In [106]:

    

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


    

In [60]:

    

df = pd.read_csv('dietbet.csv')
df.dtypes
def fix_dates(x):
    return x.split(' ')[0]
df['Posted'] = df.Posted.apply(fix_dates)


    

In [61]:

    

df.drop(['Post ID','Permalink'],inplace=True,axis=1)


    

In [62]:

    

df.drop(['Countries','Languages'],inplace=True,axis=1)


    

In [63]:

    

engagement = pd.Series(df['Lifetime Engaged Users']/df['Lifetime Post Total Impressions'])
df.insert(5,'Engagement Rate',engagement)


    

In [64]:

    

def multiply_ten(x):
    return x*100
df['Engagement Rate'] = df['Engagement Rate'].apply(multiply_ten)


    

In [65]:

    

df.drop(['Lifetime Average time video viewed':],axis=1,inplace=True)


    

    




  File "<ipython-input-65-a08d4e9d7b63>", line 1
    df.drop(['Lifetime Average time video viewed':],axis=1,inplace=True)
                                                 ^
SyntaxError: invalid syntax

In [66]:

    

df.drop(df.columns[21:],inplace=True,axis=1)


    

In [68]:

    

length_msg = pd.Series([len(x) for x in df['Post Message']])
df.insert(0,'Message Length',length_msg)


    

In [70]:

    

df.to_csv('dietbet2.csv')
df2 = pd.read_csv('dietbet2.csv',parse_dates=True)


    

In [ ]:

    

df3 = pd.read_csv('dietbet2.csv',parse_dates=True)


    

In [113]:

    

ax = df3.boxplot(column='Lifetime Post Total Reach',by='Type')


    

In [74]:

    

df2['Posted'] = pd.to_datetime(df['Posted'])


    

In [76]:

    

df.dtypes


    

    
Out[76]:





Unnamed: 0                                                                      int64
Message Length                                                                  int64
Post Message                                                                   object
Type                                                                           object
Posted                                                                 datetime64[ns]
Audience Targeting                                                             object
Lifetime Post Total Reach                                                       int64
Engagement Rate                                                               float64
Lifetime Post organic reach                                                     int64
Lifetime Post Paid Reach                                                        int64
Lifetime Post Total Impressions                                                 int64
Lifetime Post Organic Impressions                                               int64
Lifetime Post Paid Impressions                                                  int64
Lifetime Engaged Users                                                          int64
Lifetime Post Consumers                                                         int64
Lifetime Post Consumptions                                                      int64
Lifetime Negative feedback                                                      int64
Lifetime Negative Feedback from Users                                           int64
Lifetime Post Impressions by people who have liked your Page                    int64
Lifetime Post reach by people who like your Page                                int64
Lifetime Post Paid Impressions by people who have liked your Page               int64
Lifetime Paid reach of a post by people who like your Page                      int64
Lifetime People who have liked your Page and engaged with your post             int64
dtype: object

In [82]:

    

df_freq = df2[['Posted','Lifetime Post Total Reach','Engagement Rate','Lifetime Post Consumptions']]


    

In [83]:

    

df_freq['count'] = 1


    

    




/Users/Mike/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

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

In [84]:

    

df_freq.drop('Engagement Rate',inplace=True,axis=1)


    

    




/Users/Mike/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:1: 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
  if __name__ == '__main__':

In [86]:

    

df_freq.set_index('Posted',inplace=True)
df_resample = df_freq.resample('D',how='sum')


    

    




/Users/Mike/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:2: FutureWarning: how in .resample() is deprecated
the new syntax is .resample(...).sum()
  from ipykernel import kernelapp as app

In [88]:

    

df_resample.dropna(inplace=True)


    

In [90]:

    

df_resample['Mean Reach'] = df_resample['Lifetime Post Total Reach'] / df_resample['count']
df_resample['Mean Consumption'] = df_resample['Lifetime Post Consumptions'] / df_resample['count']


    

In [94]:

    

df_resample
df_resample['Consumption Rate'] = df_resample['Mean Consumption'] / df_resample['Mean Reach']


    

In [97]:

    

df_resample.corr()


    

    
Out[97]:






  

    

      

      
Lifetime Post Total Reach
      
Lifetime Post Consumptions
      
count
      
Mean Reach
      
Mean Consumption
      
Consumption Rate
    
  
  

    

      
Lifetime Post Total Reach
      
1.000000
      
0.822745
      
0.242287
      
0.863281
      
0.753697
      
0.333010
    
    

      
Lifetime Post Consumptions
      
0.822745
      
1.000000
      
0.010129
      
0.851056
      
0.975008
      
0.663392
    
    

      
count
      
0.242287
      
0.010129
      
1.000000
      
-0.211647
      
-0.161383
      
-0.017229
    
    

      
Mean Reach
      
0.863281
      
0.851056
      
-0.211647
      
1.000000
      
0.884081
      
0.387112
    
    

      
Mean Consumption
      
0.753697
      
0.975008
      
-0.161383
      
0.884081
      
1.000000
      
0.618451
    
    

      
Consumption Rate
      
0.333010
      
0.663392
      
-0.017229
      
0.387112
      
0.618451
      
1.000000
    
  

In [98]:

    

df_resample.describe()


    

    
Out[98]:






  

    

      

      
Lifetime Post Total Reach
      
Lifetime Post Consumptions
      
count
      
Mean Reach
      
Mean Consumption
      
Consumption Rate
    
  
  

    

      
count
      
75.000000
      
75.000000
      
75.000000
      
75.000000
      
75.000000
      
75.000000
    
    

      
mean
      
3343.013333
      
117.706667
      
1.426667
      
2611.907556
      
97.564667
      
0.029437
    
    

      
std
      
2632.497712
      
180.568230
      
0.756474
      
2426.448961
      
178.371113
      
0.022312
    
    

      
min
      
86.000000
      
0.000000
      
1.000000
      
86.000000
      
0.000000
      
0.000000
    
    

      
25%
      
1646.500000
      
30.000000
      
1.000000
      
1317.500000
      
23.500000
      
0.014901
    
    

      
50%
      
2593.000000
      
59.000000
      
1.000000
      
1801.000000
      
39.000000
      
0.024898
    
    

      
75%
      
4431.000000
      
129.500000
      
2.000000
      
2651.000000
      
95.250000
      
0.034212
    
    

      
max
      
14526.000000
      
1049.000000
      
5.000000
      
14526.000000
      
1049.000000
      
0.135101
    
  

In [100]:

    

df_resample[(df_resample['count'] > 4)]


    

    
Out[100]:






  

    

      

      
Lifetime Post Total Reach
      
Lifetime Post Consumptions
      
count
      
Mean Reach
      
Mean Consumption
      
Consumption Rate
    
    

      
Posted
      

      

      

      

      

      

    
  
  

    

      
2016-01-06
      
3812.0
      
123.0
      
5.0
      
762.4
      
24.6
      
0.032267
    
  

In [107]:

    

_ = df_resample.plot(kind='scatter',x='count',y='Lifetime Post Consumptions')


    

In [ ]: