DataException: MissingColumnsInData, Expected column(s) 0 not found in fitted data #209
Description
I have a model (fit during an Azure automated ml run) that predicts on a dataframe just fine, but fail when the model and dataframe are passed to interpret functions such as PartialDependence, complaining of missing columns.
# link to an AutoMLRun
from azureml.train.automl.run import AutoMLRun
automl_run = AutoMLRun(experiment=experiment, run_id='AutoML_ae0c7f63-a1b7-4892-af3e-92b79cdcf282')
# grab the best run and model
best_run, best_model = automl_run.get_output()
# get the test dataframe
from azureml.core import Dataset
test_dataset = Dataset.get_by_name(workspace=ws, name='employee_turnover_test')
df_test = test_dataset.to_pandas_dataframe()
y_col = ['EmployeeLeft']
x_col = ['City', 'EmailDomain', 'HiredthroughSMTP', 'ManagerRatingOfLikelihoodToLeave',
'MarkedForPHTProgram', 'MostRecentPerformanceEvaluation', 'SocialMediaActivity',
'Survey_AttitudeTowardWorkType', 'Survey_AttitudeTowardWorkload', 'Survey_RelativePeerAverageAttitudeTowardManager']
x_test = df_test.loc[:,x_col]
y_test = df_test.loc[:,y_col]
# confirm the model predicts on test dataframe
pred = best_model.predict_proba(x_test)
pred
# try feeding the model's predict_proba method and test dataframe to PartialDependence
from interpret.blackbox import PartialDependence
pdp = PartialDependence(predict_fn=best_model.predict_proba, data=x_test)
Full error message:
---------------------------------------------------------------------------
DataException Traceback (most recent call last)
<ipython-input-14-0bf5382bcb1b> in <module>
1 from interpret.blackbox import PartialDependence
2
----> 3 pdp = PartialDependence(predict_fn=best_model.predict_proba, data=x_test)
4 pdp_global = pdp.explain_global(name='Partial Dependence')
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/interpret/blackbox/partialdependence.py in __init__(self, predict_fn, data, sampler, feature_names, feature_types, num_points, std_coef)
43 data, None, feature_names, feature_types
44 )
---> 45 self.predict_fn = unify_predict_fn(predict_fn, self.data)
46 self.num_points = num_points
47 self.std_coef = std_coef
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/interpret/utils/all.py in unify_predict_fn(predict_fn, X)
210 def unify_predict_fn(predict_fn, X):
211 predictions = predict_fn(X[:1])
--> 212 if predictions.ndim == 2:
213 new_predict_fn = lambda x: predict_fn(x)[:, 1] # noqa: E731
214 return new_predict_fn
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/sklearn/utils/metaestimators.py in <lambda>(*args, **kwargs)
114
115 # lambda, but not partial, allows help() to work with update_wrapper
--> 116 out = lambda *args, **kwargs: self.fn(obj, *args, **kwargs)
117 # update the docstring of the returned function
118 update_wrapper(out, self.fn)
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/sklearn/pipeline.py in predict_proba(self, X)
469 Xt = X
470 for _, name, transform in self._iter(with_final=False):
--> 471 Xt = transform.transform(Xt)
472 return self.steps[-1][-1].predict_proba(Xt)
473
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/azureml/automl/core/shared/logging_utilities.py in debug_log_wrapped(self, *args, **kwargs)
299 def debug_log_wrapped(self: Any, *args: Any, **kwargs: Any) -> Any:
300 self._logger_wrapper(log_level, "Starting {} operation of {}.".format(f.__name__, self.__class__.__name__))
--> 301 r = f(self, *args, **kwargs)
302 self._logger_wrapper(log_level, "{} {} operation complete.".format(self.__class__.__name__, f.__name__))
303 return r
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/azureml/automl/runtime/featurization/data_transformer.py in transform(self, df)
406 if self._columns_types_mapping is not None:
407 df = self._check_columns_names_and_convert_types(
--> 408 df, self._columns_types_mapping
409 )
410
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/azureml/automl/runtime/featurization/data_transformer.py in _check_columns_names_and_convert_types(df, columns_types_mapping)
697 columns=col,
698 data_object_name="fitted data",
--> 699 reference_code=ReferenceCodes._DATA_TRANSFORMER_TRANSFROM_COLUMN_NOT_FOUND,
700 )
701 )
DataException: DataException:
Message: Expected column(s) 0 not found in fitted data.
InnerException: None
ErrorResponse
{
"error": {
"code": "UserError",
"message": "Expected column(s) 0 not found in fitted data.",
"target": "X",
"inner_error": {
"code": "BadArgument",
"inner_error": {
"code": "MissingColumnsInData"
}
},
"reference_code": "17049f70-3bbe-4060-a63f-f06590e784e5"
}
}