# -*- coding: utf-8 -*-
__author__ = 'gerry'

# 先匯入所有的class
import xgboost
from numpy import *
from sklearn import model_selection
from sklearn.metrics import accuracy_score

# load 資料集
dataset = loadtxt('pima-indians-diabetes.data.csv', delimiter=',')

# 把X, Y分開
X = dataset[:, 0:8]
Y = dataset[:, 8]

# 現在我們分開訓練集和測試集
 

seed = 7
test_size = 0.33
X_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, test_size=test_size, random_state=seed)
# 訓練模型
model = xgboost.XGBClassifier()
model.fit(X_train, Y_train)

# 做預測
y_pred = model.predict(X_test)
predictions = [round(value) for value in y_pred]

# 顯示準確率
 

accuracy = accuracy_score(Y_test, predictions)
print "Accuracy:%.2f%%" % (accuracy * 100.0)