_model.py 文件源码

def train(self, train_size=0.8, k_folds=5):

        # retrieve data from DB and pre-process
        self._get_data()

        # perform train/test split
        self._get_train_test_split(train_size=train_size)

        # define text pre-processing pipeline
        text_pipeline = Pipeline([
            ('extract_text', DFColumnExtractor(TEXT_FEATURES)),
            ('vect', TfidfVectorizer(tokenizer=twitter_tokenizer))
        ])

        # define pipeline for pre-processing of numeric features
        numeric_pipeline = Pipeline([
            ('extract_nums', DFColumnExtractor(NON_TEXT_FEATURES)),
            ('scaler', MinMaxScaler())
        ])

        # combine both steps into a single pipeline
        pipeline = Pipeline([
            ('features', FeatureUnion([
                ('text_processing', text_pipeline),
                ('num_processing', numeric_pipeline)
            ])),
            ('clf', self._estimator)
        ])

        self.logger.info('Fitting model hyperparameters with {0}-fold CV'.format(k_folds))
        gs = GridSearchCV(pipeline, self.params, n_jobs=-1, cv=k_folds)

        X = self.data.iloc[self.train_inds_, :]
        y = self.data[LABEL].values[self.train_inds_]

        gs.fit(X, y)

        self.logger.info('Validation set accuracy is {0}'.format(gs.best_score_))

        self.gs_ = gs
        self.model_ = gs.best_estimator_