In [1]:

    

import os
from gensim import corpora, models, similarities


lsi_matsim_fname="lsi-matsim.save"
matsim = similarities.MatrixSimilarity.load(lsi_matsim_fname)


    

In [4]:

    

import pandas as pd
df=pd.read_csv("db-readability-length.csv",index_col=0)


    

In [5]:

    

df.head(1)


    

    
Out[5]:







  

    

      

      
Readability
      
Length
    
    

      
post id
      

      

    
  
  

    

      
0
      
11.6
      
57
    
  

In [9]:

    

df.loc[0,'Readability']


    

    
Out[9]:





11.6

In [7]:

    

#forum_sources=["http://www.medhelp.org",
#      ]

df = pd.read_csv("articles-n-forums-posts.csv")
df['source'].unique()


    

    
Out[7]:





array(['https://www.autismparentingmagazine.com/',
       'http://ehealthforum.com', 'http://www.medhelp.org',
       'http://www.reditt.com'], dtype=object)

In [ ]:

    

array(['https://www.autismparentingmagazine.com/',
forum_sources=['http://ehealthforum.com', 
               'http://www.medhelp.org',
               'http://www.reditt.com']


    

In [ ]: