Files
UfaHack2024/notebooks/EDA.ipynb
2024-03-29 09:54:44 +03:00

492 lines
16 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"outputs": [],
"source": [
"import pandas as pd"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-29T06:28:51.733973600Z",
"start_time": "2024-03-29T06:28:51.165303900Z"
}
}
},
{
"cell_type": "code",
"execution_count": 10,
"outputs": [
{
"data": {
"text/plain": " id name link \\\n0 17505 Стефен Ананикз https://www.kinopoisk.ru/name/1114998 \n1 22644 Стикки Фингаз https://www.kinopoisk.ru/name/6730 \n2 48531 Теодора Ричардс https://www.kinopoisk.ru/name/1874602 \n3 4829 Коуди Роджерс https://www.kinopoisk.ru/name/2859797 \n4 41086 Joe Ariola https://www.kinopoisk.ru/name/6541368 \n... ... ... ... \n6044 7416 Кери Линн Прэтт https://www.kinopoisk.ru/name/16713 \n6045 9894 Уильям Фихтнер https://www.kinopoisk.ru/name/13096 \n6046 7419 Питер Сарсгаард https://www.kinopoisk.ru/name/32953 \n6047 9900 Лили Лабё https://www.kinopoisk.ru/name/2533068 \n6048 9908 Джош Карпентер https://www.kinopoisk.ru/name/1500397 \n\n specialization films_years \\\n0 Продюсер,Режиссер,Актер,Сценарист 8, 2006 — 2019 \n1 Актер,Композитор,Сценарист,Режиссер,Продюсер,М... 104, 1992 — 2024 \n2 Актриса 3, 2013 — 2014 \n3 Режиссер,Продюсер,Актер,Сценарист 12, 2012 — 2018 \n4 Актер 10, 1999 — 2024 \n... ... ... \n6044 Актриса 47, 1994 — 2014 \n6045 Актер,Продюсер,Режиссер,Сценарист 107, 1956 — 2024 \n6046 Актер,Продюсер 114, 1975 — 2024 \n6047 Актриса,Сценарист 121, 1998 — 2020 \n6048 Актер,Продюсер 9, 1992 — 2017 \n\n description path_to_folder \n0 NaN actors_usa/17505 \n1 Там,Щит,Однажды ночью,Напарницы,Империя actors_usa/22644 \n2 NaN actors_usa/48531 \n3 NaN actors_usa/4829 \n4 WWE SmackDown actors_usa/41086 \n... ... ... \n6044 Одинокий мужчина,Доктор Хаус,Скорая помощь,Мыс... actors_usa/7416 \n6045 Чёрный ястреб,Всё или ничего,Идеальный шторм,Э... actors_usa/9894 \n6046 К-19,Воспитание чувств,Парни не плачут,Ключ от... actors_usa/7419 \n6047 NaN actors_usa/9900 \n6048 NaN actors_usa/9908 \n\n[6049 rows x 7 columns]",
"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>id</th>\n <th>name</th>\n <th>link</th>\n <th>specialization</th>\n <th>films_years</th>\n <th>description</th>\n <th>path_to_folder</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>17505</td>\n <td>Стефен Ананикз</td>\n <td>https://www.kinopoisk.ru/name/1114998</td>\n <td>Продюсер,Режиссер,Актер,Сценарист</td>\n <td>8, 2006 — 2019</td>\n <td>NaN</td>\n <td>actors_usa/17505</td>\n </tr>\n <tr>\n <th>1</th>\n <td>22644</td>\n <td>Стикки Фингаз</td>\n <td>https://www.kinopoisk.ru/name/6730</td>\n <td>Актер,Композитор,Сценарист,Режиссер,Продюсер,М...</td>\n <td>104, 1992 — 2024</td>\n <td>Там,Щит,Однажды ночью,Напарницы,Империя</td>\n <td>actors_usa/22644</td>\n </tr>\n <tr>\n <th>2</th>\n <td>48531</td>\n <td>Теодора Ричардс</td>\n <td>https://www.kinopoisk.ru/name/1874602</td>\n <td>Актриса</td>\n <td>3, 2013 — 2014</td>\n <td>NaN</td>\n <td>actors_usa/48531</td>\n </tr>\n <tr>\n <th>3</th>\n <td>4829</td>\n <td>Коуди Роджерс</td>\n <td>https://www.kinopoisk.ru/name/2859797</td>\n <td>Режиссер,Продюсер,Актер,Сценарист</td>\n <td>12, 2012 — 2018</td>\n <td>NaN</td>\n <td>actors_usa/4829</td>\n </tr>\n <tr>\n <th>4</th>\n <td>41086</td>\n <td>Joe Ariola</td>\n <td>https://www.kinopoisk.ru/name/6541368</td>\n <td>Актер</td>\n <td>10, 1999 — 2024</td>\n <td>WWE SmackDown</td>\n <td>actors_usa/41086</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>6044</th>\n <td>7416</td>\n <td>Кери Линн Прэтт</td>\n <td>https://www.kinopoisk.ru/name/16713</td>\n <td>Актриса</td>\n <td>47, 1994 — 2014</td>\n <td>Одинокий мужчина,Доктор Хаус,Скорая помощь,Мыс...</td>\n <td>actors_usa/7416</td>\n </tr>\n <tr>\n <th>6045</th>\n <td>9894</td>\n <td>Уильям Фихтнер</td>\n <td>https://www.kinopoisk.ru/name/13096</td>\n <td>Актер,Продюсер,Режиссер,Сценарист</td>\n <td>107, 1956 — 2024</td>\n <td>Чёрный ястреб,Всё или ничего,Идеальный шторм,Э...</td>\n <td>actors_usa/9894</td>\n </tr>\n <tr>\n <th>6046</th>\n <td>7419</td>\n <td>Питер Сарсгаард</td>\n <td>https://www.kinopoisk.ru/name/32953</td>\n <td>Актер,Продюсер</td>\n <td>114, 1975 — 2024</td>\n <td>К-19,Воспитание чувств,Парни не плачут,Ключ от...</td>\n <td>actors_usa/7419</td>\n </tr>\n <tr>\n <th>6047</th>\n <td>9900</td>\n <td>Лили Лабё</td>\n <td>https://www.kinopoisk.ru/name/2533068</td>\n <td>Актриса,Сценарист</td>\n <td>121, 1998 — 2020</td>\n <td>NaN</td>\n <td>actors_usa/9900</td>\n </tr>\n <tr>\n <th>6048</th>\n <td>9908</td>\n <td>Джош Карпентер</td>\n <td>https://www.kinopoisk.ru/name/1500397</td>\n <td>Актер,Продюсер</td>\n <td>9, 1992 — 2017</td>\n <td>NaN</td>\n <td>actors_usa/9908</td>\n </tr>\n </tbody>\n</table>\n<p>6049 rows × 7 columns</p>\n</div>"
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = pd.read_csv(\"../data/usa.csv\", delimiter=\";\")\n",
"data"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-29T06:36:41.472967600Z",
"start_time": "2024-03-29T06:36:41.378668700Z"
}
}
},
{
"cell_type": "code",
"execution_count": 32,
"outputs": [],
"source": [
"columns = data.columns"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-29T06:45:12.437750900Z",
"start_time": "2024-03-29T06:45:12.414952700Z"
}
}
},
{
"cell_type": "code",
"execution_count": 62,
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\fatik\\AppData\\Local\\Temp\\ipykernel_12208\\3238385593.py:3: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n",
" dicter[x.id] = x[1]\n"
]
},
{
"data": {
"text/plain": "'Стефен Ананикз'"
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dicter = {}\n",
"def get_dict(x):\n",
" dicter[x.id] = x[1]\n",
"data[\"json\"] = data.apply(lambda x: get_dict(x), axis=1)\n",
"import pickle\n",
"\n",
"with open('saved_dictionary.pkl', 'wb') as f:\n",
" pickle.dump(dicter, f)\n",
"with open('saved_dictionary.pkl', 'rb') as f:\n",
" loaded_dict = pickle.load(f)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-29T06:54:05.064292600Z",
"start_time": "2024-03-29T06:54:04.924879400Z"
}
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 0
}