多数決の原理に基づいて予測を行う

Question

前提・実現したいこと

達人データサイエンティストによる理論と実践の本を写経しているのですが、本の通りやっているのですが、valueerrorになってしまいます。お助け願います、、、
###エラーメッセージ

10-fold cross validation:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-19-4f5b5db10c84> in <module>()
     29         y=y_train,
     30         cv=10,
---> 31         scoring='roc_auc',
     32     )
     33     print("ROC AUC:%0.2f (+/- %0.2f) [%s]" % (scores.mean(),score.std(),label))

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch)
    340                                 n_jobs=n_jobs, verbose=verbose,
    341                                 fit_params=fit_params,
--> 342                                 pre_dispatch=pre_dispatch)
    343     return cv_results['test_score']
    344 

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score)
    204             fit_params, return_train_score=return_train_score,
    205             return_times=True)
--> 206         for train, test in cv.split(X, y, groups))
    207 
    208     if return_train_score:

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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:

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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 

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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 

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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)

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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):

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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):

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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):

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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:

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
    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)
    251         return self
    252 

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/site-packages/sklearn/linear_model/logistic.py in fit(self, X, y, sample_weight)
   1235                 self.class_weight, self.penalty, self.dual, self.verbose,
   1236                 self.max_iter, self.tol, self.random_state,
-> 1237                 sample_weight=sample_weight)
   1238             self.n_iter_ = np.array([n_iter_])
   1239             return self

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/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)
    884         check_consistent_length(sample_weight, X)
    885 
--> 886     solver_type = _get_liblinear_solver_type(multi_class, penalty, loss, dual)
    887     raw_coef_, n_iter_ = liblinear.train_wrap(
    888         X, y_ind, sp.isspmatrix(X), solver_type, tol, bias, C,

~/.pyenv/versions/anaconda3-5.3.1/lib/python3.7/site-packages/sklearn/svm/base.py in _get_liblinear_solver_type(multi_class, penalty, loss, dual)
    745     raise ValueError('Unsupported set of arguments: %s, '
    746                      'Parameters: penalty=%r, loss=%r, dual=%r'
--> 747                      % (error_string, penalty, loss, dual))
    748 
    749 

ValueError: Unsupported set of arguments: The combination of penalty='12' and loss='logistic_regression' is not supported, Parameters: penalty='12', loss='logistic_regression', dual=False

該当のソースコード

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import LabelEncoder
iris=datasets.load_iris()
X,y=iris.data[50:,[1,2]],iris.target[50:]
le=LabelEncoder()
y=le.fit_transform(y)


X_train,X_test,y_train,y_test=\
    train_test_split(X,y,test_size=0.5,random_state=1,stratify=y)

from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import Pipeline
import numpy as np

clf1=LogisticRegression(penalty='12',
                        C=0.001,
                        random_state=1)
clf2=DecisionTreeClassifier(max_depth=1,
                            criterion='entropy',
                            random_state=0)
clf3=KNeighborsClassifier(n_neighbors=1,
                          p=2,
                          metric='minkowski')
pipe1=Pipeline([['sc',StandardScaler()],
                ['clf',clf1]])

pipe3=Pipeline([['sc',StandardScaler()],
                ['clf',clf3]])

clf_labels=['Logistic regression ','Decision tree','KNN']
print('10-fold cross validation:\n')
for clf,label in zip([pipe1,clf2,pipe3],clf_labels):
    scores=cross_val_score(
        estimator=clf,
        X=X_train,
        y=y_train,
        cv=10,
        scoring='roc_auc',
    )
    print("ROC AUC:%0.2f (+/- %0.2f) [%s]" % (scores.mean(),score.std(),label))

Answer 1

penalty='12'ではなくpenalty='l2'です(小文字のエル)。

Comments

[tomatoto11]

ありがとうございました!