Closed
Description
Hey, thanks for an awesome library!
There's a bit of an issue (seemingly the same as #6147) with GridSearchCV, which seems to be in 0.18.1 as well as having been present in previous versions. I get the issue when using GridSearchCV with the ElasticNet classifier:
vals = [10 ** i for i in range(0, -10, -1)] + list(np.arange(0.1, 0.999, 0.025))
parameters = {'l1_ratio': vals, 'alpha': vals}
elastic = ElasticNet(max_iter = 1000)
clf = GridSearchCV(elastic, param_grid = parameters, n_jobs = 8, scoring = 'accuracy', cv = 10)
clf.fit(X_train, y_train)Actual Results
multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 344, in __call__
return self.func(*args, **kwargs)
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 131, in __call__
return [func(*args, **kwargs) for func, args, kwargs in self.items]
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 131, in <listcomp>
return [func(*args, **kwargs) for func, args, kwargs in self.items]
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 260, in _fit_and_score
test_score = _score(estimator, X_test, y_test, scorer)
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 288, in _score
score = scorer(estimator, X_test, y_test)
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/scorer.py", line 98, in __call__
**self._kwargs)
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py", line 172, in accuracy_score
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py", line 82, in _check_targets
"".format(type_true, type_pred))
ValueError: Can't handle mix of binary and continuous
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/zeerak/anaconda3/lib/python3.6/multiprocessing/pool.py", line 119, in worker
result = (True, func(*args, **kwds))
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 353, in __call__
raise TransportableException(text, e_type)
sklearn.externals.joblib.my_exceptions.TransportableException: TransportableException
___________________________________________________________________________
ValueError Mon Jul 3 02:20:59 2017
PID: 22695 Python 3.6.0: /home/zeerak/anaconda3/bin/python3
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self=<sklearn.externals.joblib.parallel.BatchedCalls object>)
126 def __init__(self, iterator_slice):
127 self.items = list(iterator_slice)
128 self._size = len(self.items)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
self.items = [(<function _fit_and_score>, (ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], make_scorer(accuracy_score), array([ 530, 531, 532, ..., 5292, 5293, 5294]), array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), 0, {'alpha': 1, 'l1_ratio': 1}), {'error_score': 'raise', 'fit_params': {}, 'return_n_test_samples': True, 'return_parameters': True, 'return_times': True, 'return_train_score': True})]
132
133 def __len__(self):
134 return self._size
135
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
126 def __init__(self, iterator_slice):
127 self.items = list(iterator_slice)
128 self._size = len(self.items)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
func = <function _fit_and_score>
args = (ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], make_scorer(accuracy_score), array([ 530, 531, 532, ..., 5292, 5293, 5294]), array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), 0, {'alpha': 1, 'l1_ratio': 1})
kwargs = {'error_score': 'raise', 'fit_params': {}, 'return_n_test_samples': True, 'return_parameters': True, 'return_times': True, 'return_train_score': True}
132
133 def __len__(self):
134 return self._size
135
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X=<5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, y=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], scorer=make_scorer(accuracy_score), train=array([ 530, 531, 532, ..., 5292, 5293, 5294]), test=array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), verbose=0, parameters={'alpha': 1, 'l1_ratio': 1}, fit_params={}, return_train_score=True, return_parameters=True, return_n_test_samples=True, return_times=True, error_score='raise')
255 " numeric value. (Hint: if using 'raise', please"
256 " make sure that it has been spelled correctly.)")
257
258 else:
259 fit_time = time.time() - start_time
--> 260 test_score = _score(estimator, X_test, y_test, scorer)
test_score = undefined
estimator = ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False)
X_test = <530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>
y_test = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
scorer = make_scorer(accuracy_score)
261 score_time = time.time() - start_time - fit_time
262 if return_train_score:
263 train_score = _score(estimator, X_train, y_train, scorer)
264
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _score(estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X_test=<530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>, y_test=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], scorer=make_scorer(accuracy_score))
283 def _score(estimator, X_test, y_test, scorer):
284 """Compute the score of an estimator on a given test set."""
285 if y_test is None:
286 score = scorer(estimator, X_test)
287 else:
--> 288 score = scorer(estimator, X_test, y_test)
score = undefined
scorer = make_scorer(accuracy_score)
estimator = ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False)
X_test = <530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>
y_test = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
289 if hasattr(score, 'item'):
290 try:
291 # e.g. unwrap memmapped scalars
292 score = score.item()
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/scorer.py in __call__(self=make_scorer(accuracy_score), estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X=<530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>, y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], sample_weight=None)
93 return self._sign * self._score_func(y_true, y_pred,
94 sample_weight=sample_weight,
95 **self._kwargs)
96 else:
97 return self._sign * self._score_func(y_true, y_pred,
---> 98 **self._kwargs)
self._kwargs = {}
99
100
101 class _ProbaScorer(_BaseScorer):
102 def __call__(self, clf, X, y, sample_weight=None):
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py in accuracy_score(y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], y_pred=array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042]), normalize=True, sample_weight=None)
167 >>> accuracy_score(np.array([[0, 1], [1, 1]]), np.ones((2, 2)))
168 0.5
169 """
170
171 # Compute accuracy for each possible representation
--> 172 y_type, y_true, y_pred = _check_targets(y_true, y_pred)
y_type = undefined
y_true = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
y_pred = array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042])
173 if y_type.startswith('multilabel'):
174 differing_labels = count_nonzero(y_true - y_pred, axis=1)
175 score = differing_labels == 0
176 else:
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py in _check_targets(y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], y_pred=array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042]))
77 if y_type == set(["binary", "multiclass"]):
78 y_type = set(["multiclass"])
79
80 if len(y_type) > 1:
81 raise ValueError("Can't handle mix of {0} and {1}"
---> 82 "".format(type_true, type_pred))
type_true = 'binary'
type_pred = 'continuous'
83
84 # We can't have more than one value on y_type => The set is no more needed
85 y_type = y_type.pop()
86
ValueError: Can't handle mix of binary and continuous
___________________________________________________________________________
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 682, in retrieve
self._output.extend(job.get(timeout=self.timeout))
File "/home/zeerak/anaconda3/lib/python3.6/multiprocessing/pool.py", line 608, in get
raise self._value
sklearn.externals.joblib.my_exceptions.TransportableException: TransportableException
___________________________________________________________________________
ValueError Mon Jul 3 02:20:59 2017
PID: 22695 Python 3.6.0: /home/zeerak/anaconda3/bin/python3
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self=<sklearn.externals.joblib.parallel.BatchedCalls object>)
126 def __init__(self, iterator_slice):
127 self.items = list(iterator_slice)
128 self._size = len(self.items)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
self.items = [(<function _fit_and_score>, (ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], make_scorer(accuracy_score), array([ 530, 531, 532, ..., 5292, 5293, 5294]), array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), 0, {'alpha': 1, 'l1_ratio': 1}), {'error_score': 'raise', 'fit_params': {}, 'return_n_test_samples': True, 'return_parameters': True, 'return_times': True, 'return_train_score': True})]
132
133 def __len__(self):
134 return self._size
135
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
126 def __init__(self, iterator_slice):
127 self.items = list(iterator_slice)
128 self._size = len(self.items)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
func = <function _fit_and_score>
args = (ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], make_scorer(accuracy_score), array([ 530, 531, 532, ..., 5292, 5293, 5294]), array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), 0, {'alpha': 1, 'l1_ratio': 1})
kwargs = {'error_score': 'raise', 'fit_params': {}, 'return_n_test_samples': True, 'return_parameters': True, 'return_times': True, 'return_train_score': True}
132
133 def __len__(self):
134 return self._size
135
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X=<5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, y=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], scorer=make_scorer(accuracy_score), train=array([ 530, 531, 532, ..., 5292, 5293, 5294]), test=array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), verbose=0, parameters={'alpha': 1, 'l1_ratio': 1}, fit_params={}, return_train_score=True, return_parameters=True, return_n_test_samples=True, return_times=True, error_score='raise')
255 " numeric value. (Hint: if using 'raise', please"
256 " make sure that it has been spelled correctly.)")
257
258 else:
259 fit_time = time.time() - start_time
--> 260 test_score = _score(estimator, X_test, y_test, scorer)
test_score = undefined
estimator = ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False)
X_test = <530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>
y_test = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
scorer = make_scorer(accuracy_score)
261 score_time = time.time() - start_time - fit_time
262 if return_train_score:
263 train_score = _score(estimator, X_train, y_train, scorer)
264
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _score(estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X_test=<530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>, y_test=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], scorer=make_scorer(accuracy_score))
283 def _score(estimator, X_test, y_test, scorer):
284 """Compute the score of an estimator on a given test set."""
285 if y_test is None:
286 score = scorer(estimator, X_test)
287 else:
--> 288 score = scorer(estimator, X_test, y_test)
score = undefined
scorer = make_scorer(accuracy_score)
estimator = ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False)
X_test = <530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>
y_test = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
289 if hasattr(score, 'item'):
290 try:
291 # e.g. unwrap memmapped scalars
292 score = score.item()
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/scorer.py in __call__(self=make_scorer(accuracy_score), estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X=<530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>, y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], sample_weight=None)
93 return self._sign * self._score_func(y_true, y_pred,
94 sample_weight=sample_weight,
95 **self._kwargs)
96 else:
97 return self._sign * self._score_func(y_true, y_pred,
---> 98 **self._kwargs)
self._kwargs = {}
99
100
101 class _ProbaScorer(_BaseScorer):
102 def __call__(self, clf, X, y, sample_weight=None):
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py in accuracy_score(y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], y_pred=array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042]), normalize=True, sample_weight=None)
167 >>> accuracy_score(np.array([[0, 1], [1, 1]]), np.ones((2, 2)))
168 0.5
169 """
170
171 # Compute accuracy for each possible representation
--> 172 y_type, y_true, y_pred = _check_targets(y_true, y_pred)
y_type = undefined
y_true = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
y_pred = array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042])
173 if y_type.startswith('multilabel'):
174 differing_labels = count_nonzero(y_true - y_pred, axis=1)
175 score = differing_labels == 0
176 else:
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py in _check_targets(y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], y_pred=array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042]))
77 if y_type == set(["binary", "multiclass"]):
78 y_type = set(["multiclass"])
79
80 if len(y_type) > 1:
81 raise ValueError("Can't handle mix of {0} and {1}"
---> 82 "".format(type_true, type_pred))
type_true = 'binary'
type_pred = 'continuous'
83
84 # We can't have more than one value on y_type => The set is no more needed
85 y_type = y_type.pop()
86
ValueError: Can't handle mix of binary and continuous
___________________________________________________________________________
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "run.py", line 333, in <module>
runner(args)
File "run.py", line 283, in runner
feats.run_gridsearch_elastic(X_train, X_test, Y_train, Y_test)
File "/home/zeerak/Projects/repos/gender_spectrum/features.py", line 216, in run_gridsearch_elastic
clf.fit(X_train, y_train)
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 945, in fit
return self._fit(X, y, groups, ParameterGrid(self.param_grid))
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 564, in _fit
for parameters in parameter_iterable
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 768, in __call__
self.retrieve()
File "/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 719, in retrieve
raise exception
sklearn.externals.joblib.my_exceptions.JoblibValueError: JoblibValueError
___________________________________________________________________________
Multiprocessing exception:
...........................................................................
/home/zeerak/Projects/repos/gender_spectrum/run.py in <module>()
328 parser.add_argument('--probs' , action = 'store_true', help = argparse.SUPPRESS)
329 parser.add_argument('--sgdparams' , nargs = 2 , help = argparse.SUPPRESS)
330
331 args = parser.parse_args()
332
--> 333 runner(args)
334
335
336
337
...........................................................................
/home/zeerak/Projects/repos/gender_spectrum/run.py in runner(args=Namespace(data=None, feats=['unigram-counts'], h...dparams=None, test=None, user=True, workers=None))
278 feats.run_gridsearch_sgd(X_train, X_test, Y_train, Y_test)
279 # preds, weights, intercept = feats.run_sgd(X_train, X_test, Y_train, Y_test)
280
281 elif args.method == 'Elastic':
282 print('Run Elastic Net...', file=sys.stdout)
--> 283 feats.run_gridsearch_elastic(X_train, X_test, Y_train, Y_test)
X_train = <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>
X_test = <1324x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>
Y_train = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
Y_test = ['1', '0', '1', '1', '1', '1', '0', '1', '0', '0', '0', '1', '1', '0', '1', '1', '0', '0', '0', '0', ...]
284 # preds, weights, intercept = feats.run_sgd(X_train, X_test, Y_train, Y_test)
285
286
287 if __name__ == "__main__":
...........................................................................
/home/zeerak/Projects/repos/gender_spectrum/features.py in run_gridsearch_elastic(X_train=<5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, X_test=<1324x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, y_train=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], y_test=['1', '0', '1', '1', '1', '1', '0', '1', '0', '0', '0', '1', '1', '0', '1', '1', '0', '0', '0', '0', ...])
211 def run_gridsearch_elastic(X_train, X_test, y_train, y_test):
212 vals = [10 ** i for i in range(0, -10, -1)] + list(np.arange(0.1, 0.999, 0.015))
213 parameters = {'l1_ratio': vals, 'alpha': vals}
214 elastic = ElasticNet(max_iter = 1000)
215 clf = GridSearchCV(elastic, param_grid = parameters, n_jobs = 8, scoring = 'accuracy', cv = 10)
--> 216 clf.fit(X_train, y_train)
clf.fit = <bound method GridSearchCV.fit of GridSearchCV(c...core=True,
scoring='accuracy', verbose=0)>
X_train = <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>
y_train = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
217 preds = clf.predict(X_test)
218 print(clf.best_estimator_, clf.best_score_, clf.best_params_)
219 print("Accuracy: %s" % accuracy_score(y_test, preds))
220
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self=GridSearchCV(cv=10, error_score='raise',
...score=True,
scoring='accuracy', verbose=0), X=<5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, y=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], groups=None)
940
941 groups : array-like, with shape (n_samples,), optional
942 Group labels for the samples used while splitting the dataset into
943 train/test set.
944 """
--> 945 return self._fit(X, y, groups, ParameterGrid(self.param_grid))
self._fit = <bound method BaseSearchCV._fit of GridSearchCV(...core=True,
scoring='accuracy', verbose=0)>
X = <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>
y = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
groups = None
self.param_grid = {'alpha': [1, 0.1, 0.01, 0.001, 0.0001, 1e-05, 1e-06, 1e-07, 1e-08, 1e-09, 0.10000000000000001, 0.115, 0.13, 0.14500000000000002, 0.16, 0.17499999999999999, 0.19, 0.20500000000000002, 0.22, 0.23500000000000001, ...], 'l1_ratio': [1, 0.1, 0.01, 0.001, 0.0001, 1e-05, 1e-06, 1e-07, 1e-08, 1e-09, 0.10000000000000001, 0.115, 0.13, 0.14500000000000002, 0.16, 0.17499999999999999, 0.19, 0.20500000000000002, 0.22, 0.23500000000000001, ...]}
946
947
948 class RandomizedSearchCV(BaseSearchCV):
949 """Randomized search on hyper parameters.
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_search.py in _fit(self=GridSearchCV(cv=10, error_score='raise',
...score=True,
scoring='accuracy', verbose=0), X=<5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, y=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], groups=None, parameter_iterable=<sklearn.model_selection._search.ParameterGrid object>)
559 fit_params=self.fit_params,
560 return_train_score=self.return_train_score,
561 return_n_test_samples=True,
562 return_times=True, return_parameters=True,
563 error_score=self.error_score)
--> 564 for parameters in parameter_iterable
parameters = undefined
parameter_iterable = <sklearn.model_selection._search.ParameterGrid object>
565 for train, test in cv_iter)
566
567 # if one choose to see train score, "out" will contain train score info
568 if self.return_train_score:
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self=Parallel(n_jobs=8), iterable=<generator object BaseSearchCV._fit.<locals>.<genexpr>>)
763 if pre_dispatch == "all" or n_jobs == 1:
764 # The iterable was consumed all at once by the above for loop.
765 # No need to wait for async callbacks to trigger to
766 # consumption.
767 self._iterating = False
--> 768 self.retrieve()
self.retrieve = <bound method Parallel.retrieve of Parallel(n_jobs=8)>
769 # Make sure that we get a last message telling us we are done
770 elapsed_time = time.time() - self._start_time
771 self._print('Done %3i out of %3i | elapsed: %s finished',
772 (len(self._output), len(self._output),Sub-process traceback:
ValueError Mon Jul 3 02:20:59 2017
PID: 22695 Python 3.6.0: /home/zeerak/anaconda3/bin/python3
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self=<sklearn.externals.joblib.parallel.BatchedCalls object>)
126 def __init__(self, iterator_slice):
127 self.items = list(iterator_slice)
128 self._size = len(self.items)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
self.items = [(<function _fit_and_score>, (ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], make_scorer(accuracy_score), array([ 530, 531, 532, ..., 5292, 5293, 5294]), array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), 0, {'alpha': 1, 'l1_ratio': 1}), {'error_score': 'raise', 'fit_params': {}, 'return_n_test_samples': True, 'return_parameters': True, 'return_times': True, 'return_train_score': True})]
132
133 def __len__(self):
134 return self._size
135
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0=<list_iterator object>)
126 def __init__(self, iterator_slice):
127 self.items = list(iterator_slice)
128 self._size = len(self.items)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
func = <function _fit_and_score>
args = (ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), <5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], make_scorer(accuracy_score), array([ 530, 531, 532, ..., 5292, 5293, 5294]), array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), 0, {'alpha': 1, 'l1_ratio': 1})
kwargs = {'error_score': 'raise', 'fit_params': {}, 'return_n_test_samples': True, 'return_parameters': True, 'return_times': True, 'return_train_score': True}
132
133 def __len__(self):
134 return self._size
135
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X=<5295x86231 sparse matrix of type '<class 'numpy... stored elements in Compressed Sparse Row format>, y=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], scorer=make_scorer(accuracy_score), train=array([ 530, 531, 532, ..., 5292, 5293, 5294]), test=array([ 0, 1, 2, 3, 4, 5, 6, 7, ...20, 521, 522, 523, 524, 525, 526, 527, 528, 529]), verbose=0, parameters={'alpha': 1, 'l1_ratio': 1}, fit_params={}, return_train_score=True, return_parameters=True, return_n_test_samples=True, return_times=True, error_score='raise')
255 " numeric value. (Hint: if using 'raise', please"
256 " make sure that it has been spelled correctly.)")
257
258 else:
259 fit_time = time.time() - start_time
--> 260 test_score = _score(estimator, X_test, y_test, scorer)
test_score = undefined
estimator = ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False)
X_test = <530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>
y_test = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
scorer = make_scorer(accuracy_score)
261 score_time = time.time() - start_time - fit_time
262 if return_train_score:
263 train_score = _score(estimator, X_train, y_train, scorer)
264
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _score(estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X_test=<530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>, y_test=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], scorer=make_scorer(accuracy_score))
283 def _score(estimator, X_test, y_test, scorer):
284 """Compute the score of an estimator on a given test set."""
285 if y_test is None:
286 score = scorer(estimator, X_test)
287 else:
--> 288 score = scorer(estimator, X_test, y_test)
score = undefined
scorer = make_scorer(accuracy_score)
estimator = ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False)
X_test = <530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>
y_test = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
289 if hasattr(score, 'item'):
290 try:
291 # e.g. unwrap memmapped scalars
292 score = score.item()
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/scorer.py in __call__(self=make_scorer(accuracy_score), estimator=ElasticNet(alpha=1, copy_X=True, fit_intercept=T...selection='cyclic', tol=0.0001, warm_start=False), X=<530x86231 sparse matrix of type '<class 'numpy.... stored elements in Compressed Sparse Row format>, y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], sample_weight=None)
93 return self._sign * self._score_func(y_true, y_pred,
94 sample_weight=sample_weight,
95 **self._kwargs)
96 else:
97 return self._sign * self._score_func(y_true, y_pred,
---> 98 **self._kwargs)
self._kwargs = {}
99
100
101 class _ProbaScorer(_BaseScorer):
102 def __call__(self, clf, X, y, sample_weight=None):
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py in accuracy_score(y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], y_pred=array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042]), normalize=True, sample_weight=None)
167 >>> accuracy_score(np.array([[0, 1], [1, 1]]), np.ones((2, 2)))
168 0.5
169 """
170
171 # Compute accuracy for each possible representation
--> 172 y_type, y_true, y_pred = _check_targets(y_true, y_pred)
y_type = undefined
y_true = ['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...]
y_pred = array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042])
173 if y_type.startswith('multilabel'):
174 differing_labels = count_nonzero(y_true - y_pred, axis=1)
175 score = differing_labels == 0
176 else:
...........................................................................
/home/zeerak/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py in _check_targets(y_true=['0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1', '1', '1', '0', '1', '0', '1', '1', '0', ...], y_pred=array([ 0.5320042, 0.5320042, 0.5320042, 0.53... 0.5320042, 0.5320042, 0.5320042, 0.5320042]))
77 if y_type == set(["binary", "multiclass"]):
78 y_type = set(["multiclass"])
79
80 if len(y_type) > 1:
81 raise ValueError("Can't handle mix of {0} and {1}"
---> 82 "".format(type_true, type_pred))
type_true = 'binary'
type_pred = 'continuous'
83
84 # We can't have more than one value on y_type => The set is no more needed
85 y_type = y_type.pop()
86
ValueError: Can't handle mix of binary and continuous
___________________________________________________________________________
Versions
platform.platform(): Linux-4.2.3-300.fc23.x86_64-x86_64-with-fedora-25-Twenty_Five
sys.version: Python 3.6.0 |Anaconda 4.3.1 (64-bit)| (default, Dec 23 2016, 12:22:00)
[GCC 4.4.7 20120313 (Red Hat 4.4.7-1)]
numpy.version: NumPy 1.11.3
scipy.version: SciPy 0.18.1
sklearn.version: Scikit-Learn 0.18.1
Metadata
Metadata
Assignees
Labels
No labels