Learning and validation curves

Basic pipeline

import numpy as np
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split

df = pd.read_csv('https://archive.ics.uci.edu/ml/'
                 'machine-learning-databases'
                 '/breast-cancer-wisconsin/wdbc.data', header=None)

X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)

X_train, X_test, y_train, y_test = \
    train_test_split(X, y, 
                     test_size=0.20,
                     stratify=y,
                     random_state=1)

Learning curve

Vary the sample size

import matplotlib.pyplot as plt
from sklearn.model_selection import learning_curve


pipe_lr = make_pipeline(StandardScaler(),
                        LogisticRegression(penalty='l2', random_state=1,
                                           solver='lbfgs', max_iter=10000))

train_sizes, train_scores, test_scores =\
                learning_curve(estimator=pipe_lr,
                               X=X_train,
                               y=y_train,
                               train_sizes=np.linspace(0.1, 1.0, 10),
                               cv=10,
                               n_jobs=1)

train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)

plt.plot(train_sizes, train_mean,
         color='blue', marker='o',
         markersize=5, label='Training accuracy')

plt.fill_between(train_sizes,
                 train_mean + train_std,
                 train_mean - train_std,
                 alpha=0.15, color='blue')

plt.plot(train_sizes, test_mean,
         color='green', linestyle='--',
         marker='s', markersize=5,
         label='Validation accuracy')

plt.fill_between(train_sizes,
                 test_mean + test_std,
                 test_mean - test_std,
                 alpha=0.15, color='green')

plt.grid()
plt.xlabel('Number of training examples')
plt.ylabel('Accuracy')
plt.legend(loc='lower right')
plt.ylim([0.8, 1.03])
plt.tight_layout()
# plt.savefig('images/06_05.png', dpi=300)
plt.show()

png

Validation curves

Vary the parameters of the model

pipe_lr.get_params()

{'memory': None,
 'steps': [('standardscaler', StandardScaler()),
  ('logisticregression', LogisticRegression(max_iter=10000, random_state=1))],
 'verbose': False,
 'standardscaler': StandardScaler(),
 'logisticregression': LogisticRegression(max_iter=10000, random_state=1),
 'standardscaler__copy': True,
 'standardscaler__with_mean': True,
 'standardscaler__with_std': True,
 'logisticregression__C': 1.0,
 'logisticregression__class_weight': None,
 'logisticregression__dual': False,
 'logisticregression__fit_intercept': True,
 'logisticregression__intercept_scaling': 1,
 'logisticregression__l1_ratio': None,
 'logisticregression__max_iter': 10000,
 'logisticregression__multi_class': 'auto',
 'logisticregression__n_jobs': None,
 'logisticregression__penalty': 'l2',
 'logisticregression__random_state': 1,
 'logisticregression__solver': 'lbfgs',
 'logisticregression__tol': 0.0001,
 'logisticregression__verbose': 0,
 'logisticregression__warm_start': False}

param_range = [0.001, 0.01, 0.1, 1.0, 10.0, 100.0]
train_scores, test_scores = validation_curve(
                estimator=pipe_lr, 
                X=X_train, 
                y=y_train, 
                param_name='logisticregression__C',  # you get the parameter name from pipe_lr.get_params()
                param_range=param_range,
                cv=10)

train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)

plt.plot(param_range, train_mean, 
         color='blue', marker='o', 
         markersize=5, label='Training accuracy')

plt.fill_between(param_range, train_mean + train_std,
                 train_mean - train_std, alpha=0.15,
                 color='blue')

plt.plot(param_range, test_mean, 
         color='green', linestyle='--', 
         marker='s', markersize=5, 
         label='Validation accuracy')

plt.fill_between(param_range, 
                 test_mean + test_std,
                 test_mean - test_std, 
                 alpha=0.15, color='green')

plt.grid()
plt.xscale('log')
plt.legend(loc='lower right')
plt.xlabel('Parameter C')
plt.ylabel('Accuracy')
plt.ylim([0.8, 1.0])
plt.tight_layout()
# plt.savefig('images/06_06.png', dpi=300)
plt.show()

png