Skip to content

Instantly share code, notes, and snippets.

@wcneill
Created September 4, 2019 19:51
Show Gist options
  • Save wcneill/ca9b9ad0d14f2891bc063c016c696ddc to your computer and use it in GitHub Desktop.
Save wcneill/ca9b9ad0d14f2891bc063c016c696ddc to your computer and use it in GitHub Desktop.
functions for reading txt files with two different formats and counting instances of certain strings in the files
# reads a file with a single name on each line and counts the
# number of instances of that name in the file
def getcount(path):
with open(path, 'r') as open_file:
name_count = {}
for line in open_file:
if line in name_count.keys():
name_count[line] += 1
else:
name_count[line] = 1
for name, count in name_count.items():
print('The name {} occurs {} times in the file'.format(name, count))
# Reads a .txt file where each line is file path to an image.
# example: a/abbey/image_name.jpg
# Each line is parsed for the second folder in the directory, which is named
# by category. Each category is added as a key to a dictionary whose values are the
# number of instances of that category.
def getcats(path):
with open(path, 'r') as open_file:
cat_count = {}
for line in open_file:
category = line.split('/')[2]
if category in cat_count.keys():
cat_count[category] += 1
else:
cat_count[category] = 1
for cat, count in cat_count.items():
print('The number of appearences of {} in the file is {}'. format(cat, count))
if __name__ == '__main__':
getcats('Training_01.txt')
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment