12.3.10.4.5. Merge data

import pandas as pd
import numpy as np

Concat

Create a dataFrame

dataFrame = pd.DataFrame(np.random.randn(10, 4))

break in pieces

pieces = [dataFrame[:3], dataFrame[3:7], dataFrame[7:]]

pd.concat(pieces)

	0	1	2	3
0	-0.381824	-0.615609	0.353890	0.073478
1	-0.627941	0.523366	0.763896	-0.858404
2	1.434160	0.695704	0.295234	0.947809
3	-0.318871	-0.470462	-0.500630	-1.794801
4	-1.053845	0.739370	-2.324050	0.441212
5	0.585735	1.022914	0.216315	0.836352
6	-0.770376	-2.096072	0.205964	-0.445026
7	-0.081697	-0.005139	0.267725	-0.149331
8	0.386357	0.231614	1.104906	2.569610
9	0.119584	-1.526672	0.358645	-0.081198

Join

left = pd.DataFrame({"key": ["foo", "foo"], "lval": [1, 2]})
right = pd.DataFrame({"key": ["foo", "foo"], "rval": [4, 5]})

pd.merge(left, right, on="key")

	key	lval	rval
0	foo	1	4
1	foo	1	5
2	foo	2	4
3	foo	2	5

Grouping

dataFrame = pd.DataFrame(
    {
        "A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"],
        "B": ["one", "one", "two", "three", "two", "two", "one", "three"],
        "C": np.random.randn(8),
        "D": np.random.randn(8),
    }
)
dataFrame.groupby("A").sum()

	B	C	D
A
bar	onethreetwo	-0.312961	0.144192
foo	onetwotwoonethree	-1.740804	-0.837059

dataFrame.groupby(["A", "B"]).sum()

		C	D
A	B
bar	one	0.096750	0.952195
	three	0.157577	-0.027870
	two	-0.567287	-0.780133
foo	one	0.448194	-0.132610
	three	0.652331	0.879493
	two	-2.841329	-1.583942