Last active
August 29, 2015 14:03
-
-
Save stefano-maggiolo/f8ddab487ab7ba4bd204 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 python | |
import math | |
import sys | |
from collections import defaultdict | |
if __name__ == "__main__": | |
if len(sys.argv) != 3: | |
print "%s wordlist total_count" % sys.argv[0] | |
sys.exit(1) | |
total_count = int(sys.argv[2]) | |
words = defaultdict(int) | |
content = [line.strip().split('\t') | |
for line in open(sys.argv[1]).readlines()] | |
for line in content: | |
word = line[0].lower() | |
count = int(line[1]) | |
words[word] += count | |
sorted_words = sorted([(words[word], word) | |
for word in words], | |
reverse=True) | |
for count, word in sorted_words: | |
print "%6.2lf, %10d, %s" % ( | |
math.log(count * 1.0 / total_count, 10), | |
count, | |
word) |
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 | |
import sys | |
from collections import defaultdict | |
MIN_OCCURRENCES = 3 | |
content = [x for x in open(sys.argv[1]).read().split() | |
if len(x) >= 3] | |
starts = defaultdict(int) | |
ends = defaultdict(int) | |
trigrams = defaultdict(int) | |
for word in content: | |
word = word.lower() | |
if len(word) >= 2: | |
if word[0].isalpha() and word[1].isalpha(): | |
starts[word[:2]] += 1 | |
if word[-2].isalpha() and word[-1].isalpha(): | |
ends[word[-2:]] += 1 | |
for i in range(len(word) - 2): | |
if word[i].isalpha() and word[i+1].isalpha() and word[i+2].isalpha(): | |
trigrams[word[i:i+3]] += 1 | |
starts_l = [(x[1], x[0]) for x in starts.items()] | |
ends_l = [(x[1], x[0]) for x in ends.items()] | |
trigrams_l = [(x[1], x[0]) for x in trigrams.items()] | |
ret = [] | |
for score, trigram in trigrams_l: | |
if score >= MIN_OCCURRENCES: | |
if starts[trigram[:2]] >= MIN_OCCURRENCES: | |
if ends[trigram[-2:]] >= MIN_OCCURRENCES: | |
ret.append((score, | |
trigram, | |
score, | |
starts[trigram[:2]], | |
ends[trigram[-2:]])) | |
for x in sorted(ret, reverse=True): | |
print(x[1]) |
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 | |
import sys | |
if __name__ == "__main__": | |
YEARS = ['198', '199', '200', '201'] | |
for line in sys.stdin: | |
idx = 0 | |
while idx <= 4 and line[idx] != '\t' and line[idx] != '_': | |
idx += 1 | |
if idx != 3: | |
continue | |
pieces = line.split('\t') | |
if pieces[1][:3] not in YEARS: | |
continue | |
word = line[:3] | |
if not word.isalpha(): | |
continue | |
count = pieces[2] | |
sys.stdout.write('%s\t%s\n' % (word, count)) |
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 | |
import sys | |
csv = [x.strip().split(',') | |
for x in open(sys.argv[1]).readlines()[2:]] | |
langs = ['en_us', 'en_gb', 'de', 'es', 'it', 'fr'] | |
for index, lang in enumerate(langs): | |
words = [x.strip() for x in open("%s.csv" % lang).readlines()] | |
with open("%s_result.csv" % lang, "w") as f: | |
num_words = 0 | |
for line in csv: | |
word = line[index + 14].strip() | |
if word in words: | |
num_words += 1 | |
f.write(word + "\n") | |
print(lang) | |
print("%d / %d = %7.2lf\n" % (num_words, | |
len(words), | |
num_words / len(words))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment