{ "cells": [ { "cell_type": "markdown", "id": "a0f5028a", "metadata": {}, "source": [ "Определить две бизнес-цели для набора данных по Вашему варианту задания. " ] }, { "cell_type": "markdown", "id": "3baf711b", "metadata": {}, "source": [ "1. Увеличить средний балл по математике среди студентов групп льготников (те, кто на льготном питании, чьи родители без высшего образования).\n", "2. Снизить процент студентов, которые бросают учебу и прогуливают после первого семестра." ] }, { "cell_type": "markdown", "id": "e71acec5", "metadata": {}, "source": [ "Определить цели технического проекта для каждой выделенной ранее бизнес\n", "цели. " ] }, { "cell_type": "markdown", "id": "b806a073", "metadata": {}, "source": [ "1.1 Разработать систему прогнозирования и выявления студентов группы \"риска\" по низкой успеваемости в начале семестра.\n", "\n", "2.1 Разработать систему раннего предупреждения о риске снижения успеваемости" ] }, { "cell_type": "markdown", "id": "5d8f79d4", "metadata": {}, "source": [ "Сбор и подготовка данных" ] }, { "cell_type": "code", "execution_count": null, "id": "8b2bfb04", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " gender race/ethnicity parental level of education lunch \\\n", "0 female group B bachelor's degree standard \n", "1 female group C some college standard \n", "2 female group B master's degree standard \n", "3 male group A associate's degree free/reduced \n", "4 male group C some college standard \n", "\n", " test preparation course math score reading score writing score \n", "0 none 72 72 74 \n", "1 completed 69 90 88 \n", "2 none 90 95 93 \n", "3 none 47 57 44 \n", "4 none 76 78 75 \n", "gender 0\n", "race/ethnicity 0\n", "parental level of education 0\n", "lunch 0\n", "test preparation course 0\n", "math score 0\n", "reading score 0\n", "writing score 0\n", "dtype: int64\n" ] } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "\n", "# Загрузка датасета\n", "data = pd.read_csv('data_3/StudentsPerformance.csv')\n", "\n", "print(data.head())\n", "\n", "print(data.isnull().sum())\n" ] }, { "cell_type": "markdown", "id": "f87fe2d1", "metadata": {}, "source": [ "Выполнить разбиение каждого набора данных на обучающую, контрольную и \n", "тестовую выборки для устранения проблемы просачивания данных. " ] }, { "cell_type": "code", "execution_count": null, "id": "31c31c74", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Обучающая: 700 (70.0%)\n", "Валидационная: 100 (10.0%)\n", "Тестовая: 200 (20.0%)\n" ] } ], "source": [ "from sklearn.model_selection import train_test_split\n", "\n", "X = data.drop('math score', axis=1)\n", "y = data['math score']\n", "\n", "X_train, X_temp, y_train, y_temp = train_test_split(\n", " X, y, test_size=0.3, random_state=42\n", ")\n", "\n", "X_val, X_test, y_val, y_test = train_test_split(\n", " X_temp, y_temp, test_size=0.666, random_state=42\n", ")\n", "\n", "print(f\"Обучающая: {X_train.shape[0]} ({X_train.shape[0]/len(data)*100:.1f}%)\")\n", "print(f\"Валидационная: {X_val.shape[0]} ({X_val.shape[0]/len(data)*100:.1f}%)\")\n", "print(f\"Тестовая: {X_test.shape[0]} ({X_test.shape[0]/len(data)*100:.1f}%)\")" ] }, { "cell_type": "code", "execution_count": null, "id": "67e27386", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "=== ОЦЕНКА СБАЛАНСИРОВАННОСТИ ВЫБОРОК ===\n", "\n", "ОБУЧАЮЩАЯ ВЫБОРКА:\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Распределение целевой переменной:\n", "math_pass\n", "0 409\n", "1 291\n", "Name: count, dtype: int64\n", "Коэффициент сбалансированности: 0.711\n", "\n", "ВАЛИДАЦИОННАЯ ВЫБОРКА:\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Распределение целевой переменной:\n", "math_pass\n", "0 61\n", "1 39\n", "Name: count, dtype: int64\n", "Коэффициент сбалансированности: 0.639\n", "\n", "ТЕСТОВАЯ ВЫБОРКА:\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Распределение целевой переменной:\n", "math_pass\n", "0 121\n", "1 79\n", "Name: count, dtype: int64\n", "Коэффициент сбалансированности: 0.653\n", "\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "=== ПРОВЕРКА НЕОБХОДИМОСТИ АУГМЕНТАЦИИ ===\n", "Обучающая выборка: 0.711 >= 0.5 - сбалансирована\n", "Валидационная выборка: 0.639 >= 0.5 - сбалансирована\n", "Тестовая выборка: 0.653 - НЕ АУГМЕНТИРУЕТСЯ\n" ] } ], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "plt.style.use('default')\n", "sns.set_palette(\"husl\")\n", "\n", "def assess_balance_with_plot(dataset, target_column, dataset_name):\n", " value_counts = dataset[target_column].value_counts()\n", " balance_ratio = value_counts.min() / value_counts.max()\n", " \n", " # Столбчатая диаграмма\n", " plt.figure(figsize=(8, 6))\n", " bars = plt.bar(['Не сдал (0)', 'Сдал (1)'], value_counts.values, color='skyblue')\n", " plt.title(f'{dataset_name}\\nКоэффициент сбалансированности: {balance_ratio:.3f}')\n", " plt.xlabel('Класс')\n", " plt.ylabel('Количество образцов')\n", " \n", " # Добавляем значения на столбцы\n", " for bar in bars:\n", " height = bar.get_height()\n", " plt.text(bar.get_x() + bar.get_width()/2., height,\n", " f'{int(height)}', ha='center', va='bottom')\n", " \n", " plt.tight_layout()\n", " plt.show()\n", " \n", " print(f\"Распределение целевой переменной:\")\n", " print(value_counts)\n", " print(f\"Коэффициент сбалансированности: {balance_ratio:.3f}\\n\")\n", " return balance_ratio\n", "\n", "# Оценка сбалансированности для каждой выборки\n", "print(\"=== ОЦЕНКА СБАЛАНСИРОВАННОСТИ ВЫБОРОК ===\\n\")\n", "\n", "# Создаем полные датафреймы\n", "train_data = X_train.copy()\n", "train_data['math_score'] = y_train\n", "val_data = X_val.copy()\n", "val_data['math_score'] = y_val\n", "test_data = X_test.copy()\n", "test_data['math_score'] = y_test\n", "\n", "# Бинаризуем целевую переменную для классификации (порог 70 баллов)\n", "for data in [train_data, val_data, test_data]:\n", " data['math_pass'] = (data['math_score'] >= 70).astype(int)\n", "\n", "print(\"ОБУЧАЮЩАЯ ВЫБОРКА:\")\n", "balance_train = assess_balance_with_plot(train_data, 'math_pass', 'Обучающая выборка')\n", "\n", "print(\"ВАЛИДАЦИОННАЯ ВЫБОРКА:\")\n", "balance_val = assess_balance_with_plot(val_data, 'math_pass', 'Валидационная выборка')\n", "\n", "print(\"ТЕСТОВАЯ ВЫБОРКА:\")\n", "balance_test = assess_balance_with_plot(test_data, 'math_pass', 'Тестовая выборка')\n", "\n", "# Сравнительная диаграмма сбалансированности всех выборок\n", "fig, ax = plt.subplots(figsize=(10, 6))\n", "datasets = ['Обучающая', 'Валидационная', 'Тестовая']\n", "balance_scores = [balance_train, balance_val, balance_test]\n", "\n", "bars = ax.bar(datasets, balance_scores, color=['skyblue', 'lightcoral', 'lightgreen'])\n", "ax.set_ylabel('Коэффициент сбалансированности')\n", "ax.set_title('Сравнение сбалансированности всех выборок')\n", "ax.set_ylim(0, 1)\n", "\n", "# Добавляем значения на столбцы\n", "for bar, score in zip(bars, balance_scores):\n", " height = bar.get_height()\n", " ax.text(bar.get_x() + bar.get_width()/2., height + 0.01,\n", " f'{score:.3f}', ha='center', va='bottom')\n", "\n", "plt.tight_layout()\n", "plt.show()\n", "\n" ] }, { "cell_type": "markdown", "id": "fa028656", "metadata": {}, "source": [ "Выполнить процесс конструирования признаков для решения каждой из двух \n", "задач. Задача определяется совокупностью бизнес-цели и цели технического \n", "проекта. " ] }, { "cell_type": "markdown", "id": "c2c231ea", "metadata": {}, "source": [ "При конструировании признаков обязательно необходимо выполнить: унитарное \n", "кодирование категориальных признаков (one-hot encoding), дискретизацию \n", "числовых признаков, «ручной» синтез признаков, масштабирование признаков на \n", "основе нормировки и стандартизации. " ] }, { "cell_type": "code", "execution_count": null, "id": "111eb5de", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "=== КОНСТРУИРОВАНИЕ ПРИЗНАКОВ ДЛЯ ДВУХ ЗАДАЧ ===\n", "\n", "ЗАДАЧА 1: ПРОГНОЗИРОВАНИЕ БАЛЛА ПО МАТЕМАТИКЕ (РЕГРЕССИЯ)\n", "\n", "1. КОДИРОВАНИЕ КАТЕГОРИАЛЬНЫХ ПРИЗНАКОВ\n", "После One-Hot Encoding: 15 признаков\n", "Пример закодированных признаков:\n", " gender_male\n", "0 False\n", "1 False\n", "2 False\n", "\n", "2. ДИСКРЕТИЗАЦИЯ ЧИСЛОВЫХ ПРИЗНАКОВ\n", "После дискретизации числовых признаков:\n", " reading_cat_low reading_cat_medium reading_cat_high \\\n", "0 False False True \n", "1 False False False \n", "2 False False False \n", "\n", " reading_cat_very_high writing_cat_weak writing_cat_good \\\n", "0 False False True \n", "1 True False False \n", "2 True False False \n", "\n", " writing_cat_excellent \n", "0 False \n", "1 True \n", "2 True \n", "\n", "3. РУЧНОЙ СИНТЕЗ ПРИЗНАКОВ\n", "Созданные синтетические признаки:\n", " total_academic_potential reading_math_gap score_consistency \\\n", "0 72.666667 0 1.154701 \n", "1 82.333333 21 11.590226 \n", "2 92.666667 5 2.516611 \n", "\n", " all_subjects_above_70 \n", "0 1 \n", "1 0 \n", "2 1 \n", "\n", "4. МАСШТАБИРОВАНИЕ ПРИЗНАКОВ\n", "Стандартизированные числовые признаки (первые 3 строки):\n", " reading score writing score total_academic_potential reading_math_gap \\\n", "0 0.193999 0.391492 0.343574 -0.342210 \n", "1 1.427476 1.313269 1.021927 1.991042 \n", "2 1.770109 1.642475 1.747064 0.213326 \n", "\n", " score_consistency \n", "0 -1.427953 \n", "1 2.292752 \n", "2 -0.942374 \n", "\n", "Итоговый набор признаков для Задачи 1: 25 признаков\n", "ЗАДАЧА 2: КЛАССИФИКАЦИЯ СТУДЕНТОВ (СДАЛ/НЕ СДАЛ)\n", "\n", "1. ONE-HOT ENCODING КАТЕГОРИАЛЬНЫХ ПРИЗНАКОВ\n", "После One-Hot Encoding: 14 признаков\n", "\n", "2. ДИСКРЕТИЗАЦИЯ ЧИСЛОВЫХ ПРИЗНАКОВ\n", "Дискретизация по квантилям завершена\n", "\n", "3. РУЧНОЙ СИНТЕЗ ПРИЗНАКОВ ДЛЯ КЛАССИФИКАЦИИ\n", "Синтетические признаки для классификации созданы\n", "\n", "4. МАСШТАБИРОВАНИЕ ПРИЗНАКОВ\n", "Нормировка числовых признаков завершена\n", "\n", "Итоговый набор признаков для Задачи 2: 27 признаков\n" ] } ], "source": [ "import pandas as pd\n", "from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder\n", "from sklearn.compose import ColumnTransformer\n", "\n", "# Задача 1: Прогнозирование успеваемости по математике (регрессия)\n", "data_task1 = data.copy()\n", "\n", "# Задача 2: Классификация студентов на сдавших/не сдавших (бинарная классификация)\n", "data_task2 = data.copy()\n", "data_task2['math_pass'] = (data_task2['math score'] >= 70).astype(int)\n", "\n", "# 1. КОДИРОВАНИЕ КАТЕГОРИАЛЬНЫХ ПРИЗНАКОВ\n", "print(\"1. КОДИРОВАНИЕ КАТЕГОРИАЛЬНЫХ ПРИЗНАКОВ\")\n", "\n", "categorical_features = ['gender', 'race/ethnicity', 'parental level of education', \n", " 'lunch', 'test preparation course']\n", "\n", "data_task1_encoded = pd.get_dummies(data_task1, columns=categorical_features, \n", " prefix=categorical_features, drop_first=True)\n", "\n", "print(f\"После One-Hot Encoding: {data_task1_encoded.shape[1]} признаков\")\n", "print(\"Пример закодированных признаков:\")\n", "print(data_task1_encoded.filter(like='gender_').head(3))\n", "\n", "# 2. ДИСКРЕТИЗАЦИЯ ЧИСЛОВЫХ ПРИЗНАКОВ\n", "print(\"\\n2. ДИСКРЕТИЗАЦИЯ ЧИСЛОВЫХ ПРИЗНАКОВ\")\n", "\n", "data_task1_encoded['reading_score_bins'] = pd.cut(data_task1_encoded['reading score'], \n", " bins=4, labels=['low', 'medium', 'high', 'very_high'])\n", "\n", "data_task1_encoded['writing_score_bins'] = pd.cut(data_task1_encoded['writing score'],\n", " bins=[0, 60, 80, 100], \n", " labels=['weak', 'good', 'excellent'])\n", "\n", "data_task1_encoded = pd.get_dummies(data_task1_encoded, \n", " columns=['reading_score_bins', 'writing_score_bins'],\n", " prefix=['reading_cat', 'writing_cat'])\n", "\n", "print(\"После дискретизации числовых признаков:\")\n", "print(data_task1_encoded.filter(like='_cat_').head(3))\n", "\n", "data_task1_encoded['total_academic_potential'] = (\n", " data_task1_encoded['math score'] + \n", " data_task1_encoded['reading score'] + \n", " data_task1_encoded['writing score']\n", ") / 3\n", "\n", "#Разрыв между чтением и математикой (показывает склонности)\n", "data_task1_encoded['reading_math_gap'] = (\n", " data_task1_encoded['reading score'] - data_task1_encoded['math score']\n", ")\n", "\n", "# Сбалансированность успеваемости (стандартное отклонение по предметам)\n", "data_task1_encoded['score_consistency'] = data_task1_encoded[['math score', 'reading score', 'writing score']].std(axis=1)\n", "\n", "# Бинарный признак - все предметы выше порога\n", "data_task1_encoded['all_subjects_above_70'] = (\n", " (data_task1_encoded['math score'] > 70) & \n", " (data_task1_encoded['reading score'] > 70) & \n", " (data_task1_encoded['writing score'] > 70)\n", ").astype(int)\n", "\n", "print(\"Созданные синтетические признаки:\")\n", "print(data_task1_encoded[['total_academic_potential', 'reading_math_gap', \n", " 'score_consistency', 'all_subjects_above_70']].head(3))\n", "\n", "# Масштабирование\n", "# Разделяем признаки для разных типов масштабирования\n", "numerical_features = ['reading score', 'writing score', 'total_academic_potential', \n", " 'reading_math_gap', 'score_consistency']\n", "\n", "binary_features = [col for col in data_task1_encoded.columns \n", " if col.startswith(tuple(categorical_features)) or \n", " col == 'all_subjects_above_70']\n", "\n", "# Стандартизация числовых признаков\n", "scaler_standard = StandardScaler()\n", "data_task1_encoded[numerical_features] = scaler_standard.fit_transform(data_task1_encoded[numerical_features])\n", "\n", "print(\"Стандартизированные числовые признаки (первые 3 строки):\")\n", "print(data_task1_encoded[numerical_features].head(3))\n", "\n", "# Теперь создаем финальный набор признаков, удаляя целевую переменную\n", "X_task1 = data_task1_encoded.drop(['math score'], axis=1)\n", "target_task1 = data_task1_encoded['math score']\n", "\n", "print(f\"\\nИтоговый набор признаков для Задачи 1: {X_task1.shape[1]} признаков\")\n", "\n", "# 1. УНИТАРНОЕ КОДИРОВАНИЕ КАТЕГОРИАЛЬНЫХ ПРИЗНАКОВ\n", "print(\"1. ONE-HOT ENCODING КАТЕГОРИАЛЬНЫХ ПРИЗНАКОВ\")\n", "\n", "# Используем ColumnTransformer для более структурированного подхода\n", "categorical_features_task2 = ['gender', 'race/ethnicity', 'parental level of education', \n", " 'lunch', 'test preparation course']\n", "\n", "# Создаем трансформер для категориальных признаков\n", "preprocessor_task2 = ColumnTransformer(\n", " transformers=[\n", " ('cat', OneHotEncoder(drop='first'), categorical_features_task2)\n", " ],\n", " remainder='passthrough'\n", ")\n", "\n", "# Применяем трансформацию\n", "X_task2_temp = data_task2.drop(['math_pass', 'math score'], axis=1)\n", "y_task2 = data_task2['math_pass']\n", "\n", "X_task2_encoded = preprocessor_task2.fit_transform(X_task2_temp)\n", "\n", "# Получаем имена признаков после трансформации\n", "feature_names = (preprocessor_task2.named_transformers_['cat']\n", " .get_feature_names_out(categorical_features_task2))\n", "feature_names = list(feature_names) + ['reading score', 'writing score']\n", "\n", "X_task2 = pd.DataFrame(X_task2_encoded, columns=feature_names)\n", "\n", "print(f\"После One-Hot Encoding: {X_task2.shape[1]} признаков\")\n", "\n", "# 2. ДИСКРЕТИЗАЦИЯ ЧИСЛОВЫХ ПРИЗНАКОВ\n", "\n", "# Для классификации используем бининг по квантилям\n", "X_task2['reading_score_qbin'] = pd.qcut(X_task2['reading score'], q=5, \n", " labels=['q1', 'q2', 'q3', 'q4', 'q5'])\n", "X_task2['writing_score_qbin'] = pd.qcut(X_task2['writing score'], q=5, \n", " labels=['q1', 'q2', 'q3', 'q4', 'q5'])\n", "\n", "# One-Hot для дискретизированных признаков\n", "X_task2 = pd.get_dummies(X_task2, columns=['reading_score_qbin', 'writing_score_qbin'],\n", " prefix=['reading_qbin', 'writing_qbin'])\n", "\n", "print(\"Дискретизация по квантилям завершена\")\n", "\n", "# 3. «РУЧНОЙ» СИНТЕЗ ПРИЗНАКОВ ДЛЯ КЛАССИФИКАЦИИ\n", "print(\"\\n3. РУЧНОЙ СИНТЕЗ ПРИЗНАКОВ ДЛЯ КЛАССИФИКАЦИИ\")\n", "\n", "# Признак 1: Относительная сила в математике по сравнению с другими предметами\n", "X_task2['math_strength_ratio'] = (\n", " X_task2['reading score'] + X_task2['writing score']\n", ") / (2 * 100) # нормализуем\n", "\n", "# Признак 2: Бинарные индикаторы критических уровней\n", "X_task2['reading_above_60'] = (X_task2['reading score'] > 60).astype(int)\n", "X_task2['writing_above_60'] = (X_task2['writing score'] > 60).astype(int)\n", "\n", "# Признак 3: Комбинированный индикатор подготовки\n", "# Получаем столбец с подготовительным курсом\n", "test_prep_col = [col for col in X_task2.columns if 'test preparation course' in col][0]\n", "X_task2['preparation_combo'] = (\n", " X_task2[test_prep_col] + \n", " X_task2['reading_above_60'] + \n", " X_task2['writing_above_60']\n", ")\n", "\n", "# Признак 4: Взвешенная комбинация баллов\n", "X_task2['weighted_academic_score'] = (\n", " 0.5 * X_task2['reading score'] + 0.3 * X_task2['writing score']\n", ")\n", "\n", "print(\"Синтетические признаки для классификации созданы\")\n", "\n", "# 4. МАСШТАБИРОВАНИЕ ПРИЗНАКОВ ДЛЯ КЛАССИФИКАЦИИ\n", "print(\"\\n4. МАСШТАБИРОВАНИЕ ПРИЗНАКОВ\")\n", "\n", "# Разделяем на числовые и бинарные признаки\n", "numerical_features_task2 = ['reading score', 'writing score', 'math_strength_ratio', \n", " 'preparation_combo', 'weighted_academic_score']\n", "\n", "# Нормировка (MinMaxScaler)\n", "scaler_minmax = MinMaxScaler()\n", "X_task2[numerical_features_task2] = scaler_minmax.fit_transform(X_task2[numerical_features_task2])\n", "\n", "print(\"Нормировка числовых признаков завершена\")\n", "\n", "# Удаляем исходные числовые признаки, которые были дискретизированы\n", "X_task2 = X_task2.drop(['reading score', 'writing score'], axis=1)\n", "\n", "print(f\"\\nИтоговый набор признаков для Задачи 2: {X_task2.shape[1]} признаков\")\n", "\n", "# Сохраняем готовые признаки\n", "final_features_task1 = X_task1\n", "final_features_task2 = X_task2\n", "target_task2 = y_task2" ] }, { "cell_type": "markdown", "id": "368ec8b3", "metadata": {}, "source": [ "Выполнить также конструирование признаков с применением фреймворка \n", "Featuretools. " ] }, { "cell_type": "code", "execution_count": null, "id": "32381263", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Данные подготовлены для Featuretools\n", "Связи добавлены\n", "2025-11-08 12:45:06,023 featuretools - WARNING Attempting to add feature which is already present. This is likely a bug.\n", "2025-11-08 12:45:06,024 featuretools - WARNING Attempting to add feature which is already present. This is likely a bug.\n", "2025-11-08 12:45:06,025 featuretools - WARNING Attempting to add feature which is already present. This is likely a bug.\n", "2025-11-08 12:45:06,026 featuretools - WARNING Attempting to add feature which is already present. This is likely a bug.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.max. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"max\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.sum. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"sum\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.min. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"min\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.mean. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"mean\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.std. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"std\" instead.\n", " ).agg(to_agg)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Сгенерировано признаков для регрессии: 55\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\type_sys\\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.\n", " pd.to_datetime(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\woodwork\\logical_types.py:841: FutureWarning: The behavior of Series.replace (and DataFrame.replace) with CategoricalDtype is deprecated. In a future version, replace will only be used for cases that preserve the categories. To change the categories, use ser.cat.rename_categories instead.\n", " series = series.replace(ww.config.get_option(\"nan_values\"), np.nan)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\entityset\\entityset.py:724: UserWarning: A Woodwork-initialized DataFrame was provided, so the following parameters were ignored: index\n", " warnings.warn(\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.mean. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"mean\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.std. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"std\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.sum. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"sum\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.std. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"std\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.mean. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"mean\" instead.\n", " ).agg(to_agg)\n", "c:\\Users\\Мария Котова\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:785: FutureWarning: The provided callable is currently using SeriesGroupBy.sum. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"sum\" instead.\n", " ).agg(to_agg)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Подготовка признаков для регрессии:\n", "Удалено константных признаков: 8\n", "Подготовка признаков для классификации:\n", "Удалено константных признаков: 100\n", "Подготовка признаков завершена\n", "\n", "7. МАСШТАБИРОВАНИЕ ЧИСЛОВЫХ ПРИЗНАКОВ\n", "Масштабируем 41 числовых признаков\n", "Масштабируем 142 числовых признаков\n", "\n", "Регрессия (прогноз math score):\n", "- Исходных признаков: 9\n", "- Сгенерировано признаков: 55\n", "- После очистки: 46\n", "- Числовых признаков: 41\n", "- Категориальных признаков: 5\n", "\n", "Классификация (math_pass):\n", "- Исходных признаков: 9\n", "- Сгенерировано признаков: 248\n", "- После очистки: 147\n", "- Числовых признаков: 142\n", "- Категориальных признаков: 5\n" ] } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "import featuretools as ft\n", "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n", "\n", "# Создаем копию данных и преобразуем все категориальные колонки в строки\n", "data_prepared = data.copy()\n", "\n", "# Преобразуем все категориальные колонки в строки\n", "categorical_columns = ['gender', 'race/ethnicity', 'parental level of education', 'lunch', 'test preparation course']\n", "for col in categorical_columns:\n", " data_prepared[col] = data_prepared[col].astype(str)\n", "\n", "# Таблица студентов\n", "students_data = data_prepared.copy()\n", "students_data['student_id'] = range(len(students_data))\n", "\n", "# Таблица групп\n", "group_data = data_prepared[['race/ethnicity']].copy()\n", "group_data = group_data.drop_duplicates().reset_index(drop=True)\n", "group_data['group_id'] = range(len(group_data))\n", "\n", "# Таблица родителей\n", "parent_data = data_prepared[['parental level of education']].copy()\n", "parent_data = parent_data.drop_duplicates().reset_index(drop=True)\n", "parent_data['parent_id'] = range(len(parent_data))\n", "\n", "# Таблица успеваемости (только числовые данные)\n", "performance_data = data_prepared[['math score', 'reading score', 'writing score']].copy()\n", "performance_data['performance_id'] = range(len(performance_data))\n", "performance_data['student_id'] = students_data['student_id']\n", "\n", "# Таблица характеристик\n", "characteristics_data = data_prepared[['gender', 'lunch', 'test preparation course']].copy()\n", "characteristics_data['characteristic_id'] = range(len(characteristics_data))\n", "characteristics_data['student_id'] = students_data['student_id']\n", "\n", "# Добавляем связи\n", "group_mapping = group_data.set_index('race/ethnicity')['group_id'].to_dict()\n", "parent_mapping = parent_data.set_index('parental level of education')['parent_id'].to_dict()\n", "\n", "characteristics_data['group_id'] = 0 # Простое значение для связи\n", "characteristics_data['parent_id'] = 0 # Простое значение для связи\n", "\n", "print(\"Данные подготовлены для Featuretools\")\n", "\n", "es = ft.EntitySet(id=\"students_performance\")\n", "\n", "# Таблица студентов\n", "es = es.add_dataframe(\n", " dataframe_name=\"students\",\n", " dataframe=students_data,\n", " index=\"student_id\"\n", ")\n", "\n", "# Таблица групп\n", "es = es.add_dataframe(\n", " dataframe_name=\"groups\",\n", " dataframe=group_data,\n", " index=\"group_id\"\n", ")\n", "\n", "# Таблица родителей\n", "es = es.add_dataframe(\n", " dataframe_name=\"parents\",\n", " dataframe=parent_data,\n", " index=\"parent_id\"\n", ")\n", "\n", "# Таблица успеваемости\n", "es = es.add_dataframe(\n", " dataframe_name=\"performance\",\n", " dataframe=performance_data,\n", " index=\"performance_id\"\n", ")\n", "\n", "# Таблица характеристик\n", "es = es.add_dataframe(\n", " dataframe_name=\"characteristics\",\n", " dataframe=characteristics_data,\n", " index=\"characteristic_id\"\n", ")\n", "\n", "es = es.add_relationship(\"students\", \"student_id\", \"performance\", \"student_id\")\n", "es = es.add_relationship(\"students\", \"student_id\", \"characteristics\", \"student_id\")\n", "es = es.add_relationship(\"groups\", \"group_id\", \"characteristics\", \"group_id\")\n", "es = es.add_relationship(\"parents\", \"parent_id\", \"characteristics\", \"parent_id\")\n", "\n", "print(\"Связи добавлены\")\n", "\n", "try:\n", " feature_matrix_regression, feature_defs_regression = ft.dfs(\n", " entityset=es,\n", " target_dataframe_name=\"performance\",\n", " agg_primitives=[\"mean\", \"count\", \"sum\", \"std\", \"max\", \"min\"],\n", " trans_primitives=[\"add_numeric\", \"subtract_numeric\"],\n", " max_depth=2,\n", " verbose=False\n", " )\n", " \n", " print(f\"Сгенерировано признаков для регрессии: {len(feature_defs_regression)}\")\n", " \n", "except Exception as e:\n", " print(f\"Ошибка при генерации признаков для регрессии: {e}\")\n", " feature_matrix_regression = performance_data.copy()\n", " feature_defs_regression = []\n", "\n", "# Добавляем целевую переменную для классификации\n", "students_classification = students_data.copy()\n", "students_classification['math_pass'] = (students_classification['math score'] >= 70).astype(int)\n", "\n", "# Создаем новый EntitySet для классификации\n", "es_classification = ft.EntitySet(id=\"students_classification\")\n", "\n", "es_classification = es_classification.add_dataframe(\n", " dataframe_name=\"students\",\n", " dataframe=students_classification,\n", " index=\"student_id\"\n", ")\n", "\n", "es_classification = es_classification.add_dataframe(\n", " dataframe_name=\"groups\",\n", " dataframe=group_data,\n", " index=\"group_id\"\n", ")\n", "\n", "es_classification = es_classification.add_dataframe(\n", " dataframe_name=\"parents\",\n", " dataframe=parent_data,\n", " index=\"parent_id\"\n", ")\n", "\n", "es_classification = es_classification.add_dataframe(\n", " dataframe_name=\"performance\",\n", " dataframe=performance_data,\n", " index=\"performance_id\"\n", ")\n", "\n", "es_classification = es_classification.add_dataframe(\n", " dataframe_name=\"characteristics\",\n", " dataframe=characteristics_data,\n", " index=\"characteristic_id\"\n", ")\n", "\n", "# Добавляем связи\n", "es_classification = es_classification.add_relationship(\"students\", \"student_id\", \"performance\", \"student_id\")\n", "es_classification = es_classification.add_relationship(\"students\", \"student_id\", \"characteristics\", \"student_id\")\n", "es_classification = es_classification.add_relationship(\"groups\", \"group_id\", \"characteristics\", \"group_id\")\n", "es_classification = es_classification.add_relationship(\"parents\", \"parent_id\", \"characteristics\", \"parent_id\")\n", "\n", "try:\n", " feature_matrix_classification, feature_defs_classification = ft.dfs(\n", " entityset=es_classification,\n", " target_dataframe_name=\"students\",\n", " agg_primitives=[\"mean\", \"count\", \"sum\", \"std\"],\n", " trans_primitives=[\"add_numeric\", \"subtract_numeric\"],\n", " max_depth=2,\n", " verbose=False\n", " )\n", " \n", "except Exception as e:\n", " feature_matrix_classification = students_classification.copy()\n", " feature_defs_classification = []\n", "\n", "def safe_prepare_features(feature_matrix, target_column=None):\n", " \"\"\"Безопасная подготовка матрицы признаков\"\"\"\n", " try:\n", " # Преобразуем в DataFrame если нужно\n", " if not isinstance(feature_matrix, pd.DataFrame):\n", " feature_matrix = pd.DataFrame(feature_matrix)\n", " \n", " # Создаем копию и преобразуем все категориальные колонки в строки\n", " feature_matrix_clean = feature_matrix.copy()\n", " \n", " # Преобразуем все нечисловые колонки в строки\n", " for col in feature_matrix_clean.columns:\n", " if feature_matrix_clean[col].dtype == 'object' or feature_matrix_clean[col].dtype.name == 'category':\n", " feature_matrix_clean[col] = feature_matrix_clean[col].astype(str)\n", " \n", " # Заполняем пропущенные значения\n", " feature_matrix_clean = feature_matrix_clean.fillna(0)\n", " \n", " # Удаляем константные столбцы\n", " constant_cols = []\n", " for col in feature_matrix_clean.columns:\n", " try:\n", " if feature_matrix_clean[col].nunique() <= 1:\n", " constant_cols.append(col)\n", " except:\n", " continue\n", " \n", " if constant_cols:\n", " feature_matrix_clean = feature_matrix_clean.drop(columns=constant_cols)\n", " print(f\"Удалено константных признаков: {len(constant_cols)}\")\n", " \n", " # Отделяем целевую переменную\n", " if target_column and target_column in feature_matrix_clean.columns:\n", " X = feature_matrix_clean.drop(columns=[target_column])\n", " y = feature_matrix_clean[target_column]\n", " return X, y\n", " else:\n", " return feature_matrix_clean\n", " \n", " except Exception as e:\n", " print(f\"Ошибка при подготовке признаков: {e}\")\n", " if target_column and hasattr(feature_matrix, 'columns') and target_column in feature_matrix.columns:\n", " return feature_matrix.drop(columns=[target_column]), feature_matrix[target_column]\n", " else:\n", " return feature_matrix\n", "\n", "# Подготовка признаков для регрессии\n", "print(\"Подготовка признаков для регрессии:\")\n", "X_regression, y_regression = safe_prepare_features(feature_matrix_regression, 'math score')\n", "\n", "# Подготовка признаков для классификации\n", "print(\"Подготовка признаков для классификации:\")\n", "X_classification, y_classification = safe_prepare_features(feature_matrix_classification, 'math_pass')\n", "\n", "print(\"\\n7. МАСШТАБИРОВАНИЕ ЧИСЛОВЫХ ПРИЗНАКОВ\")\n", "\n", "def safe_scaling_numeric(X, scaler_type='standard'):\n", " \"\"\"Безопасное масштабирование только числовых признаков\"\"\"\n", " try:\n", " X_scaled = X.copy()\n", " \n", " # Выбираем только числовые колонки\n", " numeric_cols = X_scaled.select_dtypes(include=[np.number]).columns\n", " \n", " if len(numeric_cols) > 0:\n", " print(f\"Масштабируем {len(numeric_cols)} числовых признаков\")\n", " \n", " if scaler_type == 'standard':\n", " scaler = StandardScaler()\n", " else:\n", " scaler = MinMaxScaler()\n", " \n", " # Масштабируем только числовые колонки\n", " X_scaled[numeric_cols] = scaler.fit_transform(X_scaled[numeric_cols])\n", " \n", " return X_scaled\n", " except Exception as e:\n", " print(f\"Ошибка при масштабировании: {e}\")\n", " return X\n", "\n", "X_regression_scaled = safe_scaling_numeric(X_regression, 'standard')\n", "X_classification_scaled = safe_scaling_numeric(X_classification, 'minmax')\n", "\n", "print(f\"\\nРегрессия (прогноз math score):\")\n", "print(f\"- Исходных признаков: {data.shape[1]}\")\n", "print(f\"- Сгенерировано признаков: {len(feature_defs_regression)}\")\n", "print(f\"- После очистки: {X_regression_scaled.shape[1]}\")\n", "print(f\"- Числовых признаков: {X_regression_scaled.select_dtypes(include=[np.number]).shape[1]}\")\n", "print(f\"- Категориальных признаков: {X_regression_scaled.select_dtypes(exclude=[np.number]).shape[1]}\")\n", "\n", "print(f\"\\nКлассификация (math_pass):\")\n", "print(f\"- Исходных признаков: {data.shape[1]}\")\n", "print(f\"- Сгенерировано признаков: {len(feature_defs_classification)}\")\n", "print(f\"- После очистки: {X_classification_scaled.shape[1]}\")\n", "print(f\"- Числовых признаков: {X_classification_scaled.select_dtypes(include=[np.number]).shape[1]}\")\n", "print(f\"- Категориальных признаков: {X_classification_scaled.select_dtypes(exclude=[np.number]).shape[1]}\")\n", "\n", "# Сохраняем финальные признаки\n", "final_features_regression = X_regression_scaled\n", "final_features_classification = X_classification_scaled" ] }, { "cell_type": "markdown", "id": "0882120f", "metadata": {}, "source": [ "Оценить качество каждого набора признаков по следующим критериям:предсказательная способность, скорость вычисления, надежность, корреляция и цельность. " ] }, { "cell_type": "code", "execution_count": null, "id": "9a34cbe5", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "=== ОЦЕНКА ДЛЯ РЕГРЕССИИ (MATH SCORE) ===\n", "\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "from sklearn.ensemble import RandomForestRegressor, RandomForestClassifier\n", "from sklearn.model_selection import cross_val_score\n", "from sklearn.preprocessing import LabelEncoder\n", "import time\n", "import warnings\n", "warnings.filterwarnings('ignore')\n", "\n", "def prepare_features(X):\n", " \"\"\"Подготовка признаков для оценки\"\"\"\n", " X_prep = X.copy()\n", " for col in X_prep.select_dtypes(include=['object', 'category']).columns:\n", " le = LabelEncoder()\n", " X_prep[col] = le.fit_transform(X_prep[col].astype(str))\n", " return X_prep.fillna(0)\n", "\n", "def evaluate_predictive_power(X, y, problem_type):\n", " \"\"\"1. Предсказательная способность\"\"\"\n", " X_prep = prepare_features(X)\n", " \n", " start_time = time.time()\n", " if problem_type == 'regression':\n", " model = RandomForestRegressor(n_estimators=50, random_state=42)\n", " scores = cross_val_score(model, X_prep, y, cv=5, scoring='neg_mean_squared_error')\n", " score = -scores.mean()\n", " else:\n", " model = RandomForestClassifier(n_estimators=50, random_state=42)\n", " scores = cross_val_score(model, X_prep, y, cv=5, scoring='accuracy')\n", " score = scores.mean()\n", " \n", " computation_time = time.time() - start_time\n", " return score, computation_time\n", "\n", "def evaluate_reliability(X):\n", " \"\"\"2. Надежность\"\"\"\n", " missing_ratio = X.isnull().sum().sum() / (X.shape[0] * X.shape[1])\n", " constant_features = len([col for col in X.columns if X[col].nunique() <= 1])\n", " constant_ratio = constant_features / X.shape[1]\n", " \n", " reliability_score = 1 - (missing_ratio + constant_ratio) / 2\n", " return max(0, reliability_score)\n", "\n", "def evaluate_correlation(X):\n", " \"\"\"3. Корреляция\"\"\"\n", " X_prep = prepare_features(X)\n", " numeric_cols = X_prep.select_dtypes(include=[np.number]).columns\n", " \n", " if len(numeric_cols) > 1:\n", " corr_matrix = X_prep[numeric_cols].corr().abs()\n", " upper_triangle = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))\n", " mean_corr = upper_triangle.stack().mean()\n", " # Преобразуем в оценку: чем меньше корреляция, тем лучше\n", " correlation_score = 1 - min(mean_corr, 1.0)\n", " else:\n", " correlation_score = 1.0\n", " \n", " return correlation_score\n", "\n", "def evaluate_integrity(X, y, problem_type):\n", " \"\"\"4. Цельность\"\"\"\n", " X_prep = prepare_features(X)\n", " numeric_cols = X_prep.select_dtypes(include=[np.number]).columns\n", " \n", " if len(numeric_cols) > 0:\n", " if problem_type == 'regression':\n", " model = RandomForestRegressor(n_estimators=50, random_state=42)\n", " else:\n", " model = RandomForestClassifier(n_estimators=50, random_state=42)\n", " \n", " model.fit(X_prep[numeric_cols], y)\n", " importances = model.feature_importances_\n", " \n", " # Оценка цельности: доля информативных признаков\n", " mean_importance = np.mean(importances)\n", " informative_ratio = (importances > mean_importance).sum() / len(importances)\n", " integrity_score = informative_ratio\n", " else:\n", " integrity_score = 0\n", " \n", " return integrity_score\n", "\n", "def evaluate_feature_speed(X, y, problem_type):\n", " \"\"\"5. Скорость вычислений\"\"\"\n", " X_prep = prepare_features(X)\n", " \n", " start_time = time.time()\n", " if problem_type == 'regression':\n", " model = RandomForestRegressor(n_estimators=50, random_state=42)\n", " else:\n", " model = RandomForestClassifier(n_estimators=50, random_state=42)\n", " \n", " model.fit(X_prep, y)\n", " computation_time = time.time() - start_time\n", " \n", " # Преобразуем время в оценку: чем быстрее, тем лучше\n", " # Нормализуем относительно максимального ожидаемого времени (5 секунд)\n", " speed_score = max(0, 1 - (computation_time / 5.0))\n", " return speed_score, computation_time\n", "\n", "def plot_bar_comparison(results, problem_type):\n", " \"\"\"Столбчатые диаграммы по каждому критерию\"\"\"\n", " fig, axes = plt.subplots(2, 3, figsize=(15, 10))\n", " axes = axes.flatten()\n", " \n", " criteria = {\n", " 'predictive_score': 'Предсказательная\\nспособность',\n", " 'speed_score': 'Скорость\\nвычислений', \n", " 'reliability_score': 'Надежность',\n", " 'correlation_score': 'Низкая\\nкорреляция',\n", " 'integrity_score': 'Цельность'\n", " }\n", " \n", " colors = ['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd']\n", " \n", " for idx, (metric, title) in enumerate(criteria.items()):\n", " if idx >= len(axes):\n", " break\n", " \n", " names = list(results.keys())\n", " scores = [results[name][metric] for name in names]\n", " \n", " bars = axes[idx].bar(names, scores, color=colors[:len(names)])\n", " axes[idx].set_title(title, fontweight='bold')\n", " axes[idx].set_ylim(0, 1)\n", " \n", " # Добавляем значения на столбцы\n", " for bar, score in zip(bars, scores):\n", " height = bar.get_height()\n", " axes[idx].text(bar.get_x() + bar.get_width()/2, height + 0.02,\n", " f'{score:.2f}', ha='center', va='bottom', fontweight='bold')\n", " \n", " axes[idx].tick_params(axis='x', rotation=45)\n", " axes[idx].grid(True, alpha=0.3, axis='y')\n", " \n", " # Скрываем последний пустой subplot\n", " if len(criteria) < len(axes):\n", " axes[-1].set_visible(False)\n", " \n", " plt.suptitle(f'ОЦЕНКА КАЧЕСТВА ПРИЗНАКОВ ПО КРИТЕРИЯМ ({problem_type.upper()})', \n", " fontsize=16, fontweight='bold')\n", " plt.tight_layout()\n", " plt.show()\n", "\n", "def evaluate_all_criteria(X, y, problem_type):\n", " \"\"\"Полная оценка по всем 5 критериям\"\"\"\n", " # 1. Предсказательная способность и скорость\n", " predictive_score, predictive_time = evaluate_predictive_power(X, y, problem_type)\n", " \n", " # 2. Надежность\n", " reliability_score = evaluate_reliability(X)\n", " \n", " # 3. Корреляция\n", " correlation_score = evaluate_correlation(X)\n", " \n", " # 4. Цельность\n", " integrity_score = evaluate_integrity(X, y, problem_type)\n", " \n", " # 5. Скорость вычислений\n", " speed_score, speed_time = evaluate_feature_speed(X, y, problem_type)\n", " \n", " return {\n", " 'predictive_score': predictive_score,\n", " 'reliability_score': reliability_score,\n", " 'correlation_score': correlation_score,\n", " 'integrity_score': integrity_score,\n", " 'speed_score': speed_score,\n", " 'computation_time': predictive_time + speed_time,\n", " 'feature_count': X.shape[1]\n", " }\n", "\n", "# Подготовка данных\n", "original_features = data[['reading score', 'writing score', 'gender', 'race/ethnicity', \n", " 'parental level of education', 'lunch', 'test preparation course']].copy()\n", "\n", "# Создаем наборы для оценки\n", "feature_sets_regression = {'Исходные признаки': original_features}\n", "\n", "if 'final_features_regression' in globals():\n", " feature_sets_regression['FeatureTools'] = final_features_regression\n", "if 'X_regression' in globals():\n", " feature_sets_regression['Ручные признаки'] = X_regression\n", "\n", "# Оцениваем каждый набор\n", "results_regression = {}\n", "for name, X in feature_sets_regression.items():\n", " results_regression[name] = evaluate_all_criteria(X, y_regression, 'regression')\n", "\n", "# Визуализация результатов\n", "plot_bar_comparison(results_regression, 'regression')\n", "\n", "# Создаем наборы для классификации\n", "feature_sets_classification = {'Исходные признаки': original_features}\n", "\n", "if 'final_features_classification' in globals():\n", " feature_sets_classification['FeatureTools'] = final_features_classification\n", "if 'X_classification' in globals():\n", " feature_sets_classification['Ручные признаки'] = X_classification\n", "\n", "# Оцениваем каждый набор\n", "results_classification = {}\n", "for name, X in feature_sets_classification.items():\n", " results_classification[name] = evaluate_all_criteria(X, y_classification, 'classification')\n", "\n", "# Визуализация результатов\n", "plot_bar_comparison(results_classification, 'classification')\n" ] } ], "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": "3.12.6" } }, "nbformat": 4, "nbformat_minor": 5 }