Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #!/usr/bin/env python3
- # -*- coding: utf-8 -*-
- """
- @author: rohezal
- """
- def cleanTheme(theme):
- filler_words = ["the", "and", "an", "a", "or", "is", "was", ".", "...", "!", "?", ","]
- theme = theme.lower()
- theme_as_list = theme.split(" ")
- clean_theme = ""
- for word in theme_as_list:
- if word not in filler_words:
- clean_theme = clean_theme + word + " "
- clean_theme = clean_theme.strip()
- return clean_theme
- def findSimilarThemes(new_theme, themes):
- new_theme_list = new_theme.split()
- result_list = []
- for existing_theme in themes:
- existing_theme_list = existing_theme.split()
- for word in new_theme_list:
- if word in existing_theme_list:
- result_list.append(existing_theme)
- break
- return result_list
- def checkForDuplicateTheme(new_theme, themes):
- return new_theme in themes
- suggested_themes = ["Loving the whole world", "The dog is evil", "Enough is enough", "And the world is not enough ..."]
- suggested_themes_clean = []
- for theme in suggested_themes:
- suggested_themes_clean.append(cleanTheme(theme))
- mytheme = "The world is not enough"
- clean_theme = cleanTheme(mytheme)
- matching_themes = findSimilarThemes(clean_theme,suggested_themes_clean)
- is_duplicate = checkForDuplicateTheme(clean_theme, suggested_themes_clean)
- print (clean_theme)
- print(matching_themes)
- print("Is duplicated: " + str(is_duplicate))
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement