gistfile1.py

pipeline = sklearn.pipeline.Pipeline([
                        ('Replace nans',
                            preprocessing.Imputer(strategy='mean')),
                        ('Scale data',
                            preprocessing.StandardScaler()),
                        ('Feature Selection',
                            SelectPercentile(f_regression, percentile=60)),
                        ('Regression',
                            ensemble.ExtraTreesRegressor(
                                         n_estimators=550,
                                         max_features='sqrt',
                                         n_jobs=-1,
                                         random_state=RANDOM_STATE,
                                         oob_score=True,
                                         bootstrap=True,
                                         )),
                        ])