{ "cells": [ { "cell_type": "code", "execution_count": 33, "id": "79ac71dd", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 34, "id": "aa9117f0", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
sourcereview_iduser_namereview_titlereview_descriptionratingthumbs_upreview_datedeveloper_responsedeveloper_response_dateappVersionlaguage_codecountry_code
0Google Play18d6584c-d0e9-4833-a744-f607058aee97Milky WayNaNSuddenly, the driver can't have my location an...10.02023-08-10 17:48:51NaNNaNNaNenin
1Google Play50a08f18-cece-4ddf-b617-028844c8aa28Bradlee SeveraNaNVery cordial.. And helped with a quick turnaro...50.02023-08-10 17:38:35NaNNaN4.485.10000enin
2Google Playb0d8e75a-80a7-4dcd-abaf-72b046dbeeb7Amit AggarwalNaNVery good experience50.02023-08-10 17:38:17NaNNaN4.486.10002enin
3Google Play502702a9-25ed-4373-a96c-7fa1f06caacdBryant InmanNaNAll I use50.02023-08-10 17:37:45NaNNaN4.467.10008enin
4Google Playf47a3fb6-23db-49bd-9e63-f33c8d724d07Addie WhittakerNaNI have enjoyed traveling by Uber my drivers ha...50.02023-08-10 17:36:56NaNNaN4.486.10002enin
\n", "
" ], "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": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_csv(\"../data/raw/uber_reviews.csv\", low_memory=False)\n", "df.head(5)" ] }, { "cell_type": "code", "execution_count": 35, "id": "36683790", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 1069616 entries, 0 to 1069615\n", "Data columns (total 13 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 source 1069616 non-null str \n", " 1 review_id 1069616 non-null str \n", " 2 user_name 1069615 non-null str \n", " 3 review_title 2180 non-null str \n", " 4 review_description 1069447 non-null str \n", " 5 rating 1069616 non-null int64 \n", " 6 thumbs_up 1067436 non-null float64\n", " 7 review_date 1069616 non-null str \n", " 8 developer_response 198264 non-null str \n", " 9 developer_response_date 197278 non-null str \n", " 10 appVersion 828068 non-null str \n", " 11 laguage_code 1069616 non-null str \n", " 12 country_code 1069616 non-null str \n", "dtypes: float64(1), int64(1), str(11)\n", "memory usage: 106.1 MB\n" ] } ], "source": [ "df.info()" ] }, { "cell_type": "code", "execution_count": null, "id": "0b1c7f73", "metadata": {}, "outputs": [], "source": [ "df = df[['review_description']].reset_index(drop=True)\n" ] }, { "cell_type": "code", "execution_count": 37, "id": "90e6d653", "metadata": {}, "outputs": [], "source": [ "df.head(5)\n", "df.to_csv(\"../data/raw/review_description.csv\", index=False)" ] } ], "metadata": { "kernelspec": { "display_name": "multitag", "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": "3.11.15" } }, "nbformat": 4, "nbformat_minor": 5 }