test_dict_vectorizer.py 文件源码

def test_int_features_in_pipeline(self): 

        import numpy.random as rn
        import pandas as pd
        rn.seed(0)

        x_train_dict = [ dict( (rn.randint(100), 1) 
                          for i in range(20)) 
                            for j in range(100)]
        y_train = [0,1]*50

        from sklearn.pipeline import Pipeline
        from sklearn.feature_extraction import DictVectorizer
        from sklearn.linear_model import LogisticRegression

        pl = Pipeline([("dv", DictVectorizer()),  ("lm", LogisticRegression())])
        pl.fit(x_train_dict, y_train)

        import coremltools

        model = coremltools.converters.sklearn.convert(pl, input_features = "features", output_feature_names = "target")

        x = pd.DataFrame( {"features" : x_train_dict, 
                           "prediction" : pl.predict(x_train_dict)})

        cur_eval_metics = evaluate_classifier(model, x)
        self.assertEquals(cur_eval_metics['num_errors'], 0)