def numeric_to_buckets(df, column_name):
median = df[column_name].median()
for i, val in enumerate(df[column_name]):
    if val >= median:
        df.loc[i, column_name] = 'high'
    else:
        df.loc[i, column_name] = 'low' 
for feature in df.columns[:-1]:
numeric_to_buckets(df, feature)
print(df.groupby(feature).quality.mean(), '\n')

字符串

我不知道你到底想做什么，但是，据我所知，你可以尝试这样的事情：

import pandas as pd 
from statistics import mean
df = pd.DataFrame({'alcohol':[45, 88, 56, 15, 71], 'pH':[12, 83, 56, 25,71],'residual_sugar':[14, 25, 55, 8, 21]}) 
print(df)
#Output
>>> alcohol  pH  residual_sugar
0      45    12   14
1      88    83   25
2      56    56   55
3      15    25    8
4      71    71   21

def func(colum):
    dftemp=df.copy()
    median_colum = eval('df.'+colum).median()
    for i, item in enumerate(eval('df.'+colum)):
        dftemp.loc[i, colum] = 'high' if item >= median_colum else 'low'
    return dftemp.groupby(colum).agg(list).applymap(mean)
    
    
differentarrays = [func(i) for i in df.columns]
for array in differentarrays:
    print(array)

字符串
输出量：

pH  residual_sugar
alcohol                      
high     70.0       33.666667
low      18.5       11.000000 

        alcohol  residual_sugar
pH                             
high  71.666667       33.666667
low   30.000000       11.000000 

                  alcohol    pH
residual_sugar                 
high            71.666667  70.0
low             30.000000  18.5

型

看起来你要找的是np.where，一个沿着

pd.DataFrame(np.where(df > df.median(), "high", "low"))

字符串