In [22]:

    

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import statsmodels.api as sm
import seaborn as sns
sns.set_style("darkgrid")
import sklearn.linear_model
import datetime

%matplotlib inline


    

In [2]:

    

df = pd.read_csv('~/Downloads/all-content.csv')


    

In [3]:

    

df.head()


    

    
Out[3]:






  

    

      

      
Publisher
      
Title
      
Url
      
Published
      
Page Views
      
Uniques
      
Total Engaged Time
      
Avg Engaged Time
      
Social Actions
      
Social Referrals
      
...
      
Sharethrough Paid Desktop Referrals
      
Amplify Paid Referrals
      
Amplify Paid Mobile Referrals
      
Amplify Paid Tablet Referrals
      
Amplify Paid Desktop Referrals
      
Gravity Paid Referrals
      
Gravity Paid Mobile Referrals
      
Gravity Paid Tablet Referrals
      
Gravity Paid Desktop Referrals
      
Nativo Paid Referrals
    
  
  

    

      
0
      
Atlas Obscura
      
The Famous Photo of Chernobyl's Most Dange...
      
http://www.atlasobscura.com/articles/the-famou...
      
2016-01-25T00:30:00
      
678116
      
593158.0
      
155172300000
      
228.828549
      
26930
      
476363
      
...
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
    
    

      
1
      
Atlas Obscura
      
How Capicola Became Gabagool: The Italian New ...
      
http://www.atlasobscura.com/articles/how-capic...
      
2015-11-05T16:40:00
      
667305
      
545155.0
      
190769270000
      
285.880175
      
201909
      
443247
      
...
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
    
    

      
2
      
Atlas Obscura
      
Fascinating Photos from the Secret Trash Colle...
      
http://www.atlasobscura.com/articles/fascinati...
      
2016-03-17T15:25:00
      
380902
      
349447.0
      
50527410000
      
132.651994
      
59595
      
287620
      
...
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
    
    

      
3
      
Atlas Obscura
      
C.S. Lewis Greatest Fiction: Convincing Ameri...
      
http://www.atlasobscura.com/articles/cs-lewis-...
      
2015-12-03T12:47:00
      
344742
      
314081.0
      
61664380000
      
178.871098
      
97963
      
261005
      
...
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
    
    

      
4
      
Atlas Obscura
      
How Miracle Max Nearly Shut Down 'The Prin...
      
http://www.atlasobscura.com/articles/how-mirac...
      
2015-09-25T15:00:00
      
344233
      
314316.0
      
51442570000
      
149.441134
      
14467
      
204406
      
...
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
      
0
    
  

5 rows × 115 columns

In [4]:

    

places = df[df['Url'].str.contains('/places/')==True]


    

In [10]:

    

places_traffic = places[['Title','Published','Page Views','FaceBook Referrals','Pinterest Referrals','Search Referrals']]


    

In [11]:

    

places_traffic.head()


    

    
Out[11]:






  

    

      

      
Title
      
Published
      
Page Views
      
FaceBook Referrals
      
Pinterest Referrals
      
Search Referrals
    
  
  

    

      
5
      
Kentucky Bend
      
2015-09-16T15:00:00
      
257638
      
201893
      
9
      
550
    
    

      
17
      
Mystery Soda Machine
      
2015-12-23T15:00:00
      
133317
      
92055
      
21
      
8414
    
    

      
45
      
Long Lines Building, 33 Thomas Street
      
2015-09-01T15:00:00
      
56221
      
39888
      
5
      
734
    
    

      
66
      
Inaccessible Island
      
2016-04-13T09:00:00
      
42090
      
33775
      
1
      
38
    
    

      
136
      
Fuggerei
      
2015-08-20T15:00:00
      
32408
      
15815
      
12
      
1991
    
  

In [14]:

    

articles = df[df['Url'].str.contains('/articles/')==True]


    

In [15]:

    

articles_traffic = articles[['Title','Published','Page Views','FaceBook Referrals','Pinterest Referrals','Search Referrals']]


    

In [17]:

    

articles_traffic = articles_traffic.set_index('Published')
places_traffic = places_traffic.set_index('Published')


    

In [28]:

    

datetime.date.today()


    

    
Out[28]:





datetime.date(2016, 5, 25)

In [29]:

    

sum(places['FaceBook Referrals'])/len(places.Title)


    

    
Out[29]:





883

In [34]:

    

places_traffic = places_traffic[places_traffic['Search Referrals']>10]
places_traffic.describe()


    

    
Out[34]:






  

    

      

      
Page Views
      
FaceBook Referrals
      
Pinterest Referrals
      
Search Referrals
    
  
  

    

      
count
      
1041.000000
      
1041.000000
      
1041.000000
      
1041.000000
    
    

      
mean
      
4007.038425
      
1226.681076
      
1.512968
      
100.198847
    
    

      
std
      
11344.133195
      
7182.029749
      
4.161416
      
381.319089
    
    

      
min
      
209.000000
      
0.000000
      
0.000000
      
11.000000
    
    

      
25%
      
1289.000000
      
60.000000
      
0.000000
      
24.000000
    
    

      
50%
      
2118.000000
      
359.000000
      
0.000000
      
41.000000
    
    

      
75%
      
3954.000000
      
1003.000000
      
1.000000
      
73.000000
    
    

      
max
      
257638.000000
      
201893.000000
      
60.000000
      
8414.000000
    
  

In [35]:

    

articles_traffic = articles_traffic[articles_traffic['Search Referrals']>10]
articles_traffic.describe()


    

    
Out[35]:






  

    

      

      
Page Views
      
FaceBook Referrals
      
Pinterest Referrals
      
Search Referrals
    
  
  

    

      
count
      
1885.000000
      
1885.000000
      
1885.000000
      
1885.000000
    
    

      
mean
      
13109.864721
      
5163.321485
      
3.811671
      
301.507692
    
    

      
std
      
32724.973584
      
20117.220306
      
22.895221
      
1237.795723
    
    

      
min
      
265.000000
      
0.000000
      
0.000000
      
11.000000
    
    

      
25%
      
2797.000000
      
467.000000
      
0.000000
      
46.000000
    
    

      
50%
      
5743.000000
      
1264.000000
      
0.000000
      
101.000000
    
    

      
75%
      
11851.000000
      
3697.000000
      
2.000000
      
233.000000
    
    

      
max
      
678116.000000
      
454110.000000
      
732.000000
      
27668.000000
    
  

In [62]:

    

fig, axes = plt.subplots(nrows=2,ncols=2,sharey='row',figsize=(10,10))
axes[0,0].set_title('Places')
axes[0,1].set_title('Articles')
places_traffic.boxplot('FaceBook Referrals',showfliers=False,ax=axes[0,0])
places_traffic.boxplot('Search Referrals',showfliers=False,ax=axes[1,0])
articles_traffic.boxplot('FaceBook Referrals',showfliers=False,ax=axes[0,1])
articles_traffic.boxplot('Search Referrals',showfliers=False,ax=axes[1,1])


    

    




/Users/Mike/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:4: FutureWarning: 
The default value for 'return_type' will change to 'axes' in a future release.
 To use the future behavior now, set return_type='axes'.
 To keep the previous behavior and silence this warning, set return_type='dict'.
/Users/Mike/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:5: FutureWarning: 
The default value for 'return_type' will change to 'axes' in a future release.
 To use the future behavior now, set return_type='axes'.
 To keep the previous behavior and silence this warning, set return_type='dict'.
/Users/Mike/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:6: FutureWarning: 
The default value for 'return_type' will change to 'axes' in a future release.
 To use the future behavior now, set return_type='axes'.
 To keep the previous behavior and silence this warning, set return_type='dict'.
/Users/Mike/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:7: FutureWarning: 
The default value for 'return_type' will change to 'axes' in a future release.
 To use the future behavior now, set return_type='axes'.
 To keep the previous behavior and silence this warning, set return_type='dict'.






    
Out[62]:





{'boxes': [<matplotlib.lines.Line2D at 0x129f0a590>],
 'caps': [<matplotlib.lines.Line2D at 0x1285a1710>,
  <matplotlib.lines.Line2D at 0x1285a1d50>],
 'fliers': [],
 'means': [],
 'medians': [<matplotlib.lines.Line2D at 0x129e493d0>],
 'whiskers': [<matplotlib.lines.Line2D at 0x127f20590>,
  <matplotlib.lines.Line2D at 0x127f34990>]}






    

In [ ]: