Created
December 13, 2010 01:15
-
-
Save ogrisel/738527 to your computer and use it in GitHub Desktop.
ElasticNet and whitening
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""Evaluating the impact of PCA + whitening on low rank data""" | |
import numpy as np | |
from pprint import pprint | |
from scikits.learn.datasets.samples_generator import make_regression_dataset | |
from scikits.learn.pca import PCA | |
from scikits.learn.linear_model import ElasticNetCV | |
data_opts = { | |
'n_train_samples': 5000, | |
'n_test_samples': 1000, | |
'n_features': 300, | |
'n_informative': 100, | |
'effective_rank': 20, | |
'tail_strength': 0.01, | |
'noise': 0.01, | |
} | |
print "Generating a low rank dataset with options:" | |
pprint(data_opts) | |
X_train, y_train, X_test, y_test, coef = make_regression_dataset(**data_opts) | |
eps = 0.2 | |
print "Evaluating ElasticNetCV without preprocessing" | |
clf_raw = ElasticNetCV(eps=eps).fit(X_train, y_train) | |
print "score: %0.3f" % clf_raw.score(X_test, y_test) | |
print "best alpha: %f" % clf_raw.alpha | |
print "n predictors: %d" % np.sum(clf_raw.coef_ != 0.0) | |
print "Evaluating ElasticNetCV with PCA without whitening" | |
pca1 = PCA(whiten=False).fit(X_train) | |
X_train_pca1 = pca1.transform(X_train) | |
X_test_pca1 = pca1.transform(X_test) | |
clf_pca1 = ElasticNetCV(eps=eps).fit(X_train_pca1, y_train) | |
print "score: %0.3f" % clf_pca1.score(X_test_pca1, y_test) | |
print "best alpha: %f" % clf_pca1.alpha | |
print "n predictors: %d" % np.sum(clf_pca1.coef_ != 0.0) | |
print "Evaluating ElasticNetCV with PCA with whitening" | |
pca2 = PCA(whiten=True).fit(X_train) | |
X_train_pca2 = pca2.transform(X_train) | |
X_test_pca2 = pca2.transform(X_test) | |
clf_pca2 = ElasticNetCV(eps=eps).fit(X_train_pca2, y_train) | |
print "score: %0.3f" % clf_pca2.score(X_test_pca2, y_test) | |
print "best alpha: %f" % clf_pca2.alpha | |
print "n predictors: %d" % np.sum(clf_pca2.coef_ != 0.0) | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Generating a low rank dataset with options: | |
{'effective_rank': 20, | |
'n_features': 300, | |
'n_informative': 100, | |
'n_test_samples': 1000, | |
'n_train_samples': 5000, | |
'noise': 0.01, | |
'tail_strength': 0.01} | |
Evaluating ElasticNetCV without preprocessing | |
score: 0.056 | |
best alpha: 0.000013 | |
n predictors: 48 | |
Evaluating ElasticNetCV with PCA without whitening | |
score: 0.120 | |
best alpha: 0.000045 | |
n predictors: 14 | |
Evaluating ElasticNetCV with PCA with whitening | |
score: 0.221 | |
best alpha: 0.003274 | |
n predictors: 19 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment