Series DS



In [1]:

    
import pandas as pd
import numpy as np



In [2]:

    
pd.Series?



In [3]:

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









    Out[3]:





0     lion
1    tiger
2      cat
dtype: object



In [4]:

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









    Out[4]:





0    1
1    2
2    3
dtype: int64



In [5]:

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









    Out[5]:





0     lion
1    tiger
2     None
3      man
dtype: object



In [6]:

    
##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 [7]:

    
np.isnan(np.nan)









    Out[7]:





True



In [8]:

    
a.index









    Out[8]:





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



In [9]:

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



In [10]:

    
b=pd.Series(namesRollNUmbers)
b.index









    Out[10]:





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



In [11]:

    
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[11]:





Delhi      India
Thimpu    Bhutan
Mumbai       NaN
dtype: object

Querying Series



In [12]:

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



In [13]:

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









    Out[13]:





'Lion'



In [14]:

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









    Out[14]:





'Bald Eagle'



In [15]:

    
##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 [16]:

    
#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 [17]:

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



In [18]:

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









    Out[18]:





281



In [19]:

    
np.sum(numbers)









    Out[19]:





281



In [20]:

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

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









    Out[20]:





0    10
1    66
2    67
3    37
4     7
dtype: int64



In [21]:

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









    



100 loops, best of 3: 177 µs per loop



In [22]:

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









    



100 loops, best of 3: 46.6 µs per loop



In [23]:

    
##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()









    



0    10
1    66
2    67
3    37
4     7
dtype: int64






    Out[23]:





0    12
1    68
2    69
3    39
4     9
dtype: int64



In [24]:

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









    Out[24]:





0    14
1    70
2    71
3    41
4    11
dtype: int64



In [25]:

    
2+2









    Out[25]:





4



In [26]:

    
##Compareing the two methods of adding a numbers to all the value

%%timeit -n 10
s = pd.Series(np.random.randint(0,1000,10000))
for label, value in s.iteritems():
    s.loc[label]= value+2









    



10 loops, best of 3: 1.28 s per loop



In [27]:

    
%%timeit -n 10
s = pd.Series(np.random.randint(0,1000,10000))
s+=2









    



10 loops, best of 3: 416 µs per loop



In [30]:

    
s=pd.Series([1,2,4])
s[3]='mangesh'



In [31]:

    
s









    Out[31]:





0          1
1          2
2          4
3    mangesh
dtype: object



In [32]:

    
sports=pd.Series({"Archery":"USA","Football":"Spain","Hockey":"Canada"})



In [33]:

    
new_sports=pd.Series(["Australia","England","India","SriLanka"],index=["Cricket","Cricket","Cricket","Cricket"])



In [34]:

    
sports









    Out[34]:





Archery        USA
Football     Spain
Hockey      Canada
dtype: object



In [35]:

    
new_sports









    Out[35]:





Cricket    Australia
Cricket      England
Cricket        India
Cricket     SriLanka
dtype: object



In [36]:

    
all_sports=sports.append(new_sports)



In [37]:

    
all_sports









    Out[37]:





Archery           USA
Football        Spain
Hockey         Canada
Cricket     Australia
Cricket       England
Cricket         India
Cricket      SriLanka
dtype: object



In [38]:

    
all_sports['Cricket']









    Out[38]:





Cricket    Australia
Cricket      England
Cricket        India
Cricket     SriLanka
dtype: object



In [ ]: