from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.grid_search import GridSearchCV
from sklearn.svm import SVC
from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
from sklearn.feature_selection import SelectKBest
iris = load_iris()
X, y = iris.data, iris.target
SelectKBest(score_func , k ): score_func是選擇特徵值所依據的函式,而K值則是設定要選出多少特徵。
# This dataset is way to high-dimensional. Better do PCA:
pca = PCA(n_components=2)
# Maybe some original features where good, too?
selection = SelectKBest(k=1)
# Build estimator from PCA and Univariate selection:
combined_features = FeatureUnion([("pca", pca), ("univ_select", selection)])
# Use combined features to transform dataset:
X_features = combined_features.fit(X, y).transform(X)