VotingClassifier.txt

x=df.iloc[:,1]
y= df.iloc[:,0]

from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(analyzer = 'word',lowercase = True)
x_poly = cv.fit_transform(x).toarray()

from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x_poly,y,train_size =0.80,random_state=42)

from sklearn.ensemble import VotingClassifier
from sklearn import model_selection
seed = 7
kfold = model_selection.KFold(n_splits=50, random_state=seed)
# create the sub models
estimators = []
model1 = LogisticRegression()
estimators.append(('logistic', model1))
model2 = tree.DecisionTreeClassifier()
estimators.append(('cart', model2))
model3 = MultinomialNB(alpha=1)
estimators.append(('NB', model3))
model4 = OneVsRestClassifier(model1)
estimators.append(('OneVsRest1', model4))
model5 = OneVsRestClassifier(model2)
estimators.append(('OneVsRest2', model5))
model6 = OneVsRestClassifier(model2)
estimators.append(('OneVsRest3', model6))
# create the ensemble model
ensemble = VotingClassifier(estimators, voting = "hard")
#results = model_selection.cross_val_score(ensemble, x_poly, y, cv=kfold)

print(results.mean())

#fit model to training data
ensemble.fit(x_train, y_train)
#test our model on the test data
ensemble.score(x_test, y_test)