plot_standardizing_linear_model.py

import numpy as np
import matplotlib.pyplot as plt

from sklearn.linear_model import Ridge, Lasso
from sklearn.cross_validation import ShuffleSplit
from sklearn.grid_search import GridSearchCV
from sklearn.utils import check_random_state
from sklearn import datasets


rnd = check_random_state(1)

# set up dataset
n_samples = 200
n_features = 300

# l1 data (only 5 informative features)
X_1, y_1 = datasets.make_classification(n_samples=n_samples,
                                        n_features=n_features, n_informative=5,
                                        random_state=1)

# l2 data: non sparse, but less features
y_2 = np.sign(.5 - rnd.rand(n_samples))
X_2 = rnd.randn(n_samples, n_features / 5) + y_2[:, np.newaxis]
X_2 += 5 * rnd.randn(n_samples, n_features / 5)

clf_sets = [(Ridge(),
             np.logspace(0, 4, 20), X_1, y_1),
            (Lasso(),
             np.logspace(-2, 1, 20), X_2, y_2)]

colors = ['b', 'g', 'r', 'c']

for fignum, (clf, cs, X, y) in enumerate(clf_sets):
    # set up the plot for each regressor
    plt.figure(fignum, figsize=(9, 10))

    for k, train_size in enumerate(np.linspace(0.15, 0.7, 4)[::-1]):
        param_grid = dict(alpha=cs)
        # To get nice curve, we need a large number of iterations to
        # reduce the variance
        grid = GridSearchCV(clf, refit=False, param_grid=param_grid,
                            cv=ShuffleSplit(n=n_samples, train_size=train_size,
                                            n_iter=250, random_state=1),
                            n_jobs=-1)
        grid.fit(X, y)
        scores = [x[1] for x in grid.grid_scores_]

        scales = [(1, 'No scaling'),
                  ((n_samples * train_size), 'n_samples'),
                  ]

        for subplotnum, (scaler, name) in enumerate(scales):
            plt.subplot(2, 1, subplotnum + 1)
            plt.xlabel('alpha')
            plt.ylabel('CV Score')
            grid_cs = cs * float(scaler)  # scale the C's
            plt.semilogx(grid_cs, scores, label="fraction %.2f" %
                         train_size)
            plt.title('scaling=%s, %s' %
                      (name, clf.__class__.__name__))

    plt.legend(loc="best")
plt.show()