# Import necessary libraries
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import (accuracy_score, classification_report,
confusion_matrix, ConfusionMatrixDisplay)
import matplotlib.pyplot as plt
# Load the Iris dataset
data = load_iris()
X = data.data # Features
y = data.target # Target labels
feature_names = data.feature_names
class_names = data.target_names
# Split the data into training and testing sets (80% train, 20% test)
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=42, stratify=y
)
# Standardize features by removing the mean and scaling to unit variance
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
# Initialize the MLP classifier
mlp = MLPClassifier(
hidden_layer_sizes=(100, 50), # Two hidden layers with 100 and 50 neurons
activation='relu', # Rectified Linear Unit activation
solver='adam', # Optimization algorithm
alpha=0.0001, # L2 penalty (regularization term) parameter
batch_size='auto', # Size of minibatches
learning_rate='constant', # Learning rate schedule
learning_rate_init=0.001, # Initial learning rate
max_iter=500, # Maximum number of iterations
random_state=42, # Random seed
early_stopping=True, # Use early stopping to terminate training when validation score stops improving
validation_fraction=0.1 # Fraction of training data to set aside as validation set
)
# Train the model
mlp.fit(X_train, y_train)
# Make predictions
y_pred = mlp.predict(X_test)
y_pred_prob = mlp.predict_proba(X_test)
# Evaluate the model
print(f"Training set score: {mlp.score(X_train, y_train):.3f}")
print(f"Test set score: {mlp.score(X_test, y_test):.3f}\n")
print("Classification Report:")
print(classification_report(y_test, y_pred, target_names=class_names))
# Plot confusion matrix
