831 lines
207 KiB
Plaintext
831 lines
207 KiB
Plaintext
|
{
|
|||
|
|
"cells": [
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"# Вариант задания: Прогнозирование выпучки в магазинах\n",
|
|||
|
|
"### Бизнес-цели:\n",
|
|||
|
|
"Цель: Разработать модель машинного обучения, которая позволит прогнозировать распродажи магазина в зависимоси от его ассортимента.\n",
|
|||
|
|
"\n",
|
|||
|
|
"### Цели технического проекта:\n",
|
|||
|
|
"\n",
|
|||
|
|
"Сбор и подготовка данных:\n",
|
|||
|
|
"Очистка данных от пропусков, выбросов и дубликатов.\n",
|
|||
|
|
"Преобразование категориальных переменных в числовые.\n",
|
|||
|
|
"Разделение данных на обучающую и тестовую выборки.\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 62,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Index(['Store ID ', 'Store_Area', 'Items_Available', 'Daily_Customer_Count',\n",
|
|||
|
|
" 'Store_Sales'],\n",
|
|||
|
|
" dtype='object')\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import pandas as pn\n",
|
|||
|
|
"import matplotlib.pyplot as plt\n",
|
|||
|
|
"import matplotlib\n",
|
|||
|
|
"import matplotlib.ticker as ticker\n",
|
|||
|
|
"df = pn.read_csv(\".//static//csv//Stores.csv\")\n",
|
|||
|
|
"print(df.columns)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"Разделим на 3 выборки\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 63,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Размер обучающей выборки: 572\n",
|
|||
|
|
"Размер контрольной выборки: 144\n",
|
|||
|
|
"Размер тестовой выборки: 180\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"from sklearn.model_selection import train_test_split\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Разделение данных на обучающую и тестовую выборки (80% - обучение, 20% - тест)\n",
|
|||
|
|
"train_data, test_data = train_test_split(df, test_size=0.2, random_state=42)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Разделение обучающей выборки на обучающую и контрольную (80% - обучение, 20% - контроль)\n",
|
|||
|
|
"train_data, val_data = train_test_split(train_data, test_size=0.2, random_state=42)\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Размер обучающей выборки:\", len(train_data))\n",
|
|||
|
|
"print(\"Размер контрольной выборки:\", len(val_data))\n",
|
|||
|
|
"print(\"Размер тестовой выборки:\", len(test_data))"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 64,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 640x480 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 640x480 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 640x480 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"\n",
|
|||
|
|
"import seaborn as sns\n",
|
|||
|
|
"import matplotlib.pyplot as plt\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Гистограмма распределения цены в обучающей выборке\n",
|
|||
|
|
"sns.histplot(train_data[\"Store_Sales\"], kde=True)\n",
|
|||
|
|
"plt.title('Распределение цены в обучающей выборке')\n",
|
|||
|
|
"plt.show()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Гистограмма распределения цены в контрольной выборке\n",
|
|||
|
|
"sns.histplot(val_data[\"Store_Sales\"], kde=True)\n",
|
|||
|
|
"plt.title('Распределение цены в контрольной выборке')\n",
|
|||
|
|
"plt.show()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Гистограмма распределения цены в тестовой выборке\n",
|
|||
|
|
"sns.histplot(test_data[\"Store_Sales\"], kde=True)\n",
|
|||
|
|
"plt.title('Распределение цены в тестовой выборке')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"## Процесс конструирования признаков\n",
|
|||
|
|
"\n",
|
|||
|
|
"\n",
|
|||
|
|
"\n",
|
|||
|
|
"### Унитарное кодирование категориальных признаков (one-hot encoding)\n",
|
|||
|
|
"\n",
|
|||
|
|
"One-hot encoding: Преобразование категориальных признаков в бинарные векторы."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 65,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"import pandas as pd\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Пример категориальных признаков\n",
|
|||
|
|
"categorical_features = [\n",
|
|||
|
|
" \"Store ID \",\n",
|
|||
|
|
" \"Store_Area\"\n",
|
|||
|
|
"]\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Применение one-hot encoding\n",
|
|||
|
|
"train_data_encoded = pd.get_dummies(train_data, columns=categorical_features)\n",
|
|||
|
|
"val_data_encoded = pd.get_dummies(val_data, columns=categorical_features)\n",
|
|||
|
|
"test_data_encoded = pd.get_dummies(test_data, columns=categorical_features)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### Дискретизация числовых признаков "
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 66,
|
|||
|
|
"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>Store_Area</th>\n",
|
|||
|
|
" <th>Store_Area</th>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </thead>\n",
|
|||
|
|
" <tbody>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>0</th>\n",
|
|||
|
|
" <td>1659</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>1</th>\n",
|
|||
|
|
" <td>1461</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>2</th>\n",
|
|||
|
|
" <td>1340</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>3</th>\n",
|
|||
|
|
" <td>1451</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>4</th>\n",
|
|||
|
|
" <td>1770</td>\n",
|
|||
|
|
" <td>(1744.333, 2229.0]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5</th>\n",
|
|||
|
|
" <td>1442</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>6</th>\n",
|
|||
|
|
" <td>1542</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>7</th>\n",
|
|||
|
|
" <td>1261</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>8</th>\n",
|
|||
|
|
" <td>1090</td>\n",
|
|||
|
|
" <td>(775.0, 1259.667]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>9</th>\n",
|
|||
|
|
" <td>1030</td>\n",
|
|||
|
|
" <td>(775.0, 1259.667]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>10</th>\n",
|
|||
|
|
" <td>1187</td>\n",
|
|||
|
|
" <td>(775.0, 1259.667]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>11</th>\n",
|
|||
|
|
" <td>1751</td>\n",
|
|||
|
|
" <td>(1744.333, 2229.0]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>12</th>\n",
|
|||
|
|
" <td>1746</td>\n",
|
|||
|
|
" <td>(1744.333, 2229.0]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>13</th>\n",
|
|||
|
|
" <td>1615</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>14</th>\n",
|
|||
|
|
" <td>1469</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>15</th>\n",
|
|||
|
|
" <td>1644</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>16</th>\n",
|
|||
|
|
" <td>1578</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>17</th>\n",
|
|||
|
|
" <td>1703</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>18</th>\n",
|
|||
|
|
" <td>1438</td>\n",
|
|||
|
|
" <td>(1259.667, 1744.333]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>19</th>\n",
|
|||
|
|
" <td>1940</td>\n",
|
|||
|
|
" <td>(1744.333, 2229.0]</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </tbody>\n",
|
|||
|
|
"</table>\n",
|
|||
|
|
"</div>"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
" Store_Area Store_Area\n",
|
|||
|
|
"0 1659 (1259.667, 1744.333]\n",
|
|||
|
|
"1 1461 (1259.667, 1744.333]\n",
|
|||
|
|
"2 1340 (1259.667, 1744.333]\n",
|
|||
|
|
"3 1451 (1259.667, 1744.333]\n",
|
|||
|
|
"4 1770 (1744.333, 2229.0]\n",
|
|||
|
|
"5 1442 (1259.667, 1744.333]\n",
|
|||
|
|
"6 1542 (1259.667, 1744.333]\n",
|
|||
|
|
"7 1261 (1259.667, 1744.333]\n",
|
|||
|
|
"8 1090 (775.0, 1259.667]\n",
|
|||
|
|
"9 1030 (775.0, 1259.667]\n",
|
|||
|
|
"10 1187 (775.0, 1259.667]\n",
|
|||
|
|
"11 1751 (1744.333, 2229.0]\n",
|
|||
|
|
"12 1746 (1744.333, 2229.0]\n",
|
|||
|
|
"13 1615 (1259.667, 1744.333]\n",
|
|||
|
|
"14 1469 (1259.667, 1744.333]\n",
|
|||
|
|
"15 1644 (1259.667, 1744.333]\n",
|
|||
|
|
"16 1578 (1259.667, 1744.333]\n",
|
|||
|
|
"17 1703 (1259.667, 1744.333]\n",
|
|||
|
|
"18 1438 (1259.667, 1744.333]\n",
|
|||
|
|
"19 1940 (1744.333, 2229.0]"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 66,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"from sklearn.preprocessing import OneHotEncoder\n",
|
|||
|
|
"import numpy as np\n",
|
|||
|
|
"\n",
|
|||
|
|
"\n",
|
|||
|
|
"labels = [\"small\", \"medium\", \"large\"]\n",
|
|||
|
|
"num_bins = 3\n",
|
|||
|
|
"\n",
|
|||
|
|
"hist1, bins1 = np.histogram(\n",
|
|||
|
|
" df[\"Store_Area\"].fillna(df[\"Store_Area\"].median()), bins=num_bins\n",
|
|||
|
|
")\n",
|
|||
|
|
"bins1, hist1\n",
|
|||
|
|
"\n",
|
|||
|
|
"pd.concat([df[\"Store_Area\"], pd.cut(df[\"Store_Area\"], list(bins1))], axis=1).head(20)\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 67,
|
|||
|
|
"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>Store_Area</th>\n",
|
|||
|
|
" <th>Store_Area</th>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </thead>\n",
|
|||
|
|
" <tbody>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>0</th>\n",
|
|||
|
|
" <td>1659</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>1</th>\n",
|
|||
|
|
" <td>1461</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>2</th>\n",
|
|||
|
|
" <td>1340</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>3</th>\n",
|
|||
|
|
" <td>1451</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>4</th>\n",
|
|||
|
|
" <td>1770</td>\n",
|
|||
|
|
" <td>large</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5</th>\n",
|
|||
|
|
" <td>1442</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>6</th>\n",
|
|||
|
|
" <td>1542</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>7</th>\n",
|
|||
|
|
" <td>1261</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>8</th>\n",
|
|||
|
|
" <td>1090</td>\n",
|
|||
|
|
" <td>small</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>9</th>\n",
|
|||
|
|
" <td>1030</td>\n",
|
|||
|
|
" <td>small</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>10</th>\n",
|
|||
|
|
" <td>1187</td>\n",
|
|||
|
|
" <td>small</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>11</th>\n",
|
|||
|
|
" <td>1751</td>\n",
|
|||
|
|
" <td>large</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>12</th>\n",
|
|||
|
|
" <td>1746</td>\n",
|
|||
|
|
" <td>large</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>13</th>\n",
|
|||
|
|
" <td>1615</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>14</th>\n",
|
|||
|
|
" <td>1469</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>15</th>\n",
|
|||
|
|
" <td>1644</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>16</th>\n",
|
|||
|
|
" <td>1578</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>17</th>\n",
|
|||
|
|
" <td>1703</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>18</th>\n",
|
|||
|
|
" <td>1438</td>\n",
|
|||
|
|
" <td>medium</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>19</th>\n",
|
|||
|
|
" <td>1940</td>\n",
|
|||
|
|
" <td>large</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </tbody>\n",
|
|||
|
|
"</table>\n",
|
|||
|
|
"</div>"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
" Store_Area Store_Area\n",
|
|||
|
|
"0 1659 medium\n",
|
|||
|
|
"1 1461 medium\n",
|
|||
|
|
"2 1340 medium\n",
|
|||
|
|
"3 1451 medium\n",
|
|||
|
|
"4 1770 large\n",
|
|||
|
|
"5 1442 medium\n",
|
|||
|
|
"6 1542 medium\n",
|
|||
|
|
"7 1261 medium\n",
|
|||
|
|
"8 1090 small\n",
|
|||
|
|
"9 1030 small\n",
|
|||
|
|
"10 1187 small\n",
|
|||
|
|
"11 1751 large\n",
|
|||
|
|
"12 1746 large\n",
|
|||
|
|
"13 1615 medium\n",
|
|||
|
|
"14 1469 medium\n",
|
|||
|
|
"15 1644 medium\n",
|
|||
|
|
"16 1578 medium\n",
|
|||
|
|
"17 1703 medium\n",
|
|||
|
|
"18 1438 medium\n",
|
|||
|
|
"19 1940 large"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 67,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"pd.concat(\n",
|
|||
|
|
" [df[\"Store_Area\"], pd.cut(df[\"Store_Area\"], list(bins1), labels=labels)], axis=1\n",
|
|||
|
|
").head(20)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### Ручной синтез"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 68,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"# Пример синтеза признака коэффициента отношения размера ассортимента к его распродажам\n",
|
|||
|
|
"train_data_encoded[\"koeff\"] = (\n",
|
|||
|
|
" train_data_encoded[\"Items_Available\"] / train_data_encoded[\"Store_Sales\"]\n",
|
|||
|
|
")\n",
|
|||
|
|
"val_data_encoded[\"koeff\"] = (\n",
|
|||
|
|
" val_data_encoded[\"Items_Available\"] / val_data_encoded[\"Store_Sales\"]\n",
|
|||
|
|
")\n",
|
|||
|
|
"test_data_encoded[\"koeff\"] = (\n",
|
|||
|
|
" test_data_encoded[\"Items_Available\"] / test_data_encoded[\"Store_Sales\"]\n",
|
|||
|
|
")"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"Масштабирование признаков - это процесс преобразования числовых признаков таким образом, чтобы они имели одинаковый масштаб. Это важно для многих алгоритмов машинного обучения, которые чувствительны к масштабу признаков, таких как линейная регрессия, метод опорных векторов (SVM) и нейронные сети."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 69,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Пример масштабирования числовых признаков\n",
|
|||
|
|
"numerical_features = [\"Daily_Customer_Count\", \"Items_Available\"]\n",
|
|||
|
|
"\n",
|
|||
|
|
"scaler = StandardScaler()\n",
|
|||
|
|
"train_data_encoded[numerical_features] = scaler.fit_transform(train_data_encoded[numerical_features])\n",
|
|||
|
|
"val_data_encoded[numerical_features] = scaler.transform(val_data_encoded[numerical_features])\n",
|
|||
|
|
"test_data_encoded[numerical_features] = scaler.transform(test_data_encoded[numerical_features])"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### Конструирование признаков с применением фреймворка Featuretools"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 70,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stderr",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\featuretools\\entityset\\entityset.py:1733: UserWarning: index id not found in dataframe, creating new integer column\n",
|
|||
|
|
" warnings.warn(\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\featuretools\\synthesis\\deep_feature_synthesis.py:169: UserWarning: Only one dataframe in entityset, changing max_depth to 1 since deeper features cannot be created\n",
|
|||
|
|
" warnings.warn(\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:143: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
|
|||
|
|
" df = pd.concat([df, default_df], sort=True)\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\woodwork\\logical_types.py:841: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
|
|||
|
|
" series = series.replace(ww.config.get_option(\"nan_values\"), np.nan)\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:143: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
|
|||
|
|
" df = pd.concat([df, default_df], sort=True)\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\woodwork\\logical_types.py:841: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
|
|||
|
|
" series = series.replace(ww.config.get_option(\"nan_values\"), np.nan)\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import featuretools as ft\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Определение сущностей\n",
|
|||
|
|
"es = ft.EntitySet(id='shop_data')\n",
|
|||
|
|
"es = es.add_dataframe(dataframe_name='shops', dataframe=train_data_encoded, index='id')\n",
|
|||
|
|
"\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Генерация признаков\n",
|
|||
|
|
"feature_matrix, feature_defs = ft.dfs(entityset=es, target_dataframe_name='shops', max_depth=2)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Преобразование признаков для контрольной и тестовой выборок\n",
|
|||
|
|
"val_feature_matrix = ft.calculate_feature_matrix(features=feature_defs, entityset=es, instance_ids=val_data_encoded.index)\n",
|
|||
|
|
"test_feature_matrix = ft.calculate_feature_matrix(features=feature_defs, entityset=es, instance_ids=test_data_encoded.index)\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### Оценка качества каждого набора признаков\n",
|
|||
|
|
"Предсказательная способность\n",
|
|||
|
|
"Метрики: RMSE, MAE, R²\n",
|
|||
|
|
"\n",
|
|||
|
|
"Методы: Обучение модели на обучающей выборке и оценка на контрольной и тестовой выборках.\n",
|
|||
|
|
"\n",
|
|||
|
|
"Скорость вычисления\n",
|
|||
|
|
"Методы: Измерение времени выполнения генерации признаков и обучения модели.\n",
|
|||
|
|
"\n",
|
|||
|
|
"Надежность\n",
|
|||
|
|
"Методы: Кросс-валидация, анализ чувствительности модели к изменениям в данных.\n",
|
|||
|
|
"\n",
|
|||
|
|
"Корреляция\n",
|
|||
|
|
"Методы: Анализ корреляционной матрицы признаков, удаление мультиколлинеарных признаков.\n",
|
|||
|
|
"\n",
|
|||
|
|
"Цельность\n",
|
|||
|
|
"Методы: Проверка логической связи между признаками и целевой переменной, интерпретация результатов модели."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 71,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stderr",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\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",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\featuretools\\synthesis\\deep_feature_synthesis.py:169: UserWarning: Only one dataframe in entityset, changing max_depth to 1 since deeper features cannot be created\n",
|
|||
|
|
" warnings.warn(\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:143: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
|
|||
|
|
" df = pd.concat([df, default_df], sort=True)\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\woodwork\\logical_types.py:841: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
|
|||
|
|
" series = series.replace(ww.config.get_option(\"nan_values\"), np.nan)\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:143: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
|
|||
|
|
" df = pd.concat([df, default_df], sort=True)\n",
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\woodwork\\logical_types.py:841: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
|
|||
|
|
" series = series.replace(ww.config.get_option(\"nan_values\"), np.nan)\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import featuretools as ft\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Определение сущностей\n",
|
|||
|
|
"es = ft.EntitySet(id='shop_data')\n",
|
|||
|
|
"es = es.add_dataframe(dataframe_name='shops', dataframe=train_data_encoded, index='id')\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Генерация признаков\n",
|
|||
|
|
"feature_matrix, feature_defs = ft.dfs(entityset=es, target_dataframe_name='shops', max_depth=2)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Преобразование признаков для контрольной и тестовой выборок\n",
|
|||
|
|
"val_feature_matrix = ft.calculate_feature_matrix(features=feature_defs, entityset=es, instance_ids=val_data_encoded.index)\n",
|
|||
|
|
"test_feature_matrix = ft.calculate_feature_matrix(features=feature_defs, entityset=es, instance_ids=test_data_encoded.index)\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 72,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stderr",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\sklearn\\metrics\\_regression.py:492: FutureWarning: 'squared' is deprecated in version 1.4 and will be removed in 1.6. To calculate the root mean squared error, use the function'root_mean_squared_error'.\n",
|
|||
|
|
" warnings.warn(\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"RMSE: 935.869473619144\n",
|
|||
|
|
"R²: 0.9976677314259463\n",
|
|||
|
|
"MAE: 563.0765217391303\n",
|
|||
|
|
"Cross-validated RMSE: 2423.8868120485813\n",
|
|||
|
|
"Train RMSE: 871.8955293545159\n",
|
|||
|
|
"Train R²: 0.9975555952641544\n",
|
|||
|
|
"Train MAE: 514.1715034965034\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stderr",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"d:\\3_КУРС_ПИ\\МИИ\\aisenv\\Lib\\site-packages\\sklearn\\metrics\\_regression.py:492: FutureWarning: 'squared' is deprecated in version 1.4 and will be removed in 1.6. To calculate the root mean squared error, use the function'root_mean_squared_error'.\n",
|
|||
|
|
" warnings.warn(\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 1000x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import pandas as pd\n",
|
|||
|
|
"from sklearn.model_selection import train_test_split\n",
|
|||
|
|
"from sklearn.ensemble import RandomForestRegressor\n",
|
|||
|
|
"from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error\n",
|
|||
|
|
"from sklearn.model_selection import cross_val_score\n",
|
|||
|
|
"import matplotlib.pyplot as plt\n",
|
|||
|
|
"import seaborn as sns\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Удаление строк с NaN\n",
|
|||
|
|
"feature_matrix = feature_matrix.dropna()\n",
|
|||
|
|
"val_feature_matrix = val_feature_matrix.dropna()\n",
|
|||
|
|
"test_feature_matrix = test_feature_matrix.dropna()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Разделение данных на обучающую и тестовую выборки\n",
|
|||
|
|
"X_train = feature_matrix.drop(\"Store_Sales\", axis=1)\n",
|
|||
|
|
"y_train = feature_matrix[\"Store_Sales\"]\n",
|
|||
|
|
"X_val = val_feature_matrix.drop(\"Store_Sales\", axis=1)\n",
|
|||
|
|
"y_val = val_feature_matrix[\"Store_Sales\"]\n",
|
|||
|
|
"X_test = test_feature_matrix.drop(\"Store_Sales\", axis=1)\n",
|
|||
|
|
"y_test = test_feature_matrix[\"Store_Sales\"]\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Выбор модели\n",
|
|||
|
|
"model = RandomForestRegressor(random_state=42)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Обучение модели\n",
|
|||
|
|
"model.fit(X_train, y_train)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Предсказание и оценка\n",
|
|||
|
|
"y_pred = model.predict(X_test)\n",
|
|||
|
|
"\n",
|
|||
|
|
"rmse = mean_squared_error(y_test, y_pred, squared=False)\n",
|
|||
|
|
"r2 = r2_score(y_test, y_pred)\n",
|
|||
|
|
"mae = mean_absolute_error(y_test, y_pred)\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(f\"RMSE: {rmse}\")\n",
|
|||
|
|
"print(f\"R²: {r2}\")\n",
|
|||
|
|
"print(f\"MAE: {mae}\")\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Кросс-валидация\n",
|
|||
|
|
"scores = cross_val_score(model, X_train, y_train, cv=5, scoring='neg_mean_squared_error')\n",
|
|||
|
|
"rmse_cv = (-scores.mean())**0.5\n",
|
|||
|
|
"print(f\"Cross-validated RMSE: {rmse_cv}\")\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Анализ важности признаков\n",
|
|||
|
|
"feature_importances = model.feature_importances_\n",
|
|||
|
|
"feature_names = X_train.columns\n",
|
|||
|
|
"\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Проверка на переобучение\n",
|
|||
|
|
"y_train_pred = model.predict(X_train)\n",
|
|||
|
|
"\n",
|
|||
|
|
"rmse_train = mean_squared_error(y_train, y_train_pred, squared=False)\n",
|
|||
|
|
"r2_train = r2_score(y_train, y_train_pred)\n",
|
|||
|
|
"mae_train = mean_absolute_error(y_train, y_train_pred)\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(f\"Train RMSE: {rmse_train}\")\n",
|
|||
|
|
"print(f\"Train R²: {r2_train}\")\n",
|
|||
|
|
"print(f\"Train MAE: {mae_train}\")\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Визуализация результатов\n",
|
|||
|
|
"plt.figure(figsize=(10, 6))\n",
|
|||
|
|
"plt.scatter(y_test, y_pred, alpha=0.5)\n",
|
|||
|
|
"plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2)\n",
|
|||
|
|
"plt.xlabel('Actual Sales')\n",
|
|||
|
|
"plt.ylabel('Predicted Sales')\n",
|
|||
|
|
"plt.title(\"Actual vs Predicted Sales\")\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"Точность предсказаний: Модель показывает довольно высокий R² (0.9975), что указывает на хорошее объяснение вариации распродаж. Значения RMSE и MAE довольно низки, что говорит о том, что модель достаточно точно предсказывает цены.\n",
|
|||
|
|
"\n",
|
|||
|
|
"Переобучение: Разница между RMSE на обучающей и тестовой выборках не очень большая, что указывает на то, что переобучение не является критическим. Однако, стоит быть осторожным и продолжать мониторинг этого показателя.\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"metadata": {
|
|||
|
|
"kernelspec": {
|
|||
|
|
"display_name": "aisenv",
|
|||
|
|
"language": "python",
|
|||
|
|
"name": "python3"
|
|||
|
|
},
|
|||
|
|
"language_info": {
|
|||
|
|
"codemirror_mode": {
|
|||
|
|
"name": "ipython",
|
|||
|
|
"version": 3
|
|||
|
|
},
|
|||
|
|
"file_extension": ".py",
|
|||
|
|
"mimetype": "text/x-python",
|
|||
|
|
"name": "python",
|
|||
|
|
"nbconvert_exporter": "python",
|
|||
|
|
"pygments_lexer": "ipython3",
|
|||
|
|
"version": "3.12.6"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"nbformat": 4,
|
|||
|
|
"nbformat_minor": 2
|
|||
|
|
}
|