def main(): model = load_w2v(sys.argv[1]) words = [w for w,_ in model.most_similar(positive=['country'], topn=20)] vecs = [model[w] for w in words] result = linkage(vecs, method='ward') dendrogram(result, labels=words, orientation='right') plt.show()
def main():
model = load_w2v(sys.argv[1])
with open(sys.argv[2]) as f:
for line in f:
if line[0] == ':':
print(line.rstrip())
continue
w1, w2, w3, w4 = line.rstrip().split()
word, prob = model.most_similar(positive=[w2, w3], negative=[w1], topn=1)[0]
print(' '.join([w1, w2, w3, w4, word, str(prob)]))
def main():
model = load_w2v(sys.argv[1])
words = [w for w, _ in model.most_similar(positive=['country'], topn=20)]
vecs = [model[w] for w in words]
result = TSNE(n_components=2, random_state=0).fit_transform(vecs)
plt.scatter(result[:, 0], result[:, 1])
for point, word in zip(result, words):
x, y = point
plt.annotate(word, point)
plt.show()
def main():
model = load_w2v(sys.argv[1])
words = [w for w, _ in model.most_similar(positive=['country'], topn=20)]
vecs = [model[w] for w in words]
labels = KMeans(n_clusters=5, random_state=0).fit_predict(vecs)
result = [[], [], [], [], []]
for word, label in zip(words, labels):
result[label].append(word)
for label in range(5):
print('class {}:'.format(label))
print(', '.join(result[label]) + '\n')
def main():
model = load_w2v(sys.argv[1])
most_similars = model.most_similar(positive=['Spain', 'Athens'],
negative=['Madrid'])
for word, prob in most_similars:
print('{}\t{}'.format(word, prob))
from q63 import analogy
def load_question_words():
data = pd.read_csv(
project_path / "data/w2v/questions-words.txt",
sep=" ",
skiprows=1,
header=None,
)
data = data[data.iloc[:, 0] != ":"]
return data
if __name__ == "__main__":
print("\rSolving Q64 ... ", end="")
w2v = load_w2v()
data = load_question_words()
analogies = [
analogy(w2v, r[1], r[0], r[2], topn=1)[0]
for _, r in tqdm(list(data.iterrows()))
]
data.insert(4, 4, [a[0] for a in analogies])
data.insert(5, 5, [a[1] for a in analogies])
data.to_csv(project_path / "output/w2v/analogy.csv")
print("Done.")
def main():
model = load_w2v(sys.argv[1])
most_similars = model.most_similar('United_States', topn=10)
for word, prob in most_similars:
print('{}\t{}'.format(word, prob))
def main():
model = load_w2v(sys.argv[1])
similarity = model.similarity('United_States', 'U.S.')
print(similarity)
def __init__(self, min_freq=1, root=project_path / "data/news/"):
w2v = load_w2v()
self.w2v = w2v
self.min_freq = min_freq
self.root = root
self.padding_idx = 0
