250 lines
130 KiB
Plaintext
250 lines
130 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Импорт библиотек и загрузка датасета"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 7,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"<>:4: SyntaxWarning: invalid escape sequence '\\j'\n",
|
||
|
|
"<>:4: SyntaxWarning: invalid escape sequence '\\j'\n",
|
||
|
|
"C:\\Users\\MaD\\AppData\\Local\\Temp\\ipykernel_9800\\3091210825.py:4: SyntaxWarning: invalid escape sequence '\\j'\n",
|
||
|
|
" df = pd.read_csv(\"data\\jio_mart_items.csv\")\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"import matplotlib.pyplot as plt\n",
|
||
|
|
"\n",
|
||
|
|
"df = pd.read_csv(\"data\\jio_mart_items.csv\")"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Изучение полученных данных"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 8,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
|
|
"RangeIndex: 162313 entries, 0 to 162312\n",
|
||
|
|
"Data columns (total 5 columns):\n",
|
||
|
|
" # Column Non-Null Count Dtype \n",
|
||
|
|
"--- ------ -------------- ----- \n",
|
||
|
|
" 0 category 162313 non-null object \n",
|
||
|
|
" 1 sub_category 162313 non-null object \n",
|
||
|
|
" 2 href 162313 non-null object \n",
|
||
|
|
" 3 items 162280 non-null object \n",
|
||
|
|
" 4 price 162282 non-null float64\n",
|
||
|
|
"dtypes: float64(1), object(4)\n",
|
||
|
|
"memory usage: 6.2+ MB\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"df.info()\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df.describe().transpose())\n",
|
||
|
|
"\n",
|
||
|
|
"# cleared_df = df.drop([\"Name\", \"Ticket\", \"Embarked\"], axis=1)\n",
|
||
|
|
"# print(cleared_df.head())\n",
|
||
|
|
"# print(cleared_df.tail())\n",
|
||
|
|
"\n",
|
||
|
|
"# sorted_df = cleared_df.sort_values(by=\"Age\")\n",
|
||
|
|
"# print(sorted_df.head())\n",
|
||
|
|
"# print(sorted_df.tail())"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Захотел посмотреть кол-во подкатегорий."
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 9,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"72\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"print(len(set(df[\"sub_category\"])))\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df.sort_values(by=\"category\")[[\"category\", \"sub_category\"]])\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df.loc[100])\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df.loc[100, \"Name\"])\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df.loc[100:200, [\"Age\", \"Name\"]])\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df[0:3])\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df.iloc[0])\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df.iloc[3:5, 0:2])\n",
|
||
|
|
"\n",
|
||
|
|
"# print(df.iloc[[3, 4], [0, 1]])"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 10,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 1000x600 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"\n",
|
||
|
|
"avg_price_by_category = df.groupby('category')['price'].mean()\n",
|
||
|
|
"\n",
|
||
|
|
"plt.figure(figsize=(10, 6))\n",
|
||
|
|
"avg_price_by_category.plot(kind='bar', color='skyblue')\n",
|
||
|
|
"plt.title('Средняя цена по категории')\n",
|
||
|
|
"plt.xlabel('Категория')\n",
|
||
|
|
"plt.ylabel('Средняя цена')\n",
|
||
|
|
"plt.xticks(rotation=0)\n",
|
||
|
|
"plt.tight_layout()\n",
|
||
|
|
"plt.show()\n",
|
||
|
|
"\n",
|
||
|
|
"\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Данная диаграмма отображает среднюю цену по категории и иллюстрирует очевидный факт: электроника и ювелирные украшения стоят больше всего."
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 11,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 800x800 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"category_counts = df['category'].value_counts()\n",
|
||
|
|
"\n",
|
||
|
|
"plt.figure(figsize=(8, 8))\n",
|
||
|
|
"plt.pie(category_counts, labels=category_counts.index, autopct='%1.1f%%', colors=plt.cm.Paired.colors)\n",
|
||
|
|
"plt.title('Распространенность каждой категории')\n",
|
||
|
|
"plt.tight_layout()\n",
|
||
|
|
"plt.show()\n",
|
||
|
|
"\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Данная диаграмма отображает распространённость каждой категории"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 12,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 1000x600 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"subcategories_by_category = df.groupby('category')['sub_category'].nunique()\n",
|
||
|
|
"\n",
|
||
|
|
"plt.figure(figsize=(10, 6))\n",
|
||
|
|
"subcategories_by_category.plot(kind='bar', color='lightgreen')\n",
|
||
|
|
"plt.title('Количество подкатегорий в каждой категории')\n",
|
||
|
|
"plt.xlabel('Категория')\n",
|
||
|
|
"plt.ylabel('Количество подкатегорий')\n",
|
||
|
|
"plt.xticks(rotation=0)\n",
|
||
|
|
"plt.tight_layout()\n",
|
||
|
|
"plt.show()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Данная диаграмма отображет количество подкатегорий в категории."
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"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": 2
|
||
|
|
}
|