AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'

[snthibaud]

Describe the bug

AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'
when trying to score the model with cross validator.

To Reproduce

Run the following code with some dataset in X and y:

from autosklearn.classification import AutoSklearnClassifier
from autosklearn.metrics import average_precision

if __name__ == '__main__':
    clf = AutoSklearnClassifier(metric=average_precision, memory_limit=192*1024)
    clf.fit(X, y)
    cross_validate(clf, X, y, n_jobs=-1, scoring="average_precision")["test_score"].mean()

Expected behavior

I would expect a number to result from it.

Actual behavior, stacktrace or logfile

Stacktrace:

AttributeError                            Traceback (most recent call last)
<ipython-input-29-8d5e33cc8853> in <module>
----> 1 cross_validate(clf, Xfloat, y, n_jobs=-1, scoring="average_precision")["test_score"].mean()

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     61             extra_args = len(args) - len(all_args)
     62             if extra_args <= 0:
---> 63                 return f(*args, **kwargs)
     64 
     65             # extra_args > 0

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/model_selection/_validation.py in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score, return_estimator, error_score)
    244     parallel = Parallel(n_jobs=n_jobs, verbose=verbose,
    245                         pre_dispatch=pre_dispatch)
--> 246     results = parallel(
    247         delayed(_fit_and_score)(
    248             clone(estimator), X, y, scorers, train, test, verbose, None,

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/joblib/parallel.py in __call__(self, iterable)
   1039             # remaining jobs.
   1040             self._iterating = False
-> 1041             if self.dispatch_one_batch(iterator):
   1042                 self._iterating = self._original_iterator is not None
   1043 

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
    829                 big_batch_size = batch_size * n_jobs
    830 
--> 831                 islice = list(itertools.islice(iterator, big_batch_size))
    832                 if len(islice) == 0:
    833                     return False

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/model_selection/_validation.py in <genexpr>(.0)
    246     results = parallel(
    247         delayed(_fit_and_score)(
--> 248             clone(estimator), X, y, scorers, train, test, verbose, None,
    249             fit_params, return_train_score=return_train_score,
    250             return_times=True, return_estimator=return_estimator,

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     61             extra_args = len(args) - len(all_args)
     62             if extra_args <= 0:
---> 63                 return f(*args, **kwargs)
     64 
     65             # extra_args > 0

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/base.py in clone(estimator, safe)
     72 
     73     klass = estimator.__class__
---> 74     new_object_params = estimator.get_params(deep=False)
     75     for name, param in new_object_params.items():
     76         new_object_params[name] = clone(param, safe=False)

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/base.py in get_params(self, deep)
    193         out = dict()
    194         for key in self._get_param_names():
--> 195             value = getattr(self, key)
    196             if deep and hasattr(value, 'get_params'):
    197                 deep_items = value.get_params().items()

AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'

Environment and installation:

Please give details about your installation:

• OS: AWS Linux
• Using a Conda environment
• Python: 3.8
• Auto-sklearn version: 0.12.1

[snthibaud]

This issue also occurred when using the 'refit' method on the experimental AutoSklearn2Classifier:

/home/ec2-user/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/linear_model/_stochastic_gradient.py:574: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.
  warnings.warn("Maximum number of iteration reached before "
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/IPython/core/formatters.py in __call__(self, obj, include, exclude)
    968 
    969             if method is not None:
--> 970                 return method(include=include, exclude=exclude)
    971             return None
    972         else:

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/base.py in _repr_mimebundle_(self, **kwargs)
    462     def _repr_mimebundle_(self, **kwargs):
    463         """Mime bundle used by jupyter kernels to display estimator"""
--> 464         output = {"text/plain": repr(self)}
    465         if get_config()["display"] == 'diagram':
    466             output["text/html"] = estimator_html_repr(self)

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/base.py in __repr__(self, N_CHAR_MAX)
    258             n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
    259 
--> 260         repr_ = pp.pformat(self)
    261 
    262         # Use bruteforce ellipsis when there are a lot of non-blank characters

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/pprint.py in pformat(self, object)
    151     def pformat(self, object):
    152         sio = _StringIO()
--> 153         self._format(object, sio, 0, 0, {}, 0)
    154         return sio.getvalue()
    155 

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/pprint.py in _format(self, object, stream, indent, allowance, context, level)
    168             self._readable = False
    169             return
--> 170         rep = self._repr(object, context, level)
    171         max_width = self._width - indent - allowance
    172         if len(rep) > max_width:

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/pprint.py in _repr(self, object, context, level)
    402 
    403     def _repr(self, object, context, level):
--> 404         repr, readable, recursive = self.format(object, context.copy(),
    405                                                 self._depth, level)
    406         if not readable:

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/utils/_pprint.py in format(self, object, context, maxlevels, level)
    178 
    179     def format(self, object, context, maxlevels, level):
--> 180         return _safe_repr(object, context, maxlevels, level,
    181                           changed_only=self._changed_only)
    182 

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/utils/_pprint.py in _safe_repr(object, context, maxlevels, level, changed_only)
    423         recursive = False
    424         if changed_only:
--> 425             params = _changed_params(object)
    426         else:
    427             params = object.get_params(deep=False)

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/utils/_pprint.py in _changed_params(estimator)
     89     estimator with non-default values."""
     90 
---> 91     params = estimator.get_params(deep=False)
     92     init_func = getattr(estimator.__init__, 'deprecated_original',
     93                         estimator.__init__)

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/base.py in get_params(self, deep)
    193         out = dict()
    194         for key in self._get_param_names():
--> 195             value = getattr(self, key)
    196             if deep and hasattr(value, 'get_params'):
    197                 deep_items = value.get_params().items()

AttributeError: 'AutoSklearn2Classifier' object has no attribute 'load_models'
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/IPython/core/formatters.py in __call__(self, obj)
    700                 type_pprinters=self.type_printers,
    701                 deferred_pprinters=self.deferred_printers)
--> 702             printer.pretty(obj)
    703             printer.flush()
    704             return stream.getvalue()

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/IPython/lib/pretty.py in pretty(self, obj)
    392                         if cls is not object \
    393                                 and callable(cls.__dict__.get('__repr__')):
--> 394                             return _repr_pprint(obj, self, cycle)
    395 
    396             return _default_pprint(obj, self, cycle)

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/IPython/lib/pretty.py in _repr_pprint(obj, p, cycle)
    698     """A pprint that just redirects to the normal repr function."""
    699     # Find newlines and replace them with p.break_()
--> 700     output = repr(obj)
    701     lines = output.splitlines()
    702     with p.group():

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/base.py in __repr__(self, N_CHAR_MAX)
    258             n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
    259 
--> 260         repr_ = pp.pformat(self)
    261 
    262         # Use bruteforce ellipsis when there are a lot of non-blank characters

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/pprint.py in pformat(self, object)
    151     def pformat(self, object):
    152         sio = _StringIO()
--> 153         self._format(object, sio, 0, 0, {}, 0)
    154         return sio.getvalue()
    155 

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/pprint.py in _format(self, object, stream, indent, allowance, context, level)
    168             self._readable = False
    169             return
--> 170         rep = self._repr(object, context, level)
    171         max_width = self._width - indent - allowance
    172         if len(rep) > max_width:

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/pprint.py in _repr(self, object, context, level)
    402 
    403     def _repr(self, object, context, level):
--> 404         repr, readable, recursive = self.format(object, context.copy(),
    405                                                 self._depth, level)
    406         if not readable:

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/utils/_pprint.py in format(self, object, context, maxlevels, level)
    178 
    179     def format(self, object, context, maxlevels, level):
--> 180         return _safe_repr(object, context, maxlevels, level,
    181                           changed_only=self._changed_only)
    182 

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/utils/_pprint.py in _safe_repr(object, context, maxlevels, level, changed_only)
    423         recursive = False
    424         if changed_only:
--> 425             params = _changed_params(object)
    426         else:
    427             params = object.get_params(deep=False)

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/utils/_pprint.py in _changed_params(estimator)
     89     estimator with non-default values."""
     90 
---> 91     params = estimator.get_params(deep=False)
     92     init_func = getattr(estimator.__init__, 'deprecated_original',
     93                         estimator.__init__)

~/SageMaker/custom-miniconda/miniconda/envs/python_38/lib/python3.8/site-packages/sklearn/base.py in get_params(self, deep)
    193         out = dict()
    194         for key in self._get_param_names():
--> 195             value = getattr(self, key)
    196             if deep and hasattr(value, 'get_params'):
    197                 deep_items = value.get_params().items()

AttributeError: 'AutoSklearn2Classifier' object has no attribute 'load_models'

[jiayiwus1x]

Experience the same issue with resampling strategy = 'cv' instead of default:
code:

automl = autosklearn.classification.AutoSklearnClassifier(ensemble_size=1, initial_configurations_via_metalearning=0, output_folder='results/',
                                                          resampling_strategy = 'cv', ensemble_memory_limit=4096,
                                                          resampling_strategy_arguments= {'cv': {'folds': 5}})
automl.fit(X_train, y_train)

error:

AttributeError                            Traceback (most recent call last)
~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/IPython/core/formatters.py in __call__(self, obj, include, exclude)
    968 
    969             if method is not None:
--> 970                 return method(include=include, exclude=exclude)
    971             return None
    972         else:

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/base.py in _repr_mimebundle_(self, **kwargs)
    462     def _repr_mimebundle_(self, **kwargs):
    463         """Mime bundle used by jupyter kernels to display estimator"""
--> 464         output = {"text/plain": repr(self)}
    465         if get_config()["display"] == 'diagram':
    466             output["text/html"] = estimator_html_repr(self)

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/base.py in __repr__(self, N_CHAR_MAX)
    258             n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
    259 
--> 260         repr_ = pp.pformat(self)
    261 
    262         # Use bruteforce ellipsis when there are a lot of non-blank characters

~/.conda/envs/tf2-gpu/lib/python3.7/pprint.py in pformat(self, object)
    142     def pformat(self, object):
    143         sio = _StringIO()
--> 144         self._format(object, sio, 0, 0, {}, 0)
    145         return sio.getvalue()
    146 

~/.conda/envs/tf2-gpu/lib/python3.7/pprint.py in _format(self, object, stream, indent, allowance, context, level)
    159             self._readable = False
    160             return
--> 161         rep = self._repr(object, context, level)
    162         max_width = self._width - indent - allowance
    163         if len(rep) > max_width:

~/.conda/envs/tf2-gpu/lib/python3.7/pprint.py in _repr(self, object, context, level)
    391     def _repr(self, object, context, level):
    392         repr, readable, recursive = self.format(object, context.copy(),
--> 393                                                 self._depth, level)
    394         if not readable:
    395             self._readable = False

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/utils/_pprint.py in format(self, object, context, maxlevels, level)
    179     def format(self, object, context, maxlevels, level):
    180         return _safe_repr(object, context, maxlevels, level,
--> 181                           changed_only=self._changed_only)
    182 
    183     def _pprint_estimator(self, object, stream, indent, allowance, context,

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/utils/_pprint.py in _safe_repr(object, context, maxlevels, level, changed_only)
    423         recursive = False
    424         if changed_only:
--> 425             params = _changed_params(object)
    426         else:
    427             params = object.get_params(deep=False)

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/utils/_pprint.py in _changed_params(estimator)
     89     estimator with non-default values."""
     90 
---> 91     params = estimator.get_params(deep=False)
     92     init_func = getattr(estimator.__init__, 'deprecated_original',
     93                         estimator.__init__)

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/base.py in get_params(self, deep)
    193         out = dict()
    194         for key in self._get_param_names():
--> 195             value = getattr(self, key)
    196             if deep and hasattr(value, 'get_params'):
    197                 deep_items = value.get_params().items()

AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/IPython/core/formatters.py in __call__(self, obj)
    700                 type_pprinters=self.type_printers,
    701                 deferred_pprinters=self.deferred_printers)
--> 702             printer.pretty(obj)
    703             printer.flush()
    704             return stream.getvalue()

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/IPython/lib/pretty.py in pretty(self, obj)
    392                         if cls is not object \
    393                                 and callable(cls.__dict__.get('__repr__')):
--> 394                             return _repr_pprint(obj, self, cycle)
    395 
    396             return _default_pprint(obj, self, cycle)

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/IPython/lib/pretty.py in _repr_pprint(obj, p, cycle)
    698     """A pprint that just redirects to the normal repr function."""
    699     # Find newlines and replace them with p.break_()
--> 700     output = repr(obj)
    701     lines = output.splitlines()
    702     with p.group():

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/base.py in __repr__(self, N_CHAR_MAX)
    258             n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
    259 
--> 260         repr_ = pp.pformat(self)
    261 
    262         # Use bruteforce ellipsis when there are a lot of non-blank characters

~/.conda/envs/tf2-gpu/lib/python3.7/pprint.py in pformat(self, object)
    142     def pformat(self, object):
    143         sio = _StringIO()
--> 144         self._format(object, sio, 0, 0, {}, 0)
    145         return sio.getvalue()
    146 

~/.conda/envs/tf2-gpu/lib/python3.7/pprint.py in _format(self, object, stream, indent, allowance, context, level)
    159             self._readable = False
    160             return
--> 161         rep = self._repr(object, context, level)
    162         max_width = self._width - indent - allowance
    163         if len(rep) > max_width:

~/.conda/envs/tf2-gpu/lib/python3.7/pprint.py in _repr(self, object, context, level)
    391     def _repr(self, object, context, level):
    392         repr, readable, recursive = self.format(object, context.copy(),
--> 393                                                 self._depth, level)
    394         if not readable:
    395             self._readable = False

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/utils/_pprint.py in format(self, object, context, maxlevels, level)
    179     def format(self, object, context, maxlevels, level):
    180         return _safe_repr(object, context, maxlevels, level,
--> 181                           changed_only=self._changed_only)
    182 
    183     def _pprint_estimator(self, object, stream, indent, allowance, context,

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/utils/_pprint.py in _safe_repr(object, context, maxlevels, level, changed_only)
    423         recursive = False
    424         if changed_only:
--> 425             params = _changed_params(object)
    426         else:
    427             params = object.get_params(deep=False)

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/utils/_pprint.py in _changed_params(estimator)
     89     estimator with non-default values."""
     90 
---> 91     params = estimator.get_params(deep=False)
     92     init_func = getattr(estimator.__init__, 'deprecated_original',
     93                         estimator.__init__)

~/.conda/envs/tf2-gpu/lib/python3.7/site-packages/sklearn/base.py in get_params(self, deep)
    193         out = dict()
    194         for key in self._get_param_names():
--> 195             value = getattr(self, key)
    196             if deep and hasattr(value, 'get_params'):
    197                 deep_items = value.get_params().items()

AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'

[goyetc]

Experiencing same issue.
numpy 1.16.1
numpydoc 0.9.2
auto-sklearn 0.12.1
scikit-learn 0.24.1

auto_cls = autosklearn.classification.AutoSklearnClassifier(time_left_for_this_task=60, per_run_time_limit=15)
`print('model training in progress..')
auto_cls.fit(X_train.values, y_train.values)
model training in progress..

AttributeError Traceback (most recent call last)
/opt/conda/lib/python3.6/site-packages/IPython/core/formatters.py in call(self, obj, include, exclude)
968
969 if method is not None:
--> 970 return method(include=include, exclude=exclude)
971 return None
972 else:

/opt/conda/lib/python3.6/site-packages/sklearn/base.py in repr_mimebundle(self, **kwargs)
462 def repr_mimebundle(self, **kwargs):
463 """Mime bundle used by jupyter kernels to display estimator"""
--> 464 output = {"text/plain": repr(self)}
465 if get_config()["display"] == 'diagram':
466 output["text/html"] = estimator_html_repr(self)

/opt/conda/lib/python3.6/site-packages/sklearn/base.py in repr(self, N_CHAR_MAX)
258 n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
259
--> 260 repr_ = pp.pformat(self)
261
262 # Use bruteforce ellipsis when there are a lot of non-blank characters

/opt/conda/lib/python3.6/pprint.py in pformat(self, object)
142 def pformat(self, object):
143 sio = _StringIO()
--> 144 self._format(object, sio, 0, 0, {}, 0)
145 return sio.getvalue()
146

/opt/conda/lib/python3.6/pprint.py in _format(self, object, stream, indent, allowance, context, level)
159 self._readable = False
160 return
--> 161 rep = self._repr(object, context, level)
162 max_width = self._width - indent - allowance
163 if len(rep) > max_width:

/opt/conda/lib/python3.6/pprint.py in _repr(self, object, context, level)
391 def _repr(self, object, context, level):
392 repr, readable, recursive = self.format(object, context.copy(),
--> 393 self._depth, level)
394 if not readable:
395 self._readable = False

/opt/conda/lib/python3.6/site-packages/sklearn/utils/_pprint.py in format(self, object, context, maxlevels, level)
179 def format(self, object, context, maxlevels, level):
180 return _safe_repr(object, context, maxlevels, level,
--> 181 changed_only=self._changed_only)
182
183 def _pprint_estimator(self, object, stream, indent, allowance, context,

/opt/conda/lib/python3.6/site-packages/sklearn/utils/_pprint.py in _safe_repr(object, context, maxlevels, level, changed_only)
423 recursive = False
424 if changed_only:
--> 425 params = _changed_params(object)
426 else:
427 params = object.get_params(deep=False)

/opt/conda/lib/python3.6/site-packages/sklearn/utils/_pprint.py in _changed_params(estimator)
89 estimator with non-default values."""
90
---> 91 params = estimator.get_params(deep=False)
92 init_func = getattr(estimator.init, 'deprecated_original',
93 estimator.init)

/opt/conda/lib/python3.6/site-packages/sklearn/base.py in get_params(self, deep)
193 out = dict()
194 for key in self._get_param_names():
--> 195 value = getattr(self, key)
196 if deep and hasattr(value, 'get_params'):
197 deep_items = value.get_params().items()

AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'

AttributeError Traceback (most recent call last)
/opt/conda/lib/python3.6/site-packages/IPython/core/formatters.py in call(self, obj)
700 type_pprinters=self.type_printers,
701 deferred_pprinters=self.deferred_printers)
--> 702 printer.pretty(obj)
703 printer.flush()
704 return stream.getvalue()

/opt/conda/lib/python3.6/site-packages/IPython/lib/pretty.py in pretty(self, obj)
392 if cls is not object
393 and callable(cls.dict.get('repr')):
--> 394 return _repr_pprint(obj, self, cycle)
395
396 return _default_pprint(obj, self, cycle)

/opt/conda/lib/python3.6/site-packages/IPython/lib/pretty.py in repr_pprint(obj, p, cycle)
698 """A pprint that just redirects to the normal repr function."""
699 # Find newlines and replace them with p.break()
--> 700 output = repr(obj)
701 lines = output.splitlines()
702 with p.group():

/opt/conda/lib/python3.6/site-packages/sklearn/base.py in repr(self, N_CHAR_MAX)
258 n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
259
--> 260 repr_ = pp.pformat(self)
261
262 # Use bruteforce ellipsis when there are a lot of non-blank characters

/opt/conda/lib/python3.6/pprint.py in pformat(self, object)
142 def pformat(self, object):
143 sio = _StringIO()
--> 144 self._format(object, sio, 0, 0, {}, 0)
145 return sio.getvalue()
146

/opt/conda/lib/python3.6/pprint.py in _format(self, object, stream, indent, allowance, context, level)
159 self._readable = False
160 return
--> 161 rep = self._repr(object, context, level)
162 max_width = self._width - indent - allowance
163 if len(rep) > max_width:

/opt/conda/lib/python3.6/pprint.py in _repr(self, object, context, level)
391 def _repr(self, object, context, level):
392 repr, readable, recursive = self.format(object, context.copy(),
--> 393 self._depth, level)
394 if not readable:
395 self._readable = False

/opt/conda/lib/python3.6/site-packages/sklearn/utils/_pprint.py in format(self, object, context, maxlevels, level)
179 def format(self, object, context, maxlevels, level):
180 return _safe_repr(object, context, maxlevels, level,
--> 181 changed_only=self._changed_only)
182
183 def _pprint_estimator(self, object, stream, indent, allowance, context,

/opt/conda/lib/python3.6/site-packages/sklearn/utils/_pprint.py in _safe_repr(object, context, maxlevels, level, changed_only)
423 recursive = False
424 if changed_only:
--> 425 params = _changed_params(object)
426 else:
427 params = object.get_params(deep=False)

/opt/conda/lib/python3.6/site-packages/sklearn/utils/_pprint.py in _changed_params(estimator)
89 estimator with non-default values."""
90
---> 91 params = estimator.get_params(deep=False)
92 init_func = getattr(estimator.init, 'deprecated_original',
93 estimator.init)

/opt/conda/lib/python3.6/site-packages/sklearn/base.py in get_params(self, deep)
193 out = dict()
194 for key in self._get_param_names():
--> 195 value = getattr(self, key)
196 if deep and hasattr(value, 'get_params'):
197 deep_items = value.get_params().items()

AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'`

[ybdong919]

Meet same problem:

automl = autosklearn.classification.AutoSklearnClassifier(time_left_for_this_task=120)
automl.fit(x_train,y_train, dataset_name='howells')
Traceback (most recent call last):
File "", line 1, in
File "/usr/local/lib/python3.6/dist-packages/sklearn/base.py", line 260, in repr
repr_ = pp.pformat(self)
File "/usr/lib/python3.6/pprint.py", line 144, in pformat
self._format(object, sio, 0, 0, {}, 0)
File "/usr/lib/python3.6/pprint.py", line 161, in _format
rep = self._repr(object, context, level)
File "/usr/lib/python3.6/pprint.py", line 393, in _repr
self._depth, level)
File "/usr/local/lib/python3.6/dist-packages/sklearn/utils/_pprint.py", line 181, in format
changed_only=self._changed_only)
File "/usr/local/lib/python3.6/dist-packages/sklearn/utils/_pprint.py", line 425, in _safe_repr
params = _changed_params(object)
File "/usr/local/lib/python3.6/dist-packages/sklearn/utils/_pprint.py", line 91, in _changed_params
params = estimator.get_params(deep=False)
File "/usr/local/lib/python3.6/dist-packages/sklearn/base.py", line 195, in get_params
value = getattr(self, key)
AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'

[juliuskittler]

I am also getting this AttributeError but with the AutoSklearnRegressor: AttributeError: 'AutoSklearnRegressor' object has no attribute 'load_models'.

Code

automl = autosklearn.regression.AutoSklearnRegressor(
    time_left_for_this_task=180,
    per_run_time_limit=30,
    tmp_folder='/tmp/autosklearn_regression_example_tmp',
    output_folder='/tmp/autosklearn_regression_example_out',
    delete_output_folder_after_terminate=False,
    delete_tmp_folder_after_terminate=False
)
automl.fit(X_tr, y_tr, dataset_name=DATA_INPUT_PATH_TR.split("/")[-1].split(".")[0])

Error

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/IPython/core/formatters.py in __call__(self, obj, include, exclude)
    968 
    969             if method is not None:
--> 970                 return method(include=include, exclude=exclude)
    971             return None
    972         else:

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/base.py in _repr_mimebundle_(self, **kwargs)
    462     def _repr_mimebundle_(self, **kwargs):
    463         """Mime bundle used by jupyter kernels to display estimator"""
--> 464         output = {"text/plain": repr(self)}
    465         if get_config()["display"] == 'diagram':
    466             output["text/html"] = estimator_html_repr(self)

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/base.py in __repr__(self, N_CHAR_MAX)
    258             n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
    259 
--> 260         repr_ = pp.pformat(self)
    261 
    262         # Use bruteforce ellipsis when there are a lot of non-blank characters

~/anaconda3/envs/auto-ml/lib/python3.8/pprint.py in pformat(self, object)
    151     def pformat(self, object):
    152         sio = _StringIO()
--> 153         self._format(object, sio, 0, 0, {}, 0)
    154         return sio.getvalue()
    155 

~/anaconda3/envs/auto-ml/lib/python3.8/pprint.py in _format(self, object, stream, indent, allowance, context, level)
    168             self._readable = False
    169             return
--> 170         rep = self._repr(object, context, level)
    171         max_width = self._width - indent - allowance
    172         if len(rep) > max_width:

~/anaconda3/envs/auto-ml/lib/python3.8/pprint.py in _repr(self, object, context, level)
    402 
    403     def _repr(self, object, context, level):
--> 404         repr, readable, recursive = self.format(object, context.copy(),
    405                                                 self._depth, level)
    406         if not readable:

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/utils/_pprint.py in format(self, object, context, maxlevels, level)
    178 
    179     def format(self, object, context, maxlevels, level):
--> 180         return _safe_repr(object, context, maxlevels, level,
    181                           changed_only=self._changed_only)
    182 

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/utils/_pprint.py in _safe_repr(object, context, maxlevels, level, changed_only)
    423         recursive = False
    424         if changed_only:
--> 425             params = _changed_params(object)
    426         else:
    427             params = object.get_params(deep=False)

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/utils/_pprint.py in _changed_params(estimator)
     89     estimator with non-default values."""
     90 
---> 91     params = estimator.get_params(deep=False)
     92     init_func = getattr(estimator.__init__, 'deprecated_original',
     93                         estimator.__init__)

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/base.py in get_params(self, deep)
    193         out = dict()
    194         for key in self._get_param_names():
--> 195             value = getattr(self, key)
    196             if deep and hasattr(value, 'get_params'):
    197                 deep_items = value.get_params().items()

AttributeError: 'AutoSklearnRegressor' object has no attribute 'load_models'

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/IPython/core/formatters.py in __call__(self, obj)
    700                 type_pprinters=self.type_printers,
    701                 deferred_pprinters=self.deferred_printers)
--> 702             printer.pretty(obj)
    703             printer.flush()
    704             return stream.getvalue()

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/IPython/lib/pretty.py in pretty(self, obj)
    392                         if cls is not object \
    393                                 and callable(cls.__dict__.get('__repr__')):
--> 394                             return _repr_pprint(obj, self, cycle)
    395 
    396             return _default_pprint(obj, self, cycle)

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/IPython/lib/pretty.py in _repr_pprint(obj, p, cycle)
    698     """A pprint that just redirects to the normal repr function."""
    699     # Find newlines and replace them with p.break_()
--> 700     output = repr(obj)
    701     lines = output.splitlines()
    702     with p.group():

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/base.py in __repr__(self, N_CHAR_MAX)
    258             n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
    259 
--> 260         repr_ = pp.pformat(self)
    261 
    262         # Use bruteforce ellipsis when there are a lot of non-blank characters

~/anaconda3/envs/auto-ml/lib/python3.8/pprint.py in pformat(self, object)
    151     def pformat(self, object):
    152         sio = _StringIO()
--> 153         self._format(object, sio, 0, 0, {}, 0)
    154         return sio.getvalue()
    155 

~/anaconda3/envs/auto-ml/lib/python3.8/pprint.py in _format(self, object, stream, indent, allowance, context, level)
    168             self._readable = False
    169             return
--> 170         rep = self._repr(object, context, level)
    171         max_width = self._width - indent - allowance
    172         if len(rep) > max_width:

~/anaconda3/envs/auto-ml/lib/python3.8/pprint.py in _repr(self, object, context, level)
    402 
    403     def _repr(self, object, context, level):
--> 404         repr, readable, recursive = self.format(object, context.copy(),
    405                                                 self._depth, level)
    406         if not readable:

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/utils/_pprint.py in format(self, object, context, maxlevels, level)
    178 
    179     def format(self, object, context, maxlevels, level):
--> 180         return _safe_repr(object, context, maxlevels, level,
    181                           changed_only=self._changed_only)
    182 

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/utils/_pprint.py in _safe_repr(object, context, maxlevels, level, changed_only)
    423         recursive = False
    424         if changed_only:
--> 425             params = _changed_params(object)
    426         else:
    427             params = object.get_params(deep=False)

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/utils/_pprint.py in _changed_params(estimator)
     89     estimator with non-default values."""
     90 
---> 91     params = estimator.get_params(deep=False)
     92     init_func = getattr(estimator.__init__, 'deprecated_original',
     93                         estimator.__init__)

~/anaconda3/envs/auto-ml/lib/python3.8/site-packages/sklearn/base.py in get_params(self, deep)
    193         out = dict()
    194         for key in self._get_param_names():
--> 195             value = getattr(self, key)
    196             if deep and hasattr(value, 'get_params'):
    197                 deep_items = value.get_params().items()

AttributeError: 'AutoSklearnRegressor' object has no attribute 'load_models'

[eafpres]

I have the same error.

System:
WSL2 (ubuntu)
Code:

import autosklearn.classification
import sklearn.model_selection
import sklearn.datasets
import sklearn.metrics
X, y = sklearn.datasets.load_digits(return_X_y=True)
X_train, X_test, y_train, y_test = \
sklearn.model_selection.train_test_split(X, y, random_state=1)
automl = autosklearn.classification.AutoSklearnClassifier()
automl.fit(X_train, y_train)
y_hat = automl.predict(X_test)
print(“Accuracy score”, sklearn.metrics.accuracy_score(y_test, y_hat))

Error:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/eafpres/.local/lib/python3.6/site-packages/sklearn/base.py", line 260, in __repr__
    repr_ = pp.pformat(self)
  File "/usr/lib/python3.6/pprint.py", line 144, in pformat
    self._format(object, sio, 0, 0, {}, 0)
  File "/usr/lib/python3.6/pprint.py", line 161, in _format
    rep = self._repr(object, context, level)
  File "/usr/lib/python3.6/pprint.py", line 393, in _repr
    self._depth, level)
  File "/home/eafpres/.local/lib/python3.6/site-packages/sklearn/utils/_pprint.py", line 181, in format
    changed_only=self._changed_only)
  File "/home/eafpres/.local/lib/python3.6/site-packages/sklearn/utils/_pprint.py", line 425, in _safe_repr
    params = _changed_params(object)
  File "/home/eafpres/.local/lib/python3.6/site-packages/sklearn/utils/_pprint.py", line 91, in _changed_params
    params = estimator.get_params(deep=False)
  File "/home/eafpres/.local/lib/python3.6/site-packages/sklearn/base.py", line 195, in get_params
    value = getattr(self, key)
AttributeError: 'AutoSklearnClassifier' object has no attribute 'load_models'

I decided to look at the attributes, and I see there is a _load_models:

>>> dir(automl)
['__class__', '__delattr__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getstate__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__le__', '__lt__', '__module__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__setstate__', '__sizeof__', '__str__', '__subclasshook__', '__weakref__', '_check_n_features', '_get_automl_class', '_get_param_names', '_get_tags', '_load_models', '_metric', '_more_tags', '_n_jobs', '_repr_html_', '_repr_html_inner', '_repr_mimebundle_', '_scoring_functions', '_validate_data', 'automl_', 'build_automl', 'cv_results_', 'dask_client', 'delete_output_folder_after_terminate', 'delete_tmp_folder_after_terminate', 'disable_evaluator_output', 'ensemble_nbest', 'ensemble_size', 'exclude_estimators', 'exclude_preprocessors', 'fANOVA_input_', 'fit', 'fit_ensemble', 'get_configuration_space', 'get_models_with_weights', 'get_params', 'get_smac_object_callback', 'include_estimators', 'include_preprocessors', 'initial_configurations_via_metalearning', 'logging_config', 'max_models_on_disc', 'memory_limit', 'metadata_directory', 'n_jobs', 'output_folder', 'per_run_time_limit', 'predict', 'predict_proba', 'refit', 'resampling_strategy', 'resampling_strategy_arguments', 'score', 'seed', 'set_params', 'show_models', 'smac_scenario_args', 'sprint_statistics', 'time_left_for_this_task', 'tmp_folder', 'trajectory_']

[mfeurer]

This was fixed via #1063 and will be present in the next release we're currently preparing via #1081.