Spaces:
Running
Running
File size: 14,257 Bytes
f3d0f1e 38886c5 38166c5 38886c5 38166c5 38886c5 38166c5 f3d0f1e 58be4d5 85df319 38166c5 85df319 58be4d5 f3d0f1e 38886c5 38166c5 f3d0f1e 38166c5 f3d0f1e 38166c5 85df319 38166c5 85df319 38166c5 85df319 38166c5 f3d0f1e 85df319 38166c5 85df319 38166c5 85df319 38166c5 85df319 38166c5 85df319 38166c5 85df319 38166c5 85df319 38166c5 85df319 38166c5 85df319 38166c5 f3d0f1e 38886c5 f3d0f1e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import psycopg2\n",
"\n",
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"from langchain_community.document_loaders import DataFrameLoader\n",
"from langchain_community.embeddings import HuggingFaceEmbeddings\n",
"from langchain_community.vectorstores import FAISS\n",
"from datetime import datetime\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Retrieve Speeches"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# db_connection -----------------------------------------------------------\n",
"con_details = {\n",
" \"host\" : \"localhost\",\n",
" \"database\" : \"next\",\n",
" \"user\" : \"postgres\",\n",
" \"password\" : \"postgres\",\n",
" \"port\" : \"5433\"\n",
"}\n",
"con = psycopg2.connect(**con_details)\n",
"\n",
"# get data tables ---------------------------------------------------------\n",
"df = pd.read_sql_query(\"\"\"SELECT s.id,s.speech_content,s.date,f.abbreviation AS party\n",
" FROM open_discourse.speeches AS s\n",
" INNER JOIN open_discourse.factions AS f ON\n",
" s.faction_id = f.id;\"\"\", con)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Process speeches"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(set(df['party'].to_list()))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Removing keys from interruptions of a speech\n",
"df[\"speech_content\"].replace(\"\\({\\d+}\\)\", \"\", inplace=True, regex=True) \n",
"df['date'] = pd.to_datetime(df['date'])\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"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>id</th>\n",
" <th>speech_content</th>\n",
" <th>date</th>\n",
" <th>party</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>Meine Damen und Herren! Ich eröffne die 2. Sit...</td>\n",
" <td>1949-09-12</td>\n",
" <td>not found</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Der Bundesrat ist versammelt, Herr Präsident.\\n</td>\n",
" <td>1949-09-12</td>\n",
" <td>not found</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>Ich danke für diese Erklärung. Ich stelle dami...</td>\n",
" <td>1949-09-12</td>\n",
" <td>not found</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>Ja, ich habe den Wunsch.\\n</td>\n",
" <td>1949-09-12</td>\n",
" <td>not found</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>Ich erteile dem Herrn Bundespräsidenten das Wo...</td>\n",
" <td>1949-09-12</td>\n",
" <td>not found</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>930955</th>\n",
" <td>1084268</td>\n",
" <td>\\n\\nWir sind zwar Kollegen.</td>\n",
" <td>2022-12-16</td>\n",
" <td>not found</td>\n",
" </tr>\n",
" <tr>\n",
" <th>930956</th>\n",
" <td>1084269</td>\n",
" <td>\\n\\nLiebe, sehr geehrte Frau Präsidentin!</td>\n",
" <td>2022-12-16</td>\n",
" <td>CDU/CSU</td>\n",
" </tr>\n",
" <tr>\n",
" <th>930957</th>\n",
" <td>1084270</td>\n",
" <td>\\n\\nVielen Dank.</td>\n",
" <td>2022-12-16</td>\n",
" <td>not found</td>\n",
" </tr>\n",
" <tr>\n",
" <th>930958</th>\n",
" <td>1084272</td>\n",
" <td>\\n\\nDen Abschluss dieser Aktuellen Stunde bild...</td>\n",
" <td>2022-12-16</td>\n",
" <td>not found</td>\n",
" </tr>\n",
" <tr>\n",
" <th>930959</th>\n",
" <td>1084273</td>\n",
" <td>\\n\\nSehr geehrte Frau Präsidentin! Werte Kolle...</td>\n",
" <td>2022-12-16</td>\n",
" <td>SPD</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>930960 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" id speech_content date \\\n",
"0 0 Meine Damen und Herren! Ich eröffne die 2. Sit... 1949-09-12 \n",
"1 1 Der Bundesrat ist versammelt, Herr Präsident.\\n 1949-09-12 \n",
"2 2 Ich danke für diese Erklärung. Ich stelle dami... 1949-09-12 \n",
"3 3 Ja, ich habe den Wunsch.\\n 1949-09-12 \n",
"4 4 Ich erteile dem Herrn Bundespräsidenten das Wo... 1949-09-12 \n",
"... ... ... ... \n",
"930955 1084268 \\n\\nWir sind zwar Kollegen. 2022-12-16 \n",
"930956 1084269 \\n\\nLiebe, sehr geehrte Frau Präsidentin! 2022-12-16 \n",
"930957 1084270 \\n\\nVielen Dank. 2022-12-16 \n",
"930958 1084272 \\n\\nDen Abschluss dieser Aktuellen Stunde bild... 2022-12-16 \n",
"930959 1084273 \\n\\nSehr geehrte Frau Präsidentin! Werte Kolle... 2022-12-16 \n",
"\n",
" party \n",
"0 not found \n",
"1 not found \n",
"2 not found \n",
"3 not found \n",
"4 not found \n",
"... ... \n",
"930955 not found \n",
"930956 CDU/CSU \n",
"930957 not found \n",
"930958 not found \n",
"930959 SPD \n",
"\n",
"[930960 rows x 4 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Convert to proper time format\n",
"df['date'] = pd.to_datetime(df['date'])\n"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"def split_documents(df, min_chunk_size=100):\n",
" \"\"\"\n",
" Load documents from a DataFrame, split them into smaller chunks for vector storage and remove chunks of small size.\n",
"\n",
" Parameters\n",
" ----------\n",
" df : pandas.DataFrame\n",
" A DataFrame containing the documents to be processed, with a column named 'speech_content'.\n",
" min_chunk_size : int, optional\n",
" Minimum number of characters a chunk must have to be included in the result. Default is 100.\n",
"\n",
" Returns\n",
" -------\n",
" list\n",
" A list of split document chunks ready for further processing or vectorization.\n",
" \"\"\"\n",
" # Initialize a DataFrameLoader with the given DataFrame and specify the column containing the content to load\n",
" loader = DataFrameLoader(data_frame=df, page_content_column='speech_content')\n",
" # Load the data from the DataFrame into a suitable format for processing\n",
" data = loader.load()\n",
" # Initialize a RecursiveCharacterTextSplitter to split the text into chunks\n",
" splitter = RecursiveCharacterTextSplitter(\n",
" chunk_size=1024,\n",
" chunk_overlap=32,\n",
" length_function=len,\n",
" is_separator_regex=False,\n",
" )\n",
" # Split the loaded data into smaller chunks using the splitter\n",
" documents = splitter.split_documents(documents=data)\n",
" # Discard small chunks below the threshold\n",
" cleaned_documents = [doc for doc in documents if len(doc.page_content) >= min_chunk_size]\n",
"\n",
" return cleaned_documents"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Python\\Lib\\site-packages\\huggingface_hub\\file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Sucessfully created vector store for 1. legislature\n",
"Sucessfully created vector store for 2. legislature\n",
"Sucessfully created vector store for 3. legislature\n",
"Sucessfully created vector store for 4. legislature\n",
"Sucessfully created vector store for 5. legislature\n",
"Sucessfully created vector store for 6. legislature\n",
"Sucessfully created vector store for 7. legislature\n",
"Sucessfully created vector store for 8. legislature\n",
"Sucessfully created vector store for 9. legislature\n",
"Sucessfully created vector store for 10. legislature\n",
"Sucessfully created vector store for 11. legislature\n",
"Sucessfully created vector store for 12. legislature\n",
"Sucessfully created vector store for 13. legislature\n",
"Sucessfully created vector store for 14. legislature\n",
"Sucessfully created vector store for 15. legislature\n",
"Sucessfully created vector store for 16. legislature\n",
"Sucessfully created vector store for 17. legislature\n",
"Sucessfully created vector store for 18. legislature\n",
"Sucessfully created vector store for 19. legislature\n",
"Sucessfully created vector store for 20. legislature\n"
]
}
],
"source": [
"# Define starting dates of legislature periods\n",
"dates = [\"1953-10-06\", \"1957-10-16\", \"1961-10-17\", \"1965-10-19\", \"1969-10-20\", \"1972-12-13\", \"1976-12-14\", \"1980-11-04\", \"1983-03-29\", \"1987-02-18\",\"1990-12-20\", \"1994-11-10\", \"1998-10-26\", \"2002-10-17\", \"2005-10-18\", \"2009-10-27\", \"2013-10-22\",\"2017-10-24\",\"2021-10-26\", None]\n",
"# Load sentence transformer \n",
"embeddings = HuggingFaceEmbeddings(model_name=\"paraphrase-multilingual-MiniLM-L12-v2\")\n",
"\n",
"# Create vector store for all speaches\n",
"# Split text into documents for vectorstore\n",
"documents = split_documents(df)\n",
"# Create and save faiss vectorstorage\n",
"index_name = 'speeches_1949_09_12'\n",
"db = FAISS.from_documents(documents, embeddings)\n",
"db.save_local(folder_path=\"FAISS\", index_name=index_name)\n",
"print(\"Sucessfully created vector store for all legislature\")\n",
"\n",
"# Create vector store for each legislature\n",
"# loop parameters\n",
"period = 1\n",
"previous_date = None\n",
"\n",
"# Iterate over all date to split by legislature getting vector stores for each period\n",
"for date in dates:\n",
" if previous_date is None:\n",
" legislature_df = df.loc[df['date'] < datetime.strptime(date, \"%Y-%m-%d\")]\n",
" elif date is None:\n",
" legislature_df = df.loc[df['date'] >= datetime.strptime(previous_date, \"%Y-%m-%d\")]\n",
" else:\n",
" legislature_df = df.loc[(df['date'] >= datetime.strptime(previous_date, \"%Y-%m-%d\")) & (df['date'] < datetime.strptime(date, \"%Y-%m-%d\"))]\n",
"\n",
" \n",
" # Split text into documents for vectorstore\n",
" documents = split_documents(legislature_df)\n",
"\n",
" # Create and save faiss vectorstorage\n",
" index_name = f'{period}_legislature'\n",
" db = FAISS.from_documents(documents, embeddings)\n",
" db.save_local(folder_path=\"FAISS\", index_name=index_name)\n",
" print(f\"Sucessfully created vector store for {period}. legislature\")\n",
"\n",
" # Change loop parameters for next iteration\n",
" period += 1\n",
" previous_date = date\n",
"\n",
"\n",
" \n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This data has been uploaded to: https://huggingface.co/datasets/TomData/test"
]
}
],
"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": "3.11.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|