AttributeError: Woodwork has no attribute 'select'
See original GitHub issueHello,
While using evalml with time series regression problem, I get an error in AutoMLSearch.
automl = AutoMLSearch(X_train, y_train, problem_type="time series regression", max_batches=1, problem_configuration={"gap": 0, "max_delay": 7, "forecast_horizon": 7, "date_index": None}, allowed_model_families=["xgboost", "random_forest", "linear_model", "extra_trees", "decision_tree"] )
My data was splited with eval.ml.preprocessing.split_data as:
X_train, X_test, y_train, y_test = preprocessing.split_data(X, y, problem_type='time series regression',test_size=.3)
I am following exactly the documentation but with new data and I am getting this error.
_AttributeError Traceback (most recent call last)
<ipython-input-11-eb7c27d468d6> in <module>() 6 “forecast_horizon”: 7, “date_index”: None}, 7 allowed_model_families=[“xgboost”, “random_forest”, “linear_model”, “extra_trees”, ----> 8 “decision_tree”] 9 ) 10 automl.search()
2 frames
/usr/local/lib/python3.7/dist-packages/woodwork/column_accessor.py in getattr(self, attr) 224 return self._make_series_call(attr) 225 else: –> 226 raise AttributeError(f"Woodwork has no attribute ‘{attr}’") 227 228 @_check_column_schema
AttributeError: Woodwork has no attribute ‘select’_
Could you please help me???
Issue Analytics
- State:
- Created 2 years ago
- Reactions:1
- Comments:6 (2 by maintainers)
Top GitHub Comments
@ahmadalsharef994 Sorry you’re having difficulties! Thanks for filing the issue.
What versions of EvalML and Woodwork do you have? Did you install via conda or pip?
Also, is this the code you ran?
If so, where does the error come from? Is it from the definition of
automl
or when you calledautoml.search
?Closing due to inactivity.