SMOTE

import pandas as pd
import numpy as np
from sklearn.ensemble import GradientBoostingClassifier
from sklearn import cross_validation
from sklearn.metrics import accuracy_score

df=pd.read_csv('DadosTeseLogit.csv',sep=',',header=0)

X=np.array(df.iloc[0:96,[12,18,29]])
Y=np.array(df.iloc[0:96,30])

from imblearn.over_sampling import SMOTE
from imblearn.combine import SMOTEENN

sm = SMOTEENN()
x, y = sm.fit_sample(X, Y)


x_train, x_test, y_train, y_test = cross_validation.train_test_split(x,y, test_size=.2, random_state=4)


model=GradientBoostingClassifier(
init= None,
learning_rate= 0.1,
loss='deviance',
max_depth= 8,
max_features=2,
max_leaf_nodes=10,
min_samples_leaf= 1,
min_samples_split= 2,
min_weight_fraction_leaf= .2,
n_estimators= 100,
presort= 'auto',
random_state= None,
subsample= 1.0,
verbose=1,
warm_start= False)

a=model.fit(x_train,y_train)
print(model)

model.get_params()

model.score(x,y)

pred=model.predict(x_test)

sum(x==0 for x in pred-y_test)/len(pred)

accuracy = accuracy_score(y_test, pred)
print('Accuracy:',accuracy)