Day 5.Pandas

import pandas as pd

In [4]:

ser = pd.Series([100, 200, 300, 400, 500],[ 'tom','bob','nancy','dan', 'eric'])

ser

Out[4]:

tom      100
bob      200
nancy    300
dan      400
eric     500
dtype: int64

In [5]:

ser = pd.Series([100, 'foo', 300, 400, 500],[ 'tom','bob','nancy','dan', 'eric'])

ser

Out[5]:

tom      100
bob      foo
nancy    300
dan      400
eric     500
dtype: object

In [6]:

ser.index

Out[6]:

Index(['tom', 'bob', 'nancy', 'dan', 'eric'], dtype='object')

In [7]:

ser['nancy'] , ser.loc['nancy']

Out[7]:

(300, 300)

In [8]:

ser[['nancy', 'bob']]

Out[8]:

nancy    300
bob      foo
dtype: object

In [9]:

ser[[4, 3, 1]]

Out[9]:

eric    500
dan     400
bob     foo
dtype: object

In [10]:

ser.iloc[[4, 3, 1]]

Out[10]:

eric    500
dan     400
bob     foo
dtype: object

In [11]:

'bob' in ser #check if there is 'bob' index in serise

Out[11]:

True

In [12]:

ser * 2

Out[12]:

tom         200
bob      foofoo
nancy       600
dan         800
eric       1000
dtype: object

In [13]:

ser

Out[13]:

tom      100
bob      foo
nancy    300
dan      400
eric     500
dtype: object

In [14]:

ser[['nancy','eric',]] ** 2

Out[14]:

nancy     90000
eric     250000
dtype: object

In [15]:

d = { 'one' : pd.Series([100., 200., 300.], index=['apple', 'ball', 'clock']),
      'two' : pd.Series([111., 222., 333., 4444.], index = ['apple','ball','cerill','dancy'])}

In [16]:

d

Out[16]:

{'one': apple    100.0
 ball     200.0
 clock    300.0
 dtype: float64, 'two': apple      111.0
 ball       222.0
 cerill     333.0
 dancy     4444.0
 dtype: float64}

In [17]:

df = pd.DataFrame(d)
df

Out[17]:

	one	two
apple	100.0	111.0
ball	200.0	222.0
cerill	NaN	333.0
clock	300.0	NaN
dancy	NaN	4444.0

In [18]:

df.index

Out[18]:

Index(['apple', 'ball', 'cerill', 'clock', 'dancy'], dtype='object')

In [19]:

df.columns

Out[19]:

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

In [20]:

pd.DataFrame(d, index = [ 'dency' , 'ball' , 'apple' ])

Out[20]:

	one	two
dency	NaN	NaN
ball	200.0	222.0
apple	100.0	111.0

In [21]:

pd.DataFrame(d, index = ['dency', 'ball' ,'apple'], columns = ['two','five'])

Out[21]:

	two	five
dency	NaN	NaN
ball	222.0	NaN
apple	111.0	NaN

In [22]:

data = [{'alex' : 1, 'joe' : 2}, {'ema' : 5 , 'dora' : 10, 'alice' : 20}]

In [23]:

pd.DataFrame(data)

Out[23]:

	alex	alice	dora	ema	joe
0	1.0	NaN	NaN	NaN	2.0
1	NaN	20.0	10.0	5.0	NaN

In [24]:

pd.DataFrame(data, index = [ 'orange', 'red' ])

Out[24]:

	alex	alice	dora	ema	joe
orange	1.0	NaN	NaN	NaN	2.0
red	NaN	20.0	10.0	5.0	NaN

In [25]:

pd.DataFrame(data, columns = [ 'joe' , 'dora', 'alice'])

Out[25]:

	joe	dora	alice
0	2.0	NaN	NaN
1	NaN	10.0	20.0

In [26]:

df

Out[26]:

	one	two
apple	100.0	111.0
ball	200.0	222.0
cerill	NaN	333.0
clock	300.0	NaN
dancy	NaN	4444.0

In [27]:

df['one']

Out[27]:

apple     100.0
ball      200.0
cerill      NaN
clock     300.0
dancy       NaN
Name: one, dtype: float64

In [28]:

df['three'] = df['one'] * df['two']
df

Out[28]:

	one	two	three
apple	100.0	111.0	11100.0
ball	200.0	222.0	44400.0
cerill	NaN	333.0	NaN
clock	300.0	NaN	NaN
dancy	NaN	4444.0	NaN

In [30]:

df['flag'] = df['one'] > 250
df

Out[30]:

	one	two	three	flag
apple	100.0	111.0	11100.0	False
ball	200.0	222.0	44400.0	False
cerill	NaN	333.0	NaN	False
clock	300.0	NaN	NaN	True
dancy	NaN	4444.0	NaN	False

In [35]:

three = df.pop('three')

In [34]:

three

Out[34]:

apple     11100.0
ball      44400.0
cerill        NaN
clock         NaN
dancy         NaN
Name: three, dtype: float64

In [37]:

del df['two']

In [39]:

df.insert(2, 'copy_of_one', df['one'])
df

Out[39]:

	one	flag	copy_of_one
apple	100.0	False	100.0
ball	200.0	False	200.0
cerill	NaN	False	NaN
clock	300.0	True	300.0
dancy	NaN	False	NaN

In [40]:

df['one_upper_half'] = df['one'][:2]
df

Out[40]:

	one	flag	copy_of_one	one_upper_half
apple	100.0	False	100.0	100.0
ball	200.0	False	200.0	200.0
cerill	NaN	False	NaN	NaN
clock	300.0	True	300.0	NaN
dancy	NaN	False	NaN	NaN

In [ ]: