Data were scraped using the DHS scraper.



In [21]:

    
import pandas as pd
import numpy as np
from IPython.core.display import display, HTML
display(HTML("<style>.container { width:100% !important; }</style>"))



In [22]:

    
old = pd.read_csv('../../data/scraped/scraped_complaints_3_25.csv')



In [23]:

    
new = pd.read_csv('../../data/scraped/scraped_complaints_4_14.csv')



In [24]:

    
new.count()[0]









    Out[24]:





6784



In [25]:

    
old.count()[0]









    Out[25]:





6758



In [26]:

    
merged = new.merge(old,how = 'left',on='abuse_number')



In [28]:

    
merged2 = new.merge(old,how = 'right',on='abuse_number')

How many new complaints were put online between 3/25 and 4/14?



In [31]:

    
merged[merged['online_incident_date_y'].isnull()].count()[0]









    Out[31]:





31



In [ ]: