import pandas as pd
data = pd.read_excel(r'C:\Users\a\Desktop\Python\data.xlsx',index_col='序号') # index_col 指定某列为行索引
data.head()
# 将数据的类别转化为数据
data[data == '好'] = 1
data[data == '是'] = 1
data[data == '高'] = 1
data[data !=1] = -1
x = data.iloc[:,:3].values.astype(int)
y = data.iloc[:,3].values.astype(int)
# 决策树分类器
from sklearn.tree import DecisionTreeClassifier as DTC
dtc = DTC(criterion = 'entropy') #建立决策树模型,基于信息熵
dtc.fit(x,y) # 训练模型
#导入相关函数,可视化决策树。
#导出的结果是一个dot文件,需要安装Graphviz才能将它转换为pdf或png等格式。
from sklearn.tree import export_graphviz
x = pd.DataFrame(x)
from sklearn.externals.six import StringIO
x = pd.DataFrame(x)
with open("tree.dot", 'w') as f:
f = export_graphviz(dtc, feature_names = x.columns, out_file = f)