{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "c6c79f3c-ef79-4d29-bf1a-96c18d9ddf78",
"metadata": {},
"outputs": [],
"source": [
"#data set form kaggle :link: https://www.kaggle.com/competitions/fake-news/data?select=train.csv\n",
"\n",
"import pandas as pd\n",
"\n",
"# Load the dataset with the correct delimiter\n",
"df = pd.read_csv(\"train.csv\")\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "53e8a8a2-0286-4d01-b0db-cce04e9a8571",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" id | \n",
" title | \n",
" author | \n",
" text | \n",
" label | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 0 | \n",
" House Dem Aide: We Didn’t Even See Comey’s Let... | \n",
" Darrell Lucus | \n",
" House Dem Aide: We Didn’t Even See Comey’s Let... | \n",
" 1 | \n",
"
\n",
" \n",
" | 1 | \n",
" 1 | \n",
" FLYNN: Hillary Clinton, Big Woman on Campus - ... | \n",
" Daniel J. Flynn | \n",
" Ever get the feeling your life circles the rou... | \n",
" 0 | \n",
"
\n",
" \n",
" | 2 | \n",
" 2 | \n",
" Why the Truth Might Get You Fired | \n",
" Consortiumnews.com | \n",
" Why the Truth Might Get You Fired October 29, ... | \n",
" 1 | \n",
"
\n",
" \n",
" | 3 | \n",
" 3 | \n",
" 15 Civilians Killed In Single US Airstrike Hav... | \n",
" Jessica Purkiss | \n",
" Videos 15 Civilians Killed In Single US Airstr... | \n",
" 1 | \n",
"
\n",
" \n",
" | 4 | \n",
" 4 | \n",
" Iranian woman jailed for fictional unpublished... | \n",
" Howard Portnoy | \n",
" Print \\nAn Iranian woman has been sentenced to... | \n",
" 1 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" id | \n",
" title | \n",
" author | \n",
" text | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 0 | \n",
" House Dem Aide: We Didn’t Even See Comey’s Let... | \n",
" Darrell Lucus | \n",
" House Dem Aide: We Didn’t Even See Comey’s Let... | \n",
"
\n",
" \n",
" | 1 | \n",
" 1 | \n",
" FLYNN: Hillary Clinton, Big Woman on Campus - ... | \n",
" Daniel J. Flynn | \n",
" Ever get the feeling your life circles the rou... | \n",
"
\n",
" \n",
" | 2 | \n",
" 2 | \n",
" Why the Truth Might Get You Fired | \n",
" Consortiumnews.com | \n",
" Why the Truth Might Get You Fired October 29, ... | \n",
"
\n",
" \n",
" | 3 | \n",
" 3 | \n",
" 15 Civilians Killed In Single US Airstrike Hav... | \n",
" Jessica Purkiss | \n",
" Videos 15 Civilians Killed In Single US Airstr... | \n",
"
\n",
" \n",
" | 4 | \n",
" 4 | \n",
" Iranian woman jailed for fictional unpublished... | \n",
" Howard Portnoy | \n",
" Print \\nAn Iranian woman has been sentenced to... | \n",
"
\n",
" \n",
" | ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
"
\n",
" \n",
" | 20795 | \n",
" 20795 | \n",
" Rapper T.I.: Trump a ’Poster Child For White S... | \n",
" Jerome Hudson | \n",
" Rapper T. I. unloaded on black celebrities who... | \n",
"
\n",
" \n",
" | 20796 | \n",
" 20796 | \n",
" N.F.L. Playoffs: Schedule, Matchups and Odds -... | \n",
" Benjamin Hoffman | \n",
" When the Green Bay Packers lost to the Washing... | \n",
"
\n",
" \n",
" | 20797 | \n",
" 20797 | \n",
" Macy’s Is Said to Receive Takeover Approach by... | \n",
" Michael J. de la Merced and Rachel Abrams | \n",
" The Macy’s of today grew from the union of sev... | \n",
"
\n",
" \n",
" | 20798 | \n",
" 20798 | \n",
" NATO, Russia To Hold Parallel Exercises In Bal... | \n",
" Alex Ansary | \n",
" NATO, Russia To Hold Parallel Exercises In Bal... | \n",
"
\n",
" \n",
" | 20799 | \n",
" 20799 | \n",
" What Keeps the F-35 Alive | \n",
" David Swanson | \n",
" David Swanson is an author, activist, journa... | \n",
"
\n",
" \n",
"
\n",
"
20800 rows × 4 columns
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" id | \n",
" title | \n",
" author | \n",
" text | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 0 | \n",
" House Dem Aide: We Didn’t Even See Comey’s Let... | \n",
" Darrell Lucus | \n",
" House Dem Aide: We Didn’t Even See Comey’s Let... | \n",
"
\n",
" \n",
" | 1 | \n",
" 1 | \n",
" FLYNN: Hillary Clinton, Big Woman on Campus - ... | \n",
" Daniel J. Flynn | \n",
" Ever get the feeling your life circles the rou... | \n",
"
\n",
" \n",
" | 2 | \n",
" 2 | \n",
" Why the Truth Might Get You Fired | \n",
" Consortiumnews.com | \n",
" Why the Truth Might Get You Fired October 29, ... | \n",
"
\n",
" \n",
" | 3 | \n",
" 3 | \n",
" 15 Civilians Killed In Single US Airstrike Hav... | \n",
" Jessica Purkiss | \n",
" Videos 15 Civilians Killed In Single US Airstr... | \n",
"
\n",
" \n",
" | 4 | \n",
" 4 | \n",
" Iranian woman jailed for fictional unpublished... | \n",
" Howard Portnoy | \n",
" Print \\nAn Iranian woman has been sentenced to... | \n",
"
\n",
" \n",
" | ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
"
\n",
" \n",
" | 20795 | \n",
" 20795 | \n",
" Rapper T.I.: Trump a ’Poster Child For White S... | \n",
" Jerome Hudson | \n",
" Rapper T. I. unloaded on black celebrities who... | \n",
"
\n",
" \n",
" | 20796 | \n",
" 20796 | \n",
" N.F.L. Playoffs: Schedule, Matchups and Odds -... | \n",
" Benjamin Hoffman | \n",
" When the Green Bay Packers lost to the Washing... | \n",
"
\n",
" \n",
" | 20797 | \n",
" 20797 | \n",
" Macy’s Is Said to Receive Takeover Approach by... | \n",
" Michael J. de la Merced and Rachel Abrams | \n",
" The Macy’s of today grew from the union of sev... | \n",
"
\n",
" \n",
" | 20798 | \n",
" 20798 | \n",
" NATO, Russia To Hold Parallel Exercises In Bal... | \n",
" Alex Ansary | \n",
" NATO, Russia To Hold Parallel Exercises In Bal... | \n",
"
\n",
" \n",
" | 20799 | \n",
" 20799 | \n",
" What Keeps the F-35 Alive | \n",
" David Swanson | \n",
" David Swanson is an author, activist, journa... | \n",
"
\n",
" \n",
"
\n",
"
20800 rows × 4 columns
\n",
"
Model: \"sequential\"\n",
"\n"
],
"text/plain": [
"\u001b[1mModel: \"sequential\"\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ embedding (Embedding) │ ? │ 0 (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ bidirectional (Bidirectional) │ ? │ 0 (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense (Dense) │ ? │ 0 (unbuilt) │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
"\n"
],
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ embedding (\u001b[38;5;33mEmbedding\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ bidirectional (\u001b[38;5;33mBidirectional\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Total params: 0 (0.00 B)\n",
"\n"
],
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Trainable params: 0 (0.00 B)\n",
"\n"
],
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Non-trainable params: 0 (0.00 B)\n",
"\n"
],
"text/plain": [
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"None\n"
]
}
],
"source": [
"## Creating model\n",
"embedding_vector_features=40\n",
"model=Sequential()\n",
"model.add(Embedding(voc_size,embedding_vector_features,input_length=sent_length))\n",
"model.add(Bidirectional(LSTM(100)))\n",
"model.add(Dense(1,activation='sigmoid'))\n",
"model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])\n",
"print(model.summary())"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "72c2040b-10a7-4b8d-ab40-e383a294a477",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"x_final = np.array(embedded_docs)\n",
"y_final = np.array(y)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "cd01098e-825c-4849-9a39-5e90dad9413b",
"metadata": {},
"outputs": [],
"source": [
"##train test split \n",
"from sklearn.model_selection import train_test_split\n",
"x_train, x_test , y_train, y_test = train_test_split(x_final, y_final, test_size = 0.2, random_state = 23)"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "782f3429-8930-48e0-ae94-f00b01aaf916",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 9ms/step - accuracy: 0.8589 - loss: 0.3046 - val_accuracy: 0.9514 - val_loss: 0.1205\n",
"Epoch 2/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 8ms/step - accuracy: 0.9536 - loss: 0.1236 - val_accuracy: 0.9808 - val_loss: 0.0749\n",
"Epoch 3/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 9ms/step - accuracy: 0.9731 - loss: 0.0763 - val_accuracy: 0.9875 - val_loss: 0.0500\n",
"Epoch 4/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 9ms/step - accuracy: 0.9810 - loss: 0.0549 - val_accuracy: 0.9913 - val_loss: 0.0305\n",
"Epoch 5/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 9ms/step - accuracy: 0.9903 - loss: 0.0327 - val_accuracy: 0.9966 - val_loss: 0.0169\n",
"Epoch 6/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 10ms/step - accuracy: 0.9935 - loss: 0.0193 - val_accuracy: 0.9962 - val_loss: 0.0154\n",
"Epoch 7/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 9ms/step - accuracy: 0.9937 - loss: 0.0194 - val_accuracy: 0.9976 - val_loss: 0.0094\n",
"Epoch 8/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 9ms/step - accuracy: 0.9965 - loss: 0.0105 - val_accuracy: 0.9976 - val_loss: 0.0080\n",
"Epoch 9/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 10ms/step - accuracy: 0.9984 - loss: 0.0062 - val_accuracy: 0.9993 - val_loss: 0.0029\n",
"Epoch 10/10\n",
"\u001b[1m650/650\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 9ms/step - accuracy: 0.9980 - loss: 0.0061 - val_accuracy: 0.9986 - val_loss: 0.0038\n"
]
},
{
"data": {
"text/plain": [
""
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#model trainig \n",
"model.fit(x_final, y_final, validation_data = (x_test, y_test), epochs = 10,batch_size = 32)"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "dfbeeb2c-4bee-4ed6-a249-45d471293a35",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m130/130\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step\n"
]
}
],
"source": [
"y_pred = model.predict(x_test)"
]
},
{
"cell_type": "code",
"execution_count": 81,
"id": "0d336e65-fe30-42e9-86e4-ee17cbea0d40",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[1 1 1 ... 1 1 1]\n",
" [0 0 0 ... 0 0 0]]\n"
]
}
],
"source": [
"import numpy as np\n",
"\n",
"# If y_pred is a tuple, convert it to a numpy array\n",
"y_pred = np.array(y_pred)\n",
"\n",
"# Now apply the threshold\n",
"y_pred = np.where(y_pred >= 0.5, 1, 0)\n",
"\n",
"print(y_pred)\n"
]
},
{
"cell_type": "code",
"execution_count": 87,
"id": "019e741c-5ed6-4d47-b5f4-1a9e24b75d89",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Shape of y_test: (4160,)\n",
"Shape of y_pred: (2, 2068)\n"
]
}
],
"source": [
"print(f\"Shape of y_test: {y_test.shape}\")\n",
"print(f\"Shape of y_pred: {y_pred.shape}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 99,
"id": "fa379df9-f68d-4832-a6fb-cf76977fc340",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m130/130\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step\n"
]
}
],
"source": [
"y_pred = model.predict(x_test) # Make predictions on the test set\n",
"y_pred = (y_pred >= 0.5).astype(int) # For binary classification, threshold predictions\n"
]
},
{
"cell_type": "code",
"execution_count": 103,
"id": "d57a9b8a-a550-4beb-8478-2345c2e9f7ec",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m130/130\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step\n"
]
}
],
"source": [
"y_pred = np.argmax(model.predict(x_test), axis=1) # For multi-class classification\n"
]
},
{
"cell_type": "code",
"execution_count": 105,
"id": "dfe9a33c-c0e4-4507-9c2d-12be6b73f29d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Length of y_test: 4160\n",
"Length of y_pred: 4160\n"
]
}
],
"source": [
"print(f\"Length of y_test: {len(y_test)}\")\n",
"print(f\"Length of y_pred: {len(y_pred)}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 111,
"id": "e63b6bc0-6f3a-41d7-8922-855d38771dde",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[2098 0]\n",
" [2062 0]]\n"
]
}
],
"source": [
"from sklearn.metrics import confusion_matrix, accuracy_score\n",
"conf_matrix = confusion_matrix(y_test, y_pred)\n",
"print(conf_matrix)\n"
]
},
{
"cell_type": "code",
"execution_count": 117,
"id": "87e7c024-61ef-41aa-be1b-6a0b9d6ee628",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.5043269230769231"
]
},
"execution_count": 117,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"accuracy_score(y_test, y_pred)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "69cfd8a1-8f99-4a9a-85c6-7ce0a9279d3e",
"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": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}