46 python data frames part 03

In [6]:

import pandas as pd
import numpy as np
from numpy.random import randn
np.random.seed(3)
m1=randn(5,4)

In [7]:

df1=pd.DataFrame(m1,["a","b","c","d","e"],["w","x","y","z"])

In [7]:

df1

Out[7]:

	w	x	y	z
a	1.788628	0.436510	0.096497	-1.863493
b	-0.277388	-0.354759	-0.082741	-0.627001
c	-0.043818	-0.477218	-1.313865	0.884622
d	0.881318	1.709573	0.050034	-0.404677
e	-0.545360	-1.546477	0.982367	-1.101068

In [8]:

df1['w']

Out[8]:

a    1.788628
b   -0.277388
c   -0.043818
d    0.881318
e   -0.545360
Name: w, dtype: float64

In [9]:

df1

Out[9]:

	w	x	y	z
a	1.788628	0.436510	0.096497	-1.863493
b	-0.277388	-0.354759	-0.082741	-0.627001
c	-0.043818	-0.477218	-1.313865	0.884622
d	0.881318	1.709573	0.050034	-0.404677
e	-0.545360	-1.546477	0.982367	-1.101068

In [10]:

df1>0

Out[10]:

	w	x	y	z
a	True	True	True	False
b	False	False	False	False
c	False	False	False	True
d	True	True	True	False
e	False	False	True	False

In [11]:

z=df1>0

In [12]:

z

Out[12]:

	w	x	y	z
a	True	True	True	False
b	False	False	False	False
c	False	False	False	True
d	True	True	True	False
e	False	False	True	False

In [15]:

df1[z]

Out[15]:

	w	x	y	z
a	1.788628	0.436510	0.096497	NaN
b	NaN	NaN	NaN	NaN
c	NaN	NaN	NaN	0.884622
d	0.881318	1.709573	0.050034	NaN
e	NaN	NaN	0.982367	NaN

In [19]:

df1[df1<0]

Out[19]:

	w	x	y	z
a	NaN	NaN	NaN	-1.863493
b	-0.277388	-0.354759	-0.082741	-0.627001
c	-0.043818	-0.477218	-1.313865	NaN
d	NaN	NaN	NaN	-0.404677
e	-0.545360	-1.546477	NaN	-1.101068

In [20]:

df1

Out[20]:

	w	x	y	z
a	1.788628	0.436510	0.096497	-1.863493
b	-0.277388	-0.354759	-0.082741	-0.627001
c	-0.043818	-0.477218	-1.313865	0.884622
d	0.881318	1.709573	0.050034	-0.404677
e	-0.545360	-1.546477	0.982367	-1.101068

In [22]:

df1[df1["w"]>0]

Out[22]:

	w	x	y	z
a	1.788628	0.436510	0.096497	-1.863493
d	0.881318	1.709573	0.050034	-0.404677

In [45]:

df1[df1['w']>0]['y']
print(df1)

          w         x         y         z
a  1.788628  0.436510  0.096497 -1.863493
b -0.277388 -0.354759 -0.082741 -0.627001
c -0.043818 -0.477218 -1.313865  0.884622
d  0.881318  1.709573  0.050034 -0.404677
e -0.545360 -1.546477  0.982367 -1.101068

In [25]:

df1[df1['w']>0][['y','x']]

Out[25]:

	y	x
a	0.096497	0.436510
d	0.050034	1.709573

In [33]:

df1['w']>0

Out[33]:

a     True
b    False
c    False
d     True
e    False
Name: w, dtype: bool

In [34]:

bs=df1['w']>0

In [46]:

bs

Out[46]:

a     True
b    False
c    False
d     True
e    False
Name: w, dtype: bool

In [37]:

res=df1[bs]

In [47]:

res

Out[47]:

	w	x	y	z
a	1.788628	0.436510	0.096497	-1.863493
d	0.881318	1.709573	0.050034	-0.404677

In [52]:

res[["x","y"]]

Out[52]:

	x	y
a	0.436510	0.096497
d	1.709573	0.050034

In [44]:

res[['x','y']]

Out[44]:

	x	y
a	0.436510	0.096497
d	1.709573	0.050034

In [53]:

z=["x","y"]

In [54]:

res[z]

Out[54]:

	x	y
a	0.436510	0.096497
d	1.709573	0.050034

In [55]:

df1

Out[55]:

	w	x	y	z
a	1.788628	0.436510	0.096497	-1.863493
b	-0.277388	-0.354759	-0.082741	-0.627001
c	-0.043818	-0.477218	-1.313865	0.884622
d	0.881318	1.709573	0.050034	-0.404677
e	-0.545360	-1.546477	0.982367	-1.101068

In [66]:

df1[(df1["x"]>0) |(df1["y"]>0)]

Out[66]:

	w	x	y	z
a	1.788628	0.436510	0.096497	-1.863493
d	0.881318	1.709573	0.050034	-0.404677
e	-0.545360	-1.546477	0.982367	-1.101068

In [9]:

(df1["x"]>0)| (df1["y"]>0 )

Out[9]:

a     True
b    False
c    False
d     True
e     True
dtype: bool

In [63]:

(df1["x"]>0) & (df1["y"]>0 ) & (df1["z"]>0 )

Out[63]:

a    False
b    False
c    False
d    False
e    False
dtype: bool

In [64]:

df1[(df1["x"]>0) & (df1["y"]>0 ) & (df1["z"]>0 )]

Out[64]:

	w	x	y	z

In [1]:

True and True

Out[1]:

True

In [2]:

True and False

Out[2]:

False

In [3]:

True or False

Out[3]:

True

In [10]:

df1

Out[10]:

	w	x	y	z
a	1.788628	0.436510	0.096497	-1.863493
b	-0.277388	-0.354759	-0.082741	-0.627001
c	-0.043818	-0.477218	-1.313865	0.884622
d	0.881318	1.709573	0.050034	-0.404677
e	-0.545360	-1.546477	0.982367	-1.101068

In [18]:

df2.reset_index(inplace=True)

In [13]:

df2=df1

In [19]:

df2

Out[19]:

	index	w	x	y	z
0	a	1.788628	0.436510	0.096497	-1.863493
1	b	-0.277388	-0.354759	-0.082741	-0.627001
2	c	-0.043818	-0.477218	-1.313865	0.884622
3	d	0.881318	1.709573	0.050034	-0.404677
4	e	-0.545360	-1.546477	0.982367	-1.101068

In [20]:

in1=["AP","tg","ks","nk","ph"]

In [21]:

df1["states"] =in1

In [25]:

df1

Out[25]:

	index	w	x	y	z	states
0	a	1.788628	0.436510	0.096497	-1.863493	AP
1	b	-0.277388	-0.354759	-0.082741	-0.627001	tg
2	c	-0.043818	-0.477218	-1.313865	0.884622	ks
3	d	0.881318	1.709573	0.050034	-0.404677	nk
4	e	-0.545360	-1.546477	0.982367	-1.101068	ph

In [26]:

df1.set_index("states",imp)

Out[26]:

	index	w	x	y	z
states
AP	a	1.788628	0.436510	0.096497	-1.863493
tg	b	-0.277388	-0.354759	-0.082741	-0.627001
ks	c	-0.043818	-0.477218	-1.313865	0.884622
nk	d	0.881318	1.709573	0.050034	-0.404677
ph	e	-0.545360	-1.546477	0.982367	-1.101068

In [24]:

df1

Out[24]:

	index	w	x	y	z	states
0	a	1.788628	0.436510	0.096497	-1.863493	AP
1	b	-0.277388	-0.354759	-0.082741	-0.627001	tg
2	c	-0.043818	-0.477218	-1.313865	0.884622	ks
3	d	0.881318	1.709573	0.050034	-0.404677	nk
4	e	-0.545360	-1.546477	0.982367	-1.101068	ph

In [27]:

df1

Out[27]:

	index	w	x	y	z	states
0	a	1.788628	0.436510	0.096497	-1.863493	AP
1	b	-0.277388	-0.354759	-0.082741	-0.627001	tg
2	c	-0.043818	-0.477218	-1.313865	0.884622	ks
3	d	0.881318	1.709573	0.050034	-0.404677	nk
4	e	-0.545360	-1.546477	0.982367	-1.101068	ph