0
Jump into concepts and practice - no test required
Recommended
import numpy as np import tensorflow as tf from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense, Dropout from tensorflow.keras.callbacks import EarlyStopping from sklearn.model_selection import train_test_split from sklearn.feature_extraction.text import CountVectorizer # Sample data (replace with actual dataset loading) texts = ["Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005.", "Nah I don't think he goes to usf, he lives around here though", "WINNER!! As a valued network customer you have been selected to receivea £900 prize reward!", "Had your mobile 11 months or more? You are entitled to update to the latest colour mobiles with camera for free!", "I'm gonna be home soon and i don't want to talk about this stuff anymore tonight"] labels = [1, 0, 1, 1, 0] # 1 = spam, 0 = not spam # Vectorize text data vectorizer = CountVectorizer() X = vectorizer.fit_transform(texts).toarray() y = np.array(labels) # Split data X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.4, random_state=42) # Build model with dropout and reduced neurons model = Sequential([ Dense(16, activation='relu', input_shape=(X_train.shape[1],)), Dropout(0.5), Dense(8, activation='relu'), Dropout(0.5), Dense(1, activation='sigmoid') ]) model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001), loss='binary_crossentropy', metrics=['accuracy']) # Early stopping callback early_stop = EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True) # Train model history = model.fit(X_train, y_train, epochs=50, batch_size=2, validation_data=(X_val, y_val), callbacks=[early_stop], verbose=0) # Evaluate train_loss, train_acc = model.evaluate(X_train, y_train, verbose=0) val_loss, val_acc = model.evaluate(X_val, y_val, verbose=0) print(f"Training accuracy: {train_acc*100:.2f}%, Validation accuracy: {val_acc*100:.2f}%") print(f"Training loss: {train_loss:.4f}, Validation loss: {val_loss:.4f}")
Before: Training accuracy 98%, Validation accuracy 75%, Training loss 0.05, Validation loss 0.45
After: Training accuracy 90%, Validation accuracy 87%, Training loss 0.25, Validation loss 0.30
Pipeline with a TfidfVectorizer and a LogisticRegression model?print(predictions) if the input messages are ["Win a free prize now", "Meeting at noon"] and the model predicts 1 for spam and 0 for not spam?from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
pipeline = Pipeline([
('vectorizer', TfidfVectorizer()),
('model', LogisticRegression())
])
# Assume pipeline is already trained
messages = ["Win a free prize now", "Meeting at noon"]
predictions = pipeline.predict(messages)
print(predictions)from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
pipeline = Pipeline([
('vectorizer', CountVectorizer),
('model', LogisticRegression())
])
pipeline.fit(train_messages, train_labels)CountVectorizer with stop words removal?stop_words which can be set to 'english' to remove common English stop words automatically.stop_words='english' inside CountVectorizer. Other options either use a non-existent StopWordsRemover step or set stop_words=None, which disables removal.