def test():
alice_data = map_words(read_file('pg11.txt', open_, encoding='utf-8'))
jekyll_data = map_words(read_file('pg42.txt', open_, encoding='utf-8'))
alice_size = dataset_size(alice_data)
jekyll_size = dataset_size(jekyll_data)
words = shared_words([alice_data, jekyll_data])
"""print words
print len(words)
print len(alice_data)
print len(jekyll_data)
print sum(len(word) for word in words) / len(words) + 0.0
print sum(len(word) for word in alice_data) / (len(alice_data) + 0.0)
print sum(len(word) for word in jekyll_data) / (len(jekyll_data) + 0.0)
print perfect_matches(absolute_ratings(words, alice_data, jekyll_data))"""
near_value = 0.001
all_near_usage = all_near_usage_value(usage_ratings(words, alice_data, jekyll_data), near_value)
"""print all_near
print len(all_near)"""
absolute = absolute_ratings(words, alice_data, jekyll_data)
print perfect_matches(absolute)
all_near_absolute = all_near_absolute_value(absolute, near_value)
#print len(all_near_absolute)
for word in all_near_usage:
if word in perfect_matches(absolute):
print word
def export_all():
data = {}
for f in listdir('.'):
if f.endswith('.txt') and 'all' not in f:
print f
try:
read_data = read_file(f, codecs.open, encoding='utf-8')
map_words(read_data, data)
except UnicodeDecodeError:
pass
export_data(data, 'all2.csv', codecs.open, encoding='utf-8')
if f.endswith('.txt') and 'all' not in f:
print f
try:
read_data = read_file(f, codecs.open, encoding='utf-8')
map_words(read_data, data)
except UnicodeDecodeError:
pass
export_data(data, 'all2.csv', codecs.open, encoding='utf-8')
if __name__ == '__main__':
"""
data = read_file('svenska.txt', codecs.open, encoding='utf-8')
data = map_words(data)
export_data(data,'svenska.csv', codecs.open, encoding='utf-8')
"""
alice_data = map_words(read_file('pg11.txt', codecs.open, encoding='utf-8'))
jekyll_data = map_words(read_file('pg42.txt', codecs.open, encoding='utf-8'))
words = shared_words([alice_data, jekyll_data])
absolute = absolute_ratings(words, alice_data, jekyll_data)
usage = usage_ratings(words, alice_data, jekyll_data)
export_shared_words(words, usage, absolute, 'output_alice_jekyll_mix.csv', codecs.open, encoding='utf-8')