机器学习—决策树

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from sklearn import metrics
%matplotlib inline

#载入数据
iris = load_iris()
x = iris.data
y = iris.target
x_train,x_test,y_train,y_test = train_test_split(x,y,train_size=0.7,random_state=0)
#数据处理
sc = StandardScaler()
x_train_std = sc.fit_transform(x_train)
x_test_std = sc.transform(x_test)
#建立模型
dt = DecisionTreeClassifier(criterion=‘entropy‘,max_depth=3)  #先设置一个三层的决策树,设置划分标准为信息增益
dt.fit(x_train_std,y_train)
y_pred = dt.predict(x_test_std)
accuracy = metrics.accuracy_score(y_test,y_pred)
accuracy

#决策树输出到pdf
from sklearn import tree
import graphviz
dot_data = tree.export_graphviz(dt,out_file=None)
graph = graphviz.Source(dot_data)
graph.render(‘iris‘)

#直接输出决策树
dot_data = tree.export_graphviz(dt, out_file=None, 
                         feature_names=iris.feature_names,  
                         class_names=iris.target_names,  
                         filled=True, rounded=True,  
                         special_characters=True)  
graph = graphviz.Source(dot_data)  
graph 

#分类效果画图出来,只选择其中两个变量做图
x = iris.data
x = x[:,:2]
y = iris.target
M,N = 500,500
x1_min,x1_max = x[:,0].min(),x[:,0].max()
x2_min,x2_max = x[:,1].min(),x[:,1].max()
t1 = np.linspace(x1_min,x1_max,M)
t2 = np.linspace(x2_min,x2_max,N)
x1,x2 = np.meshgrid(t1,t2)
x_test = np.stack((x1.flat,x2.flat),axis=1)
dt = DecisionTreeClassifier(max_depth=3)
dt.fit(x,y)
y_show = dt.predict(x_test)
y_show = y_show.reshape(x1.shape)
fig = plt.figure(figsize=(10,6),facecolor=‘w‘)
plt.contourf(x1,x2,y_show,alpha=0.5)
plt.scatter(x[:,0],x[:,1],c = y.ravel(),alpha=0.8)
plt.xlim(x1_min,x1_max)
plt.ylim(x2_min,x2_max)

#不同深度的树，对预测结果的好坏
x = iris.data
x = x[:,:2]
y = iris.target
x_train,x_test,y_train,y_test = train_test_split(x,y,train_size=0.7,random_state=1)
sc = StandardScaler()
x_train_std = sc.fit_transform(x_train)
x_test_std = sc.transform(x_test)
err_list = []
for depth in range(1,15):
    dt = DecisionTreeClassifier(max_depth=depth)
    dt.fit(x_train_std,y_train)
    y_pred = dt.predict(x_test_std)
    print(‘深度是%s的准确率是%.2f%%‘%(depth,metrics.accuracy_score(y_test,y_pred)*100))
    err_list.append(metrics.accuracy_score(y_test,y_pred))
plt.plot(range(1,15),err_list)