I have a folder with 616 files, but my script only reads the first 100. What settings do I need to change around to get it to read them all? It's probably relevant, I'm using Anaconda Navigator's Jupyter Notebook.
Here's my code:
import re
import string
from collections import Counter
import os
import glob
def word_count(file_tokens):
for word in file_tokens:
count = Counter(file_tokens)
return count
files_list = glob.glob("german/test/*/negative/*")
print(files_list)
for path in files_list:
corpus, tache, classe, file_name = path.split("\\")
file = open(path, mode="r", encoding="utf-8")
read_file = file.read()
##lowercase
file_clean = read_file.lower()
##tokenize
file_tokens = file_clean.split()
##word count and sort
print(word_count(file_tokens))
Have you tried printing the length of the files_list
variable and check if it is 616 or 100 ?
print(len(files_list))