12.3.10.4.9. Reshaping data

import pandas as pd
import numpy as np


tuples = list(
    zip(
        *[
            ["bar", "bar", "baz", "baz", "foo", "foo", "qux", "qux"],
            ["one", "two", "one", "two", "one", "two", "one", "two"],
        ]
    )
)
index = pd.MultiIndex.from_tuples(tuples, names=["first", "second"])
dataFrame = pd.DataFrame(np.random.randn(8, 2), index=index, columns=["A", "B"])
dataFrame2 = dataFrame[:4]

Stack

stacked = dataFrame2.stack()

stacked.unstack()

		A	B
first	second
bar	one	-0.554887	0.638492
	two	1.603665	1.977195
baz	one	-0.433228	0.564101
	two	0.739366	-0.816024

stacked.unstack(1)

	second	one	two
first
bar	A	-0.554887	1.603665
	B	0.638492	1.977195
baz	A	-0.433228	0.739366
	B	0.564101	-0.816024

stacked.unstack(0)

	first	bar	baz
second
one	A	-0.554887	-0.433228
	B	0.638492	0.564101
two	A	1.603665	0.739366
	B	1.977195	-0.816024

Pivot tables

dataFrame = pd.DataFrame(
    {
        "A": ["one", "one", "two", "three"] * 3,
        "B": ["A", "B", "C"] * 4,
        "C": ["foo", "foo", "foo", "bar", "bar", "bar"] * 2,
        "D": np.random.randn(12),
        "E": np.random.randn(12),
    }
)

pd.pivot_table(dataFrame, values="D", index=["A", "B"], columns=["C"])

	C	bar	foo
A	B
one	A	0.427408	0.081922
	B	0.732450	-0.332109
	C	-0.668688	-0.644812
three	A	0.975939	NaN
	B	NaN	0.025847
	C	0.445298	NaN
two	A	NaN	0.472312
	B	1.680834	NaN
	C	NaN	-1.301363

Time series

indexData = pd.date_range("1/5/2022", periods=100, freq="S")
timestamps = pd.Series(np.random.randint(0, 500, len(indexData)), index=indexData)
timestamps.resample("5Min").sum()

C:\Workspace\itom_development_VS2019_Qt5.15.2_x64\itomProject\itom\demo\python_packages\pandas\demo_reshaping.py:53: FutureWarning:

'S' is deprecated and will be removed in a future version, please use 's' instead.


2022-01-05    24493
Freq: 5min, dtype: int32

timeStempsUTC = timestamps.tz_localize("UTC")

timeStempsUTC.tz_convert("US/Eastern")

2022-01-04 19:00:00-05:00    351
2022-01-04 19:00:01-05:00     77
2022-01-04 19:00:02-05:00    269
2022-01-04 19:00:03-05:00    415
2022-01-04 19:00:04-05:00     47
                            ...
2022-01-04 19:01:35-05:00    357
2022-01-04 19:01:36-05:00    484
2022-01-04 19:01:37-05:00    162
2022-01-04 19:01:38-05:00    128
2022-01-04 19:01:39-05:00    340
Freq: s, Length: 100, dtype: int32

ps = timestamps.to_period()

ps.to_timestamp()

2022-01-05 00:00:00    351
2022-01-05 00:00:01     77
2022-01-05 00:00:02    269
2022-01-05 00:00:03    415
2022-01-05 00:00:04     47
                      ...
2022-01-05 00:01:35    357
2022-01-05 00:01:36    484
2022-01-05 00:01:37    162
2022-01-05 00:01:38    128
2022-01-05 00:01:39    340
Freq: s, Length: 100, dtype: int32

prng = pd.period_range("1990Q1", "2000Q4", freq="Q-NOV")
ts = pd.Series(np.random.randn(len(prng)), prng)
ts.index = (prng.asfreq("M", "e") + 1).asfreq("H", "s") + 9

C:\Workspace\itom_development_VS2019_Qt5.15.2_x64\itomProject\itom\demo\python_packages\pandas\demo_reshaping.py:72: FutureWarning:

'H' is deprecated and will be removed in a future version, please use 'h' instead.