Script to study learning curve, model scalability, model performance

plot_learning_curve.py

from sklearn.model_selection import learning_curve

# sklearn's learning_curve function can be used for following purposes
# 1. Learning curve: To study how training and validation error varies with more training examples
#      train_scores, valid_scores vs train_sizes
# 2. Model scalability: To study the time required to fit model as training data size increases
#      fit_times vs train_sizes
# 3. Model performance: To study how training error changes with time required to fit
#      train_scores vs fit_times

train_sizes, train_scores, valid_scores, fit_times, score_times = learning_curve(model, df_features, df_labels,
                                                                                 train_sizes=[0.25, 0.5, 0.75, 1], cv=10,
                                                                                 scoring="neg_mean_squared_error", 
                                                                                 return_times=True)