import pandas as pd
pd.set_option("display.max_rows", 5)

Joins

from siuba import _, inner_join, left_join, full_join

df1 = pd.DataFrame({'id': [1,2], 'x': ['a', 'b']})
df2 = pd.DataFrame({'id': [2,2,3], 'y': ['l', 'm', 'n']})

df1

	id	x
0	1	a
1	2	b

df2

	id	y
0	2	l
1	2	m
2	3	n

⚠️Note on piping: Currently, when you use a join in a pipe, you need to pass _ as the first argument. This is because it requires two DataFrames. For single DataFrame verbs it is optional.

df1 >> inner_join(_, df2, on = "id")

	id	x	y
0	2	b	l
1	2	b	m

Inner join

inner_join(df1, df2, on = "id")

	id	x	y
0	2	b	l
1	2	b	m

Left join

left_join(df1, df2, on = "id")

	id	x	y
0	1	a	NaN
1	2	b	l
2	2	b	m

Full join

full_join(df1, df2, on = "id")

	id	x	y
0	1	a	NaN
1	2	b	l
2	2	b	m
3	3	NaN	n

Semi and anti join

from siuba import semi_join, anti_join

semi_join(df1, df2, on = "id")

	id	x
1	2	b

# TODO: implement
#anti_join(df1, df2, on = "id")

Edit page on github here. Interactive version: