我在下面有一个数据帧,并尝试创建三个更大,更小和计数的新列。 条件是计算多少值大于/小于平均值并将它们相加。
df =
APPL Std_1 Std_2 Std_3 Mean
0 ACCMGR 106.8754 130.1600 107.1861 114.750510
1 ACCOUNTS 121.7034 113.4927 114.5482 116.581458
2 AUTH 116.8585 112.4487 115.2700 114.859050
def make_count(comp_cols, mean_col):
count_d = {'greater': 0, 'less': 0}
for col in comp_cols:
if col > mean_col:
count_d['greater'] += 1
elif col < mean_col:
count_d['less'] += 1
return count_d['greater'], count_d['less'], (count_d['greater'] + count_d['less'])
def apply_make_count(df):
a,b,c,*d= df.apply(lambda row: make_count([row['Std_1'], row['Std_2'], row['Std_3']], row['Mean of Std']), axis=1)
df['greater'],df['less'],df['count']=a,b,c
apply_make_count(df)
但是我得到了错误显示:
13 df['greater'],df['less'],df['count']=list(zip(a,b,c))
ValueError: Length of values does not match length of index
输出我想成为
df =
APPL Std_1 Std_2 Std_3 Mean greater less count
0 ACCMGR 106.8754 130.1600 107.1861 114.750510 1 2 3
1 ACCOUNTS 121.7034 113.4927 114.5482 116.581458 1 2 3
2 AUTH 116.8585 112.4487 115.2700 114.859050 2 1 3
尝试
df['greater'] = (df.iloc[:, 1:4].values > df[['Mean']].values).sum(axis=1)
df['less'] = (df.iloc[:, 1:4].values < df[['Mean']].values).sum(axis=1)
df['count'] = df.iloc[:, 1:4].count(1)
APPL Std_1 Std_2 Std_3 Mean greater less count
0 ACCMGR 106.8754 130.1600 107.1861 114.750510 1 2 3
1 ACCOUNTS 121.7034 113.4927 114.5482 116.581458 1 2 3
2 AUTH 116.8585 112.4487 115.2700 114.859050 2 1 3
似乎你只需要
sub_df = df[['Std_1', 'Std_2', 'Std_3']]
df['greater'] = sub_df.gt(df.Mean.values).sum(1) # same as (sub_df > df.Mean.values).sum(1)
df['less'] = sub_df.lt(df.Mean.values).sum(1)
df['count'] = sub_df.count(1)
APPL Std_1 Std_2 Std_3 Mean greater less count
0 ACCMGR 106.8754 130.1600 107.1861 114.750510 1 2 3
1 ACCOUNTS 121.7034 113.4927 114.5482 116.581458 1 2 3
2 AUTH 116.8585 112.4487 115.2700 114.859050 2 1 3