python Albon k-fold

Posted 2021-05-09

# from Chris Albon
# https://chrisalbon.com/machine-learning/cross-validaton.html

#create pipeline
# Create standardizer
standardizer = StandardScaler()

# Create logistic regression
logit = LogisticRegression()

# Create a pipeline that standardizes, then runs logistic regression
pipeline = make_pipeline(standardizer, logit)

# Create k-Fold cross-validation
kf = KFold(n_splits=10, shuffle=True, random_state=1)

# Do k-fold cross-validation
cv_results = cross_val_score(pipeline, # Pipeline
                             X, # Feature matrix
                             y, # Target vector
                             cv=kf, # Cross-validation technique
                             scoring="accuracy", # Loss function
                             n_jobs=-1) # Use all CPU scores
# Calculate mean
cv_results.mean()