Spaces:
Build error
Build error
File size: 22,424 Bytes
0dec8a3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"workding dir: /Users/inflaton/code/engd/papers/maritime/global-incidents\n",
"loading env vars from: /Users/inflaton/code/engd/papers/maritime/global-incidents/.env\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
"\n",
"import os\n",
"import sys\n",
"from pathlib import Path\n",
"\n",
"workding_dir = str(Path.cwd().parent)\n",
"os.chdir(workding_dir)\n",
"sys.path.append(workding_dir)\n",
"print(\"workding dir:\", workding_dir)\n",
"\n",
"from dotenv import find_dotenv, load_dotenv\n",
"\n",
"found_dotenv = find_dotenv(\".env\")\n",
"\n",
"if len(found_dotenv) == 0:\n",
" found_dotenv = find_dotenv(\".env.example\")\n",
"print(f\"loading env vars from: {found_dotenv}\")\n",
"load_dotenv(found_dotenv, override=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### The file aims for the demonstration of the methdology pipeline, please used our new designed database (new excel attached )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### The following code is when user put a new news article link into the model, the model will extract the headline , Date and Content"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Headline: Singapore Airlines stops using Iranian airspace as 'precautionary measure' amid Middle East tensions\n",
"Publication Date: 2024-04-14 08:58:00\n",
"Content: Advertisement Singapore Singapore Airlines stops using Iranian airspace as 'precautionary measure' amid Middle East tensions Singapore Airlines says it is closely monitoring the situation in the Middle East. (File photo: REUTERS/Edgar Su) New: You can now listen to articles. This audio is generated by an AI tool. 14 Apr 2024 08:58AM (Updated: 14 Apr 2024 07:26PM) Bookmark Bookmark Share WhatsApp Telegram Facebook Twitter Email LinkedIn SINGAPORE: Singapore Airlines (SIA) said on Sunday (Apr 14) \n"
]
}
],
"source": [
"import requests\n",
"from bs4 import BeautifulSoup\n",
"from datetime import datetime\n",
"\n",
"\n",
"def get_article_details(article_url):\n",
" response = requests.get(article_url)\n",
" soup = BeautifulSoup(response.content, \"html.parser\")\n",
"\n",
" # Extract headline\n",
" headline_tag = soup.find(\"h1\")\n",
" headline = (\n",
" headline_tag.get_text(strip=True) if headline_tag else \"No headline found\"\n",
" )\n",
"\n",
" # Attempt to extract publication date with error handling\n",
" date_container = soup.find(\"div\", class_=\"article-publish\")\n",
" if date_container:\n",
" # Extract the text and handle cleaning it up\n",
" date_text = date_container.get_text(strip=True)\n",
" # Extract the first date assuming it's the publication date (before \"Updated:\")\n",
" publication_date_text = date_text.split(\"(Updated:\")[0].strip()\n",
" try:\n",
" publication_date = datetime.strptime(\n",
" publication_date_text, \"%d %b %Y %I:%M%p\"\n",
" ).strftime(\"%Y-%m-%d %H:%M:%S\")\n",
" except ValueError:\n",
" publication_date = \"No publication date found\"\n",
" else:\n",
" publication_date = \"No publication date found\"\n",
"\n",
" # Extract main content of the article\n",
" article_body = soup.find(\"article\")\n",
" if not article_body:\n",
" article_body = soup\n",
" article_text = (\n",
" article_body.get_text(separator=\" \", strip=True)\n",
" if article_body\n",
" else \"No article content found\"\n",
" )\n",
"\n",
" return headline, publication_date, article_text\n",
"\n",
"\n",
"# Example usage\n",
"article_url = \"https://www.channelnewsasia.com/singapore/singapore-airlines-stops-using-iran-airspace-israel-hamas-war-middle-east-escalation-4264011\"\n",
"headline, publication_date, article_content = get_article_details(article_url)\n",
"print(\"Headline:\", headline)\n",
"print(\"Publication Date:\", publication_date)\n",
"print(\"Content:\", article_content[:500]) # Print the first 500 characters to check"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Here is the code for Summarization of the aritlce (PLEASE USE UR OWN OPENAI KEY HAHA)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Summary: Singapore Airlines has stopped using Iranian airspace as a precautionary measure due to the escalating tensions in the Middle East. This move was mirrored by other airlines, including Lufthansa and Austrian Airlines, who also suspended flights to and from Tehran. The situation has also led to economic consequences, as flights\n"
]
}
],
"source": [
"import openai\n",
"\n",
"\n",
"def summarize_article(article_content):\n",
" try:\n",
" # Generating the prompt for GPT-3\n",
" prompt_text = (\n",
" \"Summarize the following article in about 70 words, focusing on \"\n",
" \"what happened, where it happened, and the consequences (economic loss, environmental impact, etc.):\\n\\n\"\n",
" f\"{article_content}\"\n",
" )\n",
"\n",
" # Call to OpenAI's Completion API\n",
" response = openai.Completion.create(\n",
" engine=\"gpt-3.5-turbo-instruct\",\n",
" prompt=prompt_text,\n",
" temperature=0.5,\n",
" max_tokens=60, # Adjust as needed to fit the summary length\n",
" top_p=1,\n",
" frequency_penalty=0,\n",
" presence_penalty=0,\n",
" )\n",
"\n",
" # Extracting the text from the response\n",
" summary = response.choices[0].text.strip()\n",
" return summary\n",
" except Exception as e:\n",
" print(f\"An error occurred: {e}\")\n",
" return \"\"\n",
"\n",
"\n",
"summary = summarize_article(article_content)\n",
"print(\"Summary:\", summary)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# unique_categories = df['Category'].unique()\n",
"# print(unique_categories)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"import openai\n",
"\n",
"\n",
"def classify_article(article_content):\n",
" prompt = f\"\"\"Read the following article and classify its content into one of these categories: 'Aviation Advisory',\n",
"'Bombing',\n",
"'Cargo Disruption',\n",
"'Warehouse Theft',\n",
"'Chemical Spill',\n",
"'Injury',\n",
"'Earthquake',\n",
"'Flooding',\n",
"'Ground Transportation Advisory',\n",
"'Hazmat Response',\n",
"'Ice Storm',\n",
"'Individuals in Focus',\n",
"'Industrial Action',\n",
"'Maritime Accident',\n",
"'Maritime Accident.Ground Transportation Advisory',\n",
"'Maritime Advisory',\n",
"'Mine Workers Strike',\n",
"'Miscellaneous Events',\n",
"'Miscellaneous Strikes',\n",
"'Network Disruption',\n",
"'Non-industrial Fire',\n",
"'Police Operations',\n",
"'Port Closure',\n",
"'Port Congestion',\n",
"'Port Disruption',\n",
"'Power Outage',\n",
"'Production Halt',\n",
"'Protest',\n",
"'Public Safety ,\n",
"'Public Transportation Disruption',\n",
"'Roadway Closuren',\n",
"'Severe Winds',\n",
"'Storm',\n",
"'Tornado',\n",
"'Train Delays,\n",
"'Travel Warning',\n",
"'Tropical Cyclone Storm',\n",
"'Typhoon',\n",
"'Vehicle Accident',\n",
"'Weather Advisory',\n",
"'Workplace Accident'\n",
"Summary: {article_content}\n",
"Category:\"\"\"\n",
"\n",
" response = openai.Completion.create(\n",
" engine=\"gpt-3.5-turbo-instruct\", # Adjust according to the latest available and appropriate model\n",
" prompt=prompt,\n",
" temperature=0.7,\n",
" max_tokens=60, # Adjust based on your needs\n",
" top_p=1.0,\n",
" frequency_penalty=0,\n",
" presence_penalty=0,\n",
" stop=[\"\\n\"], # Stop generating further when a newline character is encountered\n",
" )\n",
" category = response.choices[0].text.strip()\n",
" return category"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"from bs4 import BeautifulSoup\n",
"\n",
"\n",
"def fetch_article_content(url):\n",
" response = requests.get(url)\n",
" soup = BeautifulSoup(response.content, \"html.parser\")\n",
" article_text = \" \".join([p.text for p in soup.find_all(\"p\")])\n",
" return article_text"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Category: Aviation Advisory\n"
]
}
],
"source": [
"import openai\n",
"\n",
"\n",
"def classify_article(url):\n",
" # Fetch article content\n",
" article_content = fetch_article_content(url)\n",
"\n",
" # Construct the classification prompt\n",
" prompt = f\"\"\"Read the following article and classify its content into one of these categories:\n",
" 'Aviation Advisory', 'Bombing',\n",
"'Cargo Disruption',\n",
"'Chemical Spill',\n",
"'Death',\n",
"'Earthquake',\n",
"'Flooding',\n",
"'Ground Transportation Advisory',\n",
"'Hazmat Response',\n",
"'Ice Storm',\n",
"'Individuals in Focus',\n",
"'Industrial Action',\n",
"'Maritime Accident',\n",
"'Maritime Accident.Ground Transportation Advisory',\n",
"'Maritime Advisory',\n",
"'Mine Workers Strike',\n",
"'Miscellaneous Events',\n",
"'Miscellaneous Strikes',\n",
"'Network Disruption',\n",
"'Non-industrial Fire',\n",
"'Police Operations',\n",
"'Port Closure',\n",
"'Port Congestion',\n",
"'Port Disruption',\n",
"'Power Outage',\n",
"'Production Halt',\n",
"'Protest / Riot',\n",
"'Public Safety / Security',\n",
"'Public Transportation Disruption',\n",
"'Roadway Closure / Disruption',\n",
"'Severe Winds',\n",
"'Storm',\n",
"'Tornado',\n",
"'Train Delays / Disruption',\n",
"'Travel Warning',\n",
"'Tropical Cyclone / Storm',\n",
"'Typhoon',\n",
"'Vehicle Accident',\n",
"'Weather Advisory',\n",
"'Workplace Accident', ...\n",
" \n",
" Article:\n",
" {article_content}\n",
" \n",
" Category:\"\"\"\n",
"\n",
" # Classify using OpenAI GPT-3\n",
" response = openai.Completion.create(\n",
" engine=\"gpt-3.5-turbo-instruct\", # Ensure using a correct and non-deprecated model\n",
" prompt=prompt,\n",
" temperature=0.7,\n",
" max_tokens=60,\n",
" top_p=1.0,\n",
" frequency_penalty=0,\n",
" presence_penalty=0,\n",
" stop=[\"\\n\"], # Stop generating further when a newline character is encountered\n",
" )\n",
" category = response.choices[0].text.strip()\n",
" return category\n",
"\n",
"\n",
"# Example usage\n",
"url = \"https://www.channelnewsasia.com/singapore/singapore-airlines-stops-using-iran-airspace-israel-hamas-war-middle-east-escalation-4264011\"\n",
"category = classify_article(url)\n",
"print(\"Category:\", category)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Now you the classfication result, which is quite accurate :))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Singapore Airlines stops using Iranian airspace as 'precautionary measure' amid Middle East tensions\n"
]
}
],
"source": [
"print(headline)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Update our database!"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Database updated successfully with ID 1.\n"
]
}
],
"source": [
"import pandas as pd\n",
"from datetime import datetime\n",
"\n",
"\n",
"def update_database(file_path, url):\n",
" # Fetch details from the article\n",
" headline, publication_date, article_content = get_article_details(article_url)\n",
" summary = summarize_article(article_content)\n",
" category = classify_article(url)\n",
"\n",
" new_data = {\n",
" \"Headline\": headline,\n",
" \"Summary\": summary,\n",
" \"Category\": category,\n",
" \"Datetime\": publication_date,\n",
" \"URL\": article_url,\n",
" }\n",
"\n",
" # Load the existing data from the CSV file\n",
" try:\n",
" df = pd.read_csv(file_path)\n",
" except FileNotFoundError:\n",
" # If the file does not exist, create a new DataFrame\n",
" df = pd.DataFrame(\n",
" columns=[\"id\", \"Headline\", \"Summary\", \"Category\", \"Datetime\", \"URL\"]\n",
" )\n",
" new_id = 1 # Start with ID 1 if no file exists\n",
" else:\n",
" # If IDs exist, increment from the last used ID\n",
" new_id = df[\"id\"].max() + 1 if not df.empty else 1\n",
"\n",
" # Prepare the new data entry\n",
" new_entry = pd.DataFrame(\n",
" {\n",
" \"id\": [new_id],\n",
" \"Headline\": [new_data[\"Headline\"]],\n",
" \"Summary\": [new_data[\"Summary\"]],\n",
" \"Category\": [new_data[\"Category\"]],\n",
" \"Datetime\": [new_data[\"Datetime\"]],\n",
" \"URL\": [new_data[\"URL\"]],\n",
" }\n",
" )\n",
"\n",
" # Append the new data entry to the DataFrame using concat\n",
" df = pd.concat([df, new_entry], ignore_index=True)\n",
"\n",
" # Save the updated DataFrame back to CSV\n",
" df.to_csv(file_path, index=False)\n",
" print(f\"Database updated successfully with ID {new_id}.\")\n",
"\n",
"\n",
"# Example usage\n",
"url = \"https://www.channelnewsasia.com/singapore/singapore-airlines-stops-using-iran-airspace-israel-hamas-war-middle-east-escalation-4264011\"\n",
"file_path = \"cleaned_data1.csv\"\n",
"update_database(file_path, url)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" id Headline \\\n",
"0 1 Singapore Airlines stops using Iranian airspac... \n",
"\n",
" Summary Category \\\n",
"0 Singapore Airlines has stopped using Iranian a... Aviation Advisory \n",
"\n",
" Datetime URL \n",
"0 2024-04-14 08:58:00 https://www.channelnewsasia.com/singapore/sing... \n"
]
}
],
"source": [
"import pandas as pd\n",
"\n",
"\n",
"def rank_related_articles(file_path, category):\n",
" # Load the existing data from the CSV file\n",
" try:\n",
" df = pd.read_csv(file_path)\n",
" except FileNotFoundError:\n",
" print(\"Database file not found.\")\n",
" return\n",
"\n",
" # Filter articles by the specified category\n",
" filtered_df = df[df[\"Category\"] == category]\n",
"\n",
" # Convert 'Datetime' from string to datetime objects for accurate sorting\n",
" filtered_df[\"Datetime\"] = pd.to_datetime(filtered_df[\"Datetime\"])\n",
"\n",
" # Sort articles by 'Datetime' in descending order to get the most recent articles first\n",
" sorted_df = filtered_df.sort_values(by=\"Datetime\", ascending=False)\n",
"\n",
" # Display the sorted DataFrame\n",
" print(sorted_df[[\"id\", \"Headline\", \"Summary\", \"Category\", \"Datetime\", \"URL\"]])\n",
" return sorted_df\n",
"\n",
"\n",
"# Example usage\n",
"file_path = \"cleaned_data1.csv\"\n",
"category = \"Aviation Advisory\"\n",
"ranked_articles = rank_related_articles(file_path, category)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"+----+------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------+---------------------+----------------------------------------------------------------------------------------------------------------------------------------+\n",
"| id | Headline | Summary | Category | Datetime | URL |\n",
"+----+------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------+---------------------+----------------------------------------------------------------------------------------------------------------------------------------+\n",
"| 1 | Singapore Airlines stops using Iranian airspace as 'precautionary measure' amid Middle East tensions | Singapore Airlines has stopped using Iranian airspace as a precautionary measure amid the escalating tensions in the Middle East. This decision was made after Iran launched over 200 drones and missiles at Israel, following an Israeli strike on an Iranian building in Syria. Other airlines, such as Lufthansa and Austrian | Aviation Advisory | 2024-04-14 08:58:00 | https://www.channelnewsasia.com/singapore/singapore-airlines-stops-using-iran-airspace-israel-hamas-war-middle-east-escalation-4264011 |\n",
"+----+------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------+---------------------+----------------------------------------------------------------------------------------------------------------------------------------+\n"
]
}
],
"source": [
"import pandas as pd\n",
"from tabulate import tabulate\n",
"\n",
"\n",
"def print_ranked_articles_tabulate(file_path, category):\n",
" try:\n",
" df = pd.read_csv(file_path)\n",
" df[\"Datetime\"] = pd.to_datetime(df[\"Datetime\"])\n",
" filtered_df = df[df[\"Category\"] == category]\n",
" sorted_df = filtered_df.sort_values(by=\"Datetime\", ascending=False)\n",
"\n",
" # Print DataFrame using tabulate\n",
" print(tabulate(sorted_df, headers=\"keys\", tablefmt=\"pretty\", showindex=False))\n",
" except FileNotFoundError:\n",
" print(\"Database file not found.\")\n",
"\n",
"\n",
"# Example usage\n",
"file_path = \"cleaned_data1.csv\"\n",
"category = \"Aviation Advisory\"\n",
"print_ranked_articles_tabulate(file_path, category)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"!rm cleaned_data1.csv"
]
}
],
"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": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|