12.3.10.4.6. Grouping 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	1.637018	-0.095788	2.347225	-0.154849
1	-1.465488	-0.216412	-0.347421	0.658839
2	-0.730726	-1.934136	-0.064249	0.292632
3	-0.306315	1.245162	-1.301430	-0.520355
4	0.110070	0.442971	-1.458418	-0.524914
5	-2.091738	0.100677	0.469029	-0.941721
6	-0.317765	-0.699475	-0.270448	0.623718
7	0.167101	-0.670248	-1.233412	-0.410496
8	1.568575	1.643292	0.807052	-0.520182
9	0.014365	-0.772688	0.237279	-0.283754

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()

	C	D
A
bar	3.415306	1.891978
foo	1.344929	2.036847

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

		C	D
A	B
bar	one	1.162646	1.264296
	three	2.278214	0.676291
	two	-0.025555	-0.048609
foo	one	3.349957	0.085027
	three	-0.072058	0.578082
	two	-1.932971	1.373738