File size: 29,434 Bytes
440e9c3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "4ba6aba8"
},
"source": [
"# \ud83e\udd16 **Data Collection, Creation, Storage, and Processing**\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "jpASMyIQMaAq"
},
"source": [
"## **1.** \ud83d\udce6 Install required packages"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "f48c8f8c",
"outputId": "13d0dd5e-82c6-489f-b1f0-e970186a4eb7"
},
"outputs": [],
"source": [
"!pip install beautifulsoup4 pandas matplotlib seaborn numpy textblob"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "lquNYCbfL9IM"
},
"source": [
"## **2.** \u26cf Web-scrape all book titles, prices, and ratings from books.toscrape.com"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0IWuNpxxYDJF"
},
"source": [
"### *a. Initial setup*\n",
"Define the base url of the website you will scrape as well as how and what you will scrape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "91d52125"
},
"outputs": [],
"source": [
"import requests\n",
"from bs4 import BeautifulSoup\n",
"import pandas as pd\n",
"import time\n",
"\n",
"base_url = \"https://books.toscrape.com/catalogue/page-{}.html\"\n",
"headers = {\"User-Agent\": \"Mozilla/5.0\"}\n",
"\n",
"titles, prices, ratings = [], [], []"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "oCdTsin2Yfp3"
},
"source": [
"### *b. Fill titles, prices, and ratings from the web pages*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "xqO5Y3dnYhxt"
},
"outputs": [],
"source": [
"# Loop through all 50 pages\n",
"for page in range(1, 51):\n",
" url = base_url.format(page)\n",
" response = requests.get(url, headers=headers)\n",
" soup = BeautifulSoup(response.content, \"html.parser\")\n",
" books = soup.find_all(\"article\", class_=\"product_pod\")\n",
"\n",
" for book in books:\n",
" titles.append(book.h3.a[\"title\"])\n",
" prices.append(float(book.find(\"p\", class_=\"price_color\").text[1:]))\n",
" ratings.append(book.p.get(\"class\")[1])\n",
"\n",
" time.sleep(0.5) # polite scraping delay"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "T0TOeRC4Yrnn"
},
"source": [
"### *c. \u270b\ud83c\udffb\ud83d\uded1\u26d4\ufe0f Create a dataframe df_books that contains the now complete \"title\", \"price\", and \"rating\" objects*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "l5FkkNhUYTHh"
},
"outputs": [],
"source": [
"df_books = pd.DataFrame({\n",
" \"title\": titles,\n",
" \"price\": prices,\n",
" \"rating\": ratings\n",
"})\n",
"print(f\"Scraped {len(df_books)} books.\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "duI5dv3CZYvF"
},
"source": [
"### *d. Save web-scraped dataframe either as a CSV or Excel file*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "lC1U_YHtZifh"
},
"outputs": [],
"source": [
"# \ud83d\udcbe Save to CSV\n",
"df_books.to_csv(\"books_data.csv\", index=False)\n",
"\n",
"# \ud83d\udcbe Or save to Excel\n",
"# df_books.to_excel(\"books_data.xlsx\", index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qMjRKMBQZlJi"
},
"source": [
"### *e. \u270b\ud83c\udffb\ud83d\uded1\u26d4\ufe0f View first fiew lines*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "O_wIvTxYZqCK",
"outputId": "349b36b0-c008-4fd5-d4a4-dba38ae18337"
},
"outputs": [],
"source": [
"df_books.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "p-1Pr2szaqLk"
},
"source": [
"## **3.** \ud83e\udde9 Create a meaningful connection between real & synthetic datasets"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "SIaJUGIpaH4V"
},
"source": [
"### *a. Initial setup*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "-gPXGcRPuV_9"
},
"outputs": [],
"source": [
"import numpy as np\n",
"import random\n",
"from datetime import datetime\n",
"import warnings\n",
"\n",
"warnings.filterwarnings(\"ignore\")\n",
"random.seed(2025)\n",
"np.random.seed(2025)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "pY4yCoIuaQqp"
},
"source": [
"### *b. Generate popularity scores based on rating (with some randomness) with a generate_popularity_score function*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "mnd5hdAbaNjz"
},
"outputs": [],
"source": [
"def generate_popularity_score(rating):\n",
" base = {\"One\": 2, \"Two\": 3, \"Three\": 3, \"Four\": 4, \"Five\": 4}.get(rating, 3)\n",
" trend_factor = random.choices([-1, 0, 1], weights=[1, 3, 2])[0]\n",
" return int(np.clip(base + trend_factor, 1, 5))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "n4-TaNTFgPak"
},
"source": [
"### *c. \u270b\ud83c\udffb\ud83d\uded1\u26d4\ufe0f Run the function to create a \"popularity_score\" column from \"rating\"*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "V-G3OCUCgR07"
},
"outputs": [],
"source": [
"df_books[\"popularity_score\"] = df_books[\"rating\"].apply(generate_popularity_score)\n",
"df_books[[\"title\", \"rating\", \"popularity_score\"]].head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HnngRNTgacYt"
},
"source": [
"### *d. Decide on the sentiment_label based on the popularity score with a get_sentiment function*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "kUtWmr8maZLZ"
},
"outputs": [],
"source": [
"def get_sentiment(popularity_score):\n",
" if popularity_score <= 2:\n",
" return \"negative\"\n",
" elif popularity_score == 3:\n",
" return \"neutral\"\n",
" else:\n",
" return \"positive\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HF9F9HIzgT7Z"
},
"source": [
"### *e. \u270b\ud83c\udffb\ud83d\uded1\u26d4\ufe0f Run the function to create a \"sentiment_label\" column from \"popularity_score\"*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "tafQj8_7gYCG"
},
"outputs": [],
"source": [
"df_books[\"sentiment_label\"] = df_books[\"popularity_score\"].apply(get_sentiment)\n",
"df_books[[\"title\", \"rating\", \"popularity_score\", \"sentiment_label\"]].head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "T8AdKkmASq9a"
},
"source": [
"## **4.** \ud83d\udcc8 Generate synthetic book sales data of 18 months"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OhXbdGD5fH0c"
},
"source": [
"### *a. Create a generate_sales_profit function that would generate sales patterns based on sentiment_label (with some randomness)*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "qkVhYPXGbgEn"
},
"outputs": [],
"source": [
"def generate_sales_profile(sentiment):\n months = pd.date_range(end=datetime.today(), periods=18, freq=\"ME\")\n\n if sentiment == \"positive\":\n base = random.randint(200, 300)\n trend = np.linspace(base, base + random.randint(20, 60), len(months))\n elif sentiment == \"negative\":\n base = random.randint(20, 80)\n trend = np.linspace(base, base - random.randint(10, 30), len(months))\n else: # neutral\n base = random.randint(80, 160)\n trend = np.full(len(months), base + random.randint(-10, 10))\n\n seasonality = 10 * np.sin(np.linspace(0, 3 * np.pi, len(months)))\n noise = np.random.normal(0, 5, len(months))\n monthly_sales = np.clip(trend + seasonality + noise, a_min=0, a_max=None).astype(int)\n\n return list(zip(months.strftime(\"%Y-%m\"), monthly_sales))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "L2ak1HlcgoTe"
},
"source": [
"### *b. Run the function as part of building sales_data*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "SlJ24AUafoDB"
},
"outputs": [],
"source": [
"sales_data = []\n",
"for _, row in df_books.iterrows():\n",
" records = generate_sales_profile(row[\"sentiment_label\"])\n",
" for month, units in records:\n",
" sales_data.append({\n",
" \"title\": row[\"title\"],\n",
" \"month\": month,\n",
" \"units_sold\": units,\n",
" \"sentiment_label\": row[\"sentiment_label\"]\n",
" })"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4IXZKcCSgxnq"
},
"source": [
"### *c. \u270b\ud83c\udffb\ud83d\uded1\u26d4\ufe0f Create a df_sales DataFrame from sales_data*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "wcN6gtiZg-ws"
},
"outputs": [],
"source": [
"df_sales = pd.DataFrame(sales_data)\n",
"print(f\"Generated {len(df_sales)} sales records.\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "EhIjz9WohAmZ"
},
"source": [
"### *d. Save df_sales as synthetic_sales_data.csv & view first few lines*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "MzbZvLcAhGaH",
"outputId": "c692bb04-7263-4115-a2ba-c72fe0180722"
},
"outputs": [],
"source": [
"df_sales.to_csv(\"synthetic_sales_data.csv\", index=False)\n",
"\n",
"print(df_sales.head())"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "7g9gqBgQMtJn"
},
"source": [
"## **5.** \ud83c\udfaf Generate synthetic customer reviews"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Gi4y9M9KuDWx"
},
"source": [
"### *a. \u270b\ud83c\udffb\ud83d\uded1\u26d4\ufe0f Ask ChatGPT to create a list of 50 distinct generic book review texts for the sentiment labels \"positive\", \"neutral\", and \"negative\" called synthetic_reviews_by_sentiment*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "b3cd2a50"
},
"outputs": [],
"source": [
"synthetic_reviews_by_sentiment = {\n",
" \"positive\": [\n",
" \"A compelling and heartwarming read that stayed with me long after I finished.\",\n",
" \"Brilliantly written! The characters were unforgettable and the plot was engaging.\",\n",
" \"One of the best books I've read this year \u2014 inspiring and emotionally rich.\",\n",
" \"The author's storytelling was vivid and powerful. Highly recommended!\",\n",
" \"An absolute masterpiece. I couldn't put it down from start to finish.\",\n",
" \"Gripping, intelligent, and beautifully crafted \u2014 I loved every page.\",\n",
" \"The emotional depth and layered narrative were just perfect.\",\n",
" \"A thought-provoking journey with stunning character development.\",\n",
" \"Everything about this book just clicked. A top-tier read!\",\n",
" \"A flawless blend of emotion, intrigue, and style. Truly impressive.\",\n",
" \"Absolutely stunning work of fiction. Five stars from me.\",\n",
" \"Remarkably executed with breathtaking prose.\",\n",
" \"The pacing was perfect and I was hooked from page one.\",\n",
" \"Heartfelt and hopeful \u2014 a story well worth telling.\",\n",
" \"A vivid journey through complex emotions and stunning imagery.\",\n",
" \"This book had soul. Every word felt like it mattered.\",\n",
" \"It delivered more than I ever expected. Powerful and wise.\",\n",
" \"The characters leapt off the page and into my heart.\",\n",
" \"I could see every scene clearly in my mind \u2014 beautifully descriptive.\",\n",
" \"Refreshing, original, and impossible to forget.\",\n",
" \"A radiant celebration of resilience and love.\",\n",
" \"Powerful themes handled with grace and insight.\",\n",
" \"An unforgettable literary experience.\",\n",
" \"The best book club pick we've had all year.\",\n",
" \"A layered, lyrical narrative that resonates deeply.\",\n",
" \"Surprising, profound, and deeply humane.\",\n",
" \"One of those rare books I wish I could read again for the first time.\",\n",
" \"Both epic and intimate \u2014 a perfect balance.\",\n",
" \"It reads like a love letter to the human spirit.\",\n",
" \"Satisfying and uplifting with a memorable ending.\",\n",
" \"This novel deserves every bit of praise it gets.\",\n",
" \"Introspective, emotional, and elegantly composed.\",\n",
" \"A tour de force in contemporary fiction.\",\n",
" \"Left me smiling, teary-eyed, and completely fulfilled.\",\n",
" \"A novel with the rare ability to entertain and enlighten.\",\n",
" \"Incredibly moving. I highlighted so many lines.\",\n",
" \"A smart, sensitive take on relationships and identity.\",\n",
" \"You feel wiser by the end of it.\",\n",
" \"A gorgeously crafted tale about hope and second chances.\",\n",
" \"Poignant and real \u2014 a beautiful escape.\",\n",
" \"Brims with insight and authenticity.\",\n",
" \"Compelling characters and a satisfying plot.\",\n",
" \"An empowering and important read.\",\n",
" \"Elegantly crafted and deeply humane.\",\n",
" \"Taut storytelling that never lets go.\",\n",
" \"Each chapter offered a new treasure.\",\n",
" \"Lyrical writing that stays with you.\",\n",
" \"A wonderful blend of passion and thoughtfulness.\",\n",
" \"Uplifting, honest, and completely engrossing.\",\n",
" \"This one made me believe in storytelling again.\",\n",
" ],\n",
" \"neutral\": [\n",
" \"An average book \u2014 not great, but not bad either.\",\n",
" \"Some parts really stood out, others felt a bit flat.\",\n",
" \"It was okay overall. A decent way to pass the time.\",\n",
" \"The writing was fine, though I didn't fully connect with the story.\",\n",
" \"Had a few memorable moments but lacked depth in some areas.\",\n",
" \"A mixed experience \u2014 neither fully engaging nor forgettable.\",\n",
" \"There was potential, but it didn't quite come together for me.\",\n",
" \"A reasonable effort that just didn't leave a lasting impression.\",\n",
" \"Serviceable but not something I'd go out of my way to recommend.\",\n",
" \"Not much to dislike, but not much to rave about either.\",\n",
" \"It had its strengths, though they didn't shine consistently.\",\n",
" \"I'm on the fence \u2014 parts were enjoyable, others not so much.\",\n",
" \"The book had a unique concept but lacked execution.\",\n",
" \"A middle-of-the-road read.\",\n",
" \"Engaging at times, but it lost momentum.\",\n",
" \"Would have benefited from stronger character development.\",\n",
" \"It passed the time, but I wouldn't reread it.\",\n",
" \"The plot had some holes that affected immersion.\",\n",
" \"Mediocre pacing made it hard to stay invested.\",\n",
" \"Satisfying in parts, underwhelming in others.\",\n",
" \"Neutral on this one \u2014 didn't love it or hate it.\",\n",
" \"Fairly forgettable but with glimpses of promise.\",\n",
" \"The themes were solid, but not well explored.\",\n",
" \"Competent, just not compelling.\",\n",
" \"Had moments of clarity and moments of confusion.\",\n",
" \"I didn't regret reading it, but I wouldn't recommend it.\",\n",
" \"Readable, yet uninspired.\",\n",
" \"There was a spark, but it didn't ignite.\",\n",
" \"A slow burn that didn't quite catch fire.\",\n",
" \"I expected more nuance given the premise.\",\n",
" \"A safe, inoffensive choice.\",\n",
" \"Some parts lagged, others piqued my interest.\",\n",
" \"Decent, but needed polish.\",\n",
" \"Moderately engaging but didn't stick the landing.\",\n",
" \"It simply lacked that emotional punch.\",\n",
" \"Just fine \u2014 no better, no worse.\",\n",
" \"Some thoughtful passages amid otherwise dry writing.\",\n",
" \"I appreciated the ideas more than the execution.\",\n",
" \"Struggled with cohesion.\",\n",
" \"Solidly average.\",\n",
" \"Good on paper, flat in practice.\",\n",
" \"A few bright spots, but mostly dim.\",\n",
" \"The kind of book that fades from memory.\",\n",
" \"It scratched the surface but didn't dig deep.\",\n",
" \"Standard fare with some promise.\",\n",
" \"Okay, but not memorable.\",\n",
" \"Had potential that went unrealized.\",\n",
" \"Could have been tighter, sharper, deeper.\",\n",
" \"A blend of mediocrity and mild interest.\",\n",
" \"I kept reading, but barely.\",\n",
" ],\n",
" \"negative\": [\n",
" \"I struggled to get through this one \u2014 it just didn't grab me.\",\n",
" \"The plot was confusing and the characters felt underdeveloped.\",\n",
" \"Disappointing. I had high hopes, but they weren't met.\",\n",
" \"Uninspired writing and a story that never quite took off.\",\n",
" \"Unfortunately, it was dull and predictable throughout.\",\n",
" \"The pacing dragged and I couldn't find anything compelling.\",\n",
" \"This felt like a chore to read \u2014 lacked heart and originality.\",\n",
" \"Nothing really worked for me in this book.\",\n",
" \"A frustrating read that left me unsatisfied.\",\n",
" \"I kept hoping it would improve, but it never did.\",\n",
" \"The characters didn't feel real, and the dialogue was forced.\",\n",
" \"I couldn't connect with the story at all.\",\n",
" \"A slow, meandering narrative with little payoff.\",\n",
" \"Tried too hard to be deep, but just felt empty.\",\n",
" \"The tone was uneven and confusing.\",\n",
" \"Way too repetitive and lacking progression.\",\n",
" \"The ending was abrupt and unsatisfying.\",\n",
" \"No emotional resonance \u2014 I felt nothing throughout.\",\n",
" \"I expected much more, but this fell flat.\",\n",
" \"Poorly edited and full of clich\u00e9s.\",\n",
" \"The premise was interesting, but poorly executed.\",\n",
" \"Just didn't live up to the praise.\",\n",
" \"A disjointed mess from start to finish.\",\n",
" \"Overly long and painfully dull.\",\n",
" \"Dialogue that felt robotic and unrealistic.\",\n",
" \"A hollow shell of what it could've been.\",\n",
" \"It lacked a coherent structure.\",\n",
" \"More confusing than complex.\",\n",
" \"Reading it felt like a task, not a treat.\",\n",
" \"There was no tension, no emotion \u2014 just words.\",\n",
" \"Characters with no motivation or development.\",\n",
" \"The plot twists were nonsensical.\",\n",
" \"Regret buying this book.\",\n",
" \"Nothing drew me in, nothing made me stay.\",\n",
" \"Too many subplots and none were satisfying.\",\n",
" \"Tedious and unimaginative.\",\n",
" \"Like reading a rough draft.\",\n",
" \"Disjointed, distant, and disappointing.\",\n",
" \"A lot of buildup with no payoff.\",\n",
" \"I don't understand the hype.\",\n",
" \"This book simply didn't work.\",\n",
" \"Forgettable in every sense.\",\n",
" \"More effort should've gone into editing.\",\n",
" \"The story lost its way early on.\",\n",
" \"It dragged endlessly.\",\n",
" \"I kept checking how many pages were left.\",\n",
" \"This lacked vision and clarity.\",\n",
" \"I expected substance \u2014 got fluff.\",\n",
" \"It failed to make me care.\",\n",
" ]\n",
"}\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "fQhfVaDmuULT"
},
"source": [
"### *b. Generate 10 reviews per book using random sampling from the corresponding 50*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "l2SRc3PjuTGM"
},
"outputs": [],
"source": [
"review_rows = []\n",
"for _, row in df_books.iterrows():\n",
" title = row['title']\n",
" sentiment_label = row['sentiment_label']\n",
" review_pool = synthetic_reviews_by_sentiment[sentiment_label]\n",
" sampled_reviews = random.sample(review_pool, 10)\n",
" for review_text in sampled_reviews:\n",
" review_rows.append({\n",
" \"title\": title,\n",
" \"sentiment_label\": sentiment_label,\n",
" \"review_text\": review_text,\n",
" \"rating\": row['rating'],\n",
" \"popularity_score\": row['popularity_score']\n",
" })"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "bmJMXF-Bukdm"
},
"source": [
"### *c. Create the final dataframe df_reviews & save it as synthetic_book_reviews.csv*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ZUKUqZsuumsp"
},
"outputs": [],
"source": [
"df_reviews = pd.DataFrame(review_rows)\n",
"df_reviews.to_csv(\"synthetic_book_reviews.csv\", index=False)"
]
},
{
"cell_type": "markdown",
"source": [
"### *c. inputs for R*"
],
"metadata": {
"id": "_602pYUS3gY5"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "3946e521",
"outputId": "514d7bef-0488-4933-b03c-953b9e8a7f66"
},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"def _safe_num(s):\n",
" return pd.to_numeric(\n",
" pd.Series(s).astype(str).str.replace(r\"[^0-9.]\", \"\", regex=True),\n",
" errors=\"coerce\"\n",
" )\n",
"\n",
"# --- Clean book metadata (price/rating) ---\n",
"df_books_r = df_books.copy()\n",
"if \"price\" in df_books_r.columns:\n",
" df_books_r[\"price\"] = _safe_num(df_books_r[\"price\"])\n",
"if \"rating\" in df_books_r.columns:\n",
" df_books_r[\"rating\"] = _safe_num(df_books_r[\"rating\"])\n",
"\n",
"df_books_r[\"title\"] = df_books_r[\"title\"].astype(str).str.strip()\n",
"\n",
"# --- Clean sales ---\n",
"df_sales_r = df_sales.copy()\n",
"df_sales_r[\"title\"] = df_sales_r[\"title\"].astype(str).str.strip()\n",
"df_sales_r[\"month\"] = pd.to_datetime(df_sales_r[\"month\"], errors=\"coerce\")\n",
"df_sales_r[\"units_sold\"] = _safe_num(df_sales_r[\"units_sold\"])\n",
"\n",
"# --- Clean reviews ---\n",
"df_reviews_r = df_reviews.copy()\n",
"df_reviews_r[\"title\"] = df_reviews_r[\"title\"].astype(str).str.strip()\n",
"df_reviews_r[\"sentiment_label\"] = df_reviews_r[\"sentiment_label\"].astype(str).str.lower().str.strip()\n",
"if \"rating\" in df_reviews_r.columns:\n",
" df_reviews_r[\"rating\"] = _safe_num(df_reviews_r[\"rating\"])\n",
"if \"popularity_score\" in df_reviews_r.columns:\n",
" df_reviews_r[\"popularity_score\"] = _safe_num(df_reviews_r[\"popularity_score\"])\n",
"\n",
"# --- Sentiment shares per title (from reviews) ---\n",
"sent_counts = (\n",
" df_reviews_r.groupby([\"title\", \"sentiment_label\"])\n",
" .size()\n",
" .unstack(fill_value=0)\n",
")\n",
"for lab in [\"positive\", \"neutral\", \"negative\"]:\n",
" if lab not in sent_counts.columns:\n",
" sent_counts[lab] = 0\n",
"\n",
"sent_counts[\"total_reviews\"] = sent_counts[[\"positive\", \"neutral\", \"negative\"]].sum(axis=1)\n",
"den = sent_counts[\"total_reviews\"].replace(0, np.nan)\n",
"sent_counts[\"share_positive\"] = sent_counts[\"positive\"] / den\n",
"sent_counts[\"share_neutral\"] = sent_counts[\"neutral\"] / den\n",
"sent_counts[\"share_negative\"] = sent_counts[\"negative\"] / den\n",
"sent_counts = sent_counts.reset_index()\n",
"\n",
"# --- Sales aggregation per title ---\n",
"sales_by_title = (\n",
" df_sales_r.dropna(subset=[\"title\"])\n",
" .groupby(\"title\", as_index=False)\n",
" .agg(\n",
" months_observed=(\"month\", \"nunique\"),\n",
" avg_units_sold=(\"units_sold\", \"mean\"),\n",
" total_units_sold=(\"units_sold\", \"sum\"),\n",
" )\n",
")\n",
"\n",
"# --- Title-level features (join sales + books + sentiment) ---\n",
"df_title = (\n",
" sales_by_title\n",
" .merge(df_books_r[[\"title\", \"price\", \"rating\"]], on=\"title\", how=\"left\")\n",
" .merge(sent_counts[[\"title\", \"share_positive\", \"share_neutral\", \"share_negative\", \"total_reviews\"]],\n",
" on=\"title\", how=\"left\")\n",
")\n",
"\n",
"df_title[\"avg_revenue\"] = df_title[\"avg_units_sold\"] * df_title[\"price\"]\n",
"df_title[\"total_revenue\"] = df_title[\"total_units_sold\"] * df_title[\"price\"]\n",
"\n",
"df_title.to_csv(\"synthetic_title_level_features.csv\", index=False)\n",
"print(\"\u2705 Wrote synthetic_title_level_features.csv\")\n",
"\n",
"# --- Monthly revenue series (proxy: units_sold * price) ---\n",
"monthly_rev = (\n",
" df_sales_r.merge(df_books_r[[\"title\", \"price\"]], on=\"title\", how=\"left\")\n",
")\n",
"monthly_rev[\"revenue\"] = monthly_rev[\"units_sold\"] * monthly_rev[\"price\"]\n",
"\n",
"df_monthly = (\n",
" monthly_rev.dropna(subset=[\"month\"])\n",
" .groupby(\"month\", as_index=False)[\"revenue\"]\n",
" .sum()\n",
" .rename(columns={\"revenue\": \"total_revenue\"})\n",
" .sort_values(\"month\")\n",
")\n",
"# if revenue is all NA (e.g., missing price), fallback to units_sold as a teaching proxy\n",
"if df_monthly[\"total_revenue\"].notna().sum() == 0:\n",
" df_monthly = (\n",
" df_sales_r.dropna(subset=[\"month\"])\n",
" .groupby(\"month\", as_index=False)[\"units_sold\"]\n",
" .sum()\n",
" .rename(columns={\"units_sold\": \"total_revenue\"})\n",
" .sort_values(\"month\")\n",
" )\n",
"\n",
"df_monthly[\"month\"] = pd.to_datetime(df_monthly[\"month\"], errors=\"coerce\").dt.strftime(\"%Y-%m-%d\")\n",
"df_monthly.to_csv(\"synthetic_monthly_revenue_series.csv\", index=False)\n",
"print(\"\u2705 Wrote synthetic_monthly_revenue_series.csv\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RYvGyVfXuo54"
},
"source": [
"### *d. \u270b\ud83c\udffb\ud83d\uded1\u26d4\ufe0f View the first few lines*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "xfE8NMqOurKo",
"outputId": "191730ba-d5e2-4df7-97d2-99feb0b704af"
},
"outputs": [],
"source": [
"print(df_reviews.head())"
]
}
],
"metadata": {
"colab": {
"collapsed_sections": [
"jpASMyIQMaAq",
"lquNYCbfL9IM",
"0IWuNpxxYDJF",
"oCdTsin2Yfp3",
"T0TOeRC4Yrnn",
"duI5dv3CZYvF",
"qMjRKMBQZlJi",
"p-1Pr2szaqLk",
"SIaJUGIpaH4V",
"pY4yCoIuaQqp",
"n4-TaNTFgPak",
"HnngRNTgacYt",
"HF9F9HIzgT7Z",
"T8AdKkmASq9a",
"OhXbdGD5fH0c",
"L2ak1HlcgoTe",
"4IXZKcCSgxnq",
"EhIjz9WohAmZ",
"Gi4y9M9KuDWx",
"fQhfVaDmuULT",
"bmJMXF-Bukdm",
"RYvGyVfXuo54"
],
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |