一体、正則化とは何ですか? – KDnuggets

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report

# Assuming heart_data is already loaded
X = heart_data.drop('target', axis=1)
y = heart_data['target']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Define regularization values to explore
regularization_values = [0.001, 0.01, 0.1]

# Placeholder for storing performance metrics
performance_metrics = []

# Iterate over regularization values for L1 and L2
for C_value in regularization_values:
    # Train and evaluate L1 model
    log_reg_l1 = LogisticRegression(penalty='l1', C=C_value, solver='liblinear')
    log_reg_l1.fit(X_train_scaled, y_train)
    y_pred_l1 = log_reg_l1.predict(X_test_scaled)
    accuracy_l1 = accuracy_score(y_test, y_pred_l1)
    report_l1 = classification_report(y_test, y_pred_l1)
    performance_metrics.append(('L1', C_value, accuracy_l1))
    
    # Train and evaluate L2 model
    log_reg_l2 = LogisticRegression(penalty='l2', C=C_value, solver='liblinear')
    log_reg_l2.fit(X_train_scaled, y_train)
    y_pred_l2 = log_reg_l2.predict(X_test_scaled)
    accuracy_l2 = accuracy_score(y_test, y_pred_l2)
    report_l2 = classification_report(y_test, y_pred_l2)
    performance_metrics.append(('L2', C_value, accuracy_l2))

# Print the performance metrics for all models
print("Model Performance Evaluation:")
print("--------------------------------")
for metric in performance_metrics:
    reg_type, C_value, accuracy = metric
    print(f"Regularization: {reg_type}, C: {C_value}, Accuracy: {accuracy:.2f}")

from tensorflow.keras.regularizers import l1_l2
import numpy as np

# Define a list/grid of L1 and L2 regularization values
l1_values = [0.001, 0.01, 0.1]
l2_values = [0.001, 0.01, 0.1]

# Placeholder for storing performance metrics
performance_metrics = []

# Iterate over all combinations of L1 and L2 values
for l1_val in l1_values:
    for l2_val in l2_values:
        # Define model with the current combination of L1 and L2
        model = Sequential([
            Dense(128, activation='relu', input_shape=(X_train_scaled.shape[1],), kernel_regularizer=l1_l2(l1=l1_val, l2=l2_val)),
            Dropout(0.5),
            Dense(64, activation='relu', kernel_regularizer=l1_l2(l1=l1_val, l2=l2_val)),
            Dropout(0.5),
            Dense(1, activation='sigmoid')
        ])
        
        model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
        
        # Train the model
        history = model.fit(X_train_scaled, y_train, validation_split=0.2, epochs=100, batch_size=10, verbose=0)
        
        # Evaluate the model
        loss, accuracy = model.evaluate(X_test_scaled, y_test, verbose=0)
        
        # Store the performance along with the regularization values
        performance_metrics.append((l1_val, l2_val, accuracy))

# Find the best performing model
best_performance = max(performance_metrics, key=lambda x: x[2])
best_l1, best_l2, best_accuracy = best_performance

# After the loop, to print all performance metrics
print("All Model Performances:")
print("L1 Value | L2 Value | Accuracy")
for metrics in performance_metrics:
    print(f"{metrics[0]:8} | {metrics[1]:8} | {metrics[2]:.3f}")

# After finding the best performance, to print the best model details
print("nBest Model Performance:")
print("----------------------------")
print(f"Best L1 value: {best_l1}")
print(f"Best L2 value: {best_l2}")
print(f"Best accuracy: {best_accuracy:.3f}")