File size: 15,504 Bytes
75f0757 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"# reading dataset files\n",
"muslim_file = \"../data/right/Haqiqatjou.csv\"\n",
"muslim_df = pd.read_csv(muslim_file)\n",
"\n",
"\n",
"sanghi_file = \"../data/wrong/MrSinha_.csv\"\n",
"sanghi_df = pd.read_csv(sanghi_file)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"# dataset formatting\n",
"muslim_df['category'] = 'MUSLIM'\n",
"\n",
"sanghi_df['category'] = 'SANGHI'\n",
"\n",
"\n",
"frames = [muslim_df, sanghi_df]\n",
"final_dataset = pd.concat(frames)\n",
"final_dataset = final_dataset.drop(['index'], axis=1)\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"# ref : https://stackoverflow.com/questions/43777243/how-to-split-a-dataframe-in-pandas-in-predefined-percentages\n",
"\n",
"# 70% train dataset\n",
"# train_frames = [muslim_df.sample(frac=0.7), sanghi_df.sample(frac=0.7).reset_index(drop=True)]\n",
"train_frames = [muslim_df, sanghi_df]\n",
"train_dataset = pd.concat(train_frames)\n",
"train_dataset['content'] = train_dataset['content'].astype(str)\n",
"\n",
"\n",
"# 30% test dataset\n",
"remaining_frames = [muslim_df.drop(muslim_df.sample(frac=0.7).index), sanghi_df.drop(sanghi_df.sample(frac=0.7).index).reset_index(drop=True)]\n",
"test_dataset = pd.concat(remaining_frames)\n",
"# test_dataset['content'] = train_dataset['content'].astype(str)\n",
"# test_dataset\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-03-22 14:25:54.140036: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"2024-03-22 14:25:58.302374: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
]
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"import os\n",
"import re\n",
"import shutil\n",
"import string\n",
"import tensorflow as tf\n",
"from keras import layers\n",
"from keras import losses\n",
"import keras\n",
"from tensorflow.keras.preprocessing.text import Tokenizer\n",
"from tensorflow.keras.preprocessing.sequence import pad_sequences"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Tokenization\n",
"tokenizer = Tokenizer()\n",
"tokenizer.fit_on_texts(train_dataset['content'])\n",
"\n",
"vocab_size = len(tokenizer.word_index) + 1\n",
"max_length = 100 # adjust as needed\n",
"embedding_dim = 50 # adjust as needed\n",
"\n",
"X = tokenizer.texts_to_sequences(train_dataset['content'])\n",
"X = pad_sequences(X, maxlen=max_length, padding='post')\n",
"\n",
"# Encode labels\n",
"labels = train_dataset['category'].map({'MUSLIM': '1', 'SANGHI': 0}).astype('float32').values"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/xd/Documents/models/twitter_model/.venv/lib/python3.10/site-packages/keras/src/layers/core/embedding.py:81: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
" super().__init__(**kwargs)\n",
"2024-03-21 20:20:29.968292: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.617785: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.618176: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.620147: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.620655: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.620962: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.824877: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.825245: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.825539: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"2024-03-21 20:20:33.841867: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1928] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 1754 MB memory: -> device: 0, name: NVIDIA GeForce 920MX, pci bus id: 0000:01:00.0, compute capability: 5.0\n"
]
}
],
"source": [
"# build the model\n",
"model = keras.Sequential([\n",
" keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim, input_shape=(max_length,)),\n",
" keras.layers.GlobalAveragePooling1D(),\n",
" keras.layers.Dense(16, activation='relu'),\n",
" keras.layers.Dense(1, activation='sigmoid')\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Compile the model\n",
"model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Split into train and test datasets\n",
"from sklearn.model_selection import train_test_split\n",
"X_train, X_test, y_train, y_test = train_test_split(X, labels, test_size=0.3, random_state=42)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/10\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"I0000 00:00:1711032641.198169 31002 service.cc:145] XLA service 0x7fa54c006910 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\n",
"I0000 00:00:1711032641.198244 31002 service.cc:153] StreamExecutor device (0): NVIDIA GeForce 920MX, Compute Capability 5.0\n",
"2024-03-21 20:20:41.877803: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:268] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.\n",
"2024-03-21 20:20:42.791103: I external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:465] Loaded cuDNN version 8907\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m34/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.5261 - loss: 0.6929"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"I0000 00:00:1711032645.847800 31002 device_compiler.h:188] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 71ms/step - accuracy: 0.5337 - loss: 0.6922 - val_accuracy: 0.5514 - val_loss: 0.6814\n",
"Epoch 2/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.5740 - loss: 0.6781 - val_accuracy: 0.5563 - val_loss: 0.6636\n",
"Epoch 3/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.6603 - loss: 0.6492 - val_accuracy: 0.7781 - val_loss: 0.6244\n",
"Epoch 4/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.8210 - loss: 0.5806 - val_accuracy: 0.8328 - val_loss: 0.5476\n",
"Epoch 5/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8506 - loss: 0.4952 - val_accuracy: 0.7653 - val_loss: 0.4860\n",
"Epoch 6/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.8238 - loss: 0.4224 - val_accuracy: 0.8842 - val_loss: 0.4122\n",
"Epoch 7/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.9288 - loss: 0.3257 - val_accuracy: 0.8408 - val_loss: 0.3694\n",
"Epoch 8/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.9280 - loss: 0.2705 - val_accuracy: 0.9357 - val_loss: 0.3032\n",
"Epoch 9/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.9178 - loss: 0.2446 - val_accuracy: 0.9357 - val_loss: 0.2772\n",
"Epoch 10/10\n",
"\u001b[1m46/46\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9724 - loss: 0.1830 - val_accuracy: 0.8826 - val_loss: 0.2798\n"
]
},
{
"data": {
"text/plain": [
"<keras.src.callbacks.history.History at 0x7fa5504b6080>"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Train the model\n",
"model.fit(X_train, y_train, epochs=10, batch_size=32, validation_data=(X_test, y_test))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.8722 - loss: 0.2829\n",
"Test Accuracy: 0.8826366662979126\n"
]
}
],
"source": [
"# Evaluate the model\n",
"loss, accuracy = model.evaluate(X_test, y_test)\n",
"print(\"Test Accuracy:\", accuracy)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# save the model\n",
"try:\n",
" model.save(\"../models/muslim-sanghi-binary-classification.keras\")\n",
"except FileNotFoundError:\n",
" os.mkdir(\"../models\")\n",
" model.save(\"../models/muslim-sanghi-binary-classification.keras\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 250ms/step\n"
]
},
{
"data": {
"text/plain": [
"0.3806811"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# use model\n",
"def preprocess_text(text):\n",
" # Tokenize the text\n",
" tokenized_text = tokenizer.texts_to_sequences([text])\n",
" # Pad sequences to the same length as training data\n",
" padded_text = pad_sequences(tokenized_text, maxlen=max_length, padding='post')\n",
" return padded_text\n",
"\n",
"# load model\n",
"model = keras.models.load_model(\"../models/muslim-sanghi-binary-classification.keras\") # Replace \"your_model.h5\" with the path to your trained model\n",
"\n",
"# Preprocess the custom input text\n",
"preprocessed_text = preprocess_text(\"'Kanwariyas are slaves, they're doing slavery' A team member of Pappu shamelessly says it & Pappu happily agrees\")\n",
"\n",
"# Make predictions\n",
"predictions = model.predict(preprocessed_text)\n",
"\n",
"predictions[0][0]"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|