from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
from sklearn.feature_selection import SelectKBest

if __name__ == '__main__':
    iris = load_iris()

    X, y = iris.data, iris.target

    # This dataset is way too 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)], n_jobs=1)

    # Use combined features to transform dataset:
    X_features = combined_features.fit(X, y).transform(X)

    svm = SVC(kernel="linear")

    # Do grid search over k, n_components and C:

    pipeline = Pipeline([("features", combined_features), ("svm", svm)])

    param_grid = dict(features__pca__n_components=[1, 2, 3],
                      features__univ_select__k=[1, 2],
                      svm__C=[0.1, 1, 10])

    grid_search = GridSearchCV(pipeline, param_grid=param_grid, verbose=0, n_jobs=-1)
    grid_search.fit(X, y)
    print(grid_search.best_estimator_)