Cross-validation on Digits Dataset Exercise

A tutorial exercise using Cross-validation with an SVM on the Digits dataset.

This exercise is used in the Cross-validation generators part of the Model selection: choosing estimators and their parameters section of the A tutorial on statistical-learning for scientific data processing.

import numpy as np

from sklearn import datasets, svm
from sklearn.model_selection import cross_val_score

X, y = datasets.load_digits(return_X_y=True)

svc = svm.SVC(kernel="linear")
C_s = np.logspace(-10, 0, 10)

scores = list()
scores_std = list()
for C in C_s:
    svc.C = C
    this_scores = cross_val_score(svc, X, y, n_jobs=1)
    scores.append(np.mean(this_scores))
    scores_std.append(np.std(this_scores))

# Do the plotting
import matplotlib.pyplot as plt

plt.figure()
plt.semilogx(C_s, scores)
plt.semilogx(C_s, np.array(scores) + np.array(scores_std), "b--")
plt.semilogx(C_s, np.array(scores) - np.array(scores_std), "b--")
locs, labels = plt.yticks()
plt.yticks(locs, list(map(lambda x: "%g" % x, locs)))
plt.ylabel("CV score")
plt.xlabel("Parameter C")
plt.ylim(0, 1.1)
plt.show()