X, y = make_blobs(n_samples=100, centers=3, random_state=12, cluster_std=5) # make synthetic data
X_train_toy, X_test_toy, y_train_toy, y_test_toy = train_test_split(
    X, y, random_state=5, test_size=0.4) # split it into training and test sets
# Visualize the training data
plt.scatter(X_train_toy[:, 0], X_train_toy[:, 1], label="Training set", s=60)
plt.scatter(
    X_test_toy[:, 0], X_test_toy[:, 1], color=mglearn.cm2(1), label="Test set", s=60
)
plt.legend(loc="upper right")

scaler = StandardScaler() # Creating a scalert object 
scaler.fit(X_train_toy) # Calling fit on the training data 
train_scaled = scaler.transform(
    X_train_toy
)  # Transforming the training data using the scaler fit on training data

scaler = StandardScaler()  # Creating a separate object for scaling test data
scaler.fit(X_test_toy)  # Calling fit on the test data
test_scaled = scaler.transform(
    X_test_toy
)  # Transforming the test data using the scaler fit on test data

knn = KNeighborsClassifier()
knn.fit(train_scaled, y_train_toy)
print(f"Training score: {knn.score(train_scaled, y_train_toy):.2f}")
print(f"Test score: {knn.score(test_scaled, y_test_toy):.2f}") # misleading scores

# join the train and test sets back together
XX = np.vstack((X_train_toy, X_test_toy))

scaler = StandardScaler()
scaler.fit(XX)
XX_scaled = scaler.transform(XX)

XX_train = XX_scaled[:X_train_toy.shape[0]]
XX_test = XX_scaled[X_train_toy.shape[0]:]

knn = KNeighborsClassifier()
knn.fit(XX_train, y_train_toy)
print(f"Training score: {knn.score(XX_train, y_train_toy):.2f}")  # Misleading score
print(f"Test score: {knn.score(XX_test, y_test_toy):.2f}")  # Misleading score

knn = KNeighborsClassifier()

scaler = StandardScaler()
scaler.fit(X_train_toy)
X_train_scaled = scaler.transform(X_train_toy)
X_test_scaled = scaler.transform(X_test_toy)
cross_val_score(knn, X_train_scaled, y_train_toy)

from sklearn.pipeline import make_pipeline

pipe_knn = make_pipeline(StandardScaler(), KNeighborsClassifier())

# Correct way to do cross validation without breaking the golden rule. 
cross_val_score(pipe_knn, X_train_toy, y_train_toy)