pandas-1118-02

import pandas as pd
import numpy as np

s = pd.Series(np.random.randn(5), index=list("abcde"))
s

a    0.635448
b   -0.010749
c    0.283827
d   -1.205425
e    0.278554
dtype: float64

s.index

Index(['a', 'b', 'c', 'd', 'e'], dtype='object')

s.index.name = "aaaa"

s

aaaa
a    0.635448
b   -0.010749
c    0.283827
d   -1.205425
e    0.278554
dtype: float64

df = pd.DataFrame(np.random.randn(4,3), columns=["one","two","three"])
df

	one	two	three
0	1.230136	-0.014690	0.309240
1	0.814500	0.439564	-0.367011
2	-0.457673	-0.522634	1.284895
3	0.359858	-1.525145	-2.300325

df.columns

Index(['one', 'two', 'three'], dtype='object')

df.index.name = "row"
df.columns.name = "col"

df

col	one	two	three
row
0	1.230136	-0.014690	0.309240
1	0.814500	0.439564	-0.367011
2	-0.457673	-0.522634	1.284895
3	0.359858	-1.525145	-2.300325

s = pd.Series(np.arange(6), index=list("abcbda"))
s

a    0
b    1
c    2
b    3
d    4
a    5
dtype: int32

s["a"]

a    0
a    5
dtype: int32

s["c"]

2

s.index.is_unique

False

s.index.unique()

Index(['a', 'b', 'c', 'd'], dtype='object')

s.groupby(s.index).sum()

a    5
b    4
c    2
d    4
dtype: int32

s.groupby(s.index).first()

a    0
b    1
c    2
d    4
dtype: int32

s.groupby(s.index).mean()

a    2.5
b    2.0
c    2.0
d    4.0
dtype: float64

a = [["a","a","a","b","b","c","c"], [1,2,3,1,2,2,3]]
t = list(zip(*a))
t

[('a', 1), ('a', 2), ('a', 3), ('b', 1), ('b', 2), ('c', 2), ('c', 3)]

index = pd.MultiIndex.from_tuples(t, names=["level1","level2"])
index

MultiIndex(levels=[['a', 'b', 'c'], [1, 2, 3]],
           labels=[[0, 0, 0, 1, 1, 2, 2], [0, 1, 2, 0, 1, 1, 2]],
           names=['level1', 'level2'])

s = pd.Series(np.random.randn(7),index=index)
s

level1  level2
a       1        -2.474161
        2         1.143163
        3         1.250040
b       1         0.871456
        2         1.106340
c       2        -0.651479
        3         1.326582
dtype: float64

s["b"]

level2
1    0.871456
2    1.106340
dtype: float64

s["b":"c"]

level1  level2
b       1         0.871456
        2         1.106340
c       2        -0.651479
        3         1.326582
dtype: float64

s[["a","c"]]

level1  level2
a       1        -2.474161
        2         1.143163
        3         1.250040
c       2        -0.651479
        3         1.326582
dtype: float64

s[:, 2]

level1
a    1.143163
b    1.106340
c   -0.651479
dtype: float64

df = pd.DataFrame(np.random.randint(1,10,(4,3)),
                 index=[["a","a","b","b"],[1,2,1,2]],
                 columns=[["one","one","two"],["blue","red","blue"]])
df.index.names=["row-1","row-2"]
df.columns.names=["col-1","col-2"]

df

	col-1	one		two
	col-2	blue	red	blue
row-1	row-2
a	1	2	2	9
	2	4	8	6
b	1	7	4	6
	2	1	6	3

df.loc["a"]

col-1	one		two
col-2	blue	red	blue
row-2
1	2	2	9
2	4	8	6

df.loc["a",1]

col-1  col-2
one    blue     2
       red      2
two    blue     9
Name: (a, 1), dtype: int32

df2 = df.swaplevel("row-1","row-2")
df2

	col-1	one		two
	col-2	blue	red	blue
row-2	row-1
1	a	2	2	9
2	a	4	8	6
1	b	7	4	6
2	b	1	6	3

df2.sortlevel(0)

	col-1	one		two
	col-2	blue	red	blue
row-2	row-1
1	a	2	2	9
	b	7	4	6
2	a	4	8	6
	b	1	6	3

df.sum(level=0)

col-1	one		two
col-2	blue	red	blue
row-1
a	6	10	15
b	8	10	9

df.sum(level=1)

col-1	one		two
col-2	blue	red	blue
row-2
1	9	6	15
2	5	14	9

df = pd.DataFrame({
    "a":range(7),
    "b":range(7,0,-1),
    "c":["one","one","one","two","two","two","two"],
    "d":[0,1,2,0,1,2,3]
})
df

	a	b	c	d
0	0	7	one	0
1	1	6	one	1
2	2	5	one	2
3	3	4	two	0
4	4	3	two	1
5	5	2	two	2
6	6	1	two	3

df.set_index("c")

	a	b	d
c
one	0	7	0
one	1	6	1
one	2	5	2
two	3	4	0
two	4	3	1
two	5	2	2
two	6	1	3

df2 = df.set_index(["c","d"])
df2

		a	b
c	d
one	0	0	7
	1	1	6
	2	2	5
two	0	3	4
	1	4	3
	2	5	2
	3	6	1

df2.reset_index()

	c	d	a	b
0	one	0	0	7
1	one	1	1	6
2	one	2	2	5
3	two	0	3	4
4	two	1	4	3
5	two	2	5	2
6	two	3	6	1