SoLiXG:Greece’s recovery and resilience plan

Word frequencies

Script

<syntaxhighlight lang="python">

import re

from wordfreq import word_frequency

# this is a script to find the most frequent words in a textfile

lines = open('gr-policy.txt', 'r')

text=lines.read()

text_list=text.replace('\n', ' ').split(".")

# text_list=text_first.replace('(', ' ')

lines.close()

sep_words=[]

new_list=[]

all_freq={}

frequency={}

with open("output.txt", "a") as f:

   for l in text_list:

       for w in l.split():

           sep_words.append(w)

   for word in sep_words:

       freq = sep_words.count(word)

       frequency={word:freq}

       all_freq.update(frequency)    

           # all_freq.append(frequency)

   new_list=sorted(all_freq.items(), key=lambda item: item[1], reverse=True )

   print(*new_list, sep = "\n", file=f)

</syntaxhighlight>