本文整理汇总了Python中sklearn.ensemble.VotingClassifier.estimators_方法的典型用法代码示例。如果您正苦于以下问题：Python VotingClassifier.estimators_方法的具体用法？Python VotingClassifier.estimators_怎么用？Python VotingClassifier.estimators_使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.ensemble.VotingClassifier的用法示例。
在下文中一共展示了VotingClassifier.estimators_方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: createVotingClassifier
# 需要导入模块: from sklearn.ensemble import VotingClassifier [as 别名]
# 或者: from sklearn.ensemble.VotingClassifier import estimators_ [as 别名]
def createVotingClassifier(n_trees,X,y,depth,min_saples=2,max_feat=0.2,overhead=2.0,voting_='soft'):
N_data = int(overhead*len(X)/n_trees)
print(str(N_data)+' will be used by classifier')
estimators_ = []
estimators = []
for i in range(n_trees):
clf = RandomForestClassifier(max_depth=depth,min_samples_leaf=min_saples,max_features=max_feat)
if (i+1)*N_data<len(X):
clf.fit(X[i*N_data:(i+1)*N_data],y[i*N_data:(i+1)*N_data])
else:
X,y = shuffle(X,y)
clf.fit(X[:N_data],y[:N_data])
estimators_.append((str(i),clf))
estimators.append(clf)
tmp = VotingClassifier(estimators=estimators_, voting=voting_)
tmp.estimators_ = estimators
return tmp示例2: fit_voting
# 需要导入模块: from sklearn.ensemble import VotingClassifier [as 别名]
# 或者: from sklearn.ensemble.VotingClassifier import estimators_ [as 别名]
def fit_voting(self):
voting = 'soft'
names = [
# 'svm(word_n_grams,char_n_grams,all_caps,hashtags,punctuations,punctuation_last,emoticons,emoticon_last,'
# 'elongated,negation_count)',
# 'logreg(w2v_doc)',
# 'logreg(w2v_word_avg_google)',
'word2vec_bayes',
'cnn_word(embedding=google)',
'rnn_word(embedding=google)',
]
classifiers = [ExternalModel({
self.val_docs: os.path.join(self.data_dir, 'results/val/{}.json'.format(name)),
self.test_docs: os.path.join(self.data_dir, 'results/test/{}.json'.format(name)),
}) for name in names]
all_scores = []
for classifier in classifiers:
scores = classifier.predict_proba(self.val_docs)
if voting == 'hard':
scores = Binarizer(1 / 3).transform(scores)
all_scores.append(scores)
all_scores = np.array(all_scores)
all_scores_first, all_scores_rest = all_scores[0], all_scores[1:]
le = LabelEncoder().fit(self.classes_)
val_label_indexes = le.transform(self.val_labels())
# assume w_0=1 as w is invariant to scaling
w = basinhopping(
lambda w_: -(val_label_indexes == np.argmax((
all_scores_first + all_scores_rest * w_.reshape((len(w_), 1, 1))
).sum(axis=0), axis=1)).sum(), np.ones(len(classifiers) - 1), niter=1000,
minimizer_kwargs=dict(method='L-BFGS-B', bounds=[(0, None)] * (len(classifiers) - 1))
).x
w = np.hstack([[1], w])
w /= w.sum()
logging.info('w: {}'.format(w))
estimator = VotingClassifier(list(zip(names, classifiers)), voting=voting, weights=w)
estimator.le_ = le
estimator.estimators_ = classifiers
return 'vote({})'.format(','.join(names)), estimator示例3: fit
# 需要导入模块: from sklearn.ensemble import VotingClassifier [as 别名]
# 或者: from sklearn.ensemble.VotingClassifier import estimators_ [as 别名]
def fit(self):
clf_list=[]
# # KNN
# print "KNN"
# knn = KNeighborsClassifier(n_neighbors=35, weights='distance', leaf_size=2)
# print "Fitting KNN"
# knn.fit(self.X_train, self.y_train)
# print('KNN {score}'.format(score=log_loss(self.y_test, knn.predict_proba(self.X_test))))
# self.clfs['knn'] = knn
# clf_list.append(knn)
# Random forests
print "Random forest on gini"
rfc = RandomForestClassifier(n_estimators=43,
criterion='gini',
random_state=4141,
n_jobs=-1,
max_depth=21,
max_features=0.12)
print "Fitting random forest with gini"
rfc.fit(self.X_train, self.y_train)
print('RFC LogLoss {score}'.format(score=log_loss(self.y_test, rfc.predict_proba(self.X_test))))
self.clfs['rfc']=rfc
clf_list.append(rfc)
print "Random forest with entropy"
rfc2 = RandomForestClassifier(n_estimators=80,
criterion='entropy',
random_state=1337,
n_jobs=-1,
max_depth=36,
max_features=0.06)
print "Fitting random forest with entropy"
rfc2.fit(self.X_train, self.y_train)
print('RFC2 LogLoss {score}'.format(score=log_loss(self.y_test, rfc2.predict_proba(self.X_test))))
self.clfs['rfc2']=rfc2
clf_list.append(rfc2)
# Logistic regression
print "Logistic regression on logloss"
logreg = LogisticRegression(C=1.05, penalty='l2')
print "Fitting logistic regression"
logreg.fit(self.X_train, self.y_train)
print('LR LogLoss {score}'.format(score=log_loss(self.y_test, logreg.predict_proba(self.X_test))))
self.clfs['lr']=logreg
clf_list.append(logreg)
# # gradient boosting
# gbt1=GradientBoostingClassifier(n_estimators=100, learning_rate=1.0,max_depth = 1, random_state = 0)
# print "Fitting gradient boosting tree"
# gbt1.fit(self.X_train, self.y_train)
# print('Gbt1 LogLoss {score}'.format(score=log_loss(self.y_test, gbt1.predict_proba(self.X_test))))
# self.clfs['gbt1']=gbt1
# clf_list.append(gbt1)
# # Bad performance
# # Multinomial Naive Bayes
# print "Multinomial naive bayes"
# mnb = MultinomialNB(fit_prior=False,alpha=0.25)
# print "Fitting multinomial naive bayes"
# mnb.fit(self.X_train, self.y_train)
# print('MNB {score}'.format(score=log_loss(self.y_test, mnb.predict_proba(self.X_test))))
# self.clfs['mnb'] = mnb
# clf_list.append(mnb)
# Adaboost
print "Adaboost trees"
abc = AdaBoostClassifier(n_estimators=100,learning_rate=0.5)
print "Fitting Adaboost trees"
abc.fit(self.X_train, self.y_train)
print('ABC {score}'.format(score=log_loss(self.y_test, abc.predict_proba(self.X_test))))
self.clfs['abc'] = abc
clf_list.append(abc)
# Ensemble to models
eclf3 = VotingClassifier(estimators=[('lr', logreg), ('rf', rfc), ('rf2', rfc2),('abc',abc)], voting='soft',
weights=[2, 2, 2, 1])
eclf3.estimators_ = clf_list
print "Dig into the voting classifier"
innerClfs = eclf3.estimators_
print "Check estimators"
print innerClfs
print('Ensemble LogLoss {score}'.format(score=log_loss(self.y_test, eclf3.predict_proba(self.X_test))))
self.ensembleClf=eclf3
print "Ensemble fitting finished"