질문&답변
당뇨병 실습 코드에서도 로지스틱 회귀를 이용하였으나 오류가 생겼습니다. sklearn 버젼은 다음과 같습니다. '0.23.2' X_train 만드는 소스코드는 다음과 같습니다. # 피쳐 데이터 세트 X, 레이블 데이터 세트 y를 추출 # 맨 끝이 outcome column으로, label 값임. 컬럼 위치 -1이용해 추출 X = diabetes_data.iloc[:, :-1] y = diabetes_data.iloc[:, -1] X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.2, random_state = 156, stratify = y) # 로지스틱 회귀로 학습 예측 평가 수행 lr_clf = LogisticRegression() lr_clf.fit(X_train, y_train) pred = lr_clf.predict(X_test)
질문&답변
다른 분류기는 제대로 실행되는데, 로지스틱회귀만 오류가 나타나는 것 같습니다! from sklearn.tree import DecisionTreeClassifier from sklearn.ensemble import RandomForestClassifier from sklearn.linear_model import LogisticRegression from sklearn.metrics import accuracy_score # 결정틀, 랜덤포레스트, 로지스틱 회귀를 위한 사이킷런 Classifier 클래스 형성 dt_clf = DecisionTreeClassifier(random_state = 11) rf_clf = RandomForestClassifier(random_state = 11) lr_clf = LogisticRegression() # DecisionTreeClassifier 학습/예측/평가 dt_clf.fit(X_train, y_train) dt_pred = dt_clf.predict(X_test) print('DecisionTreeClassifier 정확도: {0:.4f}'.format(accuracy_score(y_test, dt_pred))) # RandomForestClassifier 학습/예측/평가 rf_clf.fit(X_train, y_train) rf_pred = rf_clf.predict(X_test) print('RandomForestClassifier 정확도: {0:.4f}'.format(accuracy_score(y_test, rf_pred))) # LogisticRegression 학습/예측/평가 lr_clf.fit(X_train, y_train) lr_pred = lr_clf.predict(X_test) print('LogisticRegression 정확도: {0:.4f}'.format(accuracy_score(y_test, lr_pred))) -- DecisionTreeClassifier 정확도: 0.7877 RandomForestClassifier 정확도: 0.8547 --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 22 23 # LogisticRegression 학습/예측/평가 ---> 24 lr_clf . fit ( X_train , y_train ) 25 lr_pred = lr_clf . predict ( X_test ) 26 print ( 'LogisticRegression 정확도: {0:.4f}' . format ( accuracy_score ( y_test , lr_pred ) ) ) ~/opt/anaconda3/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py in fit (self, X, y, sample_weight) 1405 else : 1406 prefer = 'processes' -> 1407 fold_coefs_ = Parallel(n_jobs=self.n_jobs, verbose=self.verbose, 1408 ** _joblib_parallel_args ( prefer = prefer ) ) ( 1409 path_func(X, y, pos_class=class_, Cs=[C_], ~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in __call__ (self, iterable) 1039 # remaining jobs. 1040 self . _iterating = False -> 1041 if self . dispatch_one_batch ( iterator ) : 1042 self . _iterating = self . _original_iterator is not None 1043 ~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in dispatch_one_batch (self, iterator) 857 return False 858 else : --> 859 self . _dispatch ( tasks ) 860 return True 861 ~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in _dispatch (self, batch) 775 with self . _lock : 776 job_idx = len ( self . _jobs ) --> 777 job = self . _backend . apply_async ( batch , callback = cb ) 778 # A job can complete so quickly than its callback is 779 # called before we get here, causing self._jobs to ~/opt/anaconda3/lib/python3.8/site-packages/joblib/_parallel_backends.py in apply_async (self, func, callback) 206 def apply_async ( self , func , callback = None ) : 207 """Schedule a func to be run""" --> 208 result = ImmediateResult ( func ) 209 if callback : 210 callback ( result ) ~/opt/anaconda3/lib/python3.8/site-packages/joblib/_parallel_backends.py in __init__ (self, batch) 570 # Don't delay the application, to avoid keeping the input 571 # arguments in memory --> 572 self . results = batch ( ) 573 574 def get ( self ) : ~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in __call__ (self) 260 # change the default number of processes to -1 261 with parallel_backend ( self . _backend , n_jobs = self . _n_jobs ) : --> 262 return [func(*args, **kwargs) 263 for func, args, kwargs in self.items] 264 ~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in (.0) 260 # change the default number of processes to -1 261 with parallel_backend ( self . _backend , n_jobs = self . _n_jobs ) : --> 262 return [func(*args, **kwargs) 263 for func, args, kwargs in self.items] 264 ~/opt/anaconda3/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py in _logistic_regression_path (X, y, pos_class, Cs, fit_intercept, max_iter, tol, verbose, solver, coef, class_weight, dual, penalty, intercept_scaling, multi_class, random_state, check_input, max_squared_sum, sample_weight, l1_ratio) 760 options = { "iprint" : iprint , "gtol" : tol , "maxiter" : max_iter } 761 ) --> 762 n_iter_i = _check_optimize_result( 763 solver , opt_res , max_iter , 764 extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG) ~/opt/anaconda3/lib/python3.8/site-packages/sklearn/utils/optimize.py in _check_optimize_result (solver, result, max_iter, extra_warning_msg) 241 " https://scikit-learn.org/stable/modules/" 242 "preprocessing.html" --> 243 ).format(solver, result.status, result.message.decode("latin1")) 244 if extra_warning_msg is not None : 245 warning_msg += "\n" + extra_warning_msg AttributeError : 'str' object has no attribute 'decode'
