Результаты\n", "results_classification = {}\n", "\n", "# Перебор моделей\n", "for name, model in models_classification.items():\n", " print(f\"Training {name}...\")\n", " pipeline = Pipeline(steps=[\n", " ('features_preprocessing', features_preprocessing),\n", " ('model', model)\n", " ])\n", " param_grid = param_grids_classification[name]\n", " grid_search = RandomizedSearchCV(pipeline, param_grid, cv=5, scoring='f1', n_jobs=-1)\n", " grid_search.fit(X_train_clf, y_train_clf)\n", "\n", " # Лучшая модель\n", " best_model = grid_search.best_estimator_\n", " y_pred = best_model.predict(X_test_clf)\n", "\n", " # Метрики\n", " acc = accuracy_score(y_test_clf, y_pred)\n", " f1 = f1_score(y_test_clf, y_pred, average=\"macro\")\n", "\n", " # Вычисление матрицы ошибок\n", " c_matrix = confusion_matrix(y_test_clf, y_pred)\n", "\n", " # Сохранение результатов\n", " results_classification[name] = {\n", " \"Best Params\": grid_search.best_params_,\n", " \"Accuracy\": acc,\n", " \"F1 Score\": f1,\n", " \"Confusion_matrix\": c_matrix\n", " }\n", "\n", "# Печать результатов\n", "for name, metrics in results_classification.items():\n", " print(f\"\\nModel: {name}\")\n", " for metric, value in metrics.items():\n", " print(f\"{metric}: {value}\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Покажем матрицы в виде диаграмм" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from sklearn.metrics import ConfusionMatrixDisplay\n", "\n", "\n", "num_models = len(results_classification)\n", "num_rows = (num_models // 2) + (num_models % 2) # Количество строк для подграфиков\n", "_, ax = plt.subplots(num_rows, 2, figsize=(17, 17), sharex=False, sharey=False)\n", "\n", "for index, (name, metrics) in enumerate(results_classification.items()):\n", " c_matrix = metrics[\"Confusion_matrix\"]\n", " disp = ConfusionMatrixDisplay(\n", " confusion_matrix=c_matrix, display_labels=[\"Under 30\", \"30-40\", \"40-50\", \"50-60\", \"60-70\", \"70-80\", \"80+\"]\n", " ).plot(ax=ax.flat[index])\n", " disp.ax_.set_title(name)\n", "\n", "# Корректировка расположения графиков\n", "plt.subplots_adjust(top=1, bottom=0, hspace=0.4, wspace=0.1)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Вывод: возраст удалось предсказать чуть успешнее. Но всё же, датасет не имеет в себе необходимых данных для более точных предсказаний" ] } ], "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": "3.12.6" } }, "nbformat": 4, "nbformat_minor": 2 }