Created
November 30, 2015 21:30
-
-
Save nmayorov/8e83bae09e9fbc9ade2f to your computer and use it in GitHub Desktop.
Feature selection for RF
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
import numpy as np | |
import matplotlib.pyplot as plt | |
from sklearn.datasets import load_diabetes, load_boston | |
from sklearn.ensemble import RandomForestRegressor | |
from sklearn.model_selection import cross_val_score | |
from sklearn.feature_selection import (SelectKBest, MutualInfoSelector, | |
f_classif, f_regression) | |
from sklearn.pipeline import make_pipeline | |
def compare_methods(clf, X, y, discrete_features, discrete_target, | |
k_all=None, cv=5): | |
if k_all is None: | |
k_all = np.arange(1, X.shape[1] + 1) | |
if discrete_target: | |
f_test = SelectKBest(score_func=f_classif) | |
else: | |
f_test = SelectKBest(score_func=f_regression) | |
max_rel = MutualInfoSelector(use_redundancy=False, | |
n_features_to_select=np.max(k_all), | |
discrete_features=discrete_features, | |
discrete_target=discrete_target, | |
random_state=0) | |
mrmr = MutualInfoSelector(n_features_to_select=np.max(k_all), | |
discrete_features=discrete_features, | |
discrete_target=discrete_target, | |
random_state=0) | |
f_test_pipeline = make_pipeline(f_test, clf) | |
max_rel_pipeline = make_pipeline(max_rel, clf) | |
mrmr_pipeline = make_pipeline(mrmr, clf) | |
f_test_scores = [] | |
max_rel_scores = [] | |
mrmr_scores = [] | |
for k in k_all: | |
f_test_pipeline.set_params(selectkbest__k=k) | |
max_rel_pipeline.set_params(mutualinfoselector__n_features_to_select=k) | |
mrmr_pipeline.set_params(mutualinfoselector__n_features_to_select=k) | |
f_test_scores.append( | |
np.mean(cross_val_score(f_test_pipeline, X, y, cv=cv))) | |
max_rel_scores.append( | |
np.mean(cross_val_score(max_rel_pipeline, X, y, cv=cv))) | |
mrmr_scores.append( | |
np.mean(cross_val_score(mrmr_pipeline, X, y, cv=cv))) | |
scores = np.vstack((f_test_scores, max_rel_scores, mrmr_scores)) | |
return k_all, scores | |
rf = RandomForestRegressor(n_estimators=30, max_depth=4, random_state=0) | |
diabetis = load_diabetes() | |
X = diabetis.data | |
y = diabetis.target | |
k_diabetis, scores_diabetis = compare_methods(rf, X, y, [1], False) | |
boston = load_boston() | |
X = boston.data | |
y = boston.target | |
k_boston, scores_boston = compare_methods(rf, X, y, [3, 8], False) | |
plt.figure(figsize=(12, 6)) | |
plt.subplot(121) | |
plt.plot(k_diabetis, scores_diabetis[0], 'x-', label='F-test') | |
plt.plot(k_diabetis, scores_diabetis[1], 'x-', label='MaxRel') | |
plt.plot(k_diabetis, scores_diabetis[2], 'x-', label='mRMR') | |
plt.title("RandomForestRegressor on diabetes dataset") | |
plt.xlabel('Number of kept features') | |
plt.ylabel('5-fold CV average score') | |
plt.legend(loc='lower right') | |
plt.subplot(122) | |
plt.plot(k_boston, scores_boston[0], 'x-', label='F-test') | |
plt.plot(k_boston, scores_boston[1], 'x-', label='MaxRel') | |
plt.plot(k_boston, scores_boston[2], 'x-', label='mRMR') | |
plt.title("RandomForestRegressor on Boston dataset") | |
plt.xlabel('Number of kept features') | |
plt.ylabel('5-fold CV average score') | |
plt.legend(loc='lower right') | |
plt.suptitle("Algorithm scores using different feature selection methods", | |
fontsize=16) | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment