Я обучаю модель, и для этого мне нужен селектор атрибутов (с RFECV), а затем мне нужно оптимизировать параметры модели (GridSearchCV).
код
model = LogisticRegression() #algorithm
my_scorer = make_scorer(score, greater_is_better=True) #The score
generador_train = GroupKFold(n_splits=10).split(X_train, y_train, order_train) #Generator 10 splits with order
C= {'C': 10. ** np.arange(-3, 4)} #C
scaler = preprocessing.StandardScaler() #Standardized
selector =RFECV(cv=generador_train, estimator=model,scoring=my_scorer) #Selection of attributes
pipe=Pipeline([('scaler', scaler),('select', selector),('model', model)]) # The pipeline is created
grid = GridSearchCV(estimator=pipe, param_grid=C,cv=generador_train,scoring=my_scorer,refit=True) #The gridSearch with CV is declared
grid.fit(X_train, y_train) # The pipeline is executed
best_pipe=grid.best_estimator_
При выполнении предыдущего кода я получаю ошибку:
TypeError Traceback (most recent call
last) <ipython-input-34-9d038a773283> in <module>()
17
18 grid = GridSearchCV(estimator=pipe, param_grid=C,cv=generador_train,scoring=my_scorer,refit=True) #Se
declara el gridSearch con CV
---> 19 grid.fit(X_train,y_train)
20 best_pipe=grid.best_estimator_
AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py
in fit(self, X, y, groups, **fit_params)
622 n_candidates * n_splits))
623
--> 624 base_estimator = clone(self.estimator)
625 pre_dispatch = self.pre_dispatch
626
AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\base.py
in clone(estimator, safe)
59 new_object_params = estimator.get_params(deep=False)
60 for name, param in six.iteritems(new_object_params):
---> 61 new_object_params[name] = clone(param, safe=False)
62 new_object = klass(**new_object_params)
63 params_set = new_object.get_params(deep=False)
AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\base.py
in clone(estimator, safe)
47 # XXX: not handling dictionaries
48 if estimator_type in (list, tuple, set, frozenset):
---> 49 return estimator_type([clone(e, safe=safe) for e in estimator])
50 elif not hasattr(estimator, 'get_params'):
51 if not safe:
AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\base.py
in <listcomp>(.0)
47 # XXX: not handling dictionaries
48 if estimator_type in (list, tuple, set, frozenset):
---> 49 return estimator_type([clone(e, safe=safe) for e in estimator])
50 elif not hasattr(estimator, 'get_params'):
51 if not safe:
AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\base.py
in clone(estimator, safe)
47 # XXX: not handling dictionaries
48 if estimator_type in (list, tuple, set, frozenset):
---> 49 return estimator_type([clone(e, safe=safe) for e in estimator])
50 elif not hasattr(estimator, 'get_params'):
51 if not safe:
AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\base.py
in <listcomp>(.0)
47 # XXX: not handling dictionaries
48 if estimator_type in (list, tuple, set, frozenset):
---> 49 return estimator_type([clone(e, safe=safe) for e in estimator])
50 elif not hasattr(estimator, 'get_params'):
51 if not safe:
AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\base.py
in clone(estimator, safe)
59 new_object_params = estimator.get_params(deep=False)
60 for name, param in six.iteritems(new_object_params):
---> 61 new_object_params[name] = clone(param, safe=False)
62 new_object = klass(**new_object_params)
63 params_set = new_object.get_params(deep=False)
AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\base.py
in clone(estimator, safe)
50 elif not hasattr(estimator, 'get_params'):
51 if not safe:
---> 52 return copy.deepcopy(estimator)
53 else:
54 raise TypeError("Cannot clone object '%s' (type %s): "
AppData\Local\Continuum\Anaconda3\lib\copy.py in
deepcopy(x, memo, _nil)
167 reductor = getattr(x, "__reduce_ex__", None)
168 if reductor:
--> 169 rv = reductor(4)
170 else:
171 reductor = getattr(x, "__reduce__", None)
TypeError: can't pickle generator objects
Как это можно решить? Что может быть связано?
ОБНОВЛЕНИЕ 1
Я положил:
list(generador_train = GroupKFold(n_splits=10).split(X_train, y_train, order_train))
но я получил эту ошибку:
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-150-d0ca294b7811> in <module>()
25
26 grid = GridSearchCV(estimator=pipe, param_grid=C, cv=generador_train,scoring=my_scorer,refit=True) #Se declara el gridSearch con CV
---> 27 grid.fit(X_train, y_train) # Se ejecuta la pipeline
28 #grid.fit(digits.data, digits.target)
29 #res=pipe.named_steps['select'].grid_scores_ #Resultados gridSearch
~\Anaconda4\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
637 error_score=self.error_score)
638 for parameters, (train, test) in product(candidate_params,
--> 639 cv.split(X, y, groups)))
640
641 # if one choose to see train score, "out" will contain train score info
~\Anaconda4\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
777 # was dispatched. In particular this covers the edge
778 # case of Parallel used with an exhausted iterator.
--> 779 while self.dispatch_one_batch(iterator):
780 self._iterating = True
781 else:
~\Anaconda4\lib\site-packages\sklearn\externals\joblib\parallel.py in dispatch_one_batch(self, iterator)
623 return False
624 else:
--> 625 self._dispatch(tasks)
626 return True
627
~\Anaconda4\lib\site-packages\sklearn\externals\joblib\parallel.py in _dispatch(self, batch)
586 dispatch_timestamp = time.time()
587 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588 job = self._backend.apply_async(batch, callback=cb)
589 self._jobs.append(job)
590
~\Anaconda4\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in apply_async(self, func, callback)
109 def apply_async(self, func, callback=None):
110 """Schedule a func to be run"""
--> 111 result = ImmediateResult(func)
112 if callback:
113 callback(result)
~\Anaconda4\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in __init__(self, batch)
330 # Don't delay the application, to avoid keeping the input
331 # arguments in memory
--> 332 self.results = batch()
333
334 def get(self):
~\Anaconda4\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~\Anaconda4\lib\site-packages\sklearn\externals\joblib\parallel.py in <listcomp>(.0)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~\Anaconda4\lib\site-packages\sklearn\model_selection\_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
456 estimator.fit(X_train, **fit_params)
457 else:
--> 458 estimator.fit(X_train, y_train, **fit_params)
459
460 except Exception as e:
~\Anaconda4\lib\site-packages\sklearn\pipeline.py in fit(self, X, y, **fit_params)
246 This estimator
247 """
--> 248 Xt, fit_params = self._fit(X, y, **fit_params)
249 if self._final_estimator is not None:
250 self._final_estimator.fit(Xt, y, **fit_params)
~\Anaconda4\lib\site-packages\sklearn\pipeline.py in _fit(self, X, y, **fit_params)
211 Xt, fitted_transformer = fit_transform_one_cached(
212 cloned_transformer, None, Xt, y,
--> 213 **fit_params_steps[name])
214 # Replace the transformer of the step with the fitted
215 # transformer. This is necessary when loading the transformer
~\Anaconda4\lib\site-packages\sklearn\externals\joblib\memory.py in __call__(self, *args, **kwargs)
360
361 def __call__(self, *args, **kwargs):
--> 362 return self.func(*args, **kwargs)
363
364 def call_and_shelve(self, *args, **kwargs):
~\Anaconda4\lib\site-packages\sklearn\pipeline.py in _fit_transform_one(transformer, weight, X, y, **fit_params)
579 **fit_params):
580 if hasattr(transformer, 'fit_transform'):
--> 581 res = transformer.fit_transform(X, y, **fit_params)
582 else:
583 res = transformer.fit(X, y, **fit_params).transform(X)
~\Anaconda4\lib\site-packages\sklearn\base.py in fit_transform(self, X, y, **fit_params)
518 else:
519 # fit method of arity 2 (supervised transformation)
--> 520 return self.fit(X, y, **fit_params).transform(X)
521
522
~\Anaconda4\lib\site-packages\sklearn\feature_selection\rfe.py in fit(self, X, y)
434 scores = parallel(
435 func(rfe, self.estimator, X, y, train, test, scorer)
--> 436 for train, test in cv.split(X, y))
437
438 scores = np.sum(scores, axis=0)
~\Anaconda4\lib\site-packages\sklearn\feature_selection\rfe.py in <genexpr>(.0)
434 scores = parallel(
435 func(rfe, self.estimator, X, y, train, test, scorer)
--> 436 for train, test in cv.split(X, y))
437
438 scores = np.sum(scores, axis=0)
~\Anaconda4\lib\site-packages\sklearn\feature_selection\rfe.py in _rfe_single_fit(rfe, estimator, X, y, train, test, scorer)
26 Return the score for a fit across one fold.
27 """
---> 28 X_train, y_train = _safe_split(estimator, X, y, train)
29 X_test, y_test = _safe_split(estimator, X, y, test, train)
30 return rfe._fit(
~\Anaconda4\lib\site-packages\sklearn\utils\metaestimators.py in _safe_split(estimator, X, y, indices, train_indices)
198 X_subset = X[np.ix_(indices, train_indices)]
199 else:
--> 200 X_subset = safe_indexing(X, indices)
201
202 if y is not None:
~\Anaconda4\lib\site-packages\sklearn\utils\__init__.py in safe_indexing(X, indices)
158 indices.dtype.kind == 'i'):
159 # This is often substantially faster than X[indices]
--> 160 return X.take(indices, axis=0)
161 else:
162 return X[indices]
IndexError: index 182 is out of bounds for size 182
Что я делаю не так?
ОБНОВЛЕНИЕ 2
Есть 2 элемента с одинаковым идентификатором, которые невозможно разделить при разделении данных.
Создание заказа на поезд:
order = mydata.iloc[:,0].values #Ids that are used by the order.
train_indices, test_indices = next(GroupShuffleSplit(test_size=0.25).split(X, y, order)) #Split the data into train and test using groups.
X_train, X_test, y_train, y_test = X[train_indices], X[test_indices], y[train_indices], y[test_indices] #Obtain the 4 datasets
order_train=mydata.iloc[train_indices,0].values #Order train
Order_train:
[ 1. 1. 2. 2. 3. 3. 4. 4. 5. 5. 6. 6.
7. 7. 8. 8. 9. 9. 10. 10. 11. 11. 12. 12.
13. 13. 14. 14. 15. 15. 16. 16. 17. 17. 18. 18.
19. 19. 20. 20. 21. 21. 22. 22. 23. 23. 24. 24.
25. 25. 26. 26. 27. 27. 28. 28. 29. 29. 30. 30.
31. 31. 32. 32. 33. 33. 34. 34. 35. 35. 36. 36.
37. 37. 38. 38. 39. 39. 40. 40. 41. 41. 42. 42.
43. 43. 44. 44. 45. 45. 46. 46. 47. 47. 48. 48.
49. 49. 50. 50. 51. 51. 52. 52. 53. 53. 54. 54.
55. 55. 56. 56. 57. 57. 58. 58. 59. 59. 60. 60.
61. 61. 62. 62. 63. 63. 64. 64. 65. 65. 66. 66.
67. 67. 68. 68. 69. 69. 70. 70. 71. 71. 72. 72.
73. 73. 74. 74. 75. 75. 76. 76. 77. 77. 78. 78.
79. 79. 80. 80. 81. 81. 82. 82. 83. 83. 84. 84.
85. 85. 86. 86. 87. 87. 88. 88. 89. 89. 90. 90.
91. 91. 92. 92. 93. 93. 94. 94. 95. 95. 96. 96.
97. 97. 98. 98. 99. 99. 100. 100. 101. 101. 102. 102.]