I've been attempting to fit a Grid Search K Nearest neighbors Classifier, but am receiving the following ValueError message
ValueError : Supported target types are: ('binary', 'multiclass'). Got 'continuous' instead. class. The raw data is as below:
X_train
compact sa area roofM3 h o glaz glazing_area_distribution
0 0.66 759.5 318.5 220.50 3.5 2 0.40 3
1 0.76 661.5 416.5 122.50 7.0 3 0.10 1
2 0.66 759.5 318.5 220.50 3.5 3 0.10 1
3 0.74 686.0 245.0 220.50 3.5 5 0.10 4
4 0.64 784.0 343.0 220.50 3.5 2 0.40 4
... ... ... ... ... ... ... ... ...
609 0.98 514.5 294.0 110.25 7.0 4 0.40 2
X_train.describe()
count 614.000000 614.000000 614.000000 614.000000 614.000000 614.000000 614.000000 614.000000
mean 0.762606 673.271173 319.617264 176.826954 5.227199 3.495114 0.236645 2.802932
std 0.106725 88.757699 43.705256 45.499990 1.751278 1.124751 0.133044 1.571128
min 0.620000 514.500000 245.000000 110.250000 3.500000 2.000000 0.000000 0.000000
25% 0.660000 612.500000 294.000000 122.500000 3.500000 2.000000 0.100000 1.000000
75% 0.820000 759.500000 343.000000 220.500000 7.000000 4.000000 0.400000 4.000000
max 0.980000 808.500000 416.500000 220.500000 7.000000 5.000000 0.400000 5.000000
**y_train
0 15.16
1 32.12
2 11.69
3 10.14
4 19.06
...
609 32.24**
Attempting to create and fit a model
from sklearn.model_selection import StratifiedKFold
model = StratifiedKFold()
cv_object = StratifiedKFold(n_splits=5, shuffle=True, random_state=50)
grid_values = {'n_neighbors': ['1','2','3','4','5'],
'weights': ['uniform', 'distance']
}
from sklearn.model_selection import GridSearchCV
model = KNeighborsRegressor()
grid_estimator = GridSearchCV(KNeighborsRegressor(), cv=cv_object,
param_grid=grid_values,
scoring='neg_mean_absolute_error')
**grid_estimator.fit(X_train, y_train)**
I tested the estimator by passing an array of zeros and ones the same length as X_train through the grid_estimator, but still receive the same error message:
Traceback error:
-------------------------------------------------- -------------------------
ValueError Traceback (most recent call last)
<ipython-input-60-bff19581180b> in <module>
18 #random_search = RandomizedSearchCV (k_model, param_distributions = param_grid,
19 # n_iter = 10, cv = 5, scoring = 'accuracy')
---> 20 gridsearch . fit ( X_train , y_train )
~ \ anaconda3 \ lib \ site-packages \ sklearn \ utils \ validation.py in inner_f (* args, ** kwargs)
70 FutureWarning)
71 kwargs . update ( { k : arg for k , arg in zip ( sig . parameters , args ) } )
---> 72 return f ( ** kwargs ) 73 return inner_f
74
~ \ anaconda3 \ lib \ site-packages \ sklearn \ model_selection \ _search.py in fit (self, X, y, groups, ** fit_params)
734 return results
735
-> 736 self . _run_search ( evaluate_candidates )
737
738 # For multi-metric evaluation, store the best_index_, best_params_ and
~ \ anaconda3 \ lib \ site-packages \ sklearn \ model_selection \ _search.py in _run_search (self, evaluate_candidates)
1186 def _run_search ( self , evaluate_candidates ) :
1187 "" "Search all candidates in param_grid" ""
-> 1188 evaluate_candidates ( ParameterGrid ( self . Param_grid ) )
1189
1190
~ \ anaconda3 \ lib \ site-packages \ sklearn \ model_selection \ _search.py in evaluate_candidates (candidate_params)
712 ** fit_and_score_kwargs)
713 for parameters , ( train , test )
-> 714 in product (candidate_params,
715 cv.split ( X, y, groups)))
716
~ \ anaconda3 \ lib \ site-packages \ sklearn \ model_selection \ _split.py in split (self, X, y, groups)
334 .format (self.n_splits, n_samples))
335
-> 336 for train , test in super ( ) . split ( X , y , groups ) : 337 yield train , test
338
~ \ anaconda3 \ lib \ site-packages \ sklearn \ model_selection \ _split.py in split (self, X, y, groups)
78 X , y , groups = indexable ( X , y , groups )
79 indices = np . arange ( _num_samples ( X ) )
---> 80 for test_index in self . _iter_test_masks ( X , y , groups ) :
81 train_index = indices [ np . logical_not ( test_index ) ]
82 test_index = indices [ test_index ]
~ \ anaconda3 \ lib \ site-packages \ sklearn \ model_selection \ _split.py in _iter_test_masks (self, X, y, groups)
695
696 def _iter_test_masks ( self , X , y = None , groups = None ) :
-> 697 test_folds = self . _make_test_folds ( X , y )
698 for i in range ( self . n_splits ) :
699 yield test_folds == i
~ \ anaconda3 \ lib \ site-packages \ sklearn \ model_selection \ _split.py in _make_test_folds (self, X, y)
647 allowed_target_types = ( 'binary' , 'multiclass' )
648 if type_of_target_y not in allowed_target_types :
-> 649 raise ValueError (
650 'Supported target types are: {}. Got {! R} instead.'. Format (
651 allowed_target_types, type_of_target_y))
ValueError : Supported target types are: ('binary', 'multiclass'). Got 'continuous' instead.
