mik/ReClass
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Everything is good to go for annotations.

Browse Source
This commit is contained in:
charlie-rasberry
2025-12-19 07:14:13 +00:00
parent 5b9fbfc75e
commit 487be5cd27
9 changed files with 33 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

370
multitag/notebooks/datasets_reviews.ipynb Normal file
View File

@@ -0,0 +1,370 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "f3da59fb-eb6b-449f-b8d5-95ddacd456f2",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"from pathlib import Path"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "0c897ead-dfb5-4d18-bcfc-949824a0868f",
"metadata": {},
"outputs": [],
"source": [
"uber = Path.home() / 'google-drive' / 'Charlie_6013_RECLASS' / 'Data' / 'Raw' / 'Uber Customer Reviews.csv'"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "75ad8e81-3f11-4152-9494-b95bbba6fa01",
"metadata": {},
"outputs": [
{
"ename": "FileNotFoundError",
"evalue": "[Errno 2] No such file or directory: 'C:\\\\Users\\\\ch\\\\google-drive\\\\Charlie_6013_RECLASS\\\\Data\\\\Raw\\\\Uber Customer Reviews.csv'",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mFileNotFoundError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[9]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m uber_df = \u001b[43mpd\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[43muber\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlow_memory\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~\\anaconda3\\envs\\multitag\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1026\u001b[39m, in \u001b[36mread_csv\u001b[39m\u001b[34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[39m\n\u001b[32m 1013\u001b[39m kwds_defaults = _refine_defaults_read(\n\u001b[32m 1014\u001b[39m dialect,\n\u001b[32m 1015\u001b[39m delimiter,\n\u001b[32m (...)\u001b[39m\u001b[32m 1022\u001b[39m dtype_backend=dtype_backend,\n\u001b[32m 1023\u001b[39m )\n\u001b[32m 1024\u001b[39m kwds.update(kwds_defaults)\n\u001b[32m-> \u001b[39m\u001b[32m1026\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~\\anaconda3\\envs\\multitag\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:620\u001b[39m, in \u001b[36m_read\u001b[39m\u001b[34m(filepath_or_buffer, kwds)\u001b[39m\n\u001b[32m 617\u001b[39m _validate_names(kwds.get(\u001b[33m\"\u001b[39m\u001b[33mnames\u001b[39m\u001b[33m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[32m 619\u001b[39m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m620\u001b[39m parser = \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 622\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[32m 623\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
"\u001b[36mFile \u001b[39m\u001b[32m~\\anaconda3\\envs\\multitag\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1620\u001b[39m, in \u001b[36mTextFileReader.__init__\u001b[39m\u001b[34m(self, f, engine, **kwds)\u001b[39m\n\u001b[32m 1617\u001b[39m \u001b[38;5;28mself\u001b[39m.options[\u001b[33m\"\u001b[39m\u001b[33mhas_index_names\u001b[39m\u001b[33m\"\u001b[39m] = kwds[\u001b[33m\"\u001b[39m\u001b[33mhas_index_names\u001b[39m\u001b[33m\"\u001b[39m]\n\u001b[32m 1619\u001b[39m \u001b[38;5;28mself\u001b[39m.handles: IOHandles | \u001b[38;5;28;01mNone\u001b[39;00m = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1620\u001b[39m \u001b[38;5;28mself\u001b[39m._engine = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~\\anaconda3\\envs\\multitag\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1880\u001b[39m, in \u001b[36mTextFileReader._make_engine\u001b[39m\u001b[34m(self, f, engine)\u001b[39m\n\u001b[32m 1878\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[32m 1879\u001b[39m mode += \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m-> \u001b[39m\u001b[32m1880\u001b[39m \u001b[38;5;28mself\u001b[39m.handles = \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1881\u001b[39m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1882\u001b[39m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1883\u001b[39m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mencoding\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1884\u001b[39m \u001b[43m \u001b[49m\u001b[43mcompression\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mcompression\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1885\u001b[39m \u001b[43m \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmemory_map\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1886\u001b[39m \u001b[43m \u001b[49m\u001b[43mis_text\u001b[49m\u001b[43m=\u001b[49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1887\u001b[39m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mencoding_errors\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstrict\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1888\u001b[39m \u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstorage_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1889\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1890\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m.handles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m 1891\u001b[39m f = \u001b[38;5;28mself\u001b[39m.handles.handle\n",
"\u001b[36mFile \u001b[39m\u001b[32m~\\anaconda3\\envs\\multitag\\Lib\\site-packages\\pandas\\io\\common.py:873\u001b[39m, in \u001b[36mget_handle\u001b[39m\u001b[34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[39m\n\u001b[32m 868\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[32m 869\u001b[39m \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[32m 870\u001b[39m \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[32m 871\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m ioargs.encoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs.mode:\n\u001b[32m 872\u001b[39m \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m873\u001b[39m handle = \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[32m 874\u001b[39m \u001b[43m \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 875\u001b[39m \u001b[43m \u001b[49m\u001b[43mioargs\u001b[49m\u001b[43m.\u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 876\u001b[39m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m=\u001b[49m\u001b[43mioargs\u001b[49m\u001b[43m.\u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 877\u001b[39m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 878\u001b[39m \u001b[43m \u001b[49m\u001b[43mnewline\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m 879\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 880\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m 881\u001b[39m \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[32m 882\u001b[39m handle = \u001b[38;5;28mopen\u001b[39m(handle, ioargs.mode)\n",
"\u001b[31mFileNotFoundError\u001b[39m: [Errno 2] No such file or directory: 'C:\\\\Users\\\\ch\\\\google-drive\\\\Charlie_6013_RECLASS\\\\Data\\\\Raw\\\\Uber Customer Reviews.csv'"
]
}
],
"source": [
"uber_df = pd.read_csv(uber, low_memory=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9b8469b3-c606-461f-aaef-9619b7dc1ffd",
"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>source</th>\n",
" <th>review_id</th>\n",
" <th>user_name</th>\n",
" <th>review_title</th>\n",
" <th>review_description</th>\n",
" <th>rating</th>\n",
" <th>thumbs_up</th>\n",
" <th>review_date</th>\n",
" <th>developer_response</th>\n",
" <th>developer_response_date</th>\n",
" <th>appVersion</th>\n",
" <th>laguage_code</th>\n",
" <th>country_code</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Google Play</td>\n",
" <td>18d6584c-d0e9-4833-a744-f607058aee97</td>\n",
" <td>Milky Way</td>\n",
" <td>NaN</td>\n",
" <td>Suddenly, the driver can't have my location an...</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:48:51</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Google Play</td>\n",
" <td>50a08f18-cece-4ddf-b617-028844c8aa28</td>\n",
" <td>Bradlee Severa</td>\n",
" <td>NaN</td>\n",
" <td>Very cordial.. And helped with a quick turnaro...</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:38:35</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.485.10000</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Google Play</td>\n",
" <td>b0d8e75a-80a7-4dcd-abaf-72b046dbeeb7</td>\n",
" <td>Amit Aggarwal</td>\n",
" <td>NaN</td>\n",
" <td>Very good experience</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:38:17</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.486.10002</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Google Play</td>\n",
" <td>502702a9-25ed-4373-a96c-7fa1f06caacd</td>\n",
" <td>Bryant Inman</td>\n",
" <td>NaN</td>\n",
" <td>All I use</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:37:45</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.467.10008</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Google Play</td>\n",
" <td>f47a3fb6-23db-49bd-9e63-f33c8d724d07</td>\n",
" <td>Addie Whittaker</td>\n",
" <td>NaN</td>\n",
" <td>I have enjoyed traveling by Uber my drivers ha...</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:36:56</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.486.10002</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" source review_id user_name \\\n",
"0 Google Play 18d6584c-d0e9-4833-a744-f607058aee97 Milky Way \n",
"1 Google Play 50a08f18-cece-4ddf-b617-028844c8aa28 Bradlee Severa \n",
"2 Google Play b0d8e75a-80a7-4dcd-abaf-72b046dbeeb7 Amit Aggarwal \n",
"3 Google Play 502702a9-25ed-4373-a96c-7fa1f06caacd Bryant Inman \n",
"4 Google Play f47a3fb6-23db-49bd-9e63-f33c8d724d07 Addie Whittaker \n",
"\n",
" review_title review_description rating \\\n",
"0 NaN Suddenly, the driver can't have my location an... 1 \n",
"1 NaN Very cordial.. And helped with a quick turnaro... 5 \n",
"2 NaN Very good experience 5 \n",
"3 NaN All I use 5 \n",
"4 NaN I have enjoyed traveling by Uber my drivers ha... 5 \n",
"\n",
" thumbs_up review_date developer_response developer_response_date \\\n",
"0 0.0 2023-08-10 17:48:51 NaN NaN \n",
"1 0.0 2023-08-10 17:38:35 NaN NaN \n",
"2 0.0 2023-08-10 17:38:17 NaN NaN \n",
"3 0.0 2023-08-10 17:37:45 NaN NaN \n",
"4 0.0 2023-08-10 17:36:56 NaN NaN \n",
"\n",
" appVersion laguage_code country_code \n",
"0 NaN en in \n",
"1 4.485.10000 en in \n",
"2 4.486.10002 en in \n",
"3 4.467.10008 en in \n",
"4 4.486.10002 en in "
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"uber_df.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1709a2cc-4f7a-4e77-994e-68668612caff",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(1069616, 13)"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.shape(uber_df)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "06c0c03c-14ba-4451-a6ea-44d36e85327c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['source',\n",
" 'review_id',\n",
" 'user_name',\n",
" 'review_title',\n",
" 'review_description',\n",
" 'rating',\n",
" 'thumbs_up',\n",
" 'review_date',\n",
" 'developer_response',\n",
" 'developer_response_date',\n",
" 'appVersion',\n",
" 'laguage_code',\n",
" 'country_code']"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"uber_df.columns.tolist()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d22d3bce-eac0-4d02-a4ef-38343f4958ff",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"source object\n",
"review_id object\n",
"user_name object\n",
"review_title object\n",
"review_description object\n",
"rating int64\n",
"thumbs_up float64\n",
"review_date object\n",
"developer_response object\n",
"developer_response_date object\n",
"appVersion object\n",
"laguage_code object\n",
"country_code object\n",
"dtype: object"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"uber_df.dtypes"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e08f5eae-7921-4526-b8fd-29038c55e1bb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"source 0\n",
"review_id 0\n",
"user_name 1\n",
"review_title 1067436\n",
"review_description 169\n",
"rating 0\n",
"thumbs_up 2180\n",
"review_date 0\n",
"developer_response 871352\n",
"developer_response_date 872338\n",
"appVersion 241548\n",
"laguage_code 0\n",
"country_code 0\n",
"dtype: int64"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"uber_df.isnull().sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ea59d211-9958-46f6-bf76-65d8d36c50e4",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "reclass",
"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": "3.14.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

481
multitag/notebooks/preprocessing_uber.ipynb Normal file
View File

@@ -0,0 +1,481 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "470fe7c6-1614-4daf-879f-e6c399117c7b",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "afe1168c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cwd: /mnt/c/Users/ch/6013/multitag/notebooks\n",
"exists data: False\n"
]
}
],
"source": [
"import os\n",
"print(\"cwd:\", os.getcwd())\n",
"print(\"exists data:\", os.path.exists(\"mullitag\"))\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b855045e-2dd1-4fa1-ab5a-8ce8b50b02ee",
"metadata": {},
"outputs": [],
"source": [
"\n",
"df = pd.read_csv('../data/uber_reviews.csv', low_memory=False)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "e7da1fb6-ede6-46c6-8fbd-fa491d3351c5",
"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>source</th>\n",
" <th>review_id</th>\n",
" <th>user_name</th>\n",
" <th>review_title</th>\n",
" <th>review_description</th>\n",
" <th>rating</th>\n",
" <th>thumbs_up</th>\n",
" <th>review_date</th>\n",
" <th>developer_response</th>\n",
" <th>developer_response_date</th>\n",
" <th>appVersion</th>\n",
" <th>laguage_code</th>\n",
" <th>country_code</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Google Play</td>\n",
" <td>18d6584c-d0e9-4833-a744-f607058aee97</td>\n",
" <td>Milky Way</td>\n",
" <td>NaN</td>\n",
" <td>Suddenly, the driver can't have my location an...</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:48:51</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Google Play</td>\n",
" <td>50a08f18-cece-4ddf-b617-028844c8aa28</td>\n",
" <td>Bradlee Severa</td>\n",
" <td>NaN</td>\n",
" <td>Very cordial.. And helped with a quick turnaro...</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:38:35</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.485.10000</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Google Play</td>\n",
" <td>b0d8e75a-80a7-4dcd-abaf-72b046dbeeb7</td>\n",
" <td>Amit Aggarwal</td>\n",
" <td>NaN</td>\n",
" <td>Very good experience</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:38:17</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.486.10002</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Google Play</td>\n",
" <td>502702a9-25ed-4373-a96c-7fa1f06caacd</td>\n",
" <td>Bryant Inman</td>\n",
" <td>NaN</td>\n",
" <td>All I use</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:37:45</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.467.10008</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Google Play</td>\n",
" <td>f47a3fb6-23db-49bd-9e63-f33c8d724d07</td>\n",
" <td>Addie Whittaker</td>\n",
" <td>NaN</td>\n",
" <td>I have enjoyed traveling by Uber my drivers ha...</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>2023-08-10 17:36:56</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.486.10002</td>\n",
" <td>en</td>\n",
" <td>in</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" source review_id user_name \\\n",
"0 Google Play 18d6584c-d0e9-4833-a744-f607058aee97 Milky Way \n",
"1 Google Play 50a08f18-cece-4ddf-b617-028844c8aa28 Bradlee Severa \n",
"2 Google Play b0d8e75a-80a7-4dcd-abaf-72b046dbeeb7 Amit Aggarwal \n",
"3 Google Play 502702a9-25ed-4373-a96c-7fa1f06caacd Bryant Inman \n",
"4 Google Play f47a3fb6-23db-49bd-9e63-f33c8d724d07 Addie Whittaker \n",
"\n",
" review_title review_description rating \\\n",
"0 NaN Suddenly, the driver can't have my location an... 1 \n",
"1 NaN Very cordial.. And helped with a quick turnaro... 5 \n",
"2 NaN Very good experience 5 \n",
"3 NaN All I use 5 \n",
"4 NaN I have enjoyed traveling by Uber my drivers ha... 5 \n",
"\n",
" thumbs_up review_date developer_response developer_response_date \\\n",
"0 0.0 2023-08-10 17:48:51 NaN NaN \n",
"1 0.0 2023-08-10 17:38:35 NaN NaN \n",
"2 0.0 2023-08-10 17:38:17 NaN NaN \n",
"3 0.0 2023-08-10 17:37:45 NaN NaN \n",
"4 0.0 2023-08-10 17:36:56 NaN NaN \n",
"\n",
" appVersion laguage_code country_code \n",
"0 NaN en in \n",
"1 4.485.10000 en in \n",
"2 4.486.10002 en in \n",
"3 4.467.10008 en in \n",
"4 4.486.10002 en in "
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "5c02ec54-4583-4720-88c6-1110b52c3f88",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"rating\n",
"1 283895\n",
"2 41707\n",
"3 49928\n",
"4 82953\n",
"5 611133\n",
"Name: count, dtype: int64\n"
]
}
],
"source": [
"print(df['rating'].value_counts().sort_index())"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "1da5d625-a4ba-49f8-8314-cc9e0f4ef96a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Review length stats:\n",
" Mean: 13.1 words\n",
" Median: 4.0 words\n",
" Min: 1.0 words\n",
" Max: 755.0 words\n"
]
}
],
"source": [
"df['word_count'] = df['review_description'].str.split().str.len()\n",
"print('Review length stats:')\n",
"print(f\" Mean: {df['word_count'].mean():.1f} words\")\n",
"print(f\" Median: {df['word_count'].median():.1f} words\")\n",
"print(f\" Min: {df['word_count'].min()} words\")\n",
"print(f\" Max: {df['word_count'].max()} words\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "1c97e396-8f05-4df7-bd0a-1bbecf6911b4",
"metadata": {},
"outputs": [],
"source": [
"short_reviews = df[df['word_count'] < 5]"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "55324c94-4944-4844-b00e-dc08c8989f7b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Reviews < 5 words: 569632 (53.3%)\n"
]
}
],
"source": [
"print(f\"\\nReviews < 5 words: {len(short_reviews)} ({len(short_reviews)/len(df)*100:.1f}%)\")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "c45959fe-3e23-4831-a41a-94c89892247f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Missing values:\n",
"source 0\n",
"review_id 0\n",
"user_name 1\n",
"review_title 1067436\n",
"review_description 169\n",
"rating 0\n",
"thumbs_up 2180\n",
"review_date 0\n",
"developer_response 871352\n",
"developer_response_date 872338\n",
"appVersion 241548\n",
"laguage_code 0\n",
"country_code 0\n",
"word_count 169\n",
"dtype: int64\n"
]
}
],
"source": [
"print(f\"\\nMissing values:\")\n",
"print(df.isnull().sum())"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "bf14e3db-a1b4-4fad-8102-b7ac25feeefa",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Duplicate reviews: 422458\n"
]
}
],
"source": [
"print(f\"Duplicate reviews: {df.duplicated(subset=['review_description']).sum()}\")"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "8ccc07fa-9913-4047-ae17-35d2454eb059",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==========================================\n",
"1 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"Once drivers confirm the rider its showing with in 2 minutes but they take 25 minutes more and if driver cancel the ride I pay for that in next ride it's redicules\n",
"(Length: 32.0 words)\n",
"\n",
"they charge very high as they show before the ride\n",
"(Length: 10.0 words)\n",
"\n",
"scam drivers, worst service\n",
"(Length: 4.0 words)\n",
"\n",
"==========================================\n",
"2 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"Drivers always ask is destination and cancel if they dont want to go ? Cant they already see destination before accepting ride ?\n",
"(Length: 23.0 words)\n",
"\n",
"she hole her phone on her hand she driving 80\n",
"(Length: 10.0 words)\n",
"\n",
"I7u.6f هنه\n",
"(Length: 2.0 words)\n",
"\n",
"==========================================\n",
"3 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"I think this app is very important to me\n",
"(Length: 9.0 words)\n",
"\n",
"Ok\n",
"(Length: 1.0 words)\n",
"\n",
"The rate will be one while booking and after the ride it changes if asked the reason is due to traffic, but it should be mentioned first only, the destination time is also calculated by uber only alon...\n",
"(Length: 53.0 words)\n",
"\n",
"==========================================\n",
"4 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"Nice\n",
"(Length: 1.0 words)\n",
"\n",
"Good app but sometimes it take long time to get booking even the cabs are nearby and sometimes they even cancel the ride after confirming and making us wait for 30 mins and above\n",
"(Length: 34.0 words)\n",
"\n",
"its good and helpful.. Thank you\n",
"(Length: 6.0 words)\n",
"\n",
"==========================================\n",
"5 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"good service\n",
"(Length: 2.0 words)\n",
"\n",
"Drivers have been getting us home quickly and effectively.\n",
"(Length: 9.0 words)\n",
"\n",
"Hbby\n",
"(Length: 1.0 words)\n"
]
}
],
"source": [
"for rating in [1, 2, 3, 4, 5]:\n",
" samples = df[df['rating'] == rating].sample(min(3, len(df[df['rating'] == rating])))\n",
" print(f\"\\n{'='*42}\")\n",
" print(f\"{rating} STAR REVIEWS:\")\n",
" print(f\"{'='*42}\")\n",
" for idx, row in samples.iterrows():\n",
" review_text = row['review_description']\n",
" print(f\"\\n{review_text[:200]}{'...' if len(review_text) > 200 else ''}\")\n",
" print(f\"(Length: {row['word_count']} words)\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b12dcb89-d291-447a-98f3-02817dc0eb8e",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "87a15e76-51c8-4586-acea-ca3176c18757",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "73c4bbb9-3f8e-4b4c-8538-539b140cf610",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "reclass",
"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": "3.14.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

283
multitag/notebooks/uber_cleaned.ipynb Normal file
View File

@@ -0,0 +1,283 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "739e61bf",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import re\n",
"from langdetect import detect, LangDetectException\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "d9da1b98",
"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>review</th>\n",
" <th>rating</th>\n",
" <th>word_count</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>suddenly, the driver can't have my location an...</td>\n",
" <td>1</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>very cordial. and helped with a quick turnarou...</td>\n",
" <td>5</td>\n",
" <td>11</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>i have enjoyed traveling by uber my drivers ha...</td>\n",
" <td>5</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>app is good but main problem is the drivers ca...</td>\n",
" <td>1</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>very bad experience no customer service</td>\n",
" <td>1</td>\n",
" <td>6</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" review rating word_count\n",
"0 suddenly, the driver can't have my location an... 1 23\n",
"1 very cordial. and helped with a quick turnarou... 5 11\n",
"2 i have enjoyed traveling by uber my drivers ha... 5 23\n",
"3 app is good but main problem is the drivers ca... 1 23\n",
"4 very bad experience no customer service 1 6"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('data/uber_reviews_cleaned.csv')\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "91dc1d9a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"np.int64(6740)"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(df['word_count'] > 100).sum()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "827b6435",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Max length review:\n",
"i've been using uber for a few years now and for the most part haven't had any problems the only problem i have ever had that was never resolved or explained to me was when i was refunded cancellation fee because the driver pulled into me and then literally looked in my face and drove away and canceled the ride.buy still charges me.a cancellation fee the problem wasn't being charged the fee because i was reimbursed a few minutes later the problem was that they gave me a $5 uber credit and i don't have a debit card so i use uber gift cards so i had a balance on the gift card of roughly $4.85 and is an uber credit of $5 but for some reason you can't combine them to use on a single gel ride and there is a minimum of i think $6 or $7 for a ride so i was never able to use the money i was reimbursed and the remaing balance on my gift card was not enough for a full ride and that was 4 months ago and still have not been able to get a response as to how i can use the funds remaining mn my uber account or the uber credits i was reimbursed. another time the driver took between 7-10 minutes to set the destination and begin driving and then when i was trying to help her with the directions because the gps was bringing us rather far out of the way to reach out destination she was very rude with me and then when we were approaching the turn that we needed to make and i warned her that it was coming up shortly and then said a few more times as we got closer to it she drove passed it the reason i was making sure she was aware of this was because we were in a rather busy highway and she would not be able to turn again for quite some time and i was already cutting it close to being late for work due to the delay in starting the trip and her failure to follow the direction i was giving her to get to.our destination so i said pull over into.the gas station and i will walk it'll be faster then driving at this point but she failed to pull into parking lot she just stopped in the middle.lf the highway granted we were in the right lane but she still put us both in a very dangerous situation and we were in a bad section of newark nj at around 10pm which for most people would put them in an uncomfortable position seeing how as the crime rate is extremely high in this area luckily i'm familiar with the residence of the neighborhood because i lived there for a few years in the past and then she notified uber that i was a disgruntled passenger and made her nervous from my reaction and in was warned to not let anything like this happen again. and the final problem.i had with uber was when my mother had ordered me.an uber through her account and during the ride we some.how started to discuss religion and i'm far from a religious person i do not even consider myself a member of any type of religion at all. but my driver was very dedicated to the religion he practiced so he got very upset and decided to call mother and tell her that i didn't not go the full distance of the original route he was hired to drive and that he had dropped me off a few blocks from where j was going to judge in some illegal activities (he knew i had some personal issues i was overcoming recently because i had mention it to him briefly in the beginning of the trip) and that he was not going to charge her the full ride amount because i did. ot cimplete the full distance and this caused my mother to become very upset with me and called me extremely untilni sent her a picture showing that i was in fact where i said i was going and the app showed that he did drop me off at the predetermined destination. sorry for the long post but out of the probably 100 or so ride i have used with uber those were the only 3 problems i have ever had and they all 3 were actually in the same week\n"
]
}
],
"source": [
"print(f\"Max length review:\\n{df.loc[df['word_count'].idxmax(), 'review']}\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "7a811e3d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"np.int64(2839)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def has_spam_repetition(text):\n",
" return bool(re.search(r'(.)\\1{4,}', str(text)))\n",
"df['review'].apply(has_spam_repetition).sum()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "0a550434",
"metadata": {},
"outputs": [],
"source": [
"sample_check = df[df['word_count'] >= 10].sample(1000)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "ec7b2ec5",
"metadata": {},
"outputs": [],
"source": [
"def detect_language(text):\n",
" \"\"\"Detect language of text\"\"\"\n",
" try:\n",
" if pd.isna(text) or len(str(text).strip()) < 10:\n",
" return 'unknown'\n",
" return detect(str(text))\n",
" except LangDetectException:\n",
" return 'unknown'"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "d68dac67",
"metadata": {},
"outputs": [],
"source": [
"sample_check['lang'] = sample_check['review'].apply(detect_language)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "9a8a49b2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Language distribution in 10+ word reviews:\n",
"lang\n",
"en 939\n",
"id 12\n",
"es 10\n",
"pt 9\n",
"ar 7\n",
"ru 5\n",
"fr 3\n",
"af 2\n",
"no 2\n",
"et 1\n",
"ca 1\n",
"hi 1\n",
"tr 1\n",
"cs 1\n",
"bn 1\n",
"sv 1\n",
"it 1\n",
"so 1\n",
"ro 1\n",
"da 1\n",
"Name: count, dtype: int64\n"
]
}
],
"source": [
"print(f\"\\nLanguage distribution in 10+ word reviews:\")\n",
"print(sample_check['lang'].value_counts())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6cf91607",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "fd7576df-ce92-4c30-8466-34274290a934",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.14.0"
}
},
"nbformat": 4,
"nbformat_minor": 5
}