GS_simple_pmml.py

pl = Pipeline([
    ('impute', Imputer(strategy='median'))
    , ('standardize', StandardScaler())
#     , ('interactions', PolynomialFeatures(include_bias=False))
    , ('clf', SGDClassifier())
])


alpha = [0.0001, 0.001, 0.1]

l1_ratio = [0.1, 0.2, 0.4]

C_options = [0.2, 0.4, 0.6, 0.8]

param_grid =  [
    {
    'clf': [SGDClassifier(penalty='elasticnet', max_iter=500, loss='log')]
    , 'clf__l1_ratio': l1_ratio
    , 'clf__alpha': alpha
    }, 
    {'clf': [LogisticRegression(penalty='l2', max_iter=500)]
    , 'clf__C': C_options
    }
]


grid = GridSearchCV(pl, param_grid=param_grid, scoring={'auc': auc_scorer, 'log': log_scorer}
                    , refit='log', cv=6, verbose=5, return_train_score=True, n_jobs=2)


pmml_pipe = make_pmml_pipeline(grid, X.columns.values, y.name)

sklearn2pmml(pmml_pipe, 'pmml_model.pmml', with_repr=True)