50 lines
1.9 KiB
Python
50 lines
1.9 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
from sklearn.metrics import accuracy_score
|
|
from tensorflow.keras.models import Sequential
|
|
from tensorflow.keras.layers import Dense, Embedding, LSTM
|
|
from tensorflow.keras.preprocessing.sequence import pad_sequences
|
|
from tensorflow.keras.utils import to_categorical
|
|
|
|
# Step 1: Data Preprocessing
|
|
df = pd.read_csv('25k_movies.csv.shuf') # Replace with the actual file name or path
|
|
text_data = df['review']
|
|
labels = df['sentiment']
|
|
|
|
# Step 2: Data Split
|
|
X_train, X_test, y_train, y_test = train_test_split(text_data, labels, test_size=0.2, random_state=42)
|
|
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
|
|
|
|
# Step 3: Vectorization
|
|
vectorizer = TfidfVectorizer()
|
|
X_train_vec = vectorizer.fit_transform(X_train)
|
|
X_val_vec = vectorizer.transform(X_val)
|
|
X_test_vec = vectorizer.transform(X_test)
|
|
|
|
# Step 4: Model Architecture
|
|
model = Sequential()
|
|
model.add(Dense(128, activation='relu', input_shape=(X_train_vec.shape[1],)))
|
|
model.add(Dense(64, activation='relu'))
|
|
model.add(Dense(1, activation='sigmoid'))
|
|
|
|
# Step 5: Training
|
|
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
|
|
model.fit(X_train_vec, y_train, batch_size=32, epochs=10, validation_data=(X_val_vec, y_val))
|
|
|
|
# Step 6: Evaluation
|
|
y_pred = model.predict_classes(X_test_vec)
|
|
accuracy = accuracy_score(y_test, y_pred)
|
|
print("Test Accuracy:", accuracy)
|
|
|
|
# Step 7: Fine-tuning and Optimization
|
|
# Adjust hyperparameters, architecture, and retrain the model as needed
|
|
|
|
# Step 8: Inference
|
|
new_reviews = ['Great movie!', 'Terrible acting.']
|
|
new_reviews_vec = vectorizer.transform(new_reviews)
|
|
predictions = model.predict_classes(new_reviews_vec)
|
|
sentiments = ['Positive' if p == 1 else 'Negative' for p in predictions]
|
|
print("Predictions:", sentiments)
|