In [34]:

    

import pandas as pd
import pip

pip.main(['install', 'xlrd'])

input_file = "input/input.xlsx"

df = pd.read_excel(input_file)
likes = df[df.TypeAction == "Like"]

likes.head()


    

    




Requirement already satisfied (use --upgrade to upgrade): xlrd in /opt/conda/lib/python3.5/site-packages






    




You are using pip version 8.1.2, however version 9.0.1 is available.
You should consider upgrading via the 'pip install --upgrade pip' command.






    
Out[34]:






  

    

      

      
Action_id
      
TypeAction
      
Page_name
      
Feed_message
      
User_name
      
CommentsForItem_message
      
Sentiment
      
Action_created_time_qvdate
    
  
  

    

      
7765
      
Like/6938264959
      
Like
      
CAPCOM
      
The team at Capcom Vancouver want to wish ever...
      
-
      
-
      
-
      
2017-01-04
    
    

      
7766
      
Like/12040282146
      
Like
      
-
      
Before it comes out, i playing all the horror ...
      
-
      
-
      
-
      
2017-01-05
    
    

      
7767
      
Like/49054165628
      
Like
      
Bandai Namco
      
Surfs up! Boruto is bringing tsunami reinforce...
      
-
      
-
      
-
      
2017-01-04
    
    

      
7768
      
Like/154718398250
      
Like
      
-
      
21 días para experimentar el miedo y el terror...
      
-
      
-
      
-
      
2017-01-04
    
    

      
7769
      
Like/285330833071
      
Like
      
-
      
Before it comes out, i playing all the horror ...
      
-
      
-
      
-
      
2017-01-05
    
  

In [36]:

    

print(likes.User_name.unique())
print(likes.CommentsForItem_message.unique())
print(likes.Sentiment.unique())


    

    




['-' 'Aaron Turness' 'Marcelo J. Biott' ..., 'Michael Tong'
 'JadieKit Louise Brown' 'Mauro Mazzariol']
['-']
['-']

In [37]:

    

# let's drop the commentsForItem and Sentiment columns, as they are empty for the likes...
likes.drop(['CommentsForItem_message', 'Sentiment'], 1,inplace=True)

# also drop the columns with no information
likes.drop(['TypeAction', 'Action_id'], 1,inplace=True)

likes.head()


    

    




/opt/conda/lib/python3.5/site-packages/ipykernel/__main__.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  from ipykernel import kernelapp as app
/opt/conda/lib/python3.5/site-packages/ipykernel/__main__.py:5: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy






    
Out[37]:






  

    

      

      
Page_name
      
Feed_message
      
User_name
      
Action_created_time_qvdate
    
  
  

    

      
7765
      
CAPCOM
      
The team at Capcom Vancouver want to wish ever...
      
-
      
2017-01-04
    
    

      
7766
      
-
      
Before it comes out, i playing all the horror ...
      
-
      
2017-01-05
    
    

      
7767
      
Bandai Namco
      
Surfs up! Boruto is bringing tsunami reinforce...
      
-
      
2017-01-04
    
    

      
7768
      
-
      
21 días para experimentar el miedo y el terror...
      
-
      
2017-01-04
    
    

      
7769
      
-
      
Before it comes out, i playing all the horror ...
      
-
      
2017-01-05
    
  

In [32]:

    

likes.describe()


    

    
Out[32]:






  

    

      

      
Page_name
      
Feed_message
      
User_name
      
Action_created_time_qvdate
    
  
  

    

      
count
      
58089
      
50987
      
58089
      
58089
    
    

      
unique
      
12
      
103
      
57090
      
7
    
    

      
top
      
Resident Evil
      
Are you afraid of the dark? Because you should...
      
-
      
2017-01-04 00:00:00
    
    

      
freq
      
28556
      
12177
      
30
      
25313
    
    

      
first
      
NaN
      
NaN
      
NaN
      
2017-01-04 00:00:00
    
    

      
last
      
NaN
      
NaN
      
NaN
      
2017-01-10 00:00:00