Hugging Face's logo

Spaces:
mim981
/
DataSynthis_ML_JobTask
No application file

App Files Community
mim981 commited on
Commit
17305e0
·
verified ·
1 Parent(s): 2e699cc

Upload MLINTERNSHIP.ipynb

Browse files
Files changed (1) hide show
  1. MLINTERNSHIP.ipynb +1355 -0
MLINTERNSHIP.ipynb ADDED
@@ -0,0 +1,1355 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "metadata": {
7
+ "id": "TjaG3WllZX3Y"
8
+ },
9
+ "outputs": [],
10
+ "source": [
11
+ "import numpy as np\n",
12
+ "import pandas as pd\n",
13
+ "from sklearn.model_selection import train_test_split\n",
14
+ "from sklearn.linear_model import LogisticRegression\n",
15
+ "from sklearn.metrics import accuracy_score\n",
16
+ "\n",
17
+ "import warnings\n",
18
+ "warnings.filterwarnings('ignore')"
19
+ ]
20
+ },
21
+ {
22
+ "cell_type": "code",
23
+ "source": [
24
+ "import re\n",
25
+ "import nltk\n",
26
+ "import string\n",
27
+ "from nltk.corpus import stopwords\n",
28
+ "from nltk.stem import WordNetLemmatizer\n",
29
+ "\n",
30
+ "nltk.download('punkt')\n",
31
+ "nltk.download('stopwords')\n",
32
+ "nltk.download('wordnet')"
33
+ ],
34
+ "metadata": {
35
+ "colab": {
36
+ "base_uri": "https://localhost:8080/"
37
+ },
38
+ "id": "s4OOuG5PQ6pJ",
39
+ "outputId": "2e06700b-0d23-40e0-edbf-5174a81625d1"
40
+ },
41
+ "execution_count": null,
42
+ "outputs": [
43
+ {
44
+ "output_type": "stream",
45
+ "name": "stderr",
46
+ "text": [
47
+ "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
48
+ "[nltk_data] Package punkt is already up-to-date!\n",
49
+ "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
50
+ "[nltk_data] Package stopwords is already up-to-date!\n",
51
+ "[nltk_data] Downloading package wordnet to /root/nltk_data...\n",
52
+ "[nltk_data] Package wordnet is already up-to-date!\n"
53
+ ]
54
+ },
55
+ {
56
+ "output_type": "execute_result",
57
+ "data": {
58
+ "text/plain": [
59
+ "True"
60
+ ]
61
+ },
62
+ "metadata": {},
63
+ "execution_count": 3
64
+ }
65
+ ]
66
+ },
67
+ {
68
+ "cell_type": "code",
69
+ "source": [
70
+ "df = pd.read_csv(\"/content/IMDB Dataset.csv\", engine=\"python\", on_bad_lines=\"skip\")\n",
71
+ "print(df.shape)\n",
72
+ "print(df.head())\n",
73
+ "\n"
74
+ ],
75
+ "metadata": {
76
+ "colab": {
77
+ "base_uri": "https://localhost:8080/"
78
+ },
79
+ "id": "EmJ8miPsQ_ix",
80
+ "outputId": "9801b4f9-f496-4860-a87e-af309576af72"
81
+ },
82
+ "execution_count": null,
83
+ "outputs": [
84
+ {
85
+ "output_type": "stream",
86
+ "name": "stdout",
87
+ "text": [
88
+ "(50000, 2)\n",
89
+ " review sentiment\n",
90
+ "0 One of the other reviewers has mentioned that ... positive\n",
91
+ "1 A wonderful little production. <br /><br />The... positive\n",
92
+ "2 I thought this was a wonderful way to spend ti... positive\n",
93
+ "3 Basically there's a family where a little boy ... negative\n",
94
+ "4 Petter Mattei's \"Love in the Time of Money\" is... positive\n"
95
+ ]
96
+ }
97
+ ]
98
+ },
99
+ {
100
+ "cell_type": "code",
101
+ "source": [
102
+ "nltk.download(\"punkt_tab\")"
103
+ ],
104
+ "metadata": {
105
+ "colab": {
106
+ "base_uri": "https://localhost:8080/"
107
+ },
108
+ "id": "DCj_cP5xQ_lA",
109
+ "outputId": "493920ed-26b6-4dec-a3e0-7d8084698a7c"
110
+ },
111
+ "execution_count": null,
112
+ "outputs": [
113
+ {
114
+ "output_type": "stream",
115
+ "name": "stderr",
116
+ "text": [
117
+ "[nltk_data] Downloading package punkt_tab to /root/nltk_data...\n",
118
+ "[nltk_data] Package punkt_tab is already up-to-date!\n"
119
+ ]
120
+ },
121
+ {
122
+ "output_type": "execute_result",
123
+ "data": {
124
+ "text/plain": [
125
+ "True"
126
+ ]
127
+ },
128
+ "metadata": {},
129
+ "execution_count": 5
130
+ }
131
+ ]
132
+ },
133
+ {
134
+ "cell_type": "code",
135
+ "source": [
136
+ "\n",
137
+ "\n",
138
+ "stop_words = set(stopwords.words('english'))\n",
139
+ "lemmatizer = WordNetLemmatizer()\n",
140
+ "\n",
141
+ "def preprocess_text(text):\n",
142
+ " # 1. Lowercase\n",
143
+ " text = text.lower()\n",
144
+ "\n",
145
+ " # 2. Remove HTML tags\n",
146
+ " text = re.sub(r'<.*?>', '', text)\n",
147
+ "\n",
148
+ " # 3. Remove punctuation & numbers\n",
149
+ " text = re.sub(r'[^a-z\\s]', '', text)\n",
150
+ "\n",
151
+ " # 4. Tokenize\n",
152
+ " tokens = nltk.word_tokenize(text)\n",
153
+ "\n",
154
+ " # 5. Remove stopwords\n",
155
+ " tokens = [word for word in tokens if word not in stop_words]\n",
156
+ "\n",
157
+ " # 6. Lemmatization\n",
158
+ " tokens = [lemmatizer.lemmatize(word) for word in tokens]\n",
159
+ "\n",
160
+ " return \" \".join(tokens)\n",
161
+ "\n"
162
+ ],
163
+ "metadata": {
164
+ "id": "zID5UONlP1ok"
165
+ },
166
+ "execution_count": null,
167
+ "outputs": []
168
+ },
169
+ {
170
+ "cell_type": "code",
171
+ "source": [
172
+ "df[\"cleaned_review\"] = df[\"review\"].apply(preprocess_text)\n",
173
+ "\n",
174
+ "\n",
175
+ "print(df[[\"review\", \"cleaned_review\", \"sentiment\"]].tail())"
176
+ ],
177
+ "metadata": {
178
+ "id": "HDsRgcxuP1rS",
179
+ "colab": {
180
+ "base_uri": "https://localhost:8080/"
181
+ },
182
+ "outputId": "a30f30f1-6640-451b-8a46-247d488c9a68"
183
+ },
184
+ "execution_count": null,
185
+ "outputs": [
186
+ {
187
+ "output_type": "stream",
188
+ "name": "stdout",
189
+ "text": [
190
+ " review \\\n",
191
+ "49995 I thought this movie did a down right good job... \n",
192
+ "49996 Bad plot, bad dialogue, bad acting, idiotic di... \n",
193
+ "49997 I am a Catholic taught in parochial elementary... \n",
194
+ "49998 I'm going to have to disagree with the previou... \n",
195
+ "49999 No one expects the Star Trek movies to be high... \n",
196
+ "\n",
197
+ " cleaned_review sentiment \n",
198
+ "49995 thought movie right good job wasnt creative or... positive \n",
199
+ "49996 bad plot bad dialogue bad acting idiotic direc... negative \n",
200
+ "49997 catholic taught parochial elementary school nu... negative \n",
201
+ "49998 im going disagree previous comment side maltin... negative \n",
202
+ "49999 one expects star trek movie high art fan expec... negative \n"
203
+ ]
204
+ }
205
+ ]
206
+ },
207
+ {
208
+ "cell_type": "code",
209
+ "source": [
210
+ "!pip install transformers torch sentence-transformers\n"
211
+ ],
212
+ "metadata": {
213
+ "id": "DUf6-RvRP1uL",
214
+ "colab": {
215
+ "base_uri": "https://localhost:8080/"
216
+ },
217
+ "outputId": "c4b4362f-8aad-43d8-ac0e-56f7d20c4140"
218
+ },
219
+ "execution_count": null,
220
+ "outputs": [
221
+ {
222
+ "output_type": "stream",
223
+ "name": "stdout",
224
+ "text": [
225
+ "Requirement already satisfied: transformers in /usr/local/lib/python3.12/dist-packages (4.56.2)\n",
226
+ "Requirement already satisfied: torch in /usr/local/lib/python3.12/dist-packages (2.8.0+cu126)\n",
227
+ "Requirement already satisfied: sentence-transformers in /usr/local/lib/python3.12/dist-packages (5.1.1)\n",
228
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from transformers) (3.19.1)\n",
229
+ "Requirement already satisfied: huggingface-hub<1.0,>=0.34.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.35.0)\n",
230
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from transformers) (1.26.0)\n",
231
+ "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (25.0)\n",
232
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from transformers) (6.0.2)\n",
233
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.12/dist-packages (from transformers) (2024.11.6)\n",
234
+ "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from transformers) (2.32.4)\n",
235
+ "Requirement already satisfied: tokenizers<=0.23.0,>=0.22.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.22.0)\n",
236
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.6.2)\n",
237
+ "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.12/dist-packages (from transformers) (4.67.1)\n",
238
+ "Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch) (4.15.0)\n",
239
+ "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch) (75.2.0)\n",
240
+ "Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch) (1.13.3)\n",
241
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch) (3.5)\n",
242
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch) (3.1.6)\n",
243
+ "Requirement already satisfied: fsspec in /usr/local/lib/python3.12/dist-packages (from torch) (2025.3.0)\n",
244
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.77)\n",
245
+ "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.77)\n",
246
+ "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.6.80 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.80)\n",
247
+ "Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch) (9.10.2.21)\n",
248
+ "Requirement already satisfied: nvidia-cublas-cu12==12.6.4.1 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.4.1)\n",
249
+ "Requirement already satisfied: nvidia-cufft-cu12==11.3.0.4 in /usr/local/lib/python3.12/dist-packages (from torch) (11.3.0.4)\n",
250
+ "Requirement already satisfied: nvidia-curand-cu12==10.3.7.77 in /usr/local/lib/python3.12/dist-packages (from torch) (10.3.7.77)\n",
251
+ "Requirement already satisfied: nvidia-cusolver-cu12==11.7.1.2 in /usr/local/lib/python3.12/dist-packages (from torch) (11.7.1.2)\n",
252
+ "Requirement already satisfied: nvidia-cusparse-cu12==12.5.4.2 in /usr/local/lib/python3.12/dist-packages (from torch) (12.5.4.2)\n",
253
+ "Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch) (0.7.1)\n",
254
+ "Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch) (2.27.3)\n",
255
+ "Requirement already satisfied: nvidia-nvtx-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.77)\n",
256
+ "Requirement already satisfied: nvidia-nvjitlink-cu12==12.6.85 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.85)\n",
257
+ "Requirement already satisfied: nvidia-cufile-cu12==1.11.1.6 in /usr/local/lib/python3.12/dist-packages (from torch) (1.11.1.6)\n",
258
+ "Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch) (3.4.0)\n",
259
+ "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.12/dist-packages (from sentence-transformers) (1.6.1)\n",
260
+ "Requirement already satisfied: scipy in /usr/local/lib/python3.12/dist-packages (from sentence-transformers) (1.16.2)\n",
261
+ "Requirement already satisfied: Pillow in /usr/local/lib/python3.12/dist-packages (from sentence-transformers) (11.3.0)\n",
262
+ "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (1.1.10)\n",
263
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch) (1.3.0)\n",
264
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch) (3.0.2)\n",
265
+ "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (3.4.3)\n",
266
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (3.10)\n",
267
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (2.5.0)\n",
268
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (2025.8.3)\n",
269
+ "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn->sentence-transformers) (1.5.2)\n",
270
+ "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn->sentence-transformers) (3.6.0)\n"
271
+ ]
272
+ }
273
+ ]
274
+ },
275
+ {
276
+ "cell_type": "code",
277
+ "source": [],
278
+ "metadata": {
279
+ "id": "so6p265dWAfb"
280
+ },
281
+ "execution_count": null,
282
+ "outputs": []
283
+ },
284
+ {
285
+ "cell_type": "code",
286
+ "source": [],
287
+ "metadata": {
288
+ "id": "j7qu7HlyWAkb"
289
+ },
290
+ "execution_count": null,
291
+ "outputs": []
292
+ },
293
+ {
294
+ "cell_type": "code",
295
+ "source": [
296
+ "!pip install -U torch torchvision torchaudio\n",
297
+ "!pip install -U transformers sentence-transformers\n"
298
+ ],
299
+ "metadata": {
300
+ "id": "kQkAlTaKP1w0",
301
+ "colab": {
302
+ "base_uri": "https://localhost:8080/"
303
+ },
304
+ "outputId": "77568f04-e205-4524-c838-c46042a317a2"
305
+ },
306
+ "execution_count": null,
307
+ "outputs": [
308
+ {
309
+ "output_type": "stream",
310
+ "name": "stdout",
311
+ "text": [
312
+ "Requirement already satisfied: torch in /usr/local/lib/python3.12/dist-packages (2.8.0+cu126)\n",
313
+ "Requirement already satisfied: torchvision in /usr/local/lib/python3.12/dist-packages (0.23.0+cu126)\n",
314
+ "Requirement already satisfied: torchaudio in /usr/local/lib/python3.12/dist-packages (2.8.0+cu126)\n",
315
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch) (3.19.1)\n",
316
+ "Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch) (4.15.0)\n",
317
+ "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch) (75.2.0)\n",
318
+ "Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch) (1.13.3)\n",
319
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch) (3.5)\n",
320
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch) (3.1.6)\n",
321
+ "Requirement already satisfied: fsspec in /usr/local/lib/python3.12/dist-packages (from torch) (2025.3.0)\n",
322
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.77)\n",
323
+ "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.77)\n",
324
+ "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.6.80 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.80)\n",
325
+ "Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch) (9.10.2.21)\n",
326
+ "Requirement already satisfied: nvidia-cublas-cu12==12.6.4.1 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.4.1)\n",
327
+ "Requirement already satisfied: nvidia-cufft-cu12==11.3.0.4 in /usr/local/lib/python3.12/dist-packages (from torch) (11.3.0.4)\n",
328
+ "Requirement already satisfied: nvidia-curand-cu12==10.3.7.77 in /usr/local/lib/python3.12/dist-packages (from torch) (10.3.7.77)\n",
329
+ "Requirement already satisfied: nvidia-cusolver-cu12==11.7.1.2 in /usr/local/lib/python3.12/dist-packages (from torch) (11.7.1.2)\n",
330
+ "Requirement already satisfied: nvidia-cusparse-cu12==12.5.4.2 in /usr/local/lib/python3.12/dist-packages (from torch) (12.5.4.2)\n",
331
+ "Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch) (0.7.1)\n",
332
+ "Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch) (2.27.3)\n",
333
+ "Requirement already satisfied: nvidia-nvtx-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.77)\n",
334
+ "Requirement already satisfied: nvidia-nvjitlink-cu12==12.6.85 in /usr/local/lib/python3.12/dist-packages (from torch) (12.6.85)\n",
335
+ "Requirement already satisfied: nvidia-cufile-cu12==1.11.1.6 in /usr/local/lib/python3.12/dist-packages (from torch) (1.11.1.6)\n",
336
+ "Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch) (3.4.0)\n",
337
+ "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from torchvision) (1.26.0)\n",
338
+ "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.12/dist-packages (from torchvision) (11.3.0)\n",
339
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch) (1.3.0)\n",
340
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch) (3.0.2)\n",
341
+ "Requirement already satisfied: transformers in /usr/local/lib/python3.12/dist-packages (4.56.2)\n",
342
+ "Requirement already satisfied: sentence-transformers in /usr/local/lib/python3.12/dist-packages (5.1.1)\n",
343
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from transformers) (3.19.1)\n",
344
+ "Requirement already satisfied: huggingface-hub<1.0,>=0.34.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.35.0)\n",
345
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from transformers) (1.26.0)\n",
346
+ "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (25.0)\n",
347
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from transformers) (6.0.2)\n",
348
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.12/dist-packages (from transformers) (2024.11.6)\n",
349
+ "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from transformers) (2.32.4)\n",
350
+ "Requirement already satisfied: tokenizers<=0.23.0,>=0.22.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.22.0)\n",
351
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.6.2)\n",
352
+ "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.12/dist-packages (from transformers) (4.67.1)\n",
353
+ "Requirement already satisfied: torch>=1.11.0 in /usr/local/lib/python3.12/dist-packages (from sentence-transformers) (2.8.0+cu126)\n",
354
+ "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.12/dist-packages (from sentence-transformers) (1.6.1)\n",
355
+ "Requirement already satisfied: scipy in /usr/local/lib/python3.12/dist-packages (from sentence-transformers) (1.16.2)\n",
356
+ "Requirement already satisfied: Pillow in /usr/local/lib/python3.12/dist-packages (from sentence-transformers) (11.3.0)\n",
357
+ "Requirement already satisfied: typing_extensions>=4.5.0 in /usr/local/lib/python3.12/dist-packages (from sentence-transformers) (4.15.0)\n",
358
+ "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (2025.3.0)\n",
359
+ "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (1.1.10)\n",
360
+ "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (75.2.0)\n",
361
+ "Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (1.13.3)\n",
362
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (3.5)\n",
363
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (3.1.6)\n",
364
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (12.6.77)\n",
365
+ "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (12.6.77)\n",
366
+ "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.6.80 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (12.6.80)\n",
367
+ "Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (9.10.2.21)\n",
368
+ "Requirement already satisfied: nvidia-cublas-cu12==12.6.4.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (12.6.4.1)\n",
369
+ "Requirement already satisfied: nvidia-cufft-cu12==11.3.0.4 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (11.3.0.4)\n",
370
+ "Requirement already satisfied: nvidia-curand-cu12==10.3.7.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (10.3.7.77)\n",
371
+ "Requirement already satisfied: nvidia-cusolver-cu12==11.7.1.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (11.7.1.2)\n",
372
+ "Requirement already satisfied: nvidia-cusparse-cu12==12.5.4.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (12.5.4.2)\n",
373
+ "Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (0.7.1)\n",
374
+ "Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (2.27.3)\n",
375
+ "Requirement already satisfied: nvidia-nvtx-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (12.6.77)\n",
376
+ "Requirement already satisfied: nvidia-nvjitlink-cu12==12.6.85 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (12.6.85)\n",
377
+ "Requirement already satisfied: nvidia-cufile-cu12==1.11.1.6 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (1.11.1.6)\n",
378
+ "Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.11.0->sentence-transformers) (3.4.0)\n",
379
+ "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (3.4.3)\n",
380
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (3.10)\n",
381
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (2.5.0)\n",
382
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (2025.8.3)\n",
383
+ "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn->sentence-transformers) (1.5.2)\n",
384
+ "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn->sentence-transformers) (3.6.0)\n",
385
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=1.11.0->sentence-transformers) (1.3.0)\n",
386
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=1.11.0->sentence-transformers) (3.0.2)\n"
387
+ ]
388
+ }
389
+ ]
390
+ },
391
+ {
392
+ "cell_type": "code",
393
+ "source": [
394
+ "\n",
395
+ "from sklearn.feature_extraction.text import TfidfVectorizer"
396
+ ],
397
+ "metadata": {
398
+ "id": "Ai71-ZR9jXUy"
399
+ },
400
+ "execution_count": null,
401
+ "outputs": []
402
+ },
403
+ {
404
+ "cell_type": "code",
405
+ "source": [
406
+ "\n",
407
+ "tfidf = TfidfVectorizer(max_features=5000)\n",
408
+ "X = tfidf.fit_transform(df[\"cleaned_review\"])\n",
409
+ "\n",
410
+ "y = df[\"sentiment\"].map({\"positive\": 1, \"negative\": 0}).values\n",
411
+ "print(X)"
412
+ ],
413
+ "metadata": {
414
+ "id": "qrre8w1hP1zn",
415
+ "colab": {
416
+ "base_uri": "https://localhost:8080/"
417
+ },
418
+ "outputId": "7e36be98-44f0-4f69-efcb-9d38c6d7a5a8"
419
+ },
420
+ "execution_count": null,
421
+ "outputs": [
422
+ {
423
+ "output_type": "stream",
424
+ "name": "stdout",
425
+ "text": [
426
+ "<Compressed Sparse Row sparse matrix of dtype 'float64'\n",
427
+ "\twith 3894163 stored elements and shape (50000, 5000)>\n",
428
+ " Coords\tValues\n",
429
+ " (0, 3086)\t0.022306340769509683\n",
430
+ " (0, 3687)\t0.0716098594890523\n",
431
+ " (0, 2778)\t0.06997013472849029\n",
432
+ " (0, 4832)\t0.08220463762202762\n",
433
+ " (0, 3137)\t0.47260726598173247\n",
434
+ " (0, 1467)\t0.11279543497089747\n",
435
+ " (0, 4990)\t0.05792759900745007\n",
436
+ " (0, 2119)\t0.0884283468115394\n",
437
+ " (0, 3707)\t0.09072957775856476\n",
438
+ " (0, 1513)\t0.06118924586115793\n",
439
+ " (0, 1993)\t0.06126011378849219\n",
440
+ " (0, 1697)\t0.06827831217826244\n",
441
+ " (0, 4468)\t0.034484905907198556\n",
442
+ " (0, 4258)\t0.1771814513806625\n",
443
+ " (0, 543)\t0.09851073786514736\n",
444
+ " (0, 3831)\t0.03333634078441469\n",
445
+ " (0, 4763)\t0.25095990028835147\n",
446
+ " (0, 3914)\t0.04650048507467132\n",
447
+ " (0, 4938)\t0.05348789066286241\n",
448
+ " (0, 1883)\t0.07135314796729297\n",
449
+ " (0, 4610)\t0.07763035600809258\n",
450
+ " (0, 3975)\t0.15304406167950377\n",
451
+ " (0, 3451)\t0.06917492387135953\n",
452
+ " (0, 3456)\t0.08224792976382196\n",
453
+ " (0, 3583)\t0.08260003424873928\n",
454
+ " :\t:\n",
455
+ " (49999, 4949)\t0.09967306284736142\n",
456
+ " (49999, 1608)\t0.18895470226431363\n",
457
+ " (49999, 2146)\t0.0938134095848708\n",
458
+ " (49999, 4608)\t0.10421390262146894\n",
459
+ " (49999, 680)\t0.1210849951944911\n",
460
+ " (49999, 3818)\t0.1207533622254777\n",
461
+ " (49999, 2470)\t0.12550521294127479\n",
462
+ " (49999, 4670)\t0.11972754064045821\n",
463
+ " (49999, 2540)\t0.10566290485449034\n",
464
+ " (49999, 1538)\t0.12096018782971787\n",
465
+ " (49999, 303)\t0.13528867065174088\n",
466
+ " (49999, 2002)\t0.14117928521526385\n",
467
+ " (49999, 2225)\t0.12437816971606588\n",
468
+ " (49999, 2205)\t0.1883414548411176\n",
469
+ " (49999, 241)\t0.12037119185480823\n",
470
+ " (49999, 4588)\t0.1774967991895605\n",
471
+ " (49999, 2457)\t0.2041086873930473\n",
472
+ " (49999, 4154)\t0.2230098076678039\n",
473
+ " (49999, 3632)\t0.17275135778399867\n",
474
+ " (49999, 581)\t0.16361717948998034\n",
475
+ " (49999, 2995)\t0.1828212276262584\n",
476
+ " (49999, 684)\t0.14413194406724505\n",
477
+ " (49999, 1897)\t0.17552265388590801\n",
478
+ " (49999, 3630)\t0.16768695545427548\n",
479
+ " (49999, 2903)\t0.19720455104959872\n"
480
+ ]
481
+ }
482
+ ]
483
+ },
484
+ {
485
+ "cell_type": "code",
486
+ "source": [
487
+ "\n",
488
+ "from sklearn.feature_extraction.text import TfidfVectorizer\n"
489
+ ],
490
+ "metadata": {
491
+ "id": "y0voh7wgYX5z"
492
+ },
493
+ "execution_count": null,
494
+ "outputs": []
495
+ },
496
+ {
497
+ "cell_type": "markdown",
498
+ "source": [
499
+ "**MODEL**"
500
+ ],
501
+ "metadata": {
502
+ "id": "9ahaUAiOjaih"
503
+ }
504
+ },
505
+ {
506
+ "cell_type": "code",
507
+ "source": [
508
+ "from sklearn.model_selection import train_test_split\n",
509
+ "from sklearn.linear_model import LogisticRegression\n",
510
+ "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n",
511
+ "\n",
512
+ "\n",
513
+ "\n"
514
+ ],
515
+ "metadata": {
516
+ "id": "fDNAJ33YP12O"
517
+ },
518
+ "execution_count": null,
519
+ "outputs": []
520
+ },
521
+ {
522
+ "cell_type": "code",
523
+ "source": [
524
+ "\n",
525
+ "X_train, X_test, y_train, y_test = train_test_split(\n",
526
+ " X, y, test_size=0.2, random_state=42\n",
527
+ ")\n"
528
+ ],
529
+ "metadata": {
530
+ "id": "a_u6DHxwP15A"
531
+ },
532
+ "execution_count": null,
533
+ "outputs": []
534
+ },
535
+ {
536
+ "cell_type": "code",
537
+ "source": [
538
+ "\n",
539
+ "clf = LogisticRegression(max_iter=200)\n",
540
+ "\n",
541
+ "clf.fit(X_train, y_train)\n"
542
+ ],
543
+ "metadata": {
544
+ "colab": {
545
+ "base_uri": "https://localhost:8080/",
546
+ "height": 80
547
+ },
548
+ "id": "rebafV7PZQa8",
549
+ "outputId": "1237907c-d30f-4e97-914f-b16a544a98bf"
550
+ },
551
+ "execution_count": null,
552
+ "outputs": [
553
+ {
554
+ "output_type": "execute_result",
555
+ "data": {
556
+ "text/plain": [
557
+ "LogisticRegression(max_iter=200)"
558
+ ],
559
+ "text/html": [
560
+ "<style>#sk-container-id-1 {\n",
561
+ " /* Definition of color scheme common for light and dark mode */\n",
562
+ " --sklearn-color-text: #000;\n",
563
+ " --sklearn-color-text-muted: #666;\n",
564
+ " --sklearn-color-line: gray;\n",
565
+ " /* Definition of color scheme for unfitted estimators */\n",
566
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
567
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
568
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
569
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
570
+ " /* Definition of color scheme for fitted estimators */\n",
571
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
572
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
573
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
574
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
575
+ "\n",
576
+ " /* Specific color for light theme */\n",
577
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
578
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
579
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
580
+ " --sklearn-color-icon: #696969;\n",
581
+ "\n",
582
+ " @media (prefers-color-scheme: dark) {\n",
583
+ " /* Redefinition of color scheme for dark theme */\n",
584
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
585
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
586
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
587
+ " --sklearn-color-icon: #878787;\n",
588
+ " }\n",
589
+ "}\n",
590
+ "\n",
591
+ "#sk-container-id-1 {\n",
592
+ " color: var(--sklearn-color-text);\n",
593
+ "}\n",
594
+ "\n",
595
+ "#sk-container-id-1 pre {\n",
596
+ " padding: 0;\n",
597
+ "}\n",
598
+ "\n",
599
+ "#sk-container-id-1 input.sk-hidden--visually {\n",
600
+ " border: 0;\n",
601
+ " clip: rect(1px 1px 1px 1px);\n",
602
+ " clip: rect(1px, 1px, 1px, 1px);\n",
603
+ " height: 1px;\n",
604
+ " margin: -1px;\n",
605
+ " overflow: hidden;\n",
606
+ " padding: 0;\n",
607
+ " position: absolute;\n",
608
+ " width: 1px;\n",
609
+ "}\n",
610
+ "\n",
611
+ "#sk-container-id-1 div.sk-dashed-wrapped {\n",
612
+ " border: 1px dashed var(--sklearn-color-line);\n",
613
+ " margin: 0 0.4em 0.5em 0.4em;\n",
614
+ " box-sizing: border-box;\n",
615
+ " padding-bottom: 0.4em;\n",
616
+ " background-color: var(--sklearn-color-background);\n",
617
+ "}\n",
618
+ "\n",
619
+ "#sk-container-id-1 div.sk-container {\n",
620
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
621
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
622
+ " so we also need the `!important` here to be able to override the\n",
623
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
624
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
625
+ " display: inline-block !important;\n",
626
+ " position: relative;\n",
627
+ "}\n",
628
+ "\n",
629
+ "#sk-container-id-1 div.sk-text-repr-fallback {\n",
630
+ " display: none;\n",
631
+ "}\n",
632
+ "\n",
633
+ "div.sk-parallel-item,\n",
634
+ "div.sk-serial,\n",
635
+ "div.sk-item {\n",
636
+ " /* draw centered vertical line to link estimators */\n",
637
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
638
+ " background-size: 2px 100%;\n",
639
+ " background-repeat: no-repeat;\n",
640
+ " background-position: center center;\n",
641
+ "}\n",
642
+ "\n",
643
+ "/* Parallel-specific style estimator block */\n",
644
+ "\n",
645
+ "#sk-container-id-1 div.sk-parallel-item::after {\n",
646
+ " content: \"\";\n",
647
+ " width: 100%;\n",
648
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
649
+ " flex-grow: 1;\n",
650
+ "}\n",
651
+ "\n",
652
+ "#sk-container-id-1 div.sk-parallel {\n",
653
+ " display: flex;\n",
654
+ " align-items: stretch;\n",
655
+ " justify-content: center;\n",
656
+ " background-color: var(--sklearn-color-background);\n",
657
+ " position: relative;\n",
658
+ "}\n",
659
+ "\n",
660
+ "#sk-container-id-1 div.sk-parallel-item {\n",
661
+ " display: flex;\n",
662
+ " flex-direction: column;\n",
663
+ "}\n",
664
+ "\n",
665
+ "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
666
+ " align-self: flex-end;\n",
667
+ " width: 50%;\n",
668
+ "}\n",
669
+ "\n",
670
+ "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
671
+ " align-self: flex-start;\n",
672
+ " width: 50%;\n",
673
+ "}\n",
674
+ "\n",
675
+ "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
676
+ " width: 0;\n",
677
+ "}\n",
678
+ "\n",
679
+ "/* Serial-specific style estimator block */\n",
680
+ "\n",
681
+ "#sk-container-id-1 div.sk-serial {\n",
682
+ " display: flex;\n",
683
+ " flex-direction: column;\n",
684
+ " align-items: center;\n",
685
+ " background-color: var(--sklearn-color-background);\n",
686
+ " padding-right: 1em;\n",
687
+ " padding-left: 1em;\n",
688
+ "}\n",
689
+ "\n",
690
+ "\n",
691
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
692
+ "clickable and can be expanded/collapsed.\n",
693
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
694
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
695
+ "*/\n",
696
+ "\n",
697
+ "/* Pipeline and ColumnTransformer style (default) */\n",
698
+ "\n",
699
+ "#sk-container-id-1 div.sk-toggleable {\n",
700
+ " /* Default theme specific background. It is overwritten whether we have a\n",
701
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
702
+ " background-color: var(--sklearn-color-background);\n",
703
+ "}\n",
704
+ "\n",
705
+ "/* Toggleable label */\n",
706
+ "#sk-container-id-1 label.sk-toggleable__label {\n",
707
+ " cursor: pointer;\n",
708
+ " display: flex;\n",
709
+ " width: 100%;\n",
710
+ " margin-bottom: 0;\n",
711
+ " padding: 0.5em;\n",
712
+ " box-sizing: border-box;\n",
713
+ " text-align: center;\n",
714
+ " align-items: start;\n",
715
+ " justify-content: space-between;\n",
716
+ " gap: 0.5em;\n",
717
+ "}\n",
718
+ "\n",
719
+ "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
720
+ " font-size: 0.6rem;\n",
721
+ " font-weight: lighter;\n",
722
+ " color: var(--sklearn-color-text-muted);\n",
723
+ "}\n",
724
+ "\n",
725
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
726
+ " /* Arrow on the left of the label */\n",
727
+ " content: \"▸\";\n",
728
+ " float: left;\n",
729
+ " margin-right: 0.25em;\n",
730
+ " color: var(--sklearn-color-icon);\n",
731
+ "}\n",
732
+ "\n",
733
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
734
+ " color: var(--sklearn-color-text);\n",
735
+ "}\n",
736
+ "\n",
737
+ "/* Toggleable content - dropdown */\n",
738
+ "\n",
739
+ "#sk-container-id-1 div.sk-toggleable__content {\n",
740
+ " max-height: 0;\n",
741
+ " max-width: 0;\n",
742
+ " overflow: hidden;\n",
743
+ " text-align: left;\n",
744
+ " /* unfitted */\n",
745
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
746
+ "}\n",
747
+ "\n",
748
+ "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
749
+ " /* fitted */\n",
750
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
751
+ "}\n",
752
+ "\n",
753
+ "#sk-container-id-1 div.sk-toggleable__content pre {\n",
754
+ " margin: 0.2em;\n",
755
+ " border-radius: 0.25em;\n",
756
+ " color: var(--sklearn-color-text);\n",
757
+ " /* unfitted */\n",
758
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
759
+ "}\n",
760
+ "\n",
761
+ "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
762
+ " /* unfitted */\n",
763
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
764
+ "}\n",
765
+ "\n",
766
+ "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
767
+ " /* Expand drop-down */\n",
768
+ " max-height: 200px;\n",
769
+ " max-width: 100%;\n",
770
+ " overflow: auto;\n",
771
+ "}\n",
772
+ "\n",
773
+ "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
774
+ " content: \"▾\";\n",
775
+ "}\n",
776
+ "\n",
777
+ "/* Pipeline/ColumnTransformer-specific style */\n",
778
+ "\n",
779
+ "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
780
+ " color: var(--sklearn-color-text);\n",
781
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
782
+ "}\n",
783
+ "\n",
784
+ "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
785
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
786
+ "}\n",
787
+ "\n",
788
+ "/* Estimator-specific style */\n",
789
+ "\n",
790
+ "/* Colorize estimator box */\n",
791
+ "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
792
+ " /* unfitted */\n",
793
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
794
+ "}\n",
795
+ "\n",
796
+ "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
797
+ " /* fitted */\n",
798
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
799
+ "}\n",
800
+ "\n",
801
+ "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
802
+ "#sk-container-id-1 div.sk-label label {\n",
803
+ " /* The background is the default theme color */\n",
804
+ " color: var(--sklearn-color-text-on-default-background);\n",
805
+ "}\n",
806
+ "\n",
807
+ "/* On hover, darken the color of the background */\n",
808
+ "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
809
+ " color: var(--sklearn-color-text);\n",
810
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
811
+ "}\n",
812
+ "\n",
813
+ "/* Label box, darken color on hover, fitted */\n",
814
+ "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
815
+ " color: var(--sklearn-color-text);\n",
816
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
817
+ "}\n",
818
+ "\n",
819
+ "/* Estimator label */\n",
820
+ "\n",
821
+ "#sk-container-id-1 div.sk-label label {\n",
822
+ " font-family: monospace;\n",
823
+ " font-weight: bold;\n",
824
+ " display: inline-block;\n",
825
+ " line-height: 1.2em;\n",
826
+ "}\n",
827
+ "\n",
828
+ "#sk-container-id-1 div.sk-label-container {\n",
829
+ " text-align: center;\n",
830
+ "}\n",
831
+ "\n",
832
+ "/* Estimator-specific */\n",
833
+ "#sk-container-id-1 div.sk-estimator {\n",
834
+ " font-family: monospace;\n",
835
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
836
+ " border-radius: 0.25em;\n",
837
+ " box-sizing: border-box;\n",
838
+ " margin-bottom: 0.5em;\n",
839
+ " /* unfitted */\n",
840
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
841
+ "}\n",
842
+ "\n",
843
+ "#sk-container-id-1 div.sk-estimator.fitted {\n",
844
+ " /* fitted */\n",
845
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
846
+ "}\n",
847
+ "\n",
848
+ "/* on hover */\n",
849
+ "#sk-container-id-1 div.sk-estimator:hover {\n",
850
+ " /* unfitted */\n",
851
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
852
+ "}\n",
853
+ "\n",
854
+ "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
855
+ " /* fitted */\n",
856
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
857
+ "}\n",
858
+ "\n",
859
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
860
+ "\n",
861
+ "/* Common style for \"i\" and \"?\" */\n",
862
+ "\n",
863
+ ".sk-estimator-doc-link,\n",
864
+ "a:link.sk-estimator-doc-link,\n",
865
+ "a:visited.sk-estimator-doc-link {\n",
866
+ " float: right;\n",
867
+ " font-size: smaller;\n",
868
+ " line-height: 1em;\n",
869
+ " font-family: monospace;\n",
870
+ " background-color: var(--sklearn-color-background);\n",
871
+ " border-radius: 1em;\n",
872
+ " height: 1em;\n",
873
+ " width: 1em;\n",
874
+ " text-decoration: none !important;\n",
875
+ " margin-left: 0.5em;\n",
876
+ " text-align: center;\n",
877
+ " /* unfitted */\n",
878
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
879
+ " color: var(--sklearn-color-unfitted-level-1);\n",
880
+ "}\n",
881
+ "\n",
882
+ ".sk-estimator-doc-link.fitted,\n",
883
+ "a:link.sk-estimator-doc-link.fitted,\n",
884
+ "a:visited.sk-estimator-doc-link.fitted {\n",
885
+ " /* fitted */\n",
886
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
887
+ " color: var(--sklearn-color-fitted-level-1);\n",
888
+ "}\n",
889
+ "\n",
890
+ "/* On hover */\n",
891
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
892
+ ".sk-estimator-doc-link:hover,\n",
893
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
894
+ ".sk-estimator-doc-link:hover {\n",
895
+ " /* unfitted */\n",
896
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
897
+ " color: var(--sklearn-color-background);\n",
898
+ " text-decoration: none;\n",
899
+ "}\n",
900
+ "\n",
901
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
902
+ ".sk-estimator-doc-link.fitted:hover,\n",
903
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
904
+ ".sk-estimator-doc-link.fitted:hover {\n",
905
+ " /* fitted */\n",
906
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
907
+ " color: var(--sklearn-color-background);\n",
908
+ " text-decoration: none;\n",
909
+ "}\n",
910
+ "\n",
911
+ "/* Span, style for the box shown on hovering the info icon */\n",
912
+ ".sk-estimator-doc-link span {\n",
913
+ " display: none;\n",
914
+ " z-index: 9999;\n",
915
+ " position: relative;\n",
916
+ " font-weight: normal;\n",
917
+ " right: .2ex;\n",
918
+ " padding: .5ex;\n",
919
+ " margin: .5ex;\n",
920
+ " width: min-content;\n",
921
+ " min-width: 20ex;\n",
922
+ " max-width: 50ex;\n",
923
+ " color: var(--sklearn-color-text);\n",
924
+ " box-shadow: 2pt 2pt 4pt #999;\n",
925
+ " /* unfitted */\n",
926
+ " background: var(--sklearn-color-unfitted-level-0);\n",
927
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
928
+ "}\n",
929
+ "\n",
930
+ ".sk-estimator-doc-link.fitted span {\n",
931
+ " /* fitted */\n",
932
+ " background: var(--sklearn-color-fitted-level-0);\n",
933
+ " border: var(--sklearn-color-fitted-level-3);\n",
934
+ "}\n",
935
+ "\n",
936
+ ".sk-estimator-doc-link:hover span {\n",
937
+ " display: block;\n",
938
+ "}\n",
939
+ "\n",
940
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
941
+ "\n",
942
+ "#sk-container-id-1 a.estimator_doc_link {\n",
943
+ " float: right;\n",
944
+ " font-size: 1rem;\n",
945
+ " line-height: 1em;\n",
946
+ " font-family: monospace;\n",
947
+ " background-color: var(--sklearn-color-background);\n",
948
+ " border-radius: 1rem;\n",
949
+ " height: 1rem;\n",
950
+ " width: 1rem;\n",
951
+ " text-decoration: none;\n",
952
+ " /* unfitted */\n",
953
+ " color: var(--sklearn-color-unfitted-level-1);\n",
954
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
955
+ "}\n",
956
+ "\n",
957
+ "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
958
+ " /* fitted */\n",
959
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
960
+ " color: var(--sklearn-color-fitted-level-1);\n",
961
+ "}\n",
962
+ "\n",
963
+ "/* On hover */\n",
964
+ "#sk-container-id-1 a.estimator_doc_link:hover {\n",
965
+ " /* unfitted */\n",
966
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
967
+ " color: var(--sklearn-color-background);\n",
968
+ " text-decoration: none;\n",
969
+ "}\n",
970
+ "\n",
971
+ "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
972
+ " /* fitted */\n",
973
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
974
+ "}\n",
975
+ "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(max_iter=200)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LogisticRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression(max_iter=200)</pre></div> </div></div></div></div>"
976
+ ]
977
+ },
978
+ "metadata": {},
979
+ "execution_count": 15
980
+ }
981
+ ]
982
+ },
983
+ {
984
+ "cell_type": "code",
985
+ "source": [
986
+ "y_pred = clf.predict(X_test)\n"
987
+ ],
988
+ "metadata": {
989
+ "id": "zutBgt6SP17z"
990
+ },
991
+ "execution_count": null,
992
+ "outputs": []
993
+ },
994
+ {
995
+ "cell_type": "code",
996
+ "source": [
997
+ "\n",
998
+ "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
999
+ "\n",
1000
+ "\n",
1001
+ "print(classification_report(y_test, y_pred))\n",
1002
+ "\n",
1003
+ "\n",
1004
+ "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n"
1005
+ ],
1006
+ "metadata": {
1007
+ "id": "lOM-9luZP1-0",
1008
+ "colab": {
1009
+ "base_uri": "https://localhost:8080/"
1010
+ },
1011
+ "outputId": "c971b06d-e98b-494a-fcb2-8e11b31aa072"
1012
+ },
1013
+ "execution_count": null,
1014
+ "outputs": [
1015
+ {
1016
+ "output_type": "stream",
1017
+ "name": "stdout",
1018
+ "text": [
1019
+ "Accuracy: 0.8845\n",
1020
+ " precision recall f1-score support\n",
1021
+ "\n",
1022
+ " 0 0.89 0.87 0.88 4961\n",
1023
+ " 1 0.88 0.90 0.89 5039\n",
1024
+ "\n",
1025
+ " accuracy 0.88 10000\n",
1026
+ " macro avg 0.88 0.88 0.88 10000\n",
1027
+ "weighted avg 0.88 0.88 0.88 10000\n",
1028
+ "\n",
1029
+ "Confusion Matrix:\n",
1030
+ " [[4318 643]\n",
1031
+ " [ 512 4527]]\n"
1032
+ ]
1033
+ }
1034
+ ]
1035
+ },
1036
+ {
1037
+ "cell_type": "code",
1038
+ "source": [
1039
+ "# Uninstall conflicting packages\n",
1040
+ "!pip uninstall -y shap scipy\n",
1041
+ "\n",
1042
+ "# Install compatible versions\n",
1043
+ "!pip install scipy==1.10.1\n",
1044
+ "!pip install shap==0.42.1"
1045
+ ],
1046
+ "metadata": {
1047
+ "colab": {
1048
+ "base_uri": "https://localhost:8080/",
1049
+ "height": 714
1050
+ },
1051
+ "id": "9FmYRCyOtS2L",
1052
+ "outputId": "5742d3ba-5692-4b0c-9bb8-6b83b49f77be"
1053
+ },
1054
+ "execution_count": null,
1055
+ "outputs": [
1056
+ {
1057
+ "output_type": "stream",
1058
+ "name": "stdout",
1059
+ "text": [
1060
+ "Found existing installation: shap 0.42.1\n",
1061
+ "Uninstalling shap-0.42.1:\n",
1062
+ " Successfully uninstalled shap-0.42.1\n",
1063
+ "Found existing installation: scipy 1.16.2\n",
1064
+ "Uninstalling scipy-1.16.2:\n",
1065
+ " Successfully uninstalled scipy-1.16.2\n",
1066
+ "\u001b[31mERROR: Ignored the following yanked versions: 1.11.0, 1.14.0rc1\u001b[0m\u001b[31m\n",
1067
+ "\u001b[0m\u001b[31mERROR: Ignored the following versions that require a different python version: 1.10.0 Requires-Python <3.12,>=3.8; 1.10.0rc1 Requires-Python <3.12,>=3.8; 1.10.0rc2 Requires-Python <3.12,>=3.8; 1.10.1 Requires-Python <3.12,>=3.8; 1.6.2 Requires-Python >=3.7,<3.10; 1.6.3 Requires-Python >=3.7,<3.10; 1.7.0 Requires-Python >=3.7,<3.10; 1.7.1 Requires-Python >=3.7,<3.10; 1.7.2 Requires-Python >=3.7,<3.11; 1.7.3 Requires-Python >=3.7,<3.11; 1.8.0 Requires-Python >=3.8,<3.11; 1.8.0rc1 Requires-Python >=3.8,<3.11; 1.8.0rc2 Requires-Python >=3.8,<3.11; 1.8.0rc3 Requires-Python >=3.8,<3.11; 1.8.0rc4 Requires-Python >=3.8,<3.11; 1.8.1 Requires-Python >=3.8,<3.11; 1.9.0 Requires-Python >=3.8,<3.12; 1.9.0rc1 Requires-Python >=3.8,<3.12; 1.9.0rc2 Requires-Python >=3.8,<3.12; 1.9.0rc3 Requires-Python >=3.8,<3.12; 1.9.1 Requires-Python >=3.8,<3.12\u001b[0m\u001b[31m\n",
1068
+ "\u001b[0m\u001b[31mERROR: Could not find a version that satisfies the requirement scipy==1.10.1 (from versions: 0.8.0, 0.9.0, 0.10.0, 0.10.1, 0.11.0, 0.12.0, 0.12.1, 0.13.0, 0.13.1, 0.13.2, 0.13.3, 0.14.0, 0.14.1, 0.15.0, 0.15.1, 0.16.0, 0.16.1, 0.17.0, 0.17.1, 0.18.0, 0.18.1, 0.19.0, 0.19.1, 1.0.0, 1.0.1, 1.1.0, 1.2.0, 1.2.1, 1.2.2, 1.2.3, 1.3.0, 1.3.1, 1.3.2, 1.3.3, 1.4.0, 1.4.1, 1.5.0, 1.5.1, 1.5.2, 1.5.3, 1.5.4, 1.6.0, 1.6.1, 1.9.2, 1.9.3, 1.11.0rc1, 1.11.0rc2, 1.11.1, 1.11.2, 1.11.3, 1.11.4, 1.12.0rc1, 1.12.0rc2, 1.12.0, 1.13.0rc1, 1.13.0, 1.13.1, 1.14.0rc2, 1.14.0, 1.14.1, 1.15.0rc1, 1.15.0rc2, 1.15.0, 1.15.1, 1.15.2, 1.15.3, 1.16.0rc1, 1.16.0rc2, 1.16.0, 1.16.1, 1.16.2)\u001b[0m\u001b[31m\n",
1069
+ "\u001b[0m\u001b[31mERROR: No matching distribution found for scipy==1.10.1\u001b[0m\u001b[31m\n",
1070
+ "\u001b[0mCollecting shap==0.42.1\n",
1071
+ " Using cached shap-0.42.1-cp312-cp312-linux_x86_64.whl\n",
1072
+ "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (1.26.0)\n",
1073
+ "Collecting scipy (from shap==0.42.1)\n",
1074
+ " Using cached scipy-1.16.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (62 kB)\n",
1075
+ "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (1.6.1)\n",
1076
+ "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (2.2.2)\n",
1077
+ "Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (4.67.1)\n",
1078
+ "Requirement already satisfied: packaging>20.9 in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (25.0)\n",
1079
+ "Requirement already satisfied: slicer==0.0.7 in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (0.0.7)\n",
1080
+ "Requirement already satisfied: numba in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (0.60.0)\n",
1081
+ "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (3.1.1)\n",
1082
+ "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba->shap==0.42.1) (0.43.0)\n",
1083
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->shap==0.42.1) (2.9.0.post0)\n",
1084
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->shap==0.42.1) (2025.2)\n",
1085
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->shap==0.42.1) (2025.2)\n",
1086
+ "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn->shap==0.42.1) (1.5.2)\n",
1087
+ "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn->shap==0.42.1) (3.6.0)\n",
1088
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas->shap==0.42.1) (1.17.0)\n",
1089
+ "Using cached scipy-1.16.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (35.7 MB)\n",
1090
+ "Installing collected packages: scipy, shap\n",
1091
+ "Successfully installed scipy-1.16.2 shap-0.42.1\n"
1092
+ ]
1093
+ },
1094
+ {
1095
+ "output_type": "display_data",
1096
+ "data": {
1097
+ "application/vnd.colab-display-data+json": {
1098
+ "pip_warning": {
1099
+ "packages": [
1100
+ "scipy",
1101
+ "shap"
1102
+ ]
1103
+ },
1104
+ "id": "471ee32ea4224e2c8848bbf1936661d7"
1105
+ }
1106
+ },
1107
+ "metadata": {}
1108
+ }
1109
+ ]
1110
+ },
1111
+ {
1112
+ "cell_type": "code",
1113
+ "source": [
1114
+ "!pip install numpy==1.26.0 shap==0.42.1\n",
1115
+ "\n"
1116
+ ],
1117
+ "metadata": {
1118
+ "colab": {
1119
+ "base_uri": "https://localhost:8080/"
1120
+ },
1121
+ "id": "sgslFrBzuj2j",
1122
+ "outputId": "c013ef49-d02a-46ed-e28f-a669fe4ad0db"
1123
+ },
1124
+ "execution_count": null,
1125
+ "outputs": [
1126
+ {
1127
+ "output_type": "stream",
1128
+ "name": "stdout",
1129
+ "text": [
1130
+ "Requirement already satisfied: numpy==1.26.0 in /usr/local/lib/python3.12/dist-packages (1.26.0)\n",
1131
+ "Requirement already satisfied: shap==0.42.1 in /usr/local/lib/python3.12/dist-packages (0.42.1)\n",
1132
+ "Requirement already satisfied: scipy in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (1.16.2)\n",
1133
+ "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (1.6.1)\n",
1134
+ "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (2.2.2)\n",
1135
+ "Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (4.67.1)\n",
1136
+ "Requirement already satisfied: packaging>20.9 in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (25.0)\n",
1137
+ "Requirement already satisfied: slicer==0.0.7 in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (0.0.7)\n",
1138
+ "Requirement already satisfied: numba in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (0.60.0)\n",
1139
+ "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.12/dist-packages (from shap==0.42.1) (3.1.1)\n",
1140
+ "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba->shap==0.42.1) (0.43.0)\n",
1141
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->shap==0.42.1) (2.9.0.post0)\n",
1142
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->shap==0.42.1) (2025.2)\n",
1143
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->shap==0.42.1) (2025.2)\n",
1144
+ "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn->shap==0.42.1) (1.5.2)\n",
1145
+ "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn->shap==0.42.1) (3.6.0)\n",
1146
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas->shap==0.42.1) (1.17.0)\n"
1147
+ ]
1148
+ }
1149
+ ]
1150
+ },
1151
+ {
1152
+ "cell_type": "code",
1153
+ "source": [
1154
+ "import numpy as np\n",
1155
+ "\n",
1156
+ "\n",
1157
+ "np.obj2sctype = lambda obj: np.dtype(obj).type\n",
1158
+ "\n",
1159
+ "import shap\n"
1160
+ ],
1161
+ "metadata": {
1162
+ "id": "ju0ZjEtXrzej"
1163
+ },
1164
+ "execution_count": null,
1165
+ "outputs": []
1166
+ },
1167
+ {
1168
+ "cell_type": "code",
1169
+ "source": [],
1170
+ "metadata": {
1171
+ "id": "2ng9Yfj-p3z4"
1172
+ },
1173
+ "execution_count": null,
1174
+ "outputs": []
1175
+ },
1176
+ {
1177
+ "cell_type": "code",
1178
+ "source": [],
1179
+ "metadata": {
1180
+ "id": "_ffFRvF8oy1l"
1181
+ },
1182
+ "execution_count": null,
1183
+ "outputs": []
1184
+ },
1185
+ {
1186
+ "cell_type": "markdown",
1187
+ "source": [
1188
+ "MODEL 2\n"
1189
+ ],
1190
+ "metadata": {
1191
+ "id": "iD0gMTx-jfP4"
1192
+ }
1193
+ },
1194
+ {
1195
+ "cell_type": "code",
1196
+ "source": [
1197
+ "\n",
1198
+ "\n",
1199
+ "from sklearn.model_selection import train_test_split\n",
1200
+ "from tensorflow.keras.preprocessing.text import Tokenizer\n",
1201
+ "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
1202
+ "from tensorflow.keras.models import Sequential\n",
1203
+ "from tensorflow.keras.layers import Embedding, LSTM, Dense, Dropout, Bidirectional\n",
1204
+ "\n",
1205
+ "max_words = 10000\n",
1206
+ "max_len = 200\n",
1207
+ "\n",
1208
+ "tokenizer = Tokenizer(num_words=max_words)\n",
1209
+ "tokenizer.fit_on_texts(df[\"cleaned_review\"])\n",
1210
+ "sequences = tokenizer.texts_to_sequences(df[\"cleaned_review\"])\n",
1211
+ "X = pad_sequences(sequences, maxlen=max_len)\n",
1212
+ "\n",
1213
+ "y = df[\"sentiment\"].map({\"positive\": 1, \"negative\": 0}).values\n",
1214
+ "\n",
1215
+ "\n",
1216
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
1217
+ "\n",
1218
+ "\n",
1219
+ "model = Sequential()\n",
1220
+ "model.add(Embedding(input_dim=max_words, output_dim=128, input_length=max_len))\n",
1221
+ "model.add(Bidirectional(LSTM(64)))\n",
1222
+ "model.add(Dropout(0.5))\n",
1223
+ "model.add(Dense(1, activation='sigmoid'))\n",
1224
+ "\n",
1225
+ "model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
1226
+ "model.summary()\n",
1227
+ "\n",
1228
+ "\n",
1229
+ "history = model.fit(\n",
1230
+ " X_train, y_train,\n",
1231
+ " epochs=5,\n",
1232
+ " batch_size=128,\n",
1233
+ " validation_split=0.1\n",
1234
+ ")\n",
1235
+ "\n",
1236
+ "\n",
1237
+ "\n",
1238
+ "loss, accuracy = model.evaluate(X_test, y_test)\n",
1239
+ "print(\"LSTM Test Accuracy:\", accuracy)\n",
1240
+ "\n",
1241
+ "\n"
1242
+ ],
1243
+ "metadata": {
1244
+ "id": "ZX3VcwlOP2EK"
1245
+ },
1246
+ "execution_count": null,
1247
+ "outputs": []
1248
+ },
1249
+ {
1250
+ "cell_type": "code",
1251
+ "source": [
1252
+ "\n",
1253
+ "!pip uninstall -y shap scipy\n",
1254
+ "\n",
1255
+ "\n",
1256
+ "!pip install scipy==1.10.1\n",
1257
+ "!pip install shap==0.42.1"
1258
+ ],
1259
+ "metadata": {
1260
+ "id": "2_DekM_ijieI"
1261
+ },
1262
+ "execution_count": null,
1263
+ "outputs": []
1264
+ },
1265
+ {
1266
+ "cell_type": "code",
1267
+ "source": [],
1268
+ "metadata": {
1269
+ "id": "_Iwjp2JpjihN"
1270
+ },
1271
+ "execution_count": null,
1272
+ "outputs": []
1273
+ },
1274
+ {
1275
+ "cell_type": "code",
1276
+ "source": [],
1277
+ "metadata": {
1278
+ "id": "QlgbCNxUjikB"
1279
+ },
1280
+ "execution_count": null,
1281
+ "outputs": []
1282
+ },
1283
+ {
1284
+ "cell_type": "code",
1285
+ "source": [],
1286
+ "metadata": {
1287
+ "id": "afS4-CfWjinK"
1288
+ },
1289
+ "execution_count": null,
1290
+ "outputs": []
1291
+ },
1292
+ {
1293
+ "cell_type": "code",
1294
+ "source": [
1295
+ "import shap\n",
1296
+ "import numpy as np\n",
1297
+ "\n",
1298
+ "X_background = X_train[:100]\n",
1299
+ "\n",
1300
+ "explainer = shap.DeepExplainer(model, X_background)\n",
1301
+ "\n",
1302
+ "\n",
1303
+ "sample_review = X_test[0:1]\n",
1304
+ "\n",
1305
+ "\n",
1306
+ "shap_values = explainer.shap_values(sample_review)\n",
1307
+ "\n",
1308
+ "\n",
1309
+ "index_word = {v: k for k, v in tokenizer.word_index.items()}\n",
1310
+ "words = [index_word.get(i, '') for i in sample_review[0] if i != 0]\n",
1311
+ "\n",
1312
+ "shap.initjs()\n",
1313
+ "shap.force_plot(explainer.expected_value[0], shap_values[0][0], words)\n"
1314
+ ],
1315
+ "metadata": {
1316
+ "id": "D1zFJ5gwP2SC"
1317
+ },
1318
+ "execution_count": null,
1319
+ "outputs": []
1320
+ },
1321
+ {
1322
+ "cell_type": "code",
1323
+ "source": [
1324
+ "import shap"
1325
+ ],
1326
+ "metadata": {
1327
+ "id": "vwQyqFNlhOc4"
1328
+ },
1329
+ "execution_count": null,
1330
+ "outputs": []
1331
+ },
1332
+ {
1333
+ "cell_type": "code",
1334
+ "source": [
1335
+ "Logistic Regression is a simple baseline model for sentiment analysis, using features like bag-of-words or TF-IDF but ignores word order. LSTM, on the other hand, is a deep learning model that captures sequence and context, making it more accurate for understanding movie reviews"
1336
+ ],
1337
+ "metadata": {
1338
+ "id": "SReiT-0giWKR"
1339
+ },
1340
+ "execution_count": null,
1341
+ "outputs": []
1342
+ }
1343
+ ],
1344
+ "metadata": {
1345
+ "colab": {
1346
+ "provenance": []
1347
+ },
1348
+ "kernelspec": {
1349
+ "display_name": "Python 3",
1350
+ "name": "python3"
1351
+ }
1352
+ },
1353
+ "nbformat": 4,
1354
+ "nbformat_minor": 0
1355
+ }