Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import numpy as np
- import re
- import os
- import glob as glob
- import math
- from collections import Counter
- # Einlesen der 4 Dateien:
- txt1_file = open('C:/Users/Friedrich/Desktop/Data Science/Data-Science-Pakete in Python/Numpy Texte/Der-Prozeß.txt')
- txt1 = txt1_file.read()
- txt2_file = open('C:/Users/Friedrich/Desktop/Data Science/Data-Science-Pakete in Python/Numpy Texte/Effi-Briest.txt')
- txt2 = txt2_file.read()
- txt3_file = open('C:/Users/Friedrich/Desktop/Data Science/Data-Science-Pakete in Python/Numpy Texte/Stopfkuchen.txt')
- txt3 = txt3_file.read()
- txt4_file = open('C:/Users/Friedrich/Desktop/Data Science/Data-Science-Pakete in Python/Numpy Texte/Wahlverwandtschaften.txt')
- txt4 = txt4_file.read()
- #
- #
- ## den Text in eine Liste auf basierend auf den Leerschlägen:
- txt1_words = txt1.lower().split(' ')
- txt2_words = txt2.lower().split(' ')
- txt3_words = txt3.lower().split(' ')
- txt4_words = txt4.lower().split(' ')
- #
- all_words = txt1_words + txt2_words + txt3_words + txt4_words
- counts = Counter(all_words)
- #Ausgeben der 30 häufigsten worte und übergeben in liste
- for key, value in counts.items():
- print (value)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement