Python机器学习应用之基于决策树算法的分类预测篇

#%%demo
##  基础函数库导入
import numpy as np 

## 导入画图库
import matplotlib.pyplot as plt
import seaborn as sns

## 导入决策树模型函数
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
import pydotplus 
from Ipython.display import Image
##Demo演示DecisionTree分类
## 构造数据集
x_fearures = np.array([[-1, -2], [-2, -1], [-3, -2], [1, 3], [2, 1], [3, 2]])
y_label = np.array([0, 1, 0, 1, 0, 1])
## 调用决策树回归模型
tree_clf = DecisionTreeClassifier()
## 调用决策树模型拟合构造的数据集
tree_clf = tree_clf.fit(x_fearures, y_label)
## 可视化构造的数据样本点
plt.figure()
plt.scatter(x_fearures[:,0],x_fearures[:,1], c=y_label, s=50, cmap='viridis')
plt.title('Dataset')
plt.show()
## 可视化决策树
import graphviz
dot_data = tree.export_graphviz(tree_clf, out_file=None)
graph = pydotplus.graph_from_dot_data(dot_data)
graph.write_pdf("D:\Python\ML\DecisionTree.pdf") 
# 模型预测
## 创建新样本
x_fearures_new1 = np.array([[0, -1]])
x_fearures_new2 = np.array([[2, 1]])

## 在训练集和测试集上分布利用训练好的模型进行预测
y_label_new1_predict = tree_clf.predict(x_fearures_new1)
y_label_new2_predict = tree_clf.predict(x_fearures_new2)

print('The New point 1 predict class:\n',y_label_new1_predict)
print('The New point 2 predict class:\n',y_label_new2_predict)