INNER CODE UNIT · Python
split_train_test
bansalkanav/Ultimate-Data-Science-Toolkit---From-Python-Basics-to-GenerativeAI · Module 5 - MLOPs/4. Orchestrate ML Pipeline/my_workflow_script.py:30
def split_train_test(X, y, test_size=0.25, random_state=0):
"""
Split data into train and test sets.
"""
return train_test_split(X, y, test_size=test_size, random_state=random_state)
@task
def preprocess_data(X_train, X_test, y_train, y_test):
"""
Rescale the data.
"""
scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
return X_train_scaled, X_test_scaled, y_train, y_test