import numpy as np
import matplotlib.pyplot as plt
from tensorflow.keras.datasets import imdb
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, Flatten, Dense
from tensorflow.keras.preprocessing.sequence import pad_sequences
from sklearn.metrics import confusion_matrix
import seaborn as sns
# Load IMDB dataset
(X_train, y_train), (X_test, y_test) = imdb.load_data(num_words=10000)
# Limit to top 10000 words
# Pad sequences
max_length = 200
X_train = pad_sequences(X_train, maxlen=max_length)
X_test = pad_sequences(X_test, maxlen=max_length)
# Build the model
model = Sequential()
model.add(Embedding(10000, 16, input_length=max_length))
model.add(Flatten())
model.add(Dense(16, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
C:\Users\nagal\anaconda3\pranathi\Lib\site-packages\keras\src\layers\
core\embedding.py:90: UserWarning: Argument `input_length` is
deprecated. Just remove it.
warnings.warn(
# Compile the model
model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy'])
# Train the model
history = model.fit(X_train, y_train, epochs=5, batch_size=128,
validation_split=0.2, verbose=1)
Epoch 1/5
157/157 ━━━━━━━━━━━━━━━━━━━━ 5s 17ms/step - accuracy: 0.5822 - loss:
0.6559 - val_accuracy: 0.8580 - val_loss: 0.3370
Epoch 2/5
157/157 ━━━━━━━━━━━━━━━━━━━━ 2s 14ms/step - accuracy: 0.8961 - loss:
0.2596 - val_accuracy: 0.8738 - val_loss: 0.2938
Epoch 3/5
157/157 ━━━━━━━━━━━━━━━━━━━━ 2s 14ms/step - accuracy: 0.9523 - loss:
0.1519 - val_accuracy: 0.8682 - val_loss: 0.3210
Epoch 4/5
157/157 ━━━━━━━━━━━━━━━━━━━━ 2s 13ms/step - accuracy: 0.9838 - loss:
0.0751 - val_accuracy: 0.8638 - val_loss: 0.3610
Epoch 5/5
157/157 ━━━━━━━━━━━━━━━━━━━━ 2s 11ms/step - accuracy: 0.9952 - loss:
0.0331 - val_accuracy: 0.8640 - val_loss: 0.3899
# Evaluate the model
loss, accuracy = model.evaluate(X_test, y_test)
print(f"Test Accuracy: {accuracy}")
782/782 ━━━━━━━━━━━━━━━━━━━━ 3s 4ms/step - accuracy: 0.8584 - loss:
0.4000
Test Accuracy: 0.8600000143051147
# Make predictions
y_pred_probs = model.predict(X_test)
y_pred = (y_pred_probs > 0.5).astype(int).flatten()
782/782 ━━━━━━━━━━━━━━━━━━━━ 3s 4ms/step
# Confusion Matrix
cm = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(8, 6))
sns.heatmap(cm, annot=True, fmt="d", cmap="Blues")
plt.title("Confusion Matrix")
plt.xlabel("Predicted Labels")
plt.ylabel("True Labels")
plt.show()
# Plot training history
plt.figure(figsize=(12, 4))
<Figure size 1200x400 with 0 Axes>
<Figure size 1200x400 with 0 Axes>
plt.subplot(1, 2, 1)
plt.plot(history.history['accuracy'], label='Training Accuracy')
plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
plt.title('Training and Validation Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
<matplotlib.legend.Legend at 0x2b037df36b0>
plt.subplot(1, 2, 2)
plt.plot(history.history['loss'], label='Training Loss')
plt.plot(history.history['val_loss'], label='Validation Loss')
plt.title('Training and Validation Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.show()
