Key-phrase extraction and Integration in Power BI

Key-phrase extraction and Integration in Power BI

"""
@author: Jayant Kumar Kodwani
"""
# 'dataset' holds the input data for this script

import RAKE
import pandas as pd

"""Add stopwords list, REPLACE path as required"""

stop_dir = r"C:\Users\Jayant\.spyder-py3\stopwords.txt"
rake_object = RAKE.Rake(stop_dir)

"""Create a empty dataframe to store output"""

Rake_Final_Output = pd.DataFrame()

#Assign your dataset to a variable
df= dataset

def Sort_Tuple(tup):
   tup.sort(key= lambda x:x[1])
   return tup

# Loop through all the field/column values and apply RAKE
for x in range(len(df)):
   subtitles = df.Answer[x]
   print (subtitles)
   
   """Run Rake Algorithm, You can change the parameter [-1:] to get more than 1 keyphrase from the text"""
   keywords=Sort_Tuple(rake_object.run(subtitles))[-1:]     
      
    # create DataFrame using RAKE output data    
   Output = pd.DataFrame(keywords, columns =['Word', 'KeywordScore'])  

   Output['Keywords']=keywords
   Output['KeywordScore'] = Output['KeywordScore'].astype('float')

   Output['Date']=df.Date[x]
   Output['Question']=df.Question[x]
   Output['Answer']=df.Answer[x]
   Output['Index']=df.Index[x]

   Rake_Final_Output = Rake_Final_Output.append(Output, ignore_index=True)