Added multitag, includes preprocess.py, sampler.py and multitag.py(the main gui for labelling/annotation)

This commit is contained in:
2025-11-06 17:40:29 +00:00
parent c0d4c13824
commit 4d6e2511e6
6 changed files with 1147 additions and 0 deletions

View File

@@ -0,0 +1,433 @@
{
"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": 23,
"id": "b855045e-2dd1-4fa1-ab5a-8ce8b50b02ee",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('data/uber_reviews.csv', low_memory=False)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"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": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 25,
"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": 26,
"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": 27,
"id": "1c97e396-8f05-4df7-bd0a-1bbecf6911b4",
"metadata": {},
"outputs": [],
"source": [
"short_reviews = df[df['word_count'] < 5]"
]
},
{
"cell_type": "code",
"execution_count": 28,
"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": 31,
"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": 35,
"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": 40,
"id": "8ccc07fa-9913-4047-ae17-35d2454eb059",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==========================================\n",
"1 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"cant put gift card on dont like app\n",
"(Length: 8.0 words)\n",
"\n",
"Zapłaciłem za przejazd, uber pobral środki z mojego konta. Potem byla aktualizacja ceny na niższą i znowu kazał płacić. Teraz aplikacja zablokowała się na ekranie potwierdzenia płatności.\n",
"(Length: 27.0 words)\n",
"\n",
"The app hasn't been able to process any payment. Takes forever to find a ride. I don't even know why this app still exists. Absolutely useless!\n",
"(Length: 26.0 words)\n",
"\n",
"==========================================\n",
"2 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"In spite of receiving payment and acknowledging by email the app shows \n",
"payment due and disallowed booking and service not available to me. 4 days \n",
"have lapsed no solution to my problem. Problem solvi...\n",
"(Length: 37.0 words)\n",
"\n",
"Poor\n",
"(Length: 1.0 words)\n",
"\n",
"I had to reset my password and now I cant get in. Its telling me that my phone number is already in use. I need this fixed\n",
"(Length: 27.0 words)\n",
"\n",
"==========================================\n",
"3 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"Nice\n",
"(Length: 1.0 words)\n",
"\n",
"Good rides\n",
"(Length: 2.0 words)\n",
"\n",
"Nice\n",
"(Length: 1.0 words)\n",
"\n",
"==========================================\n",
"4 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"Good service\n",
"(Length: 2.0 words)\n",
"\n",
"A mobile number of the car driver should be an icon if Uber book for any other person, then it can be given the number.\n",
"(Length: 25.0 words)\n",
"\n",
"many times pick up locations is shifted automatically . overall good much better\n",
"(Length: 13.0 words)\n",
"\n",
"==========================================\n",
"5 STAR REVIEWS:\n",
"==========================================\n",
"\n",
"So friendly. Thank you\n",
"(Length: 4.0 words)\n",
"\n",
"comfortable journey with effodable price\n",
"(Length: 5.0 words)\n",
"\n",
"Good\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": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}