File size: 11,256 Bytes
0e9c6bb | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 | {
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "2YpCZ5QwOGCL"
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.naive_bayes import MultinomialNB\n",
"from sklearn.utils import shuffle\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from sklearn.feature_extraction.text import CountVectorizer\n",
"import json\n"
]
},
{
"cell_type": "code",
"source": [
"# Read the dataset\n",
"df = pd.read_json(\"DATA.json\", encoding=\"utf-8\")"
],
"metadata": {
"id": "1BpsBFfLZbW8"
},
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Shuffle the dataset\n",
"df = shuffle(df)"
],
"metadata": {
"id": "lTijWIiEVjVc"
},
"execution_count": 3,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Create a training set and a test set\n",
"train_data = df[:int(len(df) * 0.8)]\n",
"test_data = df[int(len(df) * 0.8):]"
],
"metadata": {
"id": "RDTKsDCsWGRk"
},
"execution_count": 4,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Create a vocabulary of all the words in the training set\n",
"vocabulary = set()\n",
"for d in df[\"content\"]:\n",
" if isinstance(d, str):\n",
" vocabulary.update(d.split())"
],
"metadata": {
"id": "rta9jPyxVm-I"
},
"execution_count": 6,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Convert the list of text documents to a 2D array for the training set\n",
"bow_train = np.array([[str(doc).count(word) for word in vocabulary] for doc in train_data[\"content\"].fillna(\"\")])\n"
],
"metadata": {
"id": "owPao6jdVprA"
},
"execution_count": 7,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Convert the list of text documents to a 2D array for the test set\n",
"bow_test = np.array([[str(doc).count(word) for word in vocabulary] for doc in test_data[\"content\"].fillna(\"\")])"
],
"metadata": {
"id": "Blc4X_qNV72O"
},
"execution_count": 8,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Convert the labels to numeric values\n",
"label_encoder = LabelEncoder()\n",
"train_labels = label_encoder.fit_transform(train_data[\"label\"])"
],
"metadata": {
"id": "pe1Y1uNEWRek"
},
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Create a Naive Bayes model\n",
"model = MultinomialNB()"
],
"metadata": {
"id": "pv1ps_IwWV8M"
},
"execution_count": 10,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Train the model\n",
"model.fit(bow_train, train_labels)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 75
},
"id": "JYIiFXYdWY73",
"outputId": "a698f8a6-eeda-49ab-c434-f438c6967ad5"
},
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"MultinomialNB()"
],
"text/html": [
"<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultinomialNB()</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 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 sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB()</pre></div></div></div></div></div>"
]
},
"metadata": {},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"source": [
"# Test the model\n",
"test_labels = label_encoder.transform(test_data[\"label\"])\n",
"predictions = model.predict(bow_test)"
],
"metadata": {
"id": "gDcK0uiWWeKc"
},
"execution_count": 12,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Calculate the accuracy of the model\n",
"accuracy = (predictions == test_labels).mean()\n",
"print(\"Accuracy:\", accuracy)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "eBMyVM5hWjiL",
"outputId": "4c26f478-76b9-4404-9d61-10da839d6465"
},
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Accuracy: 0.9348500517063082\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"def test_model(text):\n",
" bow = {}\n",
" for word in text.split():\n",
" if word in vocabulary:\n",
" bow[word] = text.count(word)\n",
" bow = np.array([bow.get(word, 0) for word in vocabulary]).reshape(1, -1)\n",
" prediction = model.predict(bow)[0]\n",
" return label_encoder.inverse_transform([prediction])[0]\n",
"\n"
],
"metadata": {
"id": "TFH--bOmWpEU"
},
"execution_count": 14,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Test the model with some text\n",
"text = \"Aura Azure Collagen Gummies Advantages, Official Website & Reviews [2023]\"\n",
"prediction = test_model(text)\n",
"print(prediction)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GDL4OZ_5Wsc7",
"outputId": "e97b7b46-3a18-446e-e5f6-186bf285d96f"
},
"execution_count": 15,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"NSFW\n"
]
}
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "CPxtDWlYWwYC"
},
"execution_count": null,
"outputs": []
}
]
} |