def print_ppmi(line: str, t1: str, t2: str, f):
""" t1, t2 の各単語ベクトルのコサイン類似度を求める (ppmi) """
try:
res = cosine_similarity(ppmi[ppmi_index[t1]], ppmi[ppmi_index[t2]])
print(f"{line.rstrip()}\t{res}", file=f)
except KeyError:
print(f"{line.rstrip()}\t-", file=f)
def print_w2v(line: str, t1: str, t2: str, f):
""" t1, t2 の各単語ベクトルのコサイン類似度を求める (word2vec) """
try:
res = cosine_similarity(w2v[w2v_index[t1]], w2v[w2v_index[t2]])
print(f"{line.rstrip()}\t{res}", file=f)
except KeyError:
print(f"{line.rstrip()}\t-", file=f)
def similar_list(mat: M, t_idx: Dict[str, int], v: np.ndarray) -> Rank:
""" v の類似度が高い n 語とその類似度のリストを返す """
t_keys = list(t_idx.keys())
dist = {t_keys[i]: cosine_similarity(v, mat[i]) for i in range(len(t_idx))}
rank = sorted(dist.items(), key=itemgetter(1), reverse=True)
return rank
def main():
r = redis.Redis(host="localhost", port=6379, db=0)
matrix = loadmat("knock85.matrix")["knock85.matrix"]
t = pickle.loads(r.get("knock83.t"))
t_keys = list(t.keys())
t_index = OrderedDict((key, i) for i, key in enumerate(t_keys))
eng = matrix[t_index["England"]]
dist = {
t_keys[i]: cosine_similarity(eng, matrix[i])
for i in range(len(t_index))
}
rank = sorted(dist.items(), key=itemgetter(1), reverse=True)
for i in range(1, 11):
print(f"{rank[i][0]}\t{rank[i][1]}")
def main():
r = redis.Redis(host="localhost", port=6379, db=0)
matrix = loadmat("knock85.matrix")["knock85.matrix"]
t = pickle.loads(r.get("knock83.t"))
t_keys = list(t.keys())
t_index = OrderedDict((key, i) for i, key in enumerate(t_keys))
# スペイン - マドリード (首都) + アテネ (ギリシャの首都)
vec = (
matrix[t_index["Spain"]] - matrix[t_index["Madrid"]] + matrix[t_index["Athens"]]
)
dist = {t_keys[i]: cosine_similarity(vec, matrix[i]) for i in range(len(t_index))}
rank = sorted(dist.items(), key=itemgetter(1), reverse=True)
for i in range(1, 11):
print(f"{rank[i][0]}\t{rank[i][1]}")
def main():
word2vec_filepath = "../data/w2v.txt"
load_word2vec(word2vec_filepath)
matrix, t_index = deserialize("matrix"), deserialize("t_index")
# knock86
u_s = matrix[t_index["United_States"]]
# knock87
print(cosine_similarity(matrix[t_index["U.S"]], u_s))
# knock88
for rank in similar_list(matrix, t_index,
matrix[t_index["England"]])[1:11]:
print(f"{rank[0].ljust(10)} : {rank[1]}")
# knock89
for rank in multi_vec(matrix, t_index, "Spain", "Madrid", "Athens")[1:11]:
print(f"{rank[0].ljust(10)} : {rank[1]}")