Providing the full StackTrace here:[ code in previous email]
# Tuning hyper-parameters for precision
()
---------------------------------------------------------------------------ValueError
Traceback (most recent call
last)<ipython-input-85-7fedbaf85b7d> in <module>() 18
scoring='%s_weighted' % score) 19 ---> 20
clf.fit(Finaldata, y) 21 22 print("Best parameters set
found on development set:")
D:\Anaconda\lib\site-packages\sklearn\grid_search.pyc in fit(self, X,
y) 730 731 """--> 732 return self._fit(X, y,
ParameterGrid(self.param_grid)) 733 734
D:\Anaconda\lib\site-packages\sklearn\grid_search.pyc in _fit(self, X,
y, parameter_iterable) 503
self.fit_params, return_parameters=True, 504
error_score=self.error_score)--> 505 for
parameters in parameter_iterable 506 for train,
test in cv) 507
D:\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.pyc in
__call__(self, iterable) 657 self._iterating = True
658 for function, args, kwargs in iterable:--> 659
self.dispatch(function, args, kwargs) 660 661
if pre_dispatch == "all" or n_jobs == 1:
D:\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.pyc in
dispatch(self, func, args, kwargs) 404 """ 405
if self._pool is None:--> 406 job = ImmediateApply(func,
args, kwargs) 407 index = len(self._jobs) 408
if not _verbosity_filter(index, self.verbose):
D:\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.pyc in
__init__(self, func, args, kwargs) 138 # Don't delay the
application, to avoid keeping the input 139 # arguments in
memory--> 140 self.results = func(*args, **kwargs) 141
142 def get(self):
D:\Anaconda\lib\site-packages\sklearn\cross_validation.pyc in
_fit_and_score(estimator, X, y, scorer, train, test, verbose,
parameters, fit_params, return_train_score, return_parameters,
error_score) 1457 estimator.fit(X_train, **fit_params)
1458 else:-> 1459 estimator.fit(X_train, y_train,
**fit_params) 1460 1461 except Exception as e:
D:\Anaconda\lib\site-packages\sklearn\linear_model\stochastic_gradient.pyc
in fit(self, X, y, coef_init, intercept_init, class_weight,
sample_weight) 562 loss=self.loss,
learning_rate=self.learning_rate, 563
coef_init=coef_init, intercept_init=intercept_init,--> 564
sample_weight=sample_weight) 565 566
D:\Anaconda\lib\site-packages\sklearn\linear_model\stochastic_gradient.pyc
in _fit(self, X, y, alpha, C, loss, learning_rate, coef_init,
intercept_init, sample_weight) 401 self.classes_ = None
402 --> 403 X, y = check_X_y(X, y, 'csr', dtype=np.float64,
order="C") 404 n_samples, n_features = X.shape 405
D:\Anaconda\lib\site-packages\sklearn\utils\validation.pyc in
check_X_y(X, y, accept_sparse, dtype, order, copy, force_all_finite,
ensure_2d, allow_nd, multi_output, ensure_min_samples,
ensure_min_features, y_numeric) 447
dtype=None) 448 else:--> 449 y = column_or_1d(y,
warn=True) 450 _assert_all_finite(y) 451 if
y_numeric and y.dtype.kind == 'O':
D:\Anaconda\lib\site-packages\sklearn\utils\validation.pyc in
column_or_1d(y, warn) 483 return np.ravel(y) 484 --> 485
raise ValueError("bad input shape {0}".format(shape)) 486
487
ValueError: bad input shape (914551, 6)
On Mon, Dec 28, 2015 at 4:08 PM, Startup Hire <blrstartuph...@gmail.com>
wrote:
> Hi all,
>
> Hope you are doing well.
>
> I am working on fine tuning the following parameters in SGD Classifier
> which I am using inside OneVsRest Classifier.
>
> I am using GridSearch to use the same.
>
> I have following questions:
>
>
> 1. How to use GridSearch to optimize OneVsRest Classifier?
> 2. Any reason why the below code does not work? Error is bad input
> shape though the classifier.fit works find separately!
>
>
>
>
>
>
> from sklearn.grid_search import GridSearchCV
>
>
> # Set the parameters by cross-validation
>
> tuned_parameters = [{'alpha': [0.001, 0.01,0.1,0.5] ,
> 'penalty': ['l1','l2','elasticnet'],
> 'loss':['log','modified_huber']}]
>
>
> scores = ['precision', 'recall']
>
> for score in scores:
> print("# Tuning hyper-parameters for %s" % score)
> print()
>
> clf =
> GridSearchCV(SGDClassifier(random_state=0,learning_rate='optimal',class_weight='auto',n_iter=100),
> tuned_parameters, cv=5,
> scoring='%s_weighted' % score)
>
> clf.fit(Finaldata, y)
>
> print("Best parameters set found on development set:")
> print()
> print(clf.best_params_)
> print()
>
>
> Regards,
> Sanant
>
------------------------------------------------------------------------------
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
