Import commonly used modules and objects



In [1]:

    
from pandas import Series, DataFrame
import pandas as pd
import numpy as np

Let's look at some functionality of Series



In [2]:

    
s = Series([4, 7, -5, 3])
s1 = Series([4, 7, -5, 3], index=['d', 'b', 'a', 'c'])
s2 = Series([2, -9, 6, 7], index=['b', 'a', 'c', 'd'])
data = {'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000}
s3 = Series(data)



In [3]:

    
s.values









    Out[3]:





array([ 4,  7, -5,  3])



In [4]:

    
s.index









    Out[4]:





Int64Index([0, 1, 2, 3], dtype='int64')



In [7]:

    
s1['a']









    Out[7]:





-5



In [6]:

    
s[0] = 9



In [8]:

    
s1[['a', 'b', 'c']]









    Out[8]:





a   -5
b    7
c    3
dtype: int64



In [9]:

    
s > 0









    Out[9]:





0     True
1     True
2    False
3     True
dtype: bool



In [10]:

    
s[s > 0]









    Out[10]:





0    9
1    7
3    3
dtype: int64



In [11]:

    
s * 2









    Out[11]:





0    18
1    14
2   -10
3     6
dtype: int64



In [12]:

    
np.exp(s)









    Out[12]:





0    8103.083928
1    1096.633158
2       0.006738
3      20.085537
dtype: float64



In [13]:

    
'a' in s1









    Out[13]:





True



In [14]:

    
s = s.reindex([0, 1, 2, 3, 4])



In [15]:

    
s









    Out[15]:





0     9
1     7
2    -5
3     3
4   NaN
dtype: float64



In [16]:

    
s.isnull()









    Out[16]:





0    False
1    False
2    False
3    False
4     True
dtype: bool



In [17]:

    
s1 + s2









    Out[17]:





a   -14
b     9
c     9
d    11
dtype: int64



In [18]:

    
s1 * s2









    Out[18]:





a    45
b    14
c    18
d    28
dtype: int64



In [19]:

    
s1 / s2









    Out[19]:





a    0.555556
b    3.500000
c    0.500000
d    0.571429
dtype: float64

Now lets look into some DataFrame functionality



In [20]:

    
data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
'year': [2000, 2001, 2002, 2001, 2002],
'pop': [1.5, 1.7, 3.6, 2.4, 2.9]}
index=['one', 'two', 'three', 'four', 'five']
df = DataFrame(data, index=index)



In [21]:

    
df



In [22]:

    
df.columns









    Out[22]:





Index([u'pop', u'state', u'year'], dtype='object')



In [23]:

    
df['pop']









    Out[23]:





one      1.5
two      1.7
three    3.6
four     2.4
five     2.9
Name: pop, dtype: float64



In [24]:

    
df[['state', 'pop']]









    Out[24]:






  
    
      
      state
      pop
    
  
  
    
      one
      Ohio
      1.5
    
    
      two
      Ohio
      1.7
    
    
      three
      Ohio
      3.6
    
    
      four
      Nevada
      2.4
    
    
      five
      Nevada
      2.9



In [25]:

    
df.ix['one']









    Out[25]:





pop       1.5
state    Ohio
year     2000
Name: one, dtype: object



In [26]:

    
df['debt'] = np.arange(5.)
df



In [27]:

    
df.drop('five')



In [28]:

    
df.drop('debt', axis=1)



In [29]:

    
df['pop'] > 2









    Out[29]:





one      False
two      False
three     True
four      True
five      True
Name: pop, dtype: bool



In [30]:

    
df[df['pop'] > 2]

	pop	state	year
one	1.5	Ohio	2000
two	1.7	Ohio	2001
three	3.6	Ohio	2002
four	2.4	Nevada	2001
five	2.9	Nevada	2002