notebook.community

Edit and run



In [1]:

    
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

%matplotlib inline



In [3]:

    
df = pd.read_csv('~/documents/vinepair/vinepair-posts.csv',parse_dates=True,index_col=None)



In [4]:

    
df.head(1)









    Out[4]:






  
    
      
      Post ID
      Permalink
      Post Message
      Type
      Countries
      Languages
      Posted
      Audience Targeting
      Lifetime Post Total Reach
      Lifetime Post organic reach
      ...
      Lifetime Average time video viewed
      Lifetime Organic views to 95%
      Lifetime Organic views to 95%.1
      Lifetime Paid views to 95%
      Lifetime Paid views to 95%.1
      Lifetime Video length
      Lifetime Organic Video Views
      Lifetime Organic Video Views.1
      Lifetime Paid Video Views
      Lifetime Paid Video Views.1
    
  
  
    
      0
      481722305228597_1169995286401292
      https://www.facebook.com/Vinepair/posts/116999...
      Just try to keep these in your fridge ;)
      Link
      NaN
      NaN
      8/20/16 10:00 PM
      
      3880
      3880
      ...
      0
      0.0
      0.0
      0.0
      0.0
      0
      0.0
      0.0
      0.0
      0.0
    
  

1 rows × 34 columns



In [34]:

    
df['targeted'] = [1 if len(x) > 5 else 0 for x in df['Audience Targeting']]



In [36]:

    
df.targeted[30:55]









    Out[36]:





30    0
31    0
32    0
33    0
34    0
35    0
36    0
37    0
38    0
39    0
40    0
41    0
42    1
43    0
44    0
45    0
46    0
47    0
48    0
49    0
50    0
51    0
52    0
53    0
54    0
Name: targeted, dtype: int64



In [37]:

    
import seaborn as sns



In [46]:

    
df_pivoted = df[df.Type == 'Link'].pivot_table(values = 'Lifetime Post Total Reach',columns='targeted')



In [47]:

    
df_pivoted









    Out[47]:





targeted
0    7314.244589
1    4170.500000
Name: Lifetime Post Total Reach, dtype: float64



In [ ]: