Created
November 2, 2015 22:57
-
-
Save jtauber/d05bbe3ee9536bf59147 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
from collections import defaultdict | |
from pysblgnt import morphgnt_rows | |
count_by_item = defaultdict(int) | |
total_item_count = 0 | |
for book_num in range(1, 28): | |
for row in morphgnt_rows(book_num): | |
item = row["lemma"] # "lemma" or "norm" | |
count_by_item[item] += 1 | |
total_item_count += 1 | |
cummulative_count = 0 | |
items_learnt = 0 | |
for item, count in sorted(count_by_item.items(), key=lambda element: element[1], reverse=True): | |
print(item, count) | |
cummulative_count += count | |
items_learnt += 1 | |
if cummulative_count > total_item_count * 0.50: # @@@ | |
break |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment