Error: Found array with 0 feature(s) & tpot unsupported set of arguments

[krkaufma]

I am running the following software in a conda virtual env:
Ubuntu 18.04
Python 3.6.8
automatminer 1.0.3.20200727 (installed with pip, not from conda)

Both errors are encountered when fitting a MatPipe pipe in express or debug mode.

First, the array with 0 features issue:

ValueError: Found array with 0 feature(s) (shape=(25, 0)) while a minimum of 1 is required by RobustScaler.

The stack trace:

ValueError Traceback (most recent call last)
in
1 # Create Matpipe in ‘express’ mode for recommended settings
2 pipe = MatPipe.from_preset(preset=“express”, n_jobs=22)
----> 3 pipe.fit(df=train_df, target=target_name)

~/.local/lib/python3.6/site-packages/automatminer/utils/pkg.py in wrapper(*args, **kwargs)
102 def wrapper(*args, **kwargs):
103 args[0].is_fit = False
–> 104 result = func(*args, **kwargs)
105 args[0].is_fit = True
106 return result

~/.local/lib/python3.6/site-packages/automatminer/pipeline.py in fit(self, df, target)
182 df = self.cleaner.fit_transform(df, target)
183 df = self.reducer.fit_transform(df, target)
–> 184 self.learner.fit(df, target)
185 logger.info(“MatPipe successfully fit.”)
186 self.post_fit_df = df

~/.local/lib/python3.6/site-packages/automatminer/utils/log.py in wrapper(*args, **kwargs)
94 self = args[0]
95 logger.info("{}Starting {}.".format(self._log_prefix, operation))
—> 96 result = meth(*args, **kwargs)
97 logger.info("{}Finished {}.".format(self._log_prefix, operation))
98 return result

~/.local/lib/python3.6/site-packages/automatminer/utils/pkg.py in wrapper(*args, **kwargs)
102 def wrapper(*args, **kwargs):
103 args[0].is_fit = False
–> 104 result = func(*args, **kwargs)
105 args[0].is_fit = True
106 return result

~/.local/lib/python3.6/site-packages/automatminer/automl/adaptors.py in fit(self, df, target, **fit_kwargs)
135 self._features = df.drop(columns=target).columns.tolist()
136 self._fitted_target = target
–> 137 self._backend = self._backend.fit(X, y, **fit_kwargs)
138 return self
139

~/.local/lib/python3.6/site-packages/tpot/base.py in fit(self, features, target, sample_weight, groups)
744 # raise the exception if it’s our last attempt
745 if attempt == (attempts - 1):
–> 746 raise e
747 return self
748

~/.local/lib/python3.6/site-packages/tpot/base.py in fit(self, features, target, sample_weight, groups)
736
737 self._update_top_pipeline()
–> 738 self._summary_of_best_pipeline(features, target)
739 # Delete the temporary cache before exiting
740 self._cleanup_memory()

~/.local/lib/python3.6/site-packages/tpot/base.py in summary_of_best_pipeline(self, features, target)
860 with warnings.catch_warnings():
861 warnings.simplefilter(‘ignore’)
–> 862 self.pareto_front_fitted_pipelines[str(pipeline)].fit(features, target)
863
864 def predict(self, features):

~/.local/lib/python3.6/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
348 This estimator
349 “”"
–> 350 Xt, fit_params = self._fit(X, y, **fit_params)
351 with _print_elapsed_time(‘Pipeline’,
352 self._log_message(len(self.steps) - 1)):

~/.local/lib/python3.6/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params)
313 message_clsname=‘Pipeline’,
314 message=self._log_message(step_idx),
–> 315 **fit_params_steps[name])
316 # Replace the transformer of the step with the fitted
317 # transformer. This is necessary when loading the transformer

~/.local/lib/python3.6/site-packages/joblib/memory.py in call(self, *args, **kwargs)
563
564 def call(self, *args, **kwargs):
–> 565 return self._cached_call(args, kwargs)[0]
566
567 def getstate(self):

~/.local/lib/python3.6/site-packages/joblib/memory.py in _cached_call(self, args, kwargs, shelving)
529
530 if must_call:
–> 531 out, metadata = self.call(*args, **kwargs)
532 if self.mmap_mode is not None:
533 # Memmap the output at the first call to be consistent with

~/.local/lib/python3.6/site-packages/joblib/memory.py in call(self, *args, **kwargs)
725 if self._verbose > 0:
726 print(format_call(self.func, args, kwargs))
–> 727 output = self.func(*args, **kwargs)
728 self.store_backend.dump_item(
729 [func_id, args_id], output, verbose=self._verbose)

~/.local/lib/python3.6/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
726 with _print_elapsed_time(message_clsname, message):
727 if hasattr(transformer, ‘fit_transform’):
–> 728 res = transformer.fit_transform(X, y, **fit_params)
729 else:
730 res = transformer.fit(X, y, **fit_params).transform(X)

~/.local/lib/python3.6/site-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
572 else:
573 # fit method of arity 2 (supervised transformation)
–> 574 return self.fit(X, y, **fit_params).transform(X)
575
576

~/.local/lib/python3.6/site-packages/sklearn/preprocessing/_data.py in fit(self, X, y)
1198 # the quantiles
1199 X = check_array(X, accept_sparse=‘csc’, estimator=self,
-> 1200 dtype=FLOAT_DTYPES, force_all_finite=‘allow-nan’)
1201
1202 q_min, q_max = self.quantile_range

~/.local/lib/python3.6/site-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
592 " a minimum of %d is required%s."
593 % (n_features, array.shape, ensure_min_features,
–> 594 context))
595
596 if warn_on_dtype and dtype_orig is not None and array.dtype != dtype_orig:

ValueError: Found array with 0 feature(s) (shape=(25, 0)) while a minimum of 1 is required by RobustScaler.

Second, the tpot unsupported set of arguments:
It appears to me that the genetic algorithm is attempting to pass invalid combinations of arguments to sklearn models. This occurs in ‘debug’ and ‘express’ presets.

ValueError: Unsupported set of arguments: The combination of penalty=‘l2’ and loss=‘epsilon_insensitive’ are not supported when dual=False, Parameters: penalty=‘l2’, loss=‘epsilon_insensitive’, dual=False

The stack trace:

_pre_test decorator: _random_mutation_operator: num_test=0 Found array with 0 feature(s) (shape=(22, 0)) while a minimum of 1 is required by MaxAbsScaler…
_pre_test decorator: _random_mutation_operator: num_test=1 Found array with 0 feature(s) (shape=(22, 0)) while a minimum of 1 is required by MaxAbsScaler…
_pre_test decorator: _random_mutation_operator: num_test=0 Found array with 0 feature(s) (shape=(22, 0)) while a minimum of 1 is required by MaxAbsScaler…
_pre_test decorator: _random_mutation_operator: num_test=0 Found array with 0 feature(s) (shape=(22, 0)) while a minimum of 1 is required by MaxAbsScaler…
_pre_test decorator: _random_mutation_operator: num_test=0 Found array with 0 feature(s) (shape=(22, 0)) while a minimum of 1 is required by MaxAbsScaler…
Pipeline encountered that has previously been evaluated during the optimization process. Using the score from the previous evaluation.

ValueError Traceback (most recent call last)
in
1 # Create Matpipe in ‘debug’ mode for quick test
2 dummy_pipe = MatPipe.from_preset(preset=“debug”, n_jobs=20)
----> 3 dummy_pipe.fit(df=train_df, target=target_name)

~/.local/lib/python3.6/site-packages/automatminer/utils/pkg.py in wrapper(*args, **kwargs)
102 def wrapper(*args, **kwargs):
103 args[0].is_fit = False
–> 104 result = func(*args, **kwargs)
105 args[0].is_fit = True
106 return result

~/.local/lib/python3.6/site-packages/automatminer/pipeline.py in fit(self, df, target)
182 df = self.cleaner.fit_transform(df, target)
183 df = self.reducer.fit_transform(df, target)
–> 184 self.learner.fit(df, target)
185 logger.info(“MatPipe successfully fit.”)
186 self.post_fit_df = df

~/.local/lib/python3.6/site-packages/automatminer/utils/log.py in wrapper(*args, **kwargs)
94 self = args[0]
95 logger.info("{}Starting {}.".format(self._log_prefix, operation))
—> 96 result = meth(*args, **kwargs)
97 logger.info("{}Finished {}.".format(self._log_prefix, operation))
98 return result

~/.local/lib/python3.6/site-packages/automatminer/utils/pkg.py in wrapper(*args, **kwargs)
102 def wrapper(*args, **kwargs):
103 args[0].is_fit = False
–> 104 result = func(*args, **kwargs)
105 args[0].is_fit = True
106 return result

~/.local/lib/python3.6/site-packages/automatminer/automl/adaptors.py in fit(self, df, target, **fit_kwargs)
135 self._features = df.drop(columns=target).columns.tolist()
136 self._fitted_target = target
–> 137 self._backend = self._backend.fit(X, y, **fit_kwargs)
138 return self
139

~/.local/lib/python3.6/site-packages/tpot/base.py in fit(self, features, target, sample_weight, groups)
744 # raise the exception if it’s our last attempt
745 if attempt == (attempts - 1):
–> 746 raise e
747 return self
748

~/.local/lib/python3.6/site-packages/tpot/base.py in fit(self, features, target, sample_weight, groups)
736
737 self._update_top_pipeline()
–> 738 self._summary_of_best_pipeline(features, target)
739 # Delete the temporary cache before exiting
740 self._cleanup_memory()

~/.local/lib/python3.6/site-packages/tpot/base.py in summary_of_best_pipeline(self, features, target)
860 with warnings.catch_warnings():
861 warnings.simplefilter(‘ignore’)
–> 862 self.pareto_front_fitted_pipelines[str(pipeline)].fit(features, target)
863
864 def predict(self, features):

~/.local/lib/python3.6/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
352 self._log_message(len(self.steps) - 1)):
353 if self._final_estimator != ‘passthrough’:
–> 354 self._final_estimator.fit(Xt, y, **fit_params)
355 return self
356

~/.local/lib/python3.6/site-packages/sklearn/svm/classes.py in fit(self, X, y, sample_weight)
430 None, penalty, self.dual, self.verbose,
431 self.max_iter, self.tol, self.random_state, loss=self.loss,
–> 432 epsilon=self.epsilon, sample_weight=sample_weight)
433 self.coef = self.coef_.ravel()
434

~/.local/lib/python3.6/site-packages/sklearn/svm/_base.py in fit_liblinear(X, y, C, fit_intercept, intercept_scaling, class_weight, penalty, dual, verbose, max_iter, tol, random_state, multi_class, loss, epsilon, sample_weight)
933 dtype=np.float64)
934
–> 935 solver_type = get_liblinear_solver_type(multi_class, penalty, loss, dual)
936 raw_coef, n_iter = liblinear.train_wrap(
937 X, y_ind, sp.isspmatrix(X), solver_type, tol, bias, C,

~/.local/lib/python3.6/site-packages/sklearn/svm/_base.py in _get_liblinear_solver_type(multi_class, penalty, loss, dual)
791 raise ValueError('Unsupported set of arguments: %s, ’
792 'Parameters: penalty=%r, loss=%r, dual=
r
'
−
→
793
(error_string, penalty, loss, dual))
794
795

Original reports on matsci.org can be found here and here.

[gregheymans]

I have the same issue. Is there any solution now? :)

[jadelgadod]

@gregheymans, and @krkaufma. There is an update related to this issue, just uploaded on the automatminer forum. Not definitive but might be a partial solution to these kind of issues.

[gregheymans]

Ok perfect, thanks for your reply. Greg

…

Le 30 nov. 2020 à 08:32, Jorge A. Delgado ***@***.***> a écrit : @gregheymans <https://github.com/gregheymans>, and @krkaufma <https://github.com/krkaufma>. There is an update related to this issue, just uploaded on the automatminer forum <https://matsci.org/t/error-found-array-with-0-feature-s/4848/9>. Not definitive but might be a partial solution to these kind of issues. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#331 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AP4ZWRIH7V3TRSK3HCDFYZLSSNDABANCNFSM4QR77JWQ>.

[sgbaird]

Is this issue going to be resolved in the codebase?

[sgbaird]

@ardunn, curious if there's an update in the works.