Delete DNN_IMDB.py

DNN_IMDB.py

@@ -1,68 +0,0 @@
-import pandas as pd
-import numpy as np
-from sklearn.model_selection import train_test_split
-from tensorflow.keras import Sequential
-from tensorflow.keras.layers import Dense, Embedding, Flatten
-from tensorflow.keras.optimizers import Adam
-from tensorflow.keras.preprocessing.text import Tokenizer
-from tensorflow.keras.preprocessing.sequence import pad_sequences
-import pickle
-
-
-# Load the IMDB dataset from a CSV file
-path_to_csv = 'IMDB Dataset.csv'
-df = pd.read_csv(path_to_csv)
-
-reviews = df['review'].values
-labels = df['sentiment'].values
-
-# Convert string labels to numerical values
-label_encoder = {'positive': 1, 'negative': 0}
-y = np.array([label_encoder[label.lower()] for label in labels])
-
-# Tokenize the text data
-max_words = 10000
-tokenizer = Tokenizer(num_words=max_words, oov_token='<OOV>')
-tokenizer.fit_on_texts(reviews)
-sequences = tokenizer.texts_to_sequences(reviews)
-
-# Pad sequences to a fixed length
-max_review_length = 200
-x = pad_sequences(sequences, maxlen=max_review_length)
-maxlen=200
-
-# Model building
-model = Sequential()
-model.add(Embedding(input_dim=max_words, output_dim=64, input_length=maxlen))
-model.add(Flatten())
-model.add(Dense(64, activation='relu'))
-model.add(Dense(1, activation='sigmoid'))
-
-model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
-model.summary()
-
-# Training
-print("Training started...")
-history = model.fit(x, y, epochs=3, batch_size=16, validation_split=0.2)
-loss, acc = model.evaluate(x, y)
-print("Training finished.")
-print(f'Test Accuracy: {round(acc*100)}%')
-
-
-with open('tokenizer_dnn.pkl', 'wb') as tokenizer_file:
-    pickle.dump(tokenizer, tokenizer_file)
-
-
-# Save the model
-model.save('dnn_model_imdb.h5')
-print("Model saved as 'dnn_model_imdb.h5'")
-
-
-# Example: Make a prediction on a movie review
-sample_review = "I really enjoyed the movie. The plot was engaging, and the acting was superb."
-sample_sequence = tokenizer.texts_to_sequences([sample_review])
-padded_sample = pad_sequences(sample_sequence, maxlen=max_review_length)
-prediction = model.predict(padded_sample)
-sentiment = "Positive" if prediction[0][0] > 0.3 else "Negative"
-print(f'Predicted Sentiment: {sentiment} (Probability: {prediction[0][0]:.2f})')
-