import pandas as pd
pd.set_option('display.max_columns',None)#显示所有列
data=pd.read_csv(r"C:\Users\15187\Desktop\games1.csv")
colums=["firstBlood","winner"]这里这个只是为了拿到要的数据罢了,没有多余的意思
train=data[colums]
from sklearn.model_selection import KFold
columns=["firstBlood"]#定义分组依据
lable=["winner"]#Y目标值
folds = KFold(n_splits=5,shuffle=True,random_state=2020)#5折交叉运算
aggs={}
tt=pd.DataFrame()
caculate=["count","mean"]
for col in lable:
aggs[col] = caculate
for col in columns:
i=1#指示变量,为1的时候新生成一个数据框,以后直接concat即可
for fold_,(trn_idx,val_idx) in enumerate(folds.split(train,train)):
tmp = train.iloc[trn_idx]
groupby_aim=tmp.groupby(columns).agg(aggs)
#print(groupby_aim)
if i==1:
tt=pd.DataFrame(groupby_aim)
i=2
else:
p=pd.DataFrame(groupby_aim)
tt=pd.concat([tt,p