if __name__ == "__main__":
wordsim = Wordsim()
word_analogy = WordAnalogy()
word_analogy.set_top_words('../../data/processed data/top_30000_words.txt')
suffix = '_1'
dimension_list = [50, 100, 150, 200]
wa_list = []
ws_list = []
for dimension in dimension_list:
filename = '../../output/convergence_test/3000samples/31epochs/snml/{}dim/embedding-e={}-n_sampled=3000-epochs=31-batch_size=10000.txt'.format(
dimension, dimension)
print('Reading: ', filename)
embedding = Embedding.from_file(filename)
wa_result = word_analogy.evaluate(embedding,
high_level_category=False,
restrict_top_words=False)
ws_result = wordsim.evaluate(embedding)
wa_list.append(wa_result['all'])
ws_list.append(ws_result['EN-WS-353-ALL'][2])
print('Word analogy: ')
for wa in wa_list:
print(wa)
print('Word sim: ')
for ws in ws_list:
print(ws)
# accuracy
acc = mean(result)
# result
print("Category: %-30s, accuracy: %f (all: %d)" %
(cat, acc, len(X_cat)))
predictions[cat] = acc
# overrall
total_count = 0
acc = 0
for cat in cat_list:
cat_count = len(X[cat])
acc += cat_count * predictions.get(cat)
total_count += cat_count
predictions['all'] = acc / total_count
print("All Category accuracy: %f" % (acc / total_count))
return predictions
if __name__ == "__main__":
word_analogy = WordAnalogy()
word_analogy.set_top_words('../../data/processed data/top_30000_words.txt')
embedding = Embedding.from_file(
'../../output/50dim/embedding-e=50-n_sampled=200-epochs=35-batch_size=10000_1.txt'
)
result = word_analogy.evaluate(embedding,
high_level_category=False,
restrict_top_words=False)
@staticmethod
def pprint(result):
from prettytable import PrettyTable
x = PrettyTable(["Dataset", "Found", "Not Found", "Score (rho)"])
x.align["Dataset"] = "l"
for k, v in result.items():
x.add_row([k,v[0],v[1],v[2]])
print(x)
def evaluate(self, embedding):
result = {}
for file_name, data in self.dataset.items():
pred, label, found, notfound = [] ,[], 0, 0
for datum in data:
if embedding.in_vocab(datum[0]) and embedding.in_vocab(datum[1]):
found += 1
pred.append(umath.cos(embedding.vector(datum[0]), embedding.vector(datum[1])))
label.append(datum[2])
else:
notfound += 1
result[file_name] = (found, notfound, umath.rho(label,pred)*100)
return result
if __name__ == "__main__":
wordsim = Wordsim()
embedding = Embedding.from_file('../../output/100dim/embedding-e=100-n_sampled=200-epochs=10-batch_size=10000.txt')
result = wordsim.evaluate(embedding)
# wordsim.pprint(result)
print(result['EN-WS-353-ALL'][2])