Perform some statistics on ECB given ECB+ directory which include the ECB files (Cybulska and Vossen, 2014)

ecb_stats.py

import os
import re
count = 0
for root, dir_names, file_names in os.walk('ECB+'):
    for fname in file_names:
        if 'plus' not in fname:
            path = os.path.join(root, fname)
            with open(path) as f:
                content = f.read()
                print list(m.group() for m in re.finditer('<token', content))
                count += sum(1 for _ in re.finditer('<token', content))
            # print path
print count