scikit-learn/examples/feature_selection/plot_feature_selection_pipeline.py

"""
==================
Pipeline Anova SVM
==================

Simple usage of Pipeline that runs successively a univariate
feature selection with anova and then a SVM of the selected features.

Using a sub-pipeline, the fitted coefficients can be mapped back into
the original feature space.
"""
from sklearn import svm
from sklearn.datasets import make_classification
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

print(__doc__)

# import some data to play with
X, y = make_classification(
    n_features=20, n_informative=3, n_redundant=0, n_classes=4,
    n_clusters_per_class=2)

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

# ANOVA SVM-C
# 1) anova filter, take 3 best ranked features
anova_filter = SelectKBest(f_classif, k=3)
# 2) svm
clf = svm.LinearSVC()

anova_svm = make_pipeline(anova_filter, clf)
anova_svm.fit(X_train, y_train)
y_pred = anova_svm.predict(X_test)
print(classification_report(y_test, y_pred))

coef = anova_svm[:-1].inverse_transform(anova_svm['linearsvc'].coef_)
print(coef)