Reading words and printing top 10 most occurring words in descending order also list of non-repeated words.

s17q01_solution.py

''' Reading words and printing top 10 most occurring words in descending order also list of non-repeated words'''

import re

def file():
    file_path = "C:\\Users\\Ojha\\Documents\\Python exercises\\Python Scripts\\"
    file_name = "Paragraph.txt"
    return file_path, file_name

def reading_file(file_path, file_name):
    with open(file_path + file_name, 'r+') as FH:
        text = FH.read()
        text = text.lower()
        word_list = re.findall(r"[a-zA-Z]+", text, re.I)
        #text = text.split()
    return word_list

def word_occurrence_calculator(word_list):
    words = set(word_list)
    word_occurrence = dict() 
    #print(words)
    counter = 0
    for word in words:
        counter = 0
        for old in word_list:
            if word == old:
                counter += 1
        word_occurrence[word] = counter
    #print(word_occurrence)
    return word_occurrence

def occurrence_sorting(word_occurrence):
    x = sorted(word_occurrence.items(), key=lambda kv:kv[1], reverse=True)
    non_repeated = list()
    print("Top10 most occurred words are: ")
    for idx in range(10):
        print(x[idx])
    for k, v in word_occurrence.items():
        non_repeated.append(k)
    sorted_non_repeated = sorted(non_repeated)
    print("Non repeated word list: ", sorted_non_repeated)

# main starts here
if __name__ = '__main__':
    path, name = file()
    word_list = reading_file(path, name)
    word_occurrence = word_occurrence_calculator(word_list)
    occurrence_sorting(word_occurrence)