xiaowei1234

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


alpha = [0.0001, 0.001, 0.1]

xiaowei1234

pl = PMMLPipeline([
    ('featureUnion', featureU)
    , ('impute', Imputer(strategy='median'))
    , ('standardize', StandardScaler())
#     , ('interactions', PolynomialFeatures(include_bias=False))
#     , ('clf', SGDClassifier(alpha=0.008, l1_ratio=0.13, max_iter=450,loss='log'
#                             ,penalty='elasticnet', n_iter=None, tol=None))# alpha = 0.8
    , ('clf', LogisticRegression(penalty='l2', max_iter=500, C=0.8))
])

xiaowei1234

featureU = FeatureUnion([
    ('transformations', DataFrameMapper([
        (trend_vars, ExpressionTransformer("X[:, 0] - X[:, 1]"))
        , (to_logs, make_pipeline(Imputer(strategy='median')
           , FunctionTransformer(np.log1p)
                                 ))
        ])
    )
 , ('identity', DataFrameMapper([(non_trans_vars, ContinuousDomain())]))
])