Answers for "sort dataframe by multiple columns"

sort dataframe by column

df.sort_values(by='col1', ascending=False)

df sort values

>>> df.sort_values(by=['col1'], ascending = False)
    col1 col2 col3
0   A    2    0
1   A    1    1
2   B    9    9
5   C    4    3
4   D    7    2
3   NaN  8    4

sort by two columns in pandas

df.sort_values(['a', 'b'], ascending=[True, False])

pandas sort columns by name

df = df.reindex(sorted(df.columns), axis=1)

dataframe groupby multiple columns

grouped_multiple = df.groupby(['Team', 'Pos']).agg({'Age': ['mean', 'min', 'max']})
grouped_multiple.columns = ['age_mean', 'age_min', 'age_max']
grouped_multiple = grouped_multiple.reset_index()
print(grouped_multiple)

Returns a new DataFrame sorted by the specified column(s)

# Returns a new DataFrame sorted by the specified column(s)

df.sort(df.age.desc()).collect()
# [Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
df.sort("age", ascending=False).collect()
# [Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
df.orderBy(df.age.desc()).collect()
# [Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
from pyspark.sql.functions import *
df.sort(asc("age")).collect()
# [Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
df.orderBy(desc("age"), "name").collect()
# [Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]
df.orderBy(["age", "name"], ascending=[0, 1]).collect()
# [Row(age=5, name=u'Bob'), Row(age=2, name=u'Alice')]