决策树实现iris数据分类

#加载数据
import pandas as pd
import numpy as np
data = pd.read_csv('iris_data.csv')
data.head()

#定义X,y
X = data.drop(['target','label'],axis=1)
y = data.loc[:,'label']
print(X.shape,y.shape)#打印X，y的维度

(150, 4) (150,)

#建立决策树模型
from sklearn import tree
dc_tree = tree.DecisionTreeClassifier(criterion='entropy',min_samples_leaf=5)
#决策树分裂出来的叶子最少要有5个样本，如果再往下分发现少于5个样本节点就没有必要往下分了
dc_tree.fit(X,y)

#预测和准确率
y_predict = dc_tree.predict(X)
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y,y_predict)
print(accuracy)

0.96

#绘图
%matplotlib inline
from matplotlib import pyplot as plt
fig1 = plt.figure(figsize=(10,10)   )
tree.plot_tree(dc_tree,filled="True",feature_names=['SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth'],class_names=['setosa','versicolor','virginica'])
#填充底色 分类名称 
plt.show()

尝试改变参数 min_samples_leaf=1

from sklearn import tree
dc_tree = tree.DecisionTreeClassifier(criterion='entropy',min_samples_leaf=1)
dc_tree.fit(X,y)
from matplotlib import pyplot as plt
fig1 = plt.figure(figsize=(10,10)   )
tree.plot_tree(dc_tree,filled="True",feature_names=['SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth'],class_names=['setosa','versicolor','virginica'])
plt.show()