feature_scaling_example.py

from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score

import matplotlib.pyplot as plt


features, target = load_wine(return_X_y=True)

X_train, X_test, y_train, y_test = train_test_split(
    features, target, test_size=0.3, random_state=42
)

# Scale the data
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Apply dimensionality reduction
pca = PCA(n_components=2)
X_train_dim_red = pca.fit_transform(X_train_scaled)
X_test_dim_red = pca.transform(X_test_scaled)

# Visualise results
fig, ax = plt.subplots(figsize=(10, 7))
for label, color in zip(set(y_train), ('orange', 'blue', 'brown')):
    ax.scatter(
        X_train_dim_red[y_train == label, 0],
        X_train_dim_red[y_train == label, 1],
        color=color, label=f'Class {label}'
    )

ax.set_title('Dataset after Principal Component Analysis ')
ax.set_xlabel('PC1')
ax.set_ylabel('PC2')
ax.legend(loc='upper right')

# Train and evaluate a model
model = GaussianNB()
model.fit(X_train_dim_red, y_train)
predictions = model.predict(X_test_dim_red)
print(f'Model Accuracy: {accuracy_score(y_test, predictions):.2f}')


plt.show()