sklearn决策树实战案例

sklearn决策树实战案例

#全部行都能输出
from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "all"

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
plt.style.use('seaborn')

plt.rcParams['axes.unicode_minus']=False    #设置显示中文后,负号显示受影响。解决坐标轴上乱码问题
plt.rcParams['font.family'] = ['Arial Unicode MS'] #mac用解决中文显示问题

读入数据train.csv
df=pd.read_csv(r"/Users/liuzeming/Desktop/python/机器学习/练习/train.csv")
df

# 查看数据的信息
df.info
# 提取特征和标签
df1=df.drop(['客户ID','y'],axis=1)
df1
X=df1
X
y=df['y']

# 查看样本是否均衡
y.value_counts()