Open IFV opened 5 years ago
Hello you all!
I am having the error below on version 2.9.10 when trying to train a model following this https://auto-ml.readthedocs.io/en/latest/analytics.html:
**--------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-106-c3c8faf1013e> in <module>() 1 ml_predictor = Predictor(type_of_estimator='regressor', column_descriptions=column_descriptions) 2 ----> 3 ml_predictor.train(train_subset) 4 5 # Score the model on test data ~\Anaconda3\lib\site-packages\auto_ml\predictor.py in train(***failed resolving arguments***) 650 estimator_names = self._get_estimator_names() 651 --> 652 X_df = self.fit_transformation_pipeline(X_df, y, estimator_names) 653 else: 654 X_df = self.transformation_pipeline.transform(X_df) ~\Anaconda3\lib\site-packages\auto_ml\predictor.py in fit_transformation_pipeline(self, X_df, y, model_names) 901 902 # We are intentionally overwriting X_df here to try to save some memory space --> 903 X_df = ppl.fit_transform(X_df, y) 904 905 self.transformation_pipeline = self._consolidate_pipeline(ppl) ~\Anaconda3\lib\site-packages\sklearn\pipeline.py in fit_transform(self, X, y, **fit_params) 281 Xt, fit_params = self._fit(X, y, **fit_params) 282 if hasattr(last_step, 'fit_transform'): --> 283 return last_step.fit_transform(Xt, y, **fit_params) 284 elif last_step is None: 285 return Xt ~\Anaconda3\lib\site-packages\sklearn\base.py in fit_transform(self, X, y, **fit_params) 518 else: 519 # fit method of arity 2 (supervised transformation) --> 520 return self.fit(X, y, **fit_params).transform(X) 521 522 ~\Anaconda3\lib\site-packages\auto_ml\DataFrameVectorizer.py in transform(self, X, y) 269 270 def transform(self, X, y=None): --> 271 return self._transform(X) 272 273 def get_feature_names(self): ~\Anaconda3\lib\site-packages\auto_ml\DataFrameVectorizer.py in _transform(self, X) 177 X[col] = 0 178 --> 179 X.fillna(0, inplace=True) 180 181 for idx, col in enumerate(self.numerical_columns): ~\Anaconda3\lib\site-packages\pandas\core\frame.py in fillna(self, value, method, axis, inplace, limit, downcast, **kwargs) 3788 self).fillna(value=value, method=method, axis=axis, 3789 inplace=inplace, limit=limit, -> 3790 downcast=downcast, **kwargs) 3791 3792 @Appender(_shared_docs['replace'] % _shared_doc_kwargs) ~\Anaconda3\lib\site-packages\pandas\core\generic.py in fillna(self, value, method, axis, inplace, limit, downcast) 5425 new_data = self._data.fillna(value=value, limit=limit, 5426 inplace=inplace, -> 5427 downcast=downcast) 5428 elif isinstance(value, DataFrame) and self.ndim == 2: 5429 new_data = self.where(self.notna(), value) ~\Anaconda3\lib\site-packages\pandas\core\internals.py in fillna(self, **kwargs) 3706 3707 def fillna(self, **kwargs): -> 3708 return self.apply('fillna', **kwargs) 3709 3710 def downcast(self, **kwargs): ~\Anaconda3\lib\site-packages\pandas\core\internals.py in apply(self, f, axes, filter, do_integrity_check, consolidate, **kwargs) 3579 3580 kwargs['mgr'] = self -> 3581 applied = getattr(b, f)(**kwargs) 3582 result_blocks = _extend_blocks(applied, result_blocks) 3583 ~\Anaconda3\lib\site-packages\pandas\core\internals.py in fillna(self, value, limit, inplace, downcast, mgr) 2004 mgr=None): 2005 values = self.values if inplace else self.values.copy() -> 2006 values = values.fillna(value=value, limit=limit) 2007 return [self.make_block_same_class(values=values, 2008 placement=self.mgr_locs, ~\Anaconda3\lib\site-packages\pandas\util\_decorators.py in wrapper(*args, **kwargs) 176 else: 177 kwargs[new_arg_name] = new_arg_value --> 178 return func(*args, **kwargs) 179 return wrapper 180 return _deprecate_kwarg ~\Anaconda3\lib\site-packages\pandas\core\arrays\categorical.py in fillna(self, value, method, limit) 1754 elif is_hashable(value): 1755 if not isna(value) and value not in self.categories: -> 1756 raise ValueError("fill value must be in categories") 1757 1758 mask = values == -1 ValueError: fill value must be in categories **
Am I missing any pre-processing step?
column_descriptions = { 'F11': 'output', 'F0': 'categorical', 'F2': 'categorical'}
Part of the dataset (no missing values) here:
Hello you all!
I am having the error below on version 2.9.10 when trying to train a model following this https://auto-ml.readthedocs.io/en/latest/analytics.html:
Am I missing any pre-processing step?
column_descriptions = { 'F11': 'output', 'F0': 'categorical', 'F2': 'categorical'}
Part of the dataset (no missing values) here: