Series DS



In [3]:

    
import pandas as pd
import numpy as np



In [3]:

    
pd.Series?



In [4]:

    
animals=['lion','tiger','cat']
pd.Series(animals)









    Out[4]:





0     lion
1    tiger
2      cat
dtype: object



In [5]:

    
numbers=[1,2,3]
pd.Series(numbers)









    Out[5]:





0    1
1    2
2    3
dtype: int64



In [7]:

    
##Handle missing data
animals=['lion','tiger',None,'man']
pd.Series(animals)









    Out[7]:





0     lion
1    tiger
2     None
3      man
dtype: object



In [20]:

    
##In the above case dtype was object however in case of int/float it will be different
##It is NaN and NaN is not same as None
numbers=[1,2,None,4,8]
a=pd.Series(numbers)



In [21]:

    
np.isnan(np.nan)









    Out[21]:





True



In [24]:

    
a.index









    Out[24]:





RangeIndex(start=0, stop=5, step=1)



In [26]:

    
namesRollNUmbers={1:"a",2:"b",3:""}



In [28]:

    
b=pd.Series(namesRollNUmbers)
b.index









    Out[28]:





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



In [37]:

    
c=pd.Series(['India','Pakistan','Bhutan'],index=['Delhi','Islamabad','Thimpu'])
#c=pd.Series(['India','Pakistan','Bhutan'],index=['Delhi','Islamabad','Thimpu','Mombasa'])
a=pd.Series(c,index=['Delhi','Thimpu','Mumbai'])
a.index
a









    Out[37]:





Delhi      India
Thimpu    Bhutan
Mumbai       NaN
dtype: object

Querying Series



In [40]:

    
animals={'India':'Tiger','USA':'Bald Eagle','UK':'Swan','Africa':'Lion'}
animals=pd.Series(animals)



In [47]:

    
##To retrieve data with location number
animals.iloc[0]









    Out[47]:





'Lion'



In [50]:

    
##Retrieve data with key
animals.loc['USA']









    Out[50]:





'Bald Eagle'



In [53]:

    
##See how the below lines beahave, its so different from Java where encapsultion is important
print(animals[0])
print(animals['USA'])









    



Lion
Bald Eagle



In [ ]:

    
#If both keys and location are numbers the what??

primenumbers={1:2,2:3,3:5,4:7}
primenumbers=pd.Series(primenumbers)
print(primenumbers[2])
primenumbers.iloc[2]



In [68]:

    
numbers=[100,102,34,45]
numbers=pd.Series(numbers)



In [70]:

    
s=0
for i in numbers:
    s+=i
s









    Out[70]:





281



In [71]:

    
np.sum(numbers)









    Out[71]:





281



In [ ]:

    
##Which of the above sums is faster???

s=pd.Series(np.random.randint(0,100,1000))
s.head()



In [ ]:

    
%%timeit -n 100
p=0
for i in s:
    p+=i
p



In [ ]:

    
%%timeit -n 100
p=np.sum(s)



In [ ]:

    
##Say you want to add 2 to all numbers in your series
##Instead of looping thorugh you can do this directly and its faster

print(s.head())
s+=2
s.head()



In [ ]:

    
for label,value in s.iteritems():
    s.set_value(label,value+2)
s.head()



In [ ]:

    
%%timeit -n 100
s = pd.Series(np.random.randint(0,1000,10000))
for label, value in s.iteritems():
    s.loc[label]= value+2



In [ ]:

    
%%timeit -n 100
s = pd.Series(np.random.randint(0,1000,10000))
for label, value in s.iteritems():
    s.loc[label]= value+2



In [ ]:



In [ ]: