Upload 9 files

sentiment_analysis.ipynb

@@ -0,0 +1,881 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "56f827ee-ab3d-4aab-9796-aff00fa63924",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "books = pd.read_csv(\"books_with_categories.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8da98828-1909-429b-b51a-8dea366d73ad",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Device set to use cpu\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[{'label': 'joy', 'score': 0.9771687984466553}, {'label': 'surprise', 'score': 0.008528684265911579}, {'label': 'neutral', 'score': 0.005764583125710487}, {'label': 'anger', 'score': 0.004419783595949411}, {'label': 'sadness', 'score': 0.002092392183840275}, {'label': 'disgust', 'score': 0.0016119909705594182}, {'label': 'fear', 'score': 0.00041385277290828526}]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "classifier = pipeline(\n",
+    "    \"text-classification\",\n",
+    "    model=\"j-hartmann/emotion-english-distilroberta-base\",\n",
+    "    top_k=None,\n",
+    "    device=-1  # Use CPU\n",
+    ")\n",
+    "\n",
+    "print(classifier(\"I love this!\"))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ea965320-c400-4f37-bff5-ba5ee6cb7bee",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'A NOVEL THAT READERS and critics have been eagerly anticipating for over a decade, Gilead is an astonishingly imagined story of remarkable lives. John Ames is a preacher, the son of a preacher and the grandson (both maternal and paternal) of preachers. It’s 1956 in Gilead, Iowa, towards the end of the Reverend Ames’s life, and he is absorbed in recording his family’s story, a legacy for the young son he will never see grow up. Haunted by his grandfather’s presence, John tells of the rift between his grandfather and his father: the elder, an angry visionary who fought for the abolitionist cause, and his son, an ardent pacifist. He is troubled, too, by his prodigal namesake, Jack (John Ames) Boughton, his best friend’s lost son who returns to Gilead searching for forgiveness and redemption. Told in John Ames’s joyous, rambling voice that finds beauty, humour and truth in the smallest of life’s details, Gilead is a song of celebration and acceptance of the best and the worst the world has to offer. At its heart is a tale of the sacred bonds between fathers and sons, pitch-perfect in style and story, set to dazzle critics and readers alike.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "books[\"description\"][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "5f62a1cd-3dbb-48f4-ad88-acb89b7a47a4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[[{'label': 'fear', 'score': 0.6548405885696411},\n",
+       "  {'label': 'neutral', 'score': 0.16985228657722473},\n",
+       "  {'label': 'sadness', 'score': 0.11640921980142593},\n",
+       "  {'label': 'surprise', 'score': 0.02070065587759018},\n",
+       "  {'label': 'disgust', 'score': 0.019100677222013474},\n",
+       "  {'label': 'joy', 'score': 0.01516144908964634},\n",
+       "  {'label': 'anger', 'score': 0.003935146611183882}]]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "classifier(books[\"description\"][0])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "918ee472-8899-465a-8ff0-9eeef07c07f5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[[{'label': 'surprise', 'score': 0.7296020984649658},\n",
+       "  {'label': 'neutral', 'score': 0.14038600027561188},\n",
+       "  {'label': 'fear', 'score': 0.06816228479146957},\n",
+       "  {'label': 'joy', 'score': 0.04794260859489441},\n",
+       "  {'label': 'anger', 'score': 0.009156366810202599},\n",
+       "  {'label': 'disgust', 'score': 0.0026284765917807817},\n",
+       "  {'label': 'sadness', 'score': 0.002122163539752364}],\n",
+       " [{'label': 'neutral', 'score': 0.44937002658843994},\n",
+       "  {'label': 'disgust', 'score': 0.27359163761138916},\n",
+       "  {'label': 'joy', 'score': 0.10908330976963043},\n",
+       "  {'label': 'sadness', 'score': 0.09362746775150299},\n",
+       "  {'label': 'anger', 'score': 0.04047830402851105},\n",
+       "  {'label': 'surprise', 'score': 0.026970159262418747},\n",
+       "  {'label': 'fear', 'score': 0.006879047024995089}],\n",
+       " [{'label': 'neutral', 'score': 0.6462159752845764},\n",
+       "  {'label': 'sadness', 'score': 0.24273329973220825},\n",
+       "  {'label': 'disgust', 'score': 0.04342271760106087},\n",
+       "  {'label': 'surprise', 'score': 0.028300564736127853},\n",
+       "  {'label': 'joy', 'score': 0.014211472123861313},\n",
+       "  {'label': 'fear', 'score': 0.0140841044485569},\n",
+       "  {'label': 'anger', 'score': 0.011031901463866234}],\n",
+       " [{'label': 'fear', 'score': 0.9281681180000305},\n",
+       "  {'label': 'anger', 'score': 0.032191041857004166},\n",
+       "  {'label': 'neutral', 'score': 0.01280867587774992},\n",
+       "  {'label': 'sadness', 'score': 0.008756861090660095},\n",
+       "  {'label': 'surprise', 'score': 0.008597906678915024},\n",
+       "  {'label': 'disgust', 'score': 0.008431818336248398},\n",
+       "  {'label': 'joy', 'score': 0.0010455837473273277}],\n",
+       " [{'label': 'sadness', 'score': 0.9671575427055359},\n",
+       "  {'label': 'neutral', 'score': 0.015104127116501331},\n",
+       "  {'label': 'disgust', 'score': 0.006480589509010315},\n",
+       "  {'label': 'fear', 'score': 0.005393980070948601},\n",
+       "  {'label': 'surprise', 'score': 0.002286937553435564},\n",
+       "  {'label': 'anger', 'score': 0.0018428878393024206},\n",
+       "  {'label': 'joy', 'score': 0.0017338756006211042}],\n",
+       " [{'label': 'joy', 'score': 0.932798445224762},\n",
+       "  {'label': 'disgust', 'score': 0.0377168171107769},\n",
+       "  {'label': 'neutral', 'score': 0.015891803428530693},\n",
+       "  {'label': 'sadness', 'score': 0.006444480270147324},\n",
+       "  {'label': 'anger', 'score': 0.005024945829063654},\n",
+       "  {'label': 'surprise', 'score': 0.0015812049387022853},\n",
+       "  {'label': 'fear', 'score': 0.0005423048860393465}],\n",
+       " [{'label': 'joy', 'score': 0.6528708338737488},\n",
+       "  {'label': 'neutral', 'score': 0.25427478551864624},\n",
+       "  {'label': 'surprise', 'score': 0.06808284670114517},\n",
+       "  {'label': 'sadness', 'score': 0.009908987209200859},\n",
+       "  {'label': 'disgust', 'score': 0.0065122200176119804},\n",
+       "  {'label': 'anger', 'score': 0.004821304697543383},\n",
+       "  {'label': 'fear', 'score': 0.0035290175583213568}],\n",
+       " [{'label': 'neutral', 'score': 0.5494767427444458},\n",
+       "  {'label': 'sadness', 'score': 0.11169017851352692},\n",
+       "  {'label': 'disgust', 'score': 0.10400667786598206},\n",
+       "  {'label': 'surprise', 'score': 0.07876550406217575},\n",
+       "  {'label': 'anger', 'score': 0.0641336441040039},\n",
+       "  {'label': 'fear', 'score': 0.05136283114552498},\n",
+       "  {'label': 'joy', 'score': 0.04056443274021149}]]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "classifier(books[\"description\"][0].split(\".\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "f02c4264-7e91-4138-9b77-f4618b506ef3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sentences = books[\"description\"][0].split(\".\")\n",
+    "predictions = classifier(sentences)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "3e3f350f-f448-4408-90ac-842255ad7c1e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'A NOVEL THAT READERS and critics have been eagerly anticipating for over a decade, Gilead is an astonishingly imagined story of remarkable lives'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sentences[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "61d037e6-f1ca-4330-bf2a-f42063974858",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'label': 'surprise', 'score': 0.7296020984649658},\n",
+       " {'label': 'neutral', 'score': 0.14038600027561188},\n",
+       " {'label': 'fear', 'score': 0.06816228479146957},\n",
+       " {'label': 'joy', 'score': 0.04794260859489441},\n",
+       " {'label': 'anger', 'score': 0.009156366810202599},\n",
+       " {'label': 'disgust', 'score': 0.0026284765917807817},\n",
+       " {'label': 'sadness', 'score': 0.002122163539752364}]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "7287bf76-1f12-4792-8138-a74b4b876e00",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[[{'label': 'surprise', 'score': 0.7296020984649658},\n",
+       "  {'label': 'neutral', 'score': 0.14038600027561188},\n",
+       "  {'label': 'fear', 'score': 0.06816228479146957},\n",
+       "  {'label': 'joy', 'score': 0.04794260859489441},\n",
+       "  {'label': 'anger', 'score': 0.009156366810202599},\n",
+       "  {'label': 'disgust', 'score': 0.0026284765917807817},\n",
+       "  {'label': 'sadness', 'score': 0.002122163539752364}],\n",
+       " [{'label': 'neutral', 'score': 0.44937002658843994},\n",
+       "  {'label': 'disgust', 'score': 0.27359163761138916},\n",
+       "  {'label': 'joy', 'score': 0.10908330976963043},\n",
+       "  {'label': 'sadness', 'score': 0.09362746775150299},\n",
+       "  {'label': 'anger', 'score': 0.04047830402851105},\n",
+       "  {'label': 'surprise', 'score': 0.026970159262418747},\n",
+       "  {'label': 'fear', 'score': 0.006879047024995089}],\n",
+       " [{'label': 'neutral', 'score': 0.6462159752845764},\n",
+       "  {'label': 'sadness', 'score': 0.24273329973220825},\n",
+       "  {'label': 'disgust', 'score': 0.04342271760106087},\n",
+       "  {'label': 'surprise', 'score': 0.028300564736127853},\n",
+       "  {'label': 'joy', 'score': 0.014211472123861313},\n",
+       "  {'label': 'fear', 'score': 0.0140841044485569},\n",
+       "  {'label': 'anger', 'score': 0.011031901463866234}],\n",
+       " [{'label': 'fear', 'score': 0.9281681180000305},\n",
+       "  {'label': 'anger', 'score': 0.032191041857004166},\n",
+       "  {'label': 'neutral', 'score': 0.01280867587774992},\n",
+       "  {'label': 'sadness', 'score': 0.008756861090660095},\n",
+       "  {'label': 'surprise', 'score': 0.008597906678915024},\n",
+       "  {'label': 'disgust', 'score': 0.008431818336248398},\n",
+       "  {'label': 'joy', 'score': 0.0010455837473273277}],\n",
+       " [{'label': 'sadness', 'score': 0.9671575427055359},\n",
+       "  {'label': 'neutral', 'score': 0.015104127116501331},\n",
+       "  {'label': 'disgust', 'score': 0.006480589509010315},\n",
+       "  {'label': 'fear', 'score': 0.005393980070948601},\n",
+       "  {'label': 'surprise', 'score': 0.002286937553435564},\n",
+       "  {'label': 'anger', 'score': 0.0018428878393024206},\n",
+       "  {'label': 'joy', 'score': 0.0017338756006211042}],\n",
+       " [{'label': 'joy', 'score': 0.932798445224762},\n",
+       "  {'label': 'disgust', 'score': 0.0377168171107769},\n",
+       "  {'label': 'neutral', 'score': 0.015891803428530693},\n",
+       "  {'label': 'sadness', 'score': 0.006444480270147324},\n",
+       "  {'label': 'anger', 'score': 0.005024945829063654},\n",
+       "  {'label': 'surprise', 'score': 0.0015812049387022853},\n",
+       "  {'label': 'fear', 'score': 0.0005423048860393465}],\n",
+       " [{'label': 'joy', 'score': 0.6528708338737488},\n",
+       "  {'label': 'neutral', 'score': 0.25427478551864624},\n",
+       "  {'label': 'surprise', 'score': 0.06808284670114517},\n",
+       "  {'label': 'sadness', 'score': 0.009908987209200859},\n",
+       "  {'label': 'disgust', 'score': 0.0065122200176119804},\n",
+       "  {'label': 'anger', 'score': 0.004821304697543383},\n",
+       "  {'label': 'fear', 'score': 0.0035290175583213568}],\n",
+       " [{'label': 'neutral', 'score': 0.5494767427444458},\n",
+       "  {'label': 'sadness', 'score': 0.11169017851352692},\n",
+       "  {'label': 'disgust', 'score': 0.10400667786598206},\n",
+       "  {'label': 'surprise', 'score': 0.07876550406217575},\n",
+       "  {'label': 'anger', 'score': 0.0641336441040039},\n",
+       "  {'label': 'fear', 'score': 0.05136283114552498},\n",
+       "  {'label': 'joy', 'score': 0.04056443274021149}]]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "5413ca38-27a3-40a8-b17e-1b68baaa4235",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'label': 'anger', 'score': 0.009156366810202599},\n",
+       " {'label': 'disgust', 'score': 0.0026284765917807817},\n",
+       " {'label': 'fear', 'score': 0.06816228479146957},\n",
+       " {'label': 'joy', 'score': 0.04794260859489441},\n",
+       " {'label': 'neutral', 'score': 0.14038600027561188},\n",
+       " {'label': 'sadness', 'score': 0.002122163539752364},\n",
+       " {'label': 'surprise', 'score': 0.7296020984649658}]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sorted(predictions[0], key=lambda x: x[\"label\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "803691f6-a635-44f4-af31-fd7293f7ada4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "\n",
+    "emotion_labels = [\"anger\", \"disgust\", \"fear\", \"joy\", \"sadness\", \"surprise\", \"neutral\"]\n",
+    "isbn = []\n",
+    "emotion_scores = {label: [] for label in emotion_labels}\n",
+    "\n",
+    "def calculate_max_emotion_scores(predictions):\n",
+    "    per_emotion_scores = {label: [] for label in emotion_labels}\n",
+    "    for prediction in predictions:\n",
+    "        sorted_predictions = sorted(prediction, key=lambda x: x[\"label\"])\n",
+    "        for index, label in enumerate(emotion_labels):\n",
+    "            per_emotion_scores[label].append(sorted_predictions[index][\"score\"])\n",
+    "    return {label: np.max(scores) for label, scores in per_emotion_scores.items()}\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "7f5de092-255b-476b-b51a-6e9961a28f1f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(10):\n",
+    "    isbn.append(books[\"isbn13\"][i])\n",
+    "    sentences = books[\"description\"][i].split(\".\")\n",
+    "    predictions = classifier(sentences)\n",
+    "    max_scores = calculate_max_emotion_scores(predictions)\n",
+    "    for label in emotion_labels:\n",
+    "        emotion_scores[label].append(max_scores[label])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f2390bbc-c4a1-4a1c-91ac-88b48b3f2afb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'anger': [np.float64(0.0641336441040039),\n",
+       "  np.float64(0.6126197576522827),\n",
+       "  np.float64(0.0641336441040039),\n",
+       "  np.float64(0.35148438811302185),\n",
+       "  np.float64(0.08141235262155533),\n",
+       "  np.float64(0.2322252243757248),\n",
+       "  np.float64(0.5381842255592346),\n",
+       "  np.float64(0.0641336441040039),\n",
+       "  np.float64(0.3006700277328491),\n",
+       "  np.float64(0.0641336441040039)],\n",
+       " 'disgust': [np.float64(0.27359163761138916),\n",
+       "  np.float64(0.3482847511768341),\n",
+       "  np.float64(0.10400667786598206),\n",
+       "  np.float64(0.1507224589586258),\n",
+       "  np.float64(0.18449543416500092),\n",
+       "  np.float64(0.7271744608879089),\n",
+       "  np.float64(0.155854731798172),\n",
+       "  np.float64(0.10400667786598206),\n",
+       "  np.float64(0.2794816195964813),\n",
+       "  np.float64(0.17792661488056183)],\n",
+       " 'fear': [np.float64(0.9281681180000305),\n",
+       "  np.float64(0.9425276517868042),\n",
+       "  np.float64(0.9723208546638489),\n",
+       "  np.float64(0.3607059419155121),\n",
+       "  np.float64(0.09504333138465881),\n",
+       "  np.float64(0.05136283114552498),\n",
+       "  np.float64(0.7474274635314941),\n",
+       "  np.float64(0.4044976532459259),\n",
+       "  np.float64(0.9155241250991821),\n",
+       "  np.float64(0.05136283114552498)],\n",
+       " 'joy': [np.float64(0.932798445224762),\n",
+       "  np.float64(0.7044219970703125),\n",
+       "  np.float64(0.7672380805015564),\n",
+       "  np.float64(0.2518811821937561),\n",
+       "  np.float64(0.04056443274021149),\n",
+       "  np.float64(0.043375786393880844),\n",
+       "  np.float64(0.872565746307373),\n",
+       "  np.float64(0.04056443274021149),\n",
+       "  np.float64(0.04056443274021149),\n",
+       "  np.float64(0.04056443274021149)],\n",
+       " 'sadness': [np.float64(0.6462159752845764),\n",
+       "  np.float64(0.8879395127296448),\n",
+       "  np.float64(0.5494767427444458),\n",
+       "  np.float64(0.7326844930648804),\n",
+       "  np.float64(0.8843896985054016),\n",
+       "  np.float64(0.621392011642456),\n",
+       "  np.float64(0.7121941447257996),\n",
+       "  np.float64(0.5494767427444458),\n",
+       "  np.float64(0.840289294719696),\n",
+       "  np.float64(0.8603722453117371)],\n",
+       " 'surprise': [np.float64(0.9671575427055359),\n",
+       "  np.float64(0.11169017851352692),\n",
+       "  np.float64(0.11169017851352692),\n",
+       "  np.float64(0.11169017851352692),\n",
+       "  np.float64(0.47588053345680237),\n",
+       "  np.float64(0.11169017851352692),\n",
+       "  np.float64(0.40800127387046814),\n",
+       "  np.float64(0.8202826380729675),\n",
+       "  np.float64(0.35446077585220337),\n",
+       "  np.float64(0.11169017851352692)],\n",
+       " 'neutral': [np.float64(0.7296020984649658),\n",
+       "  np.float64(0.252546101808548),\n",
+       "  np.float64(0.07876550406217575),\n",
+       "  np.float64(0.07876550406217575),\n",
+       "  np.float64(0.07876550406217575),\n",
+       "  np.float64(0.27190330624580383),\n",
+       "  np.float64(0.07876550406217575),\n",
+       "  np.float64(0.2344866842031479),\n",
+       "  np.float64(0.13561423122882843),\n",
+       "  np.float64(0.07876550406217575)]}"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "emotion_scores"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "61c40789-c367-4a0f-8701-6c49a1688048",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  1%|▍                                                                             | 27/5197 [00:24<1:01:20,  1.40it/s]"
+     ]
+    }
+   ],
+   "source": [
+    "from tqdm import tqdm\n",
+    "\n",
+    "emotion_labels = [\"anger\", \"disgust\", \"fear\", \"joy\", \"sadness\", \"surprise\", \"neutral\"]\n",
+    "isbn = []\n",
+    "emotion_scores = {label: [] for label in emotion_labels}\n",
+    "\n",
+    "for i in tqdm(range(len(books))):\n",
+    "    isbn.append(books[\"isbn13\"][i])\n",
+    "    sentences = books[\"description\"][i].split(\".\")\n",
+    "    predictions = classifier(sentences)\n",
+    "    max_scores = calculate_max_emotion_scores(predictions)\n",
+    "    for label in emotion_labels:\n",
+    "        emotion_scores[label].append(max_scores[label])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "36ba8f19-3bdc-4d03-afa4-9db9c93bd488",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "emotions_df = pd.DataFrame(emotion_scores)\n",
+    "emotions_df[\"isbn13\"] = isbn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8f415e4c-9869-4fd5-b74e-3426d3ac5cb6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "emotions_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b3335a2a-13af-43f8-a6e4-0d39cc90bcce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Drop old emotion columns from books\n",
+    "emotion_cols = [\"anger\", \"disgust\", \"fear\", \"joy\", \"sadness\", \"surprise\", \"neutral\"]\n",
+    "books = books.drop(columns=emotion_cols, errors='ignore')  # errors='ignore' skips if columns not found\n",
+    "\n",
+    "# Now do the merge\n",
+    "books = pd.merge(books, emotions_df, on=\"isbn13\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8e3267bc-920e-4880-91d2-80eeaee583a9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "books.to_csv(\"books_with_emotions.csv\", index = False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "53a10c8d-7a25-48ac-92a6-61e089488e0e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5259ca8e-f373-40ee-985f-239725a7cc12",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6d147cdc-2f26-465b-8d79-1c38470bbc71",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce4a6203-d988-473e-9545-d97a5db5527c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b9d9ec7-db3a-49b2-8916-157fc5c4d2af",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a36c7be4-c24d-4075-9d2e-3aa0b571c0b5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "87f1cd5b-b853-4822-be4d-4eace4316a02",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b4e7587-2988-40d7-8642-344b20ffe895",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "acb61813-beae-4dd4-b62c-3d303868891d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54984cfc-50cf-4893-930f-be9fcab8cd03",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "63f38034-c61d-4c1c-8146-4a2fbb2e76b2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ffb41bd-24bb-4fb6-a5f3-902d62110f71",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d6b7f6c5-124c-4f36-8971-95900fa6edce",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "25d57054-8971-4baa-b8dd-23b403e3165f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8427fc4a-54bb-4c2e-bcae-b243ae46d24f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5f88e0cb-7e77-4295-959b-4ad239d3e63e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b9d2c10-1b4d-4675-a6e3-fccc3b1ff9db",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5662902f-cb8a-4fb0-aad2-c50cddba8084",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c917f161-529f-488d-9829-9a7257c6821e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d9a0a784-fa39-4412-951f-76b66d4e05f5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2949e3ea-2943-434f-95a9-22438cb21567",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7312f2a9-810e-4f48-a198-2256f656f2f0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "07662c44-73b2-47c0-9e54-9064511d44f9",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "45fd0c42-75f2-47da-8b4b-66f7c211298a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "99580564-5d8e-4b5a-8dea-49fdf0414876",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a594e162-c2e1-4202-a590-e96e63ba984f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "678eb881-c80c-47fe-bcc2-48ce8fc19b34",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f40866c7-3882-4867-a1db-92e5c27e4d3e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a8c1d89e-53b6-4b74-ab65-0235cf0c7abd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "15ad11f8-d5fa-47c6-8fc6-d3c60badb3a0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5ca0bc6e-18cd-4f74-ba65-959fc58f5a4c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "df8895f9-9e8f-4f80-91bd-1f48ba9f7716",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e4161ddf-71fe-4323-b750-099d42b52174",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aac7d70a-c92a-47d9-83ed-7bf0d2e170f6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9a438b5b-c5b7-4abe-80f6-d90217e22649",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ecca9640-fda8-4d3a-906e-952b400d0900",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "68cb657a-d404-431f-a446-390a6e2106a7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6e53f5fc-683e-4957-9fc1-dd5560c32136",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "61e5cf29-fe64-4ee7-b955-bed4ad3c0e98",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8a377345-9277-4fe1-a036-fdf0c397b257",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}