Python机器学习之决策树案例

# -*- coding: utf-8 -*-__author__ = 'gerry'# 先导入所有的classimport xgboostfrom numpy import *from sklearn import model_selectionfrom sklearn.metrics import accuracy_score# load 数据集dataset = loadtxt('pima-indians-diabetes.data.csv', delimiter=',')# 把X, Y分开X = dataset[:, 0:8]Y = dataset[:, 8]# 现在我们分开训练集和测试集seed = 7test_size = 0.33X_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, test_size=test_size, random_state=seed)# 训练模型model = xgboost.XGBClassifier()model.fit(X_train, Y_train)# 做预测y_pred = model.predict(X_test)predictions = [round(value) for value in y_pred]# 显示准确率accuracy = accuracy_score(Y_test, predictions)print "Accuracy:%.2f%%" % (accuracy * 100.0)