groupby in pandas
>>> df = pd.DataFrame({'Animal': ['Falcon', 'Falcon',
... 'Parrot', 'Parrot'],
... 'Max Speed': [380., 370., 24., 26.]})
>>> df
Animal Max Speed
0 Falcon 380.0
1 Falcon 370.0
2 Parrot 24.0
3 Parrot 26.0
>>> df.groupby(['Animal']).mean()
Max Speed
Animal
Falcon 375.0
Parrot 25.0Groups the DataFrame using the specified columns
# Groups the DataFrame using the specified columns
df.groupBy().avg().collect()
# [Row(avg(age)=3.5)]
sorted(df.groupBy('name').agg({'age': 'mean'}).collect())
# [Row(name='Alice', avg(age)=2.0), Row(name='Bob', avg(age)=5.0)]
sorted(df.groupBy(df.name).avg().collect())
# [Row(name='Alice', avg(age)=2.0), Row(name='Bob', avg(age)=5.0)]
sorted(df.groupBy(['name', df.age]).count().collect())
# [Row(name='Alice', age=2, count=1), Row(name='Bob', age=5, count=1)]Pandas groupby
>>> emp.groupby(['dept', 'gender']).agg({'salary':'mean'}).round(-3)groupby
df['frequency'] = df['county'].map(df['county'].value_counts())
county frequency
1 N 5
2 N 5
3 C 1
4 N 5
5 S 1
6 N 5
7 N 5pandas group by column
>> df = pd.read_excel(r"C:path_to_filedataset_test.xlsx")
>> print(df)
'''
name number
0 p1 64
1 p2 98
2 p1 93
3 p2 57
4 p1 89
5 p2 83
6 p1 58
7 p2 73
8 p1 64
9 p2 24
'''
>> data = df.groupby("name").number.apply(list)
>> print(data)
'''
name
p1 [64, 93, 89, 58, 64]
p2 [98, 57, 83, 73, 24]
Name: number, dtype: object
'''
>> print(data.p1)
'''
[64, 93, 89, 58, 64]
'''Copyright © 2021 Codeinu
Forgot your account's password or having trouble logging into your Account? Don't worry, we'll help you to get back your account. Enter your email address and we'll send you a recovery link to reset your password. If you are experiencing problems resetting your password contact us
