45 lines
1.2 KiB
Python
45 lines
1.2 KiB
Python
"""
|
|
=============================================
|
|
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 :ref:`cv_generators_tut` part of the
|
|
:ref:`model_selection_tut` section of the :ref:`stat_learn_tut_index`.
|
|
"""
|
|
print(__doc__)
|
|
|
|
|
|
import numpy as np
|
|
from sklearn.model_selection import cross_val_score
|
|
from sklearn import datasets, svm
|
|
|
|
digits = datasets.load_digits()
|
|
X = digits.data
|
|
y = digits.target
|
|
|
|
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, cv=5, 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()
|