2024-11-22 21:51:48 +04:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"*Вариант 19:* Данные о
]
},
{
"cell_type": "code",
"execution_count": 14,
"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",
"import seaborn as sns\n",
"\n",
"df = pd.read_csv(\"C:/Users/goldfest/Desktop/3 курс/MII/AIM-PIbd-31-LOBASHOV-I-D/static/csv/Forbes Billionaires.csv\", sep=\",\")\n",
"print(df.columns)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Бизнес-цели\n",
"\n",
"### Задача классификации\n",
"Классифицировать людей по уровню состояния (например, низкий, средний, высокий уровень богатства).\n",
"\n",
"### Задача регрессии:\n",
"Прогнозирование состояния миллионеров (Networth):\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Определение достижимого уровня качества модели для первой задачи "
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Среднее значение поля 'Networth': 4.8607499999999995\n",
" Rank Name Networth Age Country \\\n",
"0 1 Elon Musk 219.0 50 United States \n",
"1 2 Jeff Bezos 171.0 58 United States \n",
"2 3 Bernard Arnault & family 158.0 73 France \n",
"3 4 Bill Gates 129.0 66 United States \n",
"4 5 Warren Buffett 118.0 91 United States \n",
"\n",
" Source Industry above_average_networth \n",
"0 Tesla, SpaceX Automotive 1 \n",
"1 Amazon Technology 1 \n",
"2 LVMH Fashion & Retail 1 \n",
"3 Microsoft Technology 1 \n",
"4 Berkshire Hathaway Finance & Investments 1 \n"
]
}
],
"source": [
"from sklearn import set_config\n",
"\n",
"set_config(transform_output=\"pandas\")\n",
"\n",
"# Устанавливаем случайное состояние\n",
"random_state = 42\n",
"average_networth = df['Networth'].mean()\n",
"print(f\"Среднее значение поля 'Networth': {average_networth}\")\n",
"\n",
"# Создаем новую переменную, указывающую, превышает ли чистое состояние среднее\n",
"df['above_average_networth'] = (df['Networth'] > average_networth).astype(int)\n",
"\n",
"print(df.head())\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Разделение набора данных на обучающую и тестовые выборки (80/20) для задачи классификации\n",
"\n",
"Целевой признак -- above_average_networth "
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"X_train shape: (2080, 8)\n",
"y_train shape: (2080, 1)\n",
"X_test shape: (520, 8)\n",
"y_test shape: (520, 1)\n",
"X_train:\n",
" Rank Name Networth Age Country Source \\\n",
"2125 2076 Yogesh Kothari 1.4 73 India specialty chemicals \n",
"1165 1163 Yvonne Bauer 2.7 45 Germany magazines, media \n",
"397 398 Juergen Blickle 6.4 75 Germany auto parts \n",
"1432 1397 Alexander Svetakov 2.2 54 Russia real estate \n",
"1024 1012 Li Min 3.0 56 China semiconductor \n",
"\n",
" Industry above_average_networth \n",
"2125 Manufacturing 0 \n",
"1165 Media & Entertainment 0 \n",
"397 Manufacturing 1 \n",
"1432 Finance & Investments 0 \n",
"1024 Technology 0 \n",
"y_train:\n",
" above_average_networth\n",
"2125 0\n",
"1165 0\n",
"397 1\n",
"1432 0\n",
"1024 0\n",
"X_test:\n",
" Rank Name Networth Age Country \\\n",
"2437 2324 Horst Wortmann 1.2 80 Germany \n",
"2118 2076 Ramesh Juneja 1.4 66 India \n",
"1327 1292 Teresita Sy-Coson 2.4 71 Philippines \n",
"2063 1929 Myron Wentz 1.5 82 St. Kitts and Nevis \n",
"1283 1238 Suh Kyung-bae 2.5 59 South Korea \n",
"\n",
" Source Industry above_average_networth \n",
"2437 footwear Fashion & Retail 0 \n",
"2118 pharmaceuticals Healthcare 0 \n",
"1327 diversified diversified 0 \n",
"2063 health products Fashion & Retail 0 \n",
"1283 cosmetics Fashion & Retail 0 \n",
"y_test:\n",
" above_average_networth\n",
"2437 0\n",
"2118 0\n",
"1327 0\n",
"2063 0\n",
"1283 0\n"
]
}
],
"source": [
"from typing import Tuple\n",
"from pandas import DataFrame\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"def split_stratified_into_train_val_test(\n",
" df_input,\n",
" stratify_colname=\"y\",\n",
" frac_train=0.6,\n",
" frac_val=0.15,\n",
" frac_test=0.25,\n",
" random_state=None,\n",
") -> Tuple[DataFrame, DataFrame, DataFrame, DataFrame, DataFrame, DataFrame]:\n",
"\n",
"\n",
" if frac_train + frac_val + frac_test != 1.0:\n",
" raise ValueError(\n",
" \"fractions %f, %f, %f do not add up to 1.0\"\n",
" % (frac_train, frac_val, frac_test)\n",
" )\n",
" if stratify_colname not in df_input.columns:\n",
" raise ValueError(\"%s is not a column in the dataframe\" % (stratify_colname))\n",
" X = df_input\n",
" y = df_input[\n",
" [stratify_colname]\n",
" ] \n",
" df_train, df_temp, y_train, y_temp = train_test_split(\n",
" X, y, stratify=y, test_size=(1.0 - frac_train), random_state=random_state\n",
" )\n",
" if frac_val <= 0:\n",
" assert len(df_input) == len(df_train) + len(df_temp)\n",
" return df_train, pd.DataFrame(), df_temp, y_train, pd.DataFrame(), y_temp\n",
" relative_frac_test = frac_test / (frac_val + frac_test)\n",
" df_val, df_test, y_val, y_test = train_test_split(\n",
" df_temp,\n",
" y_temp,\n",
" stratify=y_temp,\n",
" test_size=relative_frac_test,\n",
" random_state=random_state,\n",
" )\n",
" assert len(df_input) == len(df_train) + len(df_val) + len(df_test)\n",
" return df_train, df_val, df_test, y_train, y_val, y_test\n",
"\n",
"random_state = 42 \n",
"X_train, X_val, X_test, y_train, y_val, y_test = split_stratified_into_train_val_test(\n",
" df, stratify_colname=\"above_average_networth\", frac_train=0.80, frac_val=0, frac_test=0.20, random_state=random_state\n",
")\n",
"\n",
"# Вывод размеров выборок\n",
"print(\"X_train shape:\", X_train.shape)\n",
"print(\"y_train shape:\", y_train.shape)\n",
"print(\"X_test shape:\", X_test.shape)\n",
"print(\"y_test shape:\", y_test.shape)\n",
"\n",
"# Отображение содержимого выборок\n",
"print(\"X_train:\\n\", X_train.head())\n",
"print(\"y_train:\\n\", y_train.head())\n",
"print(\"X_test:\\n\", X_test.head())\n",
"print(\"y_test:\\n\", y_test.head())\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Построение конвейеров предобработки \n",
"Создадим пайплайн для числовых и категориальных данных. \n",
"\n",
"preprocessing_num -- конвейер для обработки числовых данных: заполнение пропущенных значений и стандартизация\n",
"\n",
"preprocessing_cat -- конвейер для обработки категориальных данных: заполнение пропущенных данных и унитарное кодирование\n",
"\n",
"features_preprocessing -- трансформер для предобработки признаков\n",
"\n",
"features_engineering -- трансформер для конструирования признаков\n",
"\n",
"drop_columns -- трансформер для удаления колонок\n",
"\n",
"pipeline_end -- основной конвейер предобработки данных и конструирования признаков"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.compose import ColumnTransformer\n",
"from sklearn.impute import SimpleImputer\n",
"from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
"from sklearn.pipeline import Pipeline\n",
"# Определение столбцов для обработки\n",
"columns_to_drop = [\"Name\", \"Rank\"] # Столбцы, которые можно удалить\n",
"num_columns = [\"Networth\", \"Age\"] # Числовые столбцы\n",
"cat_columns = [\"Country\", \"Source\", \"Industry\"] # Категориальные столбцы\n",
"\n",
"# Препроцессинг числовых столбцов\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",
"# Препроцессинг категориальных столбцов\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",
"# Объединение препроцессинга\n",
"features_preprocessing = ColumnTransformer(\n",
" verbose_feature_names_out=False,\n",
" transformers=[\n",
" (\"preprocessing_num\", preprocessing_num, num_columns),\n",
" (\"preprocessing_cat\", preprocessing_cat, cat_columns),\n",
" ],\n",
" remainder=\"passthrough\"\n",
")\n",
"\n",
"# Удаление ненужных столбцов\n",
"drop_columns = ColumnTransformer(\n",
" verbose_feature_names_out=False,\n",
" transformers=[\n",
" (\"drop_columns\", \"drop\", columns_to_drop),\n",
" ],\n",
" remainder=\"passthrough\",\n",
")\n",
"\n",
"# Создание финального пайплайна\n",
"pipeline_end = Pipeline(\n",
" [\n",
" (\"features_preprocessing\", features_preprocessing),\n",
" (\"drop_columns\", drop_columns),\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Демонстрация работы конвейера для предобработки данных при классификации"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Networth Age Country_Argentina Country_Australia \\\n",
"2125 -0.340947 0.680013 0.0 0.0 \n",
"1165 -0.211625 -1.475070 0.0 0.0 \n",
"397 0.156447 0.833948 0.0 0.0 \n",
"1432 -0.261364 -0.782365 0.0 0.0 \n",
"1024 -0.181781 -0.628430 0.0 0.0 \n",
"\n",
" Country_Austria Country_Barbados Country_Belgium Country_Belize \\\n",
"2125 0.0 0.0 0.0 0.0 \n",
"1165 0.0 0.0 0.0 0.0 \n",
"397 0.0 0.0 0.0 0.0 \n",
"1432 0.0 0.0 0.0 0.0 \n",
"1024 0.0 0.0 0.0 0.0 \n",
"\n",
" Country_Brazil Country_Bulgaria ... Industry_Manufacturing \\\n",
"2125 0.0 0.0 ... 1.0 \n",
"1165 0.0 0.0 ... 0.0 \n",
"397 0.0 0.0 ... 1.0 \n",
"1432 0.0 0.0 ... 0.0 \n",
"1024 0.0 0.0 ... 0.0 \n",
"\n",
" Industry_Media & Entertainment Industry_Metals & Mining \\\n",
"2125 0.0 0.0 \n",
"1165 1.0 0.0 \n",
"397 0.0 0.0 \n",
"1432 0.0 0.0 \n",
"1024 0.0 0.0 \n",
"\n",
" Industry_Real Estate Industry_Service Industry_Sports \\\n",
"2125 0.0 0.0 0.0 \n",
"1165 0.0 0.0 0.0 \n",
"397 0.0 0.0 0.0 \n",
"1432 0.0 0.0 0.0 \n",
"1024 0.0 0.0 0.0 \n",
"\n",
" Industry_Technology Industry_Telecom Industry_diversified \\\n",
"2125 0.0 0.0 0.0 \n",
"1165 0.0 0.0 0.0 \n",
"397 0.0 0.0 0.0 \n",
"1432 0.0 0.0 0.0 \n",
"1024 1.0 0.0 0.0 \n",
"\n",
" above_average_networth \n",
"2125 0 \n",
"1165 0 \n",
"397 1 \n",
"1432 0 \n",
"1024 0 \n",
"\n",
"[5 rows x 859 columns]\n"
]
}
],
"source": [
"preprocessing_result = pipeline_end.fit_transform(X_train)\n",
"preprocessed_df = pd.DataFrame(\n",
" preprocessing_result,\n",
" columns=pipeline_end.get_feature_names_out(),\n",
")\n",
"\n",
"print(preprocessed_df.head())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Формирование набора моделей для классификации\n",
"\n",
"logistic -- логистическая регрессия\n",
"\n",
"ridge -- гребневая регрессия\n",
"\n",
"decision_tree -- дерево решений\n",
"\n",
"knn -- k-ближайших соседей\n",
"\n",
"naive_bayes -- наивный Байесовский классификатор\n",
"\n",
"gradient_boosting -- метод градиентного бустинга (набор деревьев решений)\n",
"\n",
"random_forest -- метод случайного леса (набор деревьев решений)\n",
"\n",
"mlp -- многослойный персептрон (нейронная сеть)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"from sklearn import linear_model, tree, neighbors, naive_bayes, ensemble, neural_network\n",
"class_models = {\n",
" \"logistic\": {\"model\": linear_model.LogisticRegression()},\n",
" \"ridge\": {\"model\": linear_model.LogisticRegression(penalty=\"l2\", class_weight=\"balanced\")},\n",
" \"decision_tree\": {\n",
" \"model\": tree.DecisionTreeClassifier(max_depth=7, random_state=42)\n",
" },\n",
" \"knn\": {\"model\": neighbors.KNeighborsClassifier(n_neighbors=7)},\n",
" \"naive_bayes\": {\"model\": naive_bayes.GaussianNB()},\n",
" \"gradient_boosting\": {\n",
" \"model\": ensemble.GradientBoostingClassifier(n_estimators=210)\n",
" },\n",
" \"random_forest\": {\n",
" \"model\": ensemble.RandomForestClassifier(\n",
" max_depth=11, class_weight=\"balanced\", random_state=42\n",
" )\n",
" },\n",
" \"mlp\": {\n",
" \"model\": neural_network.MLPClassifier(\n",
" hidden_layer_sizes=(7,),\n",
" max_iter=500,\n",
" early_stopping=True,\n",
" random_state=42,\n",
" )\n",
" },\n",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Обучение моделей и оценка их качества"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: logistic\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Model: ridge\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Model: decision_tree\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Model: knn\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Model: naive_bayes\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Model: gradient_boosting\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Model: random_forest\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Model: mlp\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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 import metrics\n",
"\n",
"for model_name in class_models.keys():\n",
" print(f\"Model: {model_name}\")\n",
" model = class_models[model_name][\"model\"]\n",
"\n",
" model_pipeline = Pipeline([(\"pipeline\", pipeline_end), (\"model\", model)])\n",
" model_pipeline = model_pipeline.fit(X_train, y_train.values.ravel())\n",
"\n",
" y_train_predict = model_pipeline.predict(X_train)\n",
" y_test_probs = model_pipeline.predict_proba(X_test)[:, 1]\n",
" y_test_predict = np.where(y_test_probs > 0.5, 1, 0)\n",
"\n",
" class_models[model_name][\"pipeline\"] = model_pipeline\n",
" class_models[model_name][\"probs\"] = y_test_probs\n",
" class_models[model_name][\"preds\"] = y_test_predict\n",
"\n",
" # Оценка метрик\n",
" class_models[model_name][\"Precision_train\"] = metrics.precision_score(\n",
" y_train, y_train_predict\n",
" )\n",
" class_models[model_name][\"Precision_test\"] = metrics.precision_score(\n",
" y_test, y_test_predict\n",
" )\n",
" class_models[model_name][\"Recall_train\"] = metrics.recall_score(\n",
" y_train, y_train_predict\n",
" )\n",
" class_models[model_name][\"Recall_test\"] = metrics.recall_score(\n",
" y_test, y_test_predict\n",
" )\n",
" class_models[model_name][\"Accuracy_train\"] = metrics.accuracy_score(\n",
" y_train, y_train_predict\n",
" )\n",
" class_models[model_name][\"Accuracy_test\"] = metrics.accuracy_score(\n",
" y_test, y_test_predict\n",
" )\n",
" class_models[model_name][\"ROC_AUC_test\"] = metrics.roc_auc_score(\n",
" y_test, y_test_probs\n",
" )\n",
" class_models[model_name][\"F1_train\"] = metrics.f1_score(y_train, y_train_predict)\n",
" class_models[model_name][\"F1_test\"] = metrics.f1_score(y_test, y_test_predict)\n",
" class_models[model_name][\"MCC_test\"] = metrics.matthews_corrcoef(\n",
" y_test, y_test_predict\n",
" )\n",
" class_models[model_name][\"Cohen_kappa_test\"] = metrics.cohen_kappa_score(\n",
" y_test, y_test_predict\n",
" )\n",
" class_models[model_name][\"Confusion_matrix\"] = metrics.confusion_matrix(\n",
" y_test, y_test_predict\n",
" )\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Сводная таблица оценок качества для использованных моделей классификации"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1200x1000 with 16 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from sklearn.metrics import ConfusionMatrixDisplay\n",
"import matplotlib.pyplot as plt\n",
"\n",
"_, ax = plt.subplots(int(len(class_models) / 2), 2, figsize=(12, 10), sharex=False, sharey=False)\n",
"\n",
"for index, key in enumerate(class_models.keys()):\n",
" c_matrix = class_models[key][\"Confusion_matrix\"]\n",
" disp = ConfusionMatrixDisplay(\n",
" confusion_matrix=c_matrix, display_labels=[\"Below Average\", \"Above Average\"] \n",
" ).plot(ax=ax.flat[index])\n",
" disp.ax_.set_title(key)\n",
"\n",
"plt.subplots_adjust(top=1, bottom=0, hspace=0.4, wspace=0.1)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"403 - это количество правильно предсказанных объектов с
"117 - это количество объектов с
"Результаты говорят о с
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Точность, полнота, верность (аккуратность), F-мера"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\">\n",
"#T_7fb0a_row0_col0, #T_7fb0a_row1_col0, #T_7fb0a_row2_col0, #T_7fb0a_row3_col0, #T_7fb0a_row4_col0, #T_7fb0a_row5_col0, #T_7fb0a_row6_col0, #T_7fb0a_row7_col0 {\n",
" background-color: #440154;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_7fb0a_row0_col1, #T_7fb0a_row0_col2, #T_7fb0a_row0_col3, #T_7fb0a_row1_col1, #T_7fb0a_row1_col2, #T_7fb0a_row1_col3, #T_7fb0a_row2_col1, #T_7fb0a_row2_col2, #T_7fb0a_row2_col3, #T_7fb0a_row3_col1, #T_7fb0a_row3_col2, #T_7fb0a_row3_col3, #T_7fb0a_row4_col1, #T_7fb0a_row4_col2, #T_7fb0a_row4_col3, #T_7fb0a_row5_col1, #T_7fb0a_row6_col2, #T_7fb0a_row7_col1 {\n",
" background-color: #a8db34;\n",
" color: #000000;\n",
"}\n",
"#T_7fb0a_row0_col4, #T_7fb0a_row0_col5, #T_7fb0a_row0_col6, #T_7fb0a_row0_col7, #T_7fb0a_row1_col4, #T_7fb0a_row1_col5, #T_7fb0a_row1_col6, #T_7fb0a_row1_col7, #T_7fb0a_row2_col4, #T_7fb0a_row2_col5, #T_7fb0a_row2_col6, #T_7fb0a_row2_col7, #T_7fb0a_row3_col4, #T_7fb0a_row3_col5, #T_7fb0a_row3_col6, #T_7fb0a_row3_col7, #T_7fb0a_row4_col4, #T_7fb0a_row4_col5, #T_7fb0a_row4_col6, #T_7fb0a_row4_col7, #T_7fb0a_row6_col4, #T_7fb0a_row6_col6 {\n",
" background-color: #da5a6a;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_7fb0a_row5_col2 {\n",
" background-color: #a0da39;\n",
" color: #000000;\n",
"}\n",
"#T_7fb0a_row5_col3 {\n",
" background-color: #8ed645;\n",
" color: #000000;\n",
"}\n",
"#T_7fb0a_row5_col4, #T_7fb0a_row5_col6 {\n",
" background-color: #d7566c;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_7fb0a_row5_col5 {\n",
" background-color: #d14e72;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_7fb0a_row5_col7 {\n",
" background-color: #d24f71;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_7fb0a_row6_col1, #T_7fb0a_row7_col2, #T_7fb0a_row7_col3 {\n",
" background-color: #26818e;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_7fb0a_row6_col3 {\n",
" background-color: #9bd93c;\n",
" color: #000000;\n",
"}\n",
"#T_7fb0a_row6_col5 {\n",
" background-color: #a11b9b;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_7fb0a_row6_col7 {\n",
" background-color: #aa2395;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_7fb0a_row7_col4, #T_7fb0a_row7_col5, #T_7fb0a_row7_col6, #T_7fb0a_row7_col7 {\n",
" background-color: #4e02a2;\n",
" color: #f1f1f1;\n",
"}\n",
"</style>\n",
"<table id=\"T_7fb0a\">\n",
" <thead>\n",
" <tr>\n",
" <th class=\"blank level0\" > </th>\n",
" <th id=\"T_7fb0a_level0_col0\" class=\"col_heading level0 col0\" >Precision_train</th>\n",
" <th id=\"T_7fb0a_level0_col1\" class=\"col_heading level0 col1\" >Precision_test</th>\n",
" <th id=\"T_7fb0a_level0_col2\" class=\"col_heading level0 col2\" >Recall_train</th>\n",
" <th id=\"T_7fb0a_level0_col3\" class=\"col_heading level0 col3\" >Recall_test</th>\n",
" <th id=\"T_7fb0a_level0_col4\" class=\"col_heading level0 col4\" >Accuracy_train</th>\n",
" <th id=\"T_7fb0a_level0_col5\" class=\"col_heading level0 col5\" >Accuracy_test</th>\n",
" <th id=\"T_7fb0a_level0_col6\" class=\"col_heading level0 col6\" >F1_train</th>\n",
" <th id=\"T_7fb0a_level0_col7\" class=\"col_heading level0 col7\" >F1_test</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th id=\"T_7fb0a_level0_row0\" class=\"row_heading level0 row0\" >logistic</th>\n",
" <td id=\"T_7fb0a_row0_col0\" class=\"data row0 col0\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row0_col1\" class=\"data row0 col1\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row0_col2\" class=\"data row0 col2\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row0_col3\" class=\"data row0 col3\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row0_col4\" class=\"data row0 col4\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row0_col5\" class=\"data row0 col5\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row0_col6\" class=\"data row0 col6\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row0_col7\" class=\"data row0 col7\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_7fb0a_level0_row1\" class=\"row_heading level0 row1\" >ridge</th>\n",
" <td id=\"T_7fb0a_row1_col0\" class=\"data row1 col0\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row1_col1\" class=\"data row1 col1\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row1_col2\" class=\"data row1 col2\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row1_col3\" class=\"data row1 col3\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row1_col4\" class=\"data row1 col4\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row1_col5\" class=\"data row1 col5\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row1_col6\" class=\"data row1 col6\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row1_col7\" class=\"data row1 col7\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_7fb0a_level0_row2\" class=\"row_heading level0 row2\" >decision_tree</th>\n",
" <td id=\"T_7fb0a_row2_col0\" class=\"data row2 col0\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row2_col1\" class=\"data row2 col1\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row2_col2\" class=\"data row2 col2\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row2_col3\" class=\"data row2 col3\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row2_col4\" class=\"data row2 col4\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row2_col5\" class=\"data row2 col5\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row2_col6\" class=\"data row2 col6\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row2_col7\" class=\"data row2 col7\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_7fb0a_level0_row3\" class=\"row_heading level0 row3\" >gradient_boosting</th>\n",
" <td id=\"T_7fb0a_row3_col0\" class=\"data row3 col0\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row3_col1\" class=\"data row3 col1\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row3_col2\" class=\"data row3 col2\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row3_col3\" class=\"data row3 col3\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row3_col4\" class=\"data row3 col4\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row3_col5\" class=\"data row3 col5\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row3_col6\" class=\"data row3 col6\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row3_col7\" class=\"data row3 col7\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_7fb0a_level0_row4\" class=\"row_heading level0 row4\" >random_forest</th>\n",
" <td id=\"T_7fb0a_row4_col0\" class=\"data row4 col0\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row4_col1\" class=\"data row4 col1\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row4_col2\" class=\"data row4 col2\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row4_col3\" class=\"data row4 col3\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row4_col4\" class=\"data row4 col4\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row4_col5\" class=\"data row4 col5\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row4_col6\" class=\"data row4 col6\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row4_col7\" class=\"data row4 col7\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_7fb0a_level0_row5\" class=\"row_heading level0 row5\" >mlp</th>\n",
" <td id=\"T_7fb0a_row5_col0\" class=\"data row5 col0\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row5_col1\" class=\"data row5 col1\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row5_col2\" class=\"data row5 col2\" >0.995726</td>\n",
" <td id=\"T_7fb0a_row5_col3\" class=\"data row5 col3\" >0.982906</td>\n",
" <td id=\"T_7fb0a_row5_col4\" class=\"data row5 col4\" >0.999038</td>\n",
" <td id=\"T_7fb0a_row5_col5\" class=\"data row5 col5\" >0.996154</td>\n",
" <td id=\"T_7fb0a_row5_col6\" class=\"data row5 col6\" >0.997859</td>\n",
" <td id=\"T_7fb0a_row5_col7\" class=\"data row5 col7\" >0.991379</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_7fb0a_level0_row6\" class=\"row_heading level0 row6\" >naive_bayes</th>\n",
" <td id=\"T_7fb0a_row6_col0\" class=\"data row6 col0\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row6_col1\" class=\"data row6 col1\" >0.920635</td>\n",
" <td id=\"T_7fb0a_row6_col2\" class=\"data row6 col2\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row6_col3\" class=\"data row6 col3\" >0.991453</td>\n",
" <td id=\"T_7fb0a_row6_col4\" class=\"data row6 col4\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row6_col5\" class=\"data row6 col5\" >0.978846</td>\n",
" <td id=\"T_7fb0a_row6_col6\" class=\"data row6 col6\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row6_col7\" class=\"data row6 col7\" >0.954733</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_7fb0a_level0_row7\" class=\"row_heading level0 row7\" >knn</th>\n",
" <td id=\"T_7fb0a_row7_col0\" class=\"data row7 col0\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row7_col1\" class=\"data row7 col1\" >1.000000</td>\n",
" <td id=\"T_7fb0a_row7_col2\" class=\"data row7 col2\" >0.848291</td>\n",
" <td id=\"T_7fb0a_row7_col3\" class=\"data row7 col3\" >0.811966</td>\n",
" <td id=\"T_7fb0a_row7_col4\" class=\"data row7 col4\" >0.965865</td>\n",
" <td id=\"T_7fb0a_row7_col5\" class=\"data row7 col5\" >0.957692</td>\n",
" <td id=\"T_7fb0a_row7_col6\" class=\"data row7 col6\" >0.917919</td>\n",
" <td id=\"T_7fb0a_row7_col7\" class=\"data row7 col7\" >0.896226</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x298e9d73680>"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"class_metrics = pd.DataFrame.from_dict(class_models, \"index\")[\n",
" [\n",
" \"Precision_train\",\n",
" \"Precision_test\",\n",
" \"Recall_train\",\n",
" \"Recall_test\",\n",
" \"Accuracy_train\",\n",
" \"Accuracy_test\",\n",
" \"F1_train\",\n",
" \"F1_test\",\n",
" ]\n",
"]\n",
"class_metrics.sort_values(\n",
" by=\"Accuracy_test\", ascending=False\n",
").style.background_gradient(\n",
" cmap=\"plasma\",\n",
" low=0.3,\n",
" high=1,\n",
" subset=[\"Accuracy_train\", \"Accuracy_test\", \"F1_train\", \"F1_test\"],\n",
").background_gradient(\n",
" cmap=\"viridis\",\n",
" low=1,\n",
" high=0.3,\n",
" subset=[\n",
" \"Precision_train\",\n",
" \"Precision_test\",\n",
" \"Recall_train\",\n",
" \"Recall_test\",\n",
" ],\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"В с е
"\n",
"Модель MLP, хотя и имеет немного более низкие значения Recall (0.994) и F1-на тестовом наборе (0.997) по сравнению с
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# ROC-кривая, каппа Коэна, коэффициент корреляции Мэтьюса"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\">\n",
"#T_61749_row0_col0, #T_61749_row0_col1, #T_61749_row1_col0, #T_61749_row1_col1, #T_61749_row2_col0, #T_61749_row2_col1, #T_61749_row3_col0, #T_61749_row3_col1, #T_61749_row5_col0, #T_61749_row5_col1 {\n",
" background-color: #a8db34;\n",
" color: #000000;\n",
"}\n",
"#T_61749_row0_col2, #T_61749_row0_col3, #T_61749_row0_col4, #T_61749_row1_col2, #T_61749_row1_col3, #T_61749_row1_col4, #T_61749_row2_col2, #T_61749_row2_col3, #T_61749_row2_col4, #T_61749_row3_col2, #T_61749_row3_col3, #T_61749_row3_col4, #T_61749_row4_col2, #T_61749_row5_col2, #T_61749_row5_col3, #T_61749_row5_col4 {\n",
" background-color: #da5a6a;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row4_col0 {\n",
" background-color: #8ed645;\n",
" color: #000000;\n",
"}\n",
"#T_61749_row4_col1 {\n",
" background-color: #90d743;\n",
" color: #000000;\n",
"}\n",
"#T_61749_row4_col3 {\n",
" background-color: #d24f71;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row4_col4 {\n",
" background-color: #d14e72;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row6_col0, #T_61749_row6_col1 {\n",
" background-color: #26818e;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row6_col2 {\n",
" background-color: #cd4a76;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row6_col3, #T_61749_row6_col4, #T_61749_row7_col2 {\n",
" background-color: #4e02a2;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row7_col0 {\n",
" background-color: #2fb47c;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row7_col1 {\n",
" background-color: #3bbb75;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row7_col3 {\n",
" background-color: #a72197;\n",
" color: #f1f1f1;\n",
"}\n",
"#T_61749_row7_col4 {\n",
" background-color: #a51f99;\n",
" color: #f1f1f1;\n",
"}\n",
"</style>\n",
"<table id=\"T_61749\">\n",
" <thead>\n",
" <tr>\n",
" <th class=\"blank level0\" > </th>\n",
" <th id=\"T_61749_level0_col0\" class=\"col_heading level0 col0\" >Accuracy_test</th>\n",
" <th id=\"T_61749_level0_col1\" class=\"col_heading level0 col1\" >F1_test</th>\n",
" <th id=\"T_61749_level0_col2\" class=\"col_heading level0 col2\" >ROC_AUC_test</th>\n",
" <th id=\"T_61749_level0_col3\" class=\"col_heading level0 col3\" >Cohen_kappa_test</th>\n",
" <th id=\"T_61749_level0_col4\" class=\"col_heading level0 col4\" >MCC_test</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th id=\"T_61749_level0_row0\" class=\"row_heading level0 row0\" >logistic</th>\n",
" <td id=\"T_61749_row0_col0\" class=\"data row0 col0\" >1.000000</td>\n",
" <td id=\"T_61749_row0_col1\" class=\"data row0 col1\" >1.000000</td>\n",
" <td id=\"T_61749_row0_col2\" class=\"data row0 col2\" >1.000000</td>\n",
" <td id=\"T_61749_row0_col3\" class=\"data row0 col3\" >1.000000</td>\n",
" <td id=\"T_61749_row0_col4\" class=\"data row0 col4\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_61749_level0_row1\" class=\"row_heading level0 row1\" >ridge</th>\n",
" <td id=\"T_61749_row1_col0\" class=\"data row1 col0\" >1.000000</td>\n",
" <td id=\"T_61749_row1_col1\" class=\"data row1 col1\" >1.000000</td>\n",
" <td id=\"T_61749_row1_col2\" class=\"data row1 col2\" >1.000000</td>\n",
" <td id=\"T_61749_row1_col3\" class=\"data row1 col3\" >1.000000</td>\n",
" <td id=\"T_61749_row1_col4\" class=\"data row1 col4\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_61749_level0_row2\" class=\"row_heading level0 row2\" >decision_tree</th>\n",
" <td id=\"T_61749_row2_col0\" class=\"data row2 col0\" >1.000000</td>\n",
" <td id=\"T_61749_row2_col1\" class=\"data row2 col1\" >1.000000</td>\n",
" <td id=\"T_61749_row2_col2\" class=\"data row2 col2\" >1.000000</td>\n",
" <td id=\"T_61749_row2_col3\" class=\"data row2 col3\" >1.000000</td>\n",
" <td id=\"T_61749_row2_col4\" class=\"data row2 col4\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_61749_level0_row3\" class=\"row_heading level0 row3\" >gradient_boosting</th>\n",
" <td id=\"T_61749_row3_col0\" class=\"data row3 col0\" >1.000000</td>\n",
" <td id=\"T_61749_row3_col1\" class=\"data row3 col1\" >1.000000</td>\n",
" <td id=\"T_61749_row3_col2\" class=\"data row3 col2\" >1.000000</td>\n",
" <td id=\"T_61749_row3_col3\" class=\"data row3 col3\" >1.000000</td>\n",
" <td id=\"T_61749_row3_col4\" class=\"data row3 col4\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_61749_level0_row4\" class=\"row_heading level0 row4\" >mlp</th>\n",
" <td id=\"T_61749_row4_col0\" class=\"data row4 col0\" >0.996154</td>\n",
" <td id=\"T_61749_row4_col1\" class=\"data row4 col1\" >0.991379</td>\n",
" <td id=\"T_61749_row4_col2\" class=\"data row4 col2\" >1.000000</td>\n",
" <td id=\"T_61749_row4_col3\" class=\"data row4 col3\" >0.988904</td>\n",
" <td id=\"T_61749_row4_col4\" class=\"data row4 col4\" >0.988965</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_61749_level0_row5\" class=\"row_heading level0 row5\" >random_forest</th>\n",
" <td id=\"T_61749_row5_col0\" class=\"data row5 col0\" >1.000000</td>\n",
" <td id=\"T_61749_row5_col1\" class=\"data row5 col1\" >1.000000</td>\n",
" <td id=\"T_61749_row5_col2\" class=\"data row5 col2\" >1.000000</td>\n",
" <td id=\"T_61749_row5_col3\" class=\"data row5 col3\" >1.000000</td>\n",
" <td id=\"T_61749_row5_col4\" class=\"data row5 col4\" >1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_61749_level0_row6\" class=\"row_heading level0 row6\" >knn</th>\n",
" <td id=\"T_61749_row6_col0\" class=\"data row6 col0\" >0.957692</td>\n",
" <td id=\"T_61749_row6_col1\" class=\"data row6 col1\" >0.896226</td>\n",
" <td id=\"T_61749_row6_col2\" class=\"data row6 col2\" >0.997858</td>\n",
" <td id=\"T_61749_row6_col3\" class=\"data row6 col3\" >0.870015</td>\n",
" <td id=\"T_61749_row6_col4\" class=\"data row6 col4\" >0.877459</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_61749_level0_row7\" class=\"row_heading level0 row7\" >naive_bayes</th>\n",
" <td id=\"T_61749_row7_col0\" class=\"data row7 col0\" >0.978846</td>\n",
" <td id=\"T_61749_row7_col1\" class=\"data row7 col1\" >0.954733</td>\n",
" <td id=\"T_61749_row7_col2\" class=\"data row7 col2\" >0.983320</td>\n",
" <td id=\"T_61749_row7_col3\" class=\"data row7 col3\" >0.940955</td>\n",
" <td id=\"T_61749_row7_col4\" class=\"data row7 col4\" >0.942055</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x298e9ed6300>"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"class_metrics = pd.DataFrame.from_dict(class_models, \"index\")[\n",
" [\n",
" \"Accuracy_test\",\n",
" \"F1_test\",\n",
" \"ROC_AUC_test\",\n",
" \"Cohen_kappa_test\",\n",
" \"MCC_test\",\n",
" ]\n",
"]\n",
"\n",
"class_metrics = class_metrics.sort_values(by=\"ROC_AUC_test\", ascending=False)\n",
"\n",
"class_metrics.style.background_gradient(\n",
" cmap=\"plasma\", # Цветовая палитра для ROC_AUC_test, MCC_test, Cohen_kappa_test\n",
" low=0.3,\n",
" high=1, \n",
" subset=[\n",
" \"ROC_AUC_test\",\n",
" \"MCC_test\",\n",
" \"Cohen_kappa_test\",\n",
" ],\n",
").background_gradient(\n",
" cmap=\"viridis\", # Цветовая палитра для Accuracy_test, F1_test\n",
" low=1, \n",
" high=0.3, \n",
" subset=[\n",
" \"Accuracy_test\",\n",
" \"F1_test\",\n",
" ],\n",
")\n"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'logistic'"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"best_model = str(class_metrics.sort_values(by=\"MCC_test\", ascending=False).iloc[0].name)\n",
"\n",
"display(best_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Вывод данных с
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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"
]
},
{
"data": {
"text/plain": [
"'Error items count: 0'"
]
},
"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>Rank</th>\n",
" <th>Predicted</th>\n",
" <th>Name</th>\n",
" <th>Networth</th>\n",
" <th>Age</th>\n",
" <th>Country</th>\n",
" <th>Source</th>\n",
" <th>Industry</th>\n",
" <th>above_average_networth</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Empty DataFrame\n",
"Columns: [Rank, Predicted, Name, Networth, Age, Country, Source, Industry, above_average_networth]\n",
"Index: []"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"preprocessing_result = pipeline_end.transform(X_test)\n",
"preprocessed_df = pd.DataFrame(\n",
" preprocessing_result,\n",
" columns=pipeline_end.get_feature_names_out(),\n",
")\n",
"\n",
"y_pred = class_models[best_model][\"preds\"]\n",
"\n",
"error_index = y_test[y_test[\"above_average_networth\"] != y_pred].index.tolist() \n",
"display(f\"Error items count: {len(error_index)}\")\n",
"\n",
"error_predicted = pd.Series(y_pred, index=y_test.index).loc[error_index]\n",
"error_df = X_test.loc[error_index].copy()\n",
"error_df.insert(loc=1, column=\"Predicted\", value=error_predicted)\n",
"error_df = error_df.sort_index() \n",
"\n",
"display(error_df)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"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>Rank</th>\n",
" <th>Name</th>\n",
" <th>Networth</th>\n",
" <th>Age</th>\n",
" <th>Country</th>\n",
" <th>Source</th>\n",
" <th>Industry</th>\n",
" <th>above_average_networth</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>231</th>\n",
" <td>230</td>\n",
" <td>Xavier Niel</td>\n",
" <td>8.9</td>\n",
" <td>54</td>\n",
" <td>France</td>\n",
" <td>internet, telecom</td>\n",
" <td>Telecom</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Rank Name Networth Age Country Source Industry \\\n",
"231 230 Xavier Niel 8.9 54 France internet, telecom Telecom \n",
"\n",
" above_average_networth \n",
"231 1 "
]
},
"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>Networth</th>\n",
" <th>Age</th>\n",
" <th>Country_Argentina</th>\n",
" <th>Country_Australia</th>\n",
" <th>Country_Austria</th>\n",
" <th>Country_Barbados</th>\n",
" <th>Country_Belgium</th>\n",
" <th>Country_Belize</th>\n",
" <th>Country_Brazil</th>\n",
" <th>Country_Bulgaria</th>\n",
" <th>...</th>\n",
" <th>Industry_Manufacturing</th>\n",
" <th>Industry_Media & Entertainment</th>\n",
" <th>Industry_Metals & Mining</th>\n",
" <th>Industry_Real Estate</th>\n",
" <th>Industry_Service</th>\n",
" <th>Industry_Sports</th>\n",
" <th>Industry_Technology</th>\n",
" <th>Industry_Telecom</th>\n",
" <th>Industry_diversified</th>\n",
" <th>above_average_networth</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>231</th>\n",
" <td>0.405144</td>\n",
" <td>-0.782365</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows ×
"</div>"
],
"text/plain": [
" Networth Age Country_Argentina Country_Australia \\\n",
"231 0.405144 -0.782365 0.0 0.0 \n",
"\n",
" Country_Austria Country_Barbados Country_Belgium Country_Belize \\\n",
"231 0.0 0.0 0.0 0.0 \n",
"\n",
" Country_Brazil Country_Bulgaria ... Industry_Manufacturing \\\n",
"231 0.0 0.0 ... 0.0 \n",
"\n",
" Industry_Media & Entertainment Industry_Metals & Mining \\\n",
"231 0.0 0.0 \n",
"\n",
" Industry_Real Estate Industry_Service Industry_Sports \\\n",
"231 0.0 0.0 0.0 \n",
"\n",
" Industry_Technology Industry_Telecom Industry_diversified \\\n",
"231 0.0 1.0 0.0 \n",
"\n",
" above_average_networth \n",
"231 1.0 \n",
"\n",
"[1 rows x 859 columns]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"predicted: 1 (proba: [0.01305711 0.98694289])\n",
"real: 1\n"
]
}
],
"source": [
"model = class_models[best_model][\"pipeline\"]\n",
"\n",
"example_id = 253\n",
"test = pd.DataFrame(X_test.iloc[example_id, :]).T\n",
"display(test)\n",
"test_preprocessed = pd.DataFrame(preprocessed_df.iloc[example_id, :]).T\n",
"display(test_preprocessed)\n",
"result_proba = model.predict_proba(test)[0]\n",
"result = model.predict(test)[0]\n",
"real = int(y_test.iloc[example_id].values[0])\n",
"print(f\"predicted: {result} (proba: {result_proba})\")\n",
"print(f\"real: {real}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Задача регрессии - прогнозирование состояния миллионеров"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Среднее значение поля 'Networth': 4.8607499999999995\n",
" Rank Name Networth Age Country \\\n",
"0 1 Elon Musk 219.0 50 United States \n",
"1 2 Jeff Bezos 171.0 58 United States \n",
"2 3 Bernard Arnault & family 158.0 73 France \n",
"3 4 Bill Gates 129.0 66 United States \n",
"4 5 Warren Buffett 118.0 91 United States \n",
"\n",
" Source Industry above_average_networth \n",
"0 Tesla, SpaceX Automotive 1 \n",
"1 Amazon Technology 1 \n",
"2 LVMH Fashion & Retail 1 \n",
"3 Microsoft Technology 1 \n",
"4 Berkshire Hathaway Finance & Investments 1 \n",
"Статистическое описание DataFrame:\n",
" Rank Networth Age above_average_networth\n",
"count 2600.000000 2600.000000 2600.000000 2600.000000\n",
"mean 1269.570769 4.860750 64.271923 0.225000\n",
"std 728.146364 10.659671 13.220607 0.417663\n",
"min 1.000000 1.000000 19.000000 0.000000\n",
"25% 637.000000 1.500000 55.000000 0.000000\n",
"50% 1292.000000 2.400000 64.000000 0.000000\n",
"75% 1929.000000 4.500000 74.000000 0.000000\n",
"max 2578.000000 219.000000 100.000000 1.000000\n"
]
}
],
"source": [
"import pandas as pd\n",
"from sklearn import set_config\n",
"\n",
"set_config(transform_output=\"pandas\")\n",
"\n",
"df = pd.read_csv(\"..//static//csv//Forbes Billionaires.csv\")\n",
"random_state = 42\n",
"\n",
"# Вычисление среднего значения поля \"Networth\"\n",
"average_networth = df['Networth'].mean()\n",
"print(f\"Среднее значение поля 'Networth': {average_networth}\")\n",
"\n",
"# Создание новой колонки, указывающей, выше или ниже среднего значение чистого состояния\n",
"df['above_average_networth'] = (df['Networth'] > average_networth).astype(int)\n",
"\n",
"print(df.head())\n",
"print(\"Статистическое описание DataFrame:\")\n",
"print(df.describe())\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Разделение набора данных на обучающую и тестовые выборки (80/20) для задачи регрессии\n",
"\n",
"Целевой признак -- above_average_networth"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'X_train'"
]
},
"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>Rank</th>\n",
" <th>Name</th>\n",
" <th>Networth</th>\n",
" <th>Age</th>\n",
" <th>Country</th>\n",
" <th>Source</th>\n",
" <th>Industry</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>582</th>\n",
" <td>579</td>\n",
" <td>Alexandra Schoerghuber & family</td>\n",
" <td>4.9</td>\n",
" <td>63</td>\n",
" <td>Germany</td>\n",
" <td>real estate</td>\n",
" <td>Real Estate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48</th>\n",
" <td>49</td>\n",
" <td>He Xiangjian</td>\n",
" <td>28.3</td>\n",
" <td>79</td>\n",
" <td>China</td>\n",
" <td>home appliances</td>\n",
" <td>Manufacturing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1772</th>\n",
" <td>1729</td>\n",
" <td>Bruce Mathieson</td>\n",
" <td>1.7</td>\n",
" <td>78</td>\n",
" <td>Australia</td>\n",
" <td>hotels</td>\n",
" <td>Food & Beverage</td>\n",
" </tr>\n",
" <tr>\n",
" <th>964</th>\n",
" <td>951</td>\n",
" <td>Pansy Ho</td>\n",
" <td>3.2</td>\n",
" <td>59</td>\n",
" <td>Hong Kong</td>\n",
" <td>casinos</td>\n",
" <td>Gambling & Casinos</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2213</th>\n",
" <td>2190</td>\n",
" <td>Sasson Dayan & family</td>\n",
" <td>1.3</td>\n",
" <td>82</td>\n",
" <td>Brazil</td>\n",
" <td>banking</td>\n",
" <td>Finance & Investments</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1638</th>\n",
" <td>1579</td>\n",
" <td>Wang Chou-hsiong</td>\n",
" <td>1.9</td>\n",
" <td>81</td>\n",
" <td>Taiwan</td>\n",
" <td>footwear</td>\n",
" <td>Manufacturing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095</th>\n",
" <td>1096</td>\n",
" <td>Jose Joao Abdalla Filho</td>\n",
" <td>2.8</td>\n",
" <td>76</td>\n",
" <td>Brazil</td>\n",
" <td>investments</td>\n",
" <td>Finance & Investments</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1130</th>\n",
" <td>1096</td>\n",
" <td>Lin Chen-hai</td>\n",
" <td>2.8</td>\n",
" <td>75</td>\n",
" <td>Taiwan</td>\n",
" <td>real estate</td>\n",
" <td>Real Estate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1294</th>\n",
" <td>1292</td>\n",
" <td>Banwari Lal Bawri</td>\n",
" <td>2.4</td>\n",
" <td>69</td>\n",
" <td>India</td>\n",
" <td>pharmaceuticals</td>\n",
" <td>Healthcare</td>\n",
" </tr>\n",
" <tr>\n",
" <th>860</th>\n",
" <td>851</td>\n",
" <td>Kuok Khoon Hong</td>\n",
" <td>3.5</td>\n",
" <td>72</td>\n",
" <td>Singapore</td>\n",
" <td>palm oil</td>\n",
" <td>Manufacturing</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2080 rows ×
"</div>"
],
"text/plain": [
" Rank Name Networth Age Country \\\n",
"582 579 Alexandra Schoerghuber & family 4.9 63 Germany \n",
"48 49 He Xiangjian 28.3 79 China \n",
"1772 1729 Bruce Mathieson 1.7 78 Australia \n",
"964 951 Pansy Ho 3.2 59 Hong Kong \n",
"2213 2190 Sasson Dayan & family 1.3 82 Brazil \n",
"... ... ... ... ... ... \n",
"1638 1579 Wang Chou-hsiong 1.9 81 Taiwan \n",
"1095 1096 Jose Joao Abdalla Filho 2.8 76 Brazil \n",
"1130 1096 Lin Chen-hai 2.8 75 Taiwan \n",
"1294 1292 Banwari Lal Bawri 2.4 69 India \n",
"860 851 Kuok Khoon Hong 3.5 72 Singapore \n",
"\n",
" Source Industry \n",
"582 real estate Real Estate \n",
"48 home appliances Manufacturing \n",
"1772 hotels Food & Beverage \n",
"964 casinos Gambling & Casinos \n",
"2213 banking Finance & Investments \n",
"... ... ... \n",
"1638 footwear Manufacturing \n",
"1095 investments Finance & Investments \n",
"1130 real estate Real Estate \n",
"1294 pharmaceuticals Healthcare \n",
"860 palm oil Manufacturing \n",
"\n",
"[2080 rows x 7 columns]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"'y_train'"
]
},
"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>above_average_networth</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>582</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1772</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>964</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2213</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1638</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1130</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1294</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>860</th>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2080 rows ×
"</div>"
],
"text/plain": [
" above_average_networth\n",
"582 1\n",
"48 1\n",
"1772 0\n",
"964 0\n",
"2213 0\n",
"... ...\n",
"1638 0\n",
"1095 0\n",
"1130 0\n",
"1294 0\n",
"860 0\n",
"\n",
"[2080 rows x 1 columns]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"'X_test'"
]
},
"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>Rank</th>\n",
" <th>Name</th>\n",
" <th>Networth</th>\n",
" <th>Age</th>\n",
" <th>Country</th>\n",
" <th>Source</th>\n",
" <th>Industry</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1593</th>\n",
" <td>1579</td>\n",
" <td>Guangming Fu & family</td>\n",
" <td>1.9</td>\n",
" <td>68</td>\n",
" <td>China</td>\n",
" <td>poultry</td>\n",
" <td>Food & Beverage</td>\n",
" </tr>\n",
" <tr>\n",
" <th>196</th>\n",
" <td>197</td>\n",
" <td>Leon Black</td>\n",
" <td>10.0</td>\n",
" <td>70</td>\n",
" <td>United States</td>\n",
" <td>private equity</td>\n",
" <td>Finance & Investments</td>\n",
" </tr>\n",
" <tr>\n",
" <th>239</th>\n",
" <td>235</td>\n",
" <td>Zong Qinghou</td>\n",
" <td>8.8</td>\n",
" <td>76</td>\n",
" <td>China</td>\n",
" <td>beverages</td>\n",
" <td>Food & Beverage</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2126</th>\n",
" <td>2076</td>\n",
" <td>Kurt Krieger</td>\n",
" <td>1.4</td>\n",
" <td>74</td>\n",
" <td>Germany</td>\n",
" <td>furniture retailing</td>\n",
" <td>Fashion & Retail</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1587</th>\n",
" <td>1579</td>\n",
" <td>Chen Kaichen</td>\n",
" <td>1.9</td>\n",
" <td>64</td>\n",
" <td>China</td>\n",
" <td>household chemicals</td>\n",
" <td>Manufacturing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1778</th>\n",
" <td>1729</td>\n",
" <td>Jorge Perez</td>\n",
" <td>1.7</td>\n",
" <td>72</td>\n",
" <td>United States</td>\n",
" <td>real estate</td>\n",
" <td>Real Estate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>166</th>\n",
" <td>167</td>\n",
" <td>Brian Chesky</td>\n",
" <td>11.5</td>\n",
" <td>40</td>\n",
" <td>United States</td>\n",
" <td>Airbnb</td>\n",
" <td>Technology</td>\n",
" </tr>\n",
" <tr>\n",
" <th>949</th>\n",
" <td>913</td>\n",
" <td>Zhong Ruonong & family</td>\n",
" <td>3.3</td>\n",
" <td>59</td>\n",
" <td>China</td>\n",
" <td>electronics</td>\n",
" <td>Manufacturing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49</th>\n",
" <td>50</td>\n",
" <td>Miriam Adelson</td>\n",
" <td>27.5</td>\n",
" <td>76</td>\n",
" <td>United States</td>\n",
" <td>casinos</td>\n",
" <td>Gambling & Casinos</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2511</th>\n",
" <td>2448</td>\n",
" <td>Lou Boliang</td>\n",
" <td>1.1</td>\n",
" <td>58</td>\n",
" <td>United States</td>\n",
" <td>pharmaceuticals</td>\n",
" <td>Healthcare</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>520 rows ×
"</div>"
],
"text/plain": [
" Rank Name Networth Age Country \\\n",
"1593 1579 Guangming Fu & family 1.9 68 China \n",
"196 197 Leon Black 10.0 70 United States \n",
"239 235 Zong Qinghou 8.8 76 China \n",
"2126 2076 Kurt Krieger 1.4 74 Germany \n",
"1587 1579 Chen Kaichen 1.9 64 China \n",
"... ... ... ... ... ... \n",
"1778 1729 Jorge Perez 1.7 72 United States \n",
"166 167 Brian Chesky 11.5 40 United States \n",
"949 913 Zhong Ruonong & family 3.3 59 China \n",
"49 50 Miriam Adelson 27.5 76 United States \n",
"2511 2448 Lou Boliang 1.1 58 United States \n",
"\n",
" Source Industry \n",
"1593 poultry Food & Beverage \n",
"196 private equity Finance & Investments \n",
"239 beverages Food & Beverage \n",
"2126 furniture retailing Fashion & Retail \n",
"1587 household chemicals Manufacturing \n",
"... ... ... \n",
"1778 real estate Real Estate \n",
"166 Airbnb Technology \n",
"949 electronics Manufacturing \n",
"49 casinos Gambling & Casinos \n",
"2511 pharmaceuticals Healthcare \n",
"\n",
"[520 rows x 7 columns]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"'y_test'"
]
},
"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>above_average_networth</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1593</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>196</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>239</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2126</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1587</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1778</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>166</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>949</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2511</th>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>520 rows ×
"</div>"
],
"text/plain": [
" above_average_networth\n",
"1593 0\n",
"196 1\n",
"239 1\n",
"2126 0\n",
"1587 0\n",
"... ...\n",
"1778 0\n",
"166 1\n",
"949 0\n",
"49 1\n",
"2511 0\n",
"\n",
"[520 rows x 1 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from typing import Tuple\n",
"import pandas as pd\n",
"from pandas import DataFrame\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"def split_into_train_test(\n",
" df_input: DataFrame,\n",
" target_colname: str = \"above_average_networth\", \n",
" frac_train: float = 0.8,\n",
" random_state: int = None,\n",
") -> Tuple[DataFrame, DataFrame, DataFrame, DataFrame]:\n",
" \n",
" if not (0 < frac_train < 1):\n",
" raise ValueError(\"Fraction must be between 0 and 1.\")\n",
" if target_colname not in df_input.columns:\n",
" raise ValueError(f\"{target_colname} is not a column in the DataFrame.\")\n",
"\n",
" X = df_input.drop(columns=[target_colname]) \n",
" y = df_input[[target_colname]] \n",
"\n",
" X_train, X_test, y_train, y_test = train_test_split(\n",
" X, y,\n",
" test_size=(1.0 - frac_train),\n",
" random_state=random_state\n",
" )\n",
" \n",
" return X_train, X_test, y_train, y_test\n",
"\n",
"X_train, X_test, y_train, y_test = split_into_train_test(\n",
" df, \n",
" target_colname=\"above_average_networth\", \n",
" frac_train=0.8, \n",
" random_state=42 \n",
")\n",
"\n",
"# Отображение результатов\n",
"display(\"X_train\", X_train)\n",
"display(\"y_train\", y_train)\n",
"\n",
"display(\"X_test\", X_test)\n",
"display(\"y_test\", y_test)\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Формирование конвейера для решения задачи регрессии"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Networth Age Country_Argentina Country_Australia \\\n",
"0 20.092595 -1.079729 0.0 0.0 \n",
"1 15.588775 -0.474496 0.0 0.0 \n",
"2 14.368991 0.660314 0.0 0.0 \n",
"3 11.647933 0.130736 0.0 0.0 \n",
"4 10.615808 2.022087 0.0 0.0 \n",
"... ... ... ... ... \n",
"2595 -0.362253 1.189893 0.0 0.0 \n",
"2596 -0.362253 1.341201 0.0 0.0 \n",
"2597 -0.362253 0.509006 0.0 0.0 \n",
"2598 -0.362253 0.282044 0.0 0.0 \n",
"2599 -0.362253 0.357698 0.0 0.0 \n",
"\n",
" Country_Austria Country_Barbados Country_Belgium Country_Belize \\\n",
"0 0.0 0.0 0.0 0.0 \n",
"1 0.0 0.0 0.0 0.0 \n",
"2 0.0 0.0 0.0 0.0 \n",
"3 0.0 0.0 0.0 0.0 \n",
"4 0.0 0.0 0.0 0.0 \n",
"... ... ... ... ... \n",
"2595 0.0 0.0 0.0 0.0 \n",
"2596 0.0 0.0 0.0 0.0 \n",
"2597 0.0 0.0 0.0 0.0 \n",
"2598 0.0 0.0 0.0 0.0 \n",
"2599 0.0 0.0 0.0 0.0 \n",
"\n",
" Country_Brazil Country_Bulgaria ... Industry_Manufacturing \\\n",
"0 0.0 0.0 ... 0.0 \n",
"1 0.0 0.0 ... 0.0 \n",
"2 0.0 0.0 ... 0.0 \n",
"3 0.0 0.0 ... 0.0 \n",
"4 0.0 0.0 ... 0.0 \n",
"... ... ... ... ... \n",
"2595 0.0 0.0 ... 0.0 \n",
"2596 0.0 0.0 ... 0.0 \n",
"2597 0.0 0.0 ... 0.0 \n",
"2598 0.0 0.0 ... 0.0 \n",
"2599 0.0 0.0 ... 0.0 \n",
"\n",
" Industry_Media & Entertainment Industry_Metals & Mining \\\n",
"0 0.0 0.0 \n",
"1 0.0 0.0 \n",
"2 0.0 0.0 \n",
"3 0.0 0.0 \n",
"4 0.0 0.0 \n",
"... ... ... \n",
"2595 0.0 0.0 \n",
"2596 0.0 0.0 \n",
"2597 0.0 0.0 \n",
"2598 0.0 0.0 \n",
"2599 0.0 0.0 \n",
"\n",
" Industry_Real Estate Industry_Service Industry_Sports \\\n",
"0 0.0 0.0 0.0 \n",
"1 0.0 0.0 0.0 \n",
"2 0.0 0.0 0.0 \n",
"3 0.0 0.0 0.0 \n",
"4 0.0 0.0 0.0 \n",
"... ... ... ... \n",
"2595 0.0 0.0 0.0 \n",
"2596 0.0 0.0 0.0 \n",
"2597 0.0 0.0 0.0 \n",
"2598 0.0 0.0 0.0 \n",
"2599 0.0 0.0 0.0 \n",
"\n",
" Industry_Technology Industry_Telecom Industry_diversified \\\n",
"0 0.0 0.0 0.0 \n",
"1 1.0 0.0 0.0 \n",
"2 0.0 0.0 0.0 \n",
"3 1.0 0.0 0.0 \n",
"4 0.0 0.0 0.0 \n",
"... ... ... ... \n",
"2595 0.0 0.0 0.0 \n",
"2596 0.0 0.0 0.0 \n",
"2597 0.0 0.0 0.0 \n",
"2598 0.0 0.0 0.0 \n",
"2599 0.0 0.0 0.0 \n",
"\n",
" Networth_per_Age \n",
"0 -18.608929 \n",
"1 -32.853309 \n",
"2 21.760834 \n",
"3 89.095063 \n",
"4 5.249926 \n",
"... ... \n",
"2595 -0.304441 \n",
"2596 -0.270096 \n",
"2597 -0.711686 \n",
"2598 -1.284383 \n",
"2599 -1.012732 \n",
"\n",
"[2600 rows x 988 columns]\n",
"(2600, 988)\n"
]
}
],
"source": [
"import numpy as np\n",
"from sklearn.base import BaseEstimator, TransformerMixin\n",
"from sklearn.compose import ColumnTransformer\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.impute import SimpleImputer\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.preprocessing import OneHotEncoder\n",
"from sklearn.ensemble import RandomForestRegressor \n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.pipeline import make_pipeline\n",
"\n",
"class ForbesBillionairesFeatures(BaseEstimator, TransformerMixin): \n",
" def __init__(self):\n",
" pass\n",
"\n",
" def fit(self, X, y=None):\n",
" return self\n",
"\n",
" def transform(self, X, y=None):\n",
" X[\"Networth_per_Age\"] = X[\"Networth\"] / X[\"Age\"]\n",
" return X\n",
"\n",
" def get_feature_names_out(self, features_in):\n",
" return np.append(features_in, [\"Networth_per_Age\"], axis=0) \n",
"\n",
"columns_to_drop = [\"Rank\", \"Name\"] \n",
"num_columns = [\"Networth\", \"Age\"] \n",
"cat_columns = [\"Country\", \"Source\", \"Industry\"]\n",
"\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",
"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",
"features_preprocessing = ColumnTransformer(\n",
" verbose_feature_names_out=False,\n",
" transformers=[\n",
" (\"prepocessing_num\", preprocessing_num, num_columns),\n",
" (\"prepocessing_cat\", preprocessing_cat, cat_columns),\n",
" ],\n",
" remainder=\"passthrough\" \n",
")\n",
"\n",
"drop_columns = ColumnTransformer(\n",
" verbose_feature_names_out=False,\n",
" transformers=[\n",
" (\"drop_columns\", \"drop\", columns_to_drop),\n",
" ],\n",
" remainder=\"passthrough\",\n",
")\n",
"\n",
"pipeline_end = Pipeline(\n",
" [\n",
" (\"features_preprocessing\", features_preprocessing),\n",
" (\"drop_columns\", drop_columns),\n",
" (\"custom_features\", ForbesBillionairesFeatures()), # Добавляем custom_features\n",
" ]\n",
")\n",
"\n",
"df = pd.read_csv(\"..//static//csv//Forbes Billionaires.csv\")\n",
"\n",
"average_networth = df['Networth'].mean()\n",
"df['above_average_networth'] = (df['Networth'] > average_networth).astype(int)\n",
"\n",
"X = df.drop('above_average_networth', axis=1)\n",
"y = df['above_average_networth'].values.ravel()\n",
"\n",
"X_processed = pipeline_end.fit_transform(X)\n",
"\n",
"print(X_processed)\n",
"print(X_processed.shape)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Формирование набора моделей для регрессии"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\base.py:1473: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
" return fit_method(estimator, *args, **kwargs)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\base.py:1473: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
" return fit_method(estimator, *args, **kwargs)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\base.py:1473: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
" return fit_method(estimator, *args, **kwargs)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\base.py:1473: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
" return fit_method(estimator, *args, **kwargs)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\base.py:1473: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
" return fit_method(estimator, *args, **kwargs)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\ensemble\\_gb.py:668: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True) # TODO: Is this still required?\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\ensemble\\_gb.py:668: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True) # TODO: Is this still required?\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\ensemble\\_gb.py:668: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True) # TODO: Is this still required?\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\ensemble\\_gb.py:668: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True) # TODO: Is this still required?\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\ensemble\\_gb.py:668: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True) # TODO: Is this still required?\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\utils\\validation.py:1339: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\utils\\validation.py:1339: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\utils\\validation.py:1339: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\utils\\validation.py:1339: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\utils\\validation.py:1339: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Random Forest: Mean Score = 0.9999853281013186, Standard Deviation = 2.6771556649877537e-05\n",
"Linear Regression: Mean Score = -2.4184625766523136e+22, Standard Deviation = 2.867931120379175e+22\n",
"Gradient Boosting: Mean Score = 0.9999999992916644, Standard Deviation = 2.7301021406313204e-12\n",
"Support Vector Regression: Mean Score = 0.6826855358064325, Standard Deviation = 0.02039531518474594\n"
]
}
],
"source": [
"from sklearn.linear_model import LinearRegression\n",
"from sklearn.ensemble import GradientBoostingRegressor\n",
"from sklearn.svm import SVR\n",
"from sklearn.model_selection import cross_val_score\n",
"\n",
"def train_multiple_models(X, y, models):\n",
" results = {}\n",
" for model_name, model in models.items():\n",
" model_pipeline = Pipeline(\n",
" [\n",
" (\"features_preprocessing\", features_preprocessing),\n",
" (\"drop_columns\", drop_columns),\n",
" (\"model\", model) \n",
" ]\n",
" )\n",
"\n",
" scores = cross_val_score(model_pipeline, X, y, cv=5) \n",
" results[model_name] = {\n",
" \"mean_score\": scores.mean(),\n",
" \"std_dev\": scores.std()\n",
" }\n",
" \n",
" return results\n",
"\n",
"models = {\n",
" \"Random Forest\": RandomForestRegressor(),\n",
" \"Linear Regression\": LinearRegression(),\n",
" \"Gradient Boosting\": GradientBoostingRegressor(),\n",
" \"Support Vector Regression\": SVR()\n",
"}\n",
"\n",
"results = train_multiple_models(X_train, y_train, models)\n",
"\n",
"for model_name, scores in results.items():\n",
" print(f\"{model_name}: Mean Score = {scores['mean_score']}, Standard Deviation = {scores['std_dev']}\")"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: logistic\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"MSE (train): 0.0125\n",
"MSE (test): 0.04038461538461539\n",
"MAE (train): 0.0125\n",
"MAE (test): 0.04038461538461539\n",
"R2 (train): 0.9275415718173158\n",
"R2 (test): 0.7776148582600195\n",
"STD (train): 0.11110243021644485\n",
"STD (test): 0.19685959012669935\n",
"----------------------------------------\n",
"Model: ridge\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"MSE (train): 0.004326923076923077\n",
"MSE (test): 0.013461538461538462\n",
"MAE (train): 0.004326923076923077\n",
"MAE (test): 0.013461538461538462\n",
"R2 (train): 0.9749182363983017\n",
"R2 (test): 0.9258716194200065\n",
"STD (train): 0.0656368860749005\n",
"STD (test): 0.11588034534756023\n",
"----------------------------------------\n",
"Model: decision_tree\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"MSE (train): 0.0\n",
"MSE (test): 0.0\n",
"MAE (train): 0.0\n",
"MAE (test): 0.0\n",
"R2 (train): 1.0\n",
"R2 (test): 1.0\n",
"STD (train): 0.0\n",
"STD (test): 0.0\n",
"----------------------------------------\n",
"Model: knn\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"MSE (train): 0.09278846153846154\n",
"MSE (test): 0.15384615384615385\n",
"MAE (train): 0.09278846153846154\n",
"MAE (test): 0.15384615384615385\n",
"R2 (train): 0.4621355138746903\n",
"R2 (test): 0.1528185076572175\n",
"STD (train): 0.29276240884468824\n",
"STD (test): 0.3684085396282311\n",
"----------------------------------------\n",
"Model: naive_bayes\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"MSE (train): 0.37740384615384615\n",
"MSE (test): 0.6096153846153847\n",
"MAE (train): 0.37740384615384615\n",
"MAE (test): 0.6096153846153847\n",
"R2 (train): -1.1876871585925808\n",
"R2 (test): -2.3569566634082757\n",
"STD (train): 0.4847372309428379\n",
"STD (test): 0.5672229402142737\n",
"----------------------------------------\n",
"Model: gradient_boosting\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"MSE (train): 0.0\n",
"MSE (test): 0.0\n",
"MAE (train): 0.0\n",
"MAE (test): 0.0\n",
"R2 (train): 1.0\n",
"R2 (test): 1.0\n",
"STD (train): 0.0\n",
"STD (test): 0.0\n",
"----------------------------------------\n",
"Model: random_forest\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"MSE (train): 0.0\n",
"MSE (test): 0.0\n",
"MAE (train): 0.0\n",
"MAE (test): 0.0\n",
"R2 (train): 1.0\n",
"R2 (test): 1.0\n",
"STD (train): 0.0\n",
"STD (test): 0.0\n",
"----------------------------------------\n",
"Model: mlp\n",
"MSE (train): 0.06778846153846153\n",
"MSE (test): 0.12692307692307692\n",
"MAE (train): 0.06778846153846153\n",
"MAE (test): 0.12692307692307692\n",
"R2 (train): 0.6070523702400588\n",
"R2 (test): 0.30107526881720437\n",
"STD (train): 0.2521427220700598\n",
"STD (test): 0.3370600353877945\n",
"----------------------------------------\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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 import metrics\n",
"from sklearn.pipeline import Pipeline\n",
"\n",
"if 'class_models' not in locals():\n",
" raise ValueError(\"class_models is not defined\")\n",
"if 'X_train' not in locals() or 'X_test' not in locals() or 'y_train' not in locals() or 'y_test' not in locals():\n",
" raise ValueError(\"Train/test data is not defined\")\n",
"\n",
"\n",
"y_train = np.ravel(y_train) \n",
"y_test = np.ravel(y_test) \n",
"\n",
"results = []\n",
"\n",
"for model_name in class_models.keys():\n",
" print(f\"Model: {model_name}\")\n",
" \n",
" model = class_models[model_name][\"model\"]\n",
" \n",
" model_pipeline = Pipeline([(\"pipeline\", pipeline_end), (\"model\", model)])\n",
" \n",
" model_pipeline.fit(X_train, y_train)\n",
"\n",
" y_train_predict = model_pipeline.predict(X_train)\n",
" y_test_predict = model_pipeline.predict(X_test)\n",
"\n",
" class_models[model_name][\"pipeline\"] = model_pipeline\n",
" class_models[model_name][\"preds\"] = y_test_predict\n",
"\n",
" class_models[model_name][\"MSE_train\"] = metrics.mean_squared_error(y_train, y_train_predict)\n",
" class_models[model_name][\"MSE_test\"] = metrics.mean_squared_error(y_test, y_test_predict)\n",
" class_models[model_name][\"MAE_train\"] = metrics.mean_absolute_error(y_train, y_train_predict)\n",
" class_models[model_name][\"MAE_test\"] = metrics.mean_absolute_error(y_test, y_test_predict)\n",
" class_models[model_name][\"R2_train\"] = metrics.r2_score(y_train, y_train_predict)\n",
" class_models[model_name][\"R2_test\"] = metrics.r2_score(y_test, y_test_predict)\n",
"\n",
" class_models[model_name][\"STD_train\"] = np.std(y_train - y_train_predict)\n",
" class_models[model_name][\"STD_test\"] = np.std(y_test - y_test_predict)\n",
"\n",
" print(f\"MSE (train): {class_models[model_name]['MSE_train']}\")\n",
" print(f\"MSE (test): {class_models[model_name]['MSE_test']}\")\n",
" print(f\"MAE (train): {class_models[model_name]['MAE_train']}\")\n",
" print(f\"MAE (test): {class_models[model_name]['MAE_test']}\")\n",
" print(f\"R2 (train): {class_models[model_name]['R2_train']}\")\n",
" print(f\"R2 (test): {class_models[model_name]['R2_test']}\")\n",
" print(f\"STD (train): {class_models[model_name]['STD_train']}\")\n",
" print(f\"STD (test): {class_models[model_name]['STD_test']}\")\n",
" print(\"-\" * 40) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Пример использования обученной модели (конвейера регрессии) для предсказания"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: RandomForest\n",
"MSE (train): 24.028673442957558\n",
"MSE (test): 68.96006650623248\n",
"MAE (train): 1.548185999451937\n",
"MAE (test): 3.372747412240537\n",
"R2 (train): 0.8231149198653249\n",
"R2 (test): -1.9013866015383956\n",
"----------------------------------------\n",
"Прогнозируемое чистое состояние: 1.3689999999999998\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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",
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:242: UserWarning: Found unknown categories in columns [0, 1, 2] during transform. These unknown categories will be encoded as all zeros\n",
" warnings.warn(\n"
]
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn import metrics\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.ensemble import RandomForestRegressor \n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.compose import ColumnTransformer\n",
"from sklearn.impute import SimpleImputer\n",
"from sklearn.preprocessing import OneHotEncoder\n",
"\n",
"data = pd.read_csv(\"..//static//csv//Forbes Billionaires.csv\") \n",
"\n",
"average_networth = data['Networth'].mean()\n",
"data['above_average_networth'] = (data['Networth'] > average_networth).astype(int) \n",
"\n",
"X = data.drop('Networth', axis=1) \n",
"y = data['Networth']\n",
"\n",
"class_models = {\n",
" \"RandomForest\": {\n",
" \"model\": RandomForestRegressor(n_estimators=100, random_state=42),\n",
" }\n",
"}\n",
"\n",
"num_columns = ['Age']\n",
"cat_columns = ['Country', 'Source', 'Industry']\n",
"\n",
"num_transformer = Pipeline(steps=[\n",
" ('imputer', SimpleImputer(strategy='median')),\n",
" ('scaler', StandardScaler())\n",
"])\n",
"\n",
"cat_transformer = Pipeline(steps=[\n",
" ('imputer', SimpleImputer(strategy='constant', fill_value='unknown')),\n",
" ('onehot', OneHotEncoder(handle_unknown='ignore', sparse_output=False, drop=\"first\"))\n",
"])\n",
"\n",
"preprocessor = ColumnTransformer(\n",
" transformers=[\n",
" ('num', num_transformer, num_columns),\n",
" ('cat', cat_transformer, cat_columns)\n",
" ])\n",
"\n",
"pipeline_end = Pipeline(steps=[\n",
" ('preprocessor', preprocessor),\n",
"])\n",
"\n",
"results = []\n",
"\n",
"for model_name in class_models.keys():\n",
" print(f\"Model: {model_name}\")\n",
"\n",
" model = class_models[model_name][\"model\"]\n",
" model_pipeline = Pipeline(steps=[\n",
" ('preprocessor', preprocessor),\n",
" ('model', model)\n",
" ])\n",
"\n",
" X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
"\n",
" model_pipeline.fit(X_train, y_train)\n",
"\n",
" y_train_predict = model_pipeline.predict(X_train)\n",
" y_test_predict = model_pipeline.predict(X_test)\n",
"\n",
" class_models[model_name][\"preds\"] = y_test_predict\n",
"\n",
" class_models[model_name][\"MSE_train\"] = metrics.mean_squared_error(y_train, y_train_predict)\n",
" class_models[model_name][\"MSE_test\"] = metrics.mean_squared_error(y_test, y_test_predict)\n",
" class_models[model_name][\"MAE_train\"] = metrics.mean_absolute_error(y_train, y_train_predict)\n",
" class_models[model_name][\"MAE_test\"] = metrics.mean_absolute_error(y_test, y_test_predict)\n",
" class_models[model_name][\"R2_train\"] = metrics.r2_score(y_train, y_train_predict)\n",
" class_models[model_name][\"R2_test\"] = metrics.r2_score(y_test, y_test_predict)\n",
"\n",
" print(f\"MSE (train): {class_models[model_name]['MSE_train']}\")\n",
" print(f\"MSE (test): {class_models[model_name]['MSE_test']}\")\n",
" print(f\"MAE (train): {class_models[model_name]['MAE_train']}\")\n",
" print(f\"MAE (test): {class_models[model_name]['MAE_test']}\")\n",
" print(f\"R2 (train): {class_models[model_name]['R2_train']}\")\n",
" print(f\"R2 (test): {class_models[model_name]['R2_test']}\")\n",
" print(\"-\" * 40)\n",
"\n",
"new_billionaire_data = pd.DataFrame({\n",
" 'Age': [50],\n",
" 'Country': ['USA'],\n",
" 'Source': ['Self Made'], \n",
" 'Industry': ['Technology'], \n",
"})\n",
"\n",
"predicted_networth = model_pipeline.predict(new_billionaire_data)\n",
"print(f\"Прогнозируемое чистое состояние: {predicted_networth[0]}\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Подбор гиперпараметров методом поиска по сетке"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\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": [
"Fitting 3 folds for each of 36 candidates, totalling 108 fits\n",
"Лучшие параметры: {'max_depth': 10, 'min_samples_split': 2, 'n_estimators': 200}\n",
"Лучший результат (MSE): 5.631552208172496\n"
]
}
],
"source": [
"from sklearn.pipeline import Pipeline\n",
"from sklearn.model_selection import train_test_split, GridSearchCV\n",
"from sklearn.ensemble import RandomForestRegressor\n",
"from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder\n",
"from sklearn.compose import ColumnTransformer\n",
"from sklearn.impute import SimpleImputer\n",
"\n",
"df = df.dropna()\n",
"target = df['Networth']\n",
"\n",
"features = df.drop(columns=['Networth'])\n",
"\n",
"features = features.drop(columns=['Name'])\n",
"\n",
"num_columns = features.select_dtypes(include=['number']).columns\n",
"cat_columns = features.select_dtypes(include=['object']).columns\n",
"\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",
"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",
"features_preprocessing = ColumnTransformer(\n",
" verbose_feature_names_out=False,\n",
" transformers=[\n",
" (\"preprocessing_num\", preprocessing_num, num_columns),\n",
" (\"preprocessing_cat\", preprocessing_cat, cat_columns),\n",
" ],\n",
" remainder=\"passthrough\"\n",
")\n",
"\n",
"pipeline_end = Pipeline(\n",
" [\n",
" (\"features_preprocessing\", features_preprocessing),\n",
" ]\n",
")\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)\n",
"\n",
"X_train_processed = pipeline_end.fit_transform(X_train)\n",
"X_test_processed = pipeline_end.transform(X_test)\n",
"\n",
"model = RandomForestRegressor()\n",
"\n",
"param_grid = {\n",
" 'n_estimators': [50, 100, 200],\n",
" 'max_depth': [None, 10, 20, 30], \n",
" 'min_samples_split': [2, 5, 10] \n",
"}\n",
"\n",
"grid_search = GridSearchCV(estimator=model, param_grid=param_grid,\n",
" scoring='neg_mean_squared_error', cv=3, n_jobs=-1, verbose=2)\n",
"\n",
"grid_search.fit(X_train_processed, y_train)\n",
"\n",
"print(\"Лучшие параметры:\", grid_search.best_params_)\n",
"print(\"Лучший результат (MSE):\", -grid_search.best_score_) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Обучение модели с
]
},
{
"cell_type": "code",
2024-11-22 21:52:24 +04:00
"execution_count": null,
2024-11-22 21:51:48 +04:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\goldfest\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:242: UserWarning: Found unknown categories in columns [0, 1, 2] during transform. These unknown categories will be encoded as all zeros\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Fitting 3 folds for each of 36 candidates, totalling 108 fits\n",
"Старые параметры: {'max_depth': 30, 'min_samples_split': 2, 'n_estimators': 50}\n",
"Лучший результат (MSE) на старых параметрах: 76.4137021557455\n",
"\n",
"Новые параметры: {'max_depth': 10, 'min_samples_split': 10, 'n_estimators': 200}\n",
"Лучший результат (MSE) на новых параметрах: 180.57283215031268\n",
"Среднеквадратическая ошибка (MSE) на тестовых данных: 507.05822479642404\n",
"Корень среднеквадратичной ошибки (RMSE) на тестовых данных: 22.517953388272748\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x500 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn import metrics\n",
"from sklearn.ensemble import RandomForestRegressor\n",
"from sklearn.model_selection import train_test_split, GridSearchCV\n",
"from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder\n",
"from sklearn.compose import ColumnTransformer\n",
"from sklearn.impute import SimpleImputer\n",
"from sklearn.pipeline import Pipeline\n",
"import matplotlib.pyplot as plt\n",
"\n",
"df = pd.read_csv(\"..//static//csv//Forbes Billionaires.csv\").head(100)\n",
"\n",
"df = df.dropna()\n",
"target = df['Networth']\n",
"\n",
"features = df.drop(columns=['Networth'])\n",
"\n",
"features = features.drop(columns=['Name'])\n",
"num_columns = features.select_dtypes(include=['number']).columns\n",
"cat_columns = features.select_dtypes(include=['object']).columns\n",
"\n",
2024-11-22 21:52:24 +04:00
"num_imputer = SimpleImputer(strategy=\"median\") \n",
2024-11-22 21:51:48 +04:00
"num_scaler = StandardScaler()\n",
"preprocessing_num = Pipeline(\n",
" [\n",
" (\"imputer\", num_imputer),\n",
" (\"scaler\", num_scaler),\n",
" ]\n",
")\n",
"\n",
2024-11-22 21:52:24 +04:00
"cat_imputer = SimpleImputer(strategy=\"constant\", fill_value=\"unknown\") \n",
2024-11-22 21:51:48 +04:00
"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",
"features_preprocessing = ColumnTransformer(\n",
" verbose_feature_names_out=False,\n",
" transformers=[\n",
" (\"preprocessing_num\", preprocessing_num, num_columns),\n",
" (\"preprocessing_cat\", preprocessing_cat, cat_columns),\n",
" ],\n",
" remainder=\"passthrough\"\n",
")\n",
"\n",
"pipeline_end = Pipeline(\n",
" [\n",
" (\"features_preprocessing\", features_preprocessing),\n",
" ]\n",
")\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)\n",
"\n",
"X_train_processed = pipeline_end.fit_transform(X_train)\n",
"X_test_processed = pipeline_end.transform(X_test)\n",
"\n",
"old_param_grid = {\n",
2024-11-22 21:52:24 +04:00
" 'n_estimators': [50, 100, 200], \n",
" 'max_depth': [None, 10, 20, 30],\n",
" 'min_samples_split': [2, 5, 10] \n",
2024-11-22 21:51:48 +04:00
"}\n",
"\n",
"old_grid_search = GridSearchCV(estimator=RandomForestRegressor(), \n",
" param_grid=old_param_grid,\n",
" scoring='neg_mean_squared_error', cv=3, n_jobs=-1, verbose=2)\n",
"\n",
"old_grid_search.fit(X_train_processed, y_train)\n",
"old_best_params = old_grid_search.best_params_\n",
2024-11-22 21:52:24 +04:00
"old_best_mse = -old_grid_search.best_score_ \n",
2024-11-22 21:51:48 +04:00
"new_param_grid = {\n",
" 'n_estimators': [200],\n",
" 'max_depth': [10],\n",
" 'min_samples_split': [10]\n",
"}\n",
"\n",
"new_grid_search = GridSearchCV(estimator=RandomForestRegressor(), \n",
" param_grid=new_param_grid,\n",
" scoring='neg_mean_squared_error', cv=2)\n",
"\n",
"new_grid_search.fit(X_train_processed, y_train)\n",
"\n",
2024-11-22 21:52:24 +04:00
"# Результаты подбора для новых параметров\n",
2024-11-22 21:51:48 +04:00
"new_best_params = new_grid_search.best_params_\n",
"new_best_mse = -new_grid_search.best_score_ # Меняем знак, так как берем отрицательное значение MSE\n",
"\n",
2024-11-22 21:52:24 +04:00
"# Обучение модели с
2024-11-22 21:51:48 +04:00
"model_best = RandomForestRegressor(**new_best_params)\n",
"model_best.fit(X_train_processed, y_train)\n",
"\n",
"# Прогнозирование на тестовой выборке\n",
"y_pred = model_best.predict(X_test_processed)\n",
"\n",
"# Оценка производительности модели\n",
"mse = metrics.mean_squared_error(y_test, y_pred)\n",
"rmse = np.sqrt(mse)\n",
"\n",
"# Вывод результатов\n",
"print(\"Старые параметры:\", old_best_params)\n",
"print(\"Лучший результат (MSE) на старых параметрах:\", old_best_mse)\n",
"print(\"\\nН о е
"print(\"Лучший результат (MSE) на новых параметрах:\", new_best_mse)\n",
"print(\"Среднеквадратическая ошибка (MSE) на тестовых данных:\", mse)\n",
"print(\"Корень среднеквадратичной ошибки (RMSE) на тестовых данных:\", rmse)\n",
"\n",
"model_old = RandomForestRegressor(**old_best_params)\n",
"model_old.fit(X_train_processed, y_train)\n",
"\n",
"y_pred_old = model_old.predict(X_test_processed)\n",
"\n",
"# Визуализация ошибок\n",
"plt.figure(figsize=(10, 5))\n",
"plt.plot(y_test.values, label='Реальные значения', marker='o', linestyle='-', color='black')\n",
"plt.plot(y_pred_old, label='Предсказанные значения (старые параметры)', marker='x', linestyle='--', color='blue')\n",
"plt.plot(y_pred, label='Предсказанные значения (новые параметры)', marker='s', linestyle='--', color='orange')\n",
"plt.xlabel('Объекты')\n",
"plt.ylabel('Значения')\n",
"plt.title('Сравнение реальных и предсказанных значений')\n",
"plt.legend()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Модель, обученная на новых параметрах, показала худший результат (MSE) на кросс-валидации, что указывает на е е с о о б е
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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
}
