Python SVC.C方法代码示例

# 需要导入模块: from sklearn.svm import SVC [as 别名]
# 或者: from sklearn.svm.SVC import C [as 别名]
    def trainauc (self, train, trainlabel, seed, Cmin, Cmax, numC, rmin, rmax, numr, degree=3, method = 'roc_auc', rad_stat =2):
        C_range=np.logspace(Cmin, Cmax, num=numC, base=2,endpoint= True)
        gamma_range=np.logspace(rmin, rmax, num=numr, base=2,endpoint= True)
        
        svc = SVC(kernel=seed)
#        mean_score=[]
        df_C_gamma= DataFrame({'gamma_range':gamma_range})
#        df_this = DataFrame({'gamma_range':gamma_range})
        count = 0 
        for C in C_range:    
            score_C=[]    
#            score_C_this = []
            count=count+1
            for gamma in gamma_range:                   
     
                svc.C = C
                svc.gamma = gamma
                svc.degree = degree
                svc.random_state = rad_stat
                this_scores = cross_val_score(svc, train, trainlabel, scoring=method, cv=10, n_jobs=-1 \
                                              )
                
                score_C.append(np.mean(this_scores))                                      

               #score_C_this.append(np.mean(this_scores))
            print (np.mean(score_C) )
            print ("%r cycle finished, %r left" %(count, numC-count))
            df_C_gamma[C]= score_C
            #df_this[C] = score_C_this        
        
        return df_C_gamma 

# 需要导入模块: from sklearn.svm import SVC [as 别名]
# 或者: from sklearn.svm.SVC import C [as 别名]
 def new_pipe(mod):
     svc = SVC()
     svc.kernel = 'linear'
     svc.C = params_map[mod]['C']
     svc.probability = True
     masker = SimpleMaskerPipeline(.2)
     return Pipeline([
         ('columns', ColumnSelector(index_map[mod])),
         ('whitematter', masker),
         ('anova', SelectKBest(k=500)),
         ('svc', svc)
     ])

# 需要导入模块: from sklearn.svm import SVC [as 别名]
# 或者: from sklearn.svm.SVC import C [as 别名]
    def trainSVC (self, train, trainlabel, seed, Cmin, Cmax, numC, rmin, rmax, numr, degree=3):
        C_range=np.logspace(Cmin, Cmax, num=numC, base=2,endpoint= True)
        gamma_range=np.logspace(rmin, rmax, num=numr, base=2,endpoint= True)
        
        svc = SVC(kernel=seed)
#        mean_score=[]
        df_C_gamma= DataFrame({'gamma_range':gamma_range})
#        df_this = DataFrame({'gamma_range':gamma_range})
        count = 0 
        for C in C_range:    
            score_C=[]    
#            score_C_this = []
            count=count+1
            for gamma in gamma_range:
                
                training_manCV.secret_cm=[]     
                training_manCV.secret_score=[]      
                svc.C = C
                svc.gamma = gamma
                svc.degree = degree
                this_scores = cross_val_score(svc, train, trainlabel, scoring=training_manCV().metric_scores, cv=10, n_jobs=-1)
                
       

                df_raw0 = DataFrame({'cm':training_manCV.secret_cm})
               
                
                score_C.append(np.mean(df_raw0['cm'].tail(10)))

               #score_C_this.append(np.mean(this_scores))
            print (np.mean(this_scores) )
            print ("%r cycle finished, %r left" %(count, numC-count))
            df_C_gamma[C]= score_C
            #df_this[C] = score_C_this 
        
        
        return df_C_gamma  

# 需要导入模块: from sklearn.svm import SVC [as 别名]
# 或者: from sklearn.svm.SVC import C [as 别名]
     joblib.dump(gs, "grid_cv_rbm.pkl", compress=3)
     
 else:
     # 直接设置参数训练
     bow = BoWFeature()
     bow.patch_num=10000
     bow.patch_size=(20,20)
     bow.learning_rate=0.001
     bow.n_components=512
     bow.n_iter=100
     bow.sample_num = 1000
     
     bow.fit(x_train)
     
     svm = SVC(kernel='linear', probability = True, random_state=42)
     svm.C = 1000
     #lr = LogisticRegression()
     #lr.C = 100
     best = Pipeline([('bow', bow),('svm',svm)])
     best.fit(x_train, y_train)
     
     print "*********************Save*******************************"
     joblib.dump(best, "classifier_rbm.pkl", compress=3)
             
 print "*********************Test*******************************"
 y_test_pre = best.predict(x_test)
 cm = confusion_matrix(y_test, y_test_pre)
 from map_confusion import plot_conf
 plot_conf(cm, range(le.classes_.size), 'RSDataset.png')
 
 from sklearn.metrics import classification_report

# 需要导入模块: from sklearn.svm import SVC [as 别名]
# 或者: from sklearn.svm.SVC import C [as 别名]
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(newsgroup.data)
y = newsgroup.target

C = np.power(10.0, np.arange(-5, 6))
grid = {'C': C}
k_folder = KFold(X.shape[0], n_folds=5, shuffle=True, random_state=241)
clf = SVC(kernel='linear', random_state=241)
grid_search = GridSearchCV(clf, grid, scoring='accuracy', cv=k_folder)
grid_search.fit(X, y)

optimal_parameters = {}
max_score = max(x.mean_validation_score for x in grid_search.grid_scores_)
optimal_c = next(x.parameters['C'] for x in grid_search.grid_scores_ if x.mean_validation_score == max_score)

clf.C = optimal_c
clf.fit(X, y)

feature_mappings = vectorizer.get_feature_names()
result = {
    'words': list(feature_mappings[i] for i in clf.coef_.indices),
    'values': list(abs(weight) for weight in clf.coef_.data),
}
coef = DataFrame(data=result)
coef = coef.sort_values(by='values', ascending=False)

words = coef.head(10)['words'].values.tolist()

output = " ".join(sorted(words))
coursera.output("svm_text_analyze.txt", output)