predictor.py 文件源码

def _validate_input_col_descriptions(self):
        found_output_column = False
        self.cols_to_ignore = []
        expected_vals = set(['categorical', 'text', 'nlp'])

        for key, value in self.column_descriptions.items():
            value = value.lower()
            self.column_descriptions[key] = value
            if value == 'output':
                self.output_column = key
                found_output_column = True
            elif value == 'date':
                self.date_cols.append(key)
            elif value == 'ignore':
                self.cols_to_ignore.append(key)
            elif value in expected_vals:
                pass
            else:
                raise ValueError('We are not sure how to process this column of data: ' + str(value) + '. Please pass in "output", "categorical", "ignore", "nlp", or "date".')
        if found_output_column is False:
            print('Here is the column_descriptions that was passed in:')
            print(self.column_descriptions)
            raise ValueError('In your column_descriptions, please make sure exactly one column has the value "output", which is the value we will be training models to predict.')

        # We will be adding one new categorical variable for each date col
        # Be sure to add it here so the rest of the pipeline knows to handle it as a categorical column
        for date_col in self.date_cols:
            self.column_descriptions[date_col + '_day_part'] = 'categorical'

        self.cols_to_ignore = set(self.cols_to_ignore)


    # We use _construct_pipeline at both the start and end of our training.
    # At the start, it constructs the pipeline from scratch
    # At the end, it takes FeatureSelection out after we've used it to restrict DictVectorizer, and adds final_model back in if we did grid search on it