machine_learning_learning_curve_breastcancer.py

from sklearn import datasets
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.ensemble import RandomForestClassifier
from sklearn.learning_curve import learning_curve
import matplotlib.pyplot as plt
import numpy as np

cancer = datasets.load_breast_cancer()
x = cancer.data
y = cancer.target

print(x.shape)
## (569, 30)

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)
print(x_train.shape)
## (455, 30)

ppln = Pipeline([
           ('scale', StandardScaler()),
           ('pca', PCA(0.80)),
           ('clf', RandomForestClassifier(max_depth=3))
       ])


train_sizes, train_scores, valid_scores = learning_curve(estimator=ppln,
                                              X=x_train, y=y_train,
                                              train_sizes=np.linspace(0.1, 1.0, 10),
                                              cv=5, n_jobs=1)

# calculate the coorinates for plots
train_mean = np.mean(train_scores, axis=1)
train_std  = np.std(train_scores, axis=1)
valid_mean = np.mean(valid_scores, axis=1)
valid_std  = np.std(valid_scores, axis=1)


plt.style.use('seaborn-whitegrid')

# draw the training scores
plt.plot(train_sizes, train_mean, color='orange', marker='o', markersize=5, label='training accuracy')
plt.fill_between(train_sizes, train_mean + train_std, train_mean - train_std, alpha=0.1, color='orange')

# draw the validation scores
plt.plot(train_sizes, valid_mean, color='darkblue', marker='o', markersize=5,label='validation accuracy')
plt.fill_between(train_sizes, valid_mean + valid_std,valid_mean - valid_std, alpha=0.1, color='darkblue') 

plt.xlabel('#training samples')
plt.ylabel('accuracy')
plt.legend(loc='lower right')
plt.ylim([0.7, 1.01])
plt.show()