def main():
model = FastText('model_text8.bin')
target_words = [
'granada', 'python', 'harmony', 'mafia', 'yoga', 'goth', 'cyberpunk',
'nasa', 'japan', 'boolean', 'foodball', 'algorithm', 'china', 'usa',
'internet', 'harvard', 'earth', 'horse', 'angel', 'rock'
]
for t_word in target_words:
# get embedding
target_word_embedding = model.get_numpy_vector(t_word)
print('Target word:', t_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(t_word, k=15)
# init array
nn_word_embedding = np.zeros(shape=(15, 128))
i = 0
for word, similarity in closest_words:
# get each word embedding
nn_word_embedding[i] = model.get_numpy_vector(word)
#print('Word:', word, 'Vec:', nn_word_embedding[i])
i = i + 1
# kmeans
#print(nn_word_embedding.shape)
#print(closest_words)
cluster_model = KMeans(n_clusters=3, init='k-means++')
prediction = cluster_model.fit_predict(nn_word_embedding)
print(prediction)
j = 0
for word in closest_words:
print('Word:', word[0], '- Cluster #%d' % (prediction[j] + 1))
j = j + 1
def text():
model = FastText('wiki.zh.bin')
print('load over..')
s1 = '启航'
s2 = '董启航'
s3 = ' 董启文'
print(model.nearest_neighbors('桃', k=5))
#text()
def main():
model = FastText('model_text8.bin')
target_word = 'dog'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
print('Embedding shape:', target_word_embedding.shape)
print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
class FastTextEmbedding(Embedding):
def __init__(self, binfile, normalize = False):
self.file = binfile
self.vdim = -1
self.normalize = normalize
def load(self):
print('Loading fasttext model.')
self.ftmodel = FastText()
self.ftmodel.load_model(self.file)
self.vdim = len(self.ftmodel['is'])
print('Finished loading fasttext model.')
return self
def getVector(self, word):
return self.ftmodel.get_numpy_vector(word, normalized = self.normalize)
def search(self, q, topk = 4):
raise NotImplementedError()
def wordForVec(self, v):
word, sim = self.ftmodel.words_for_vector(v)[0]
return word, sim
def containsWord(self, word):
return True
def vocabulary(self):
return self.ftmodel.words
def nearest_neighbors(self, term, n=1000):
return self.ftmodel.nearest_neighbors(term, n)
def all_nearest_neighbors(self, term):
return self.nearest_neighbors(term, len(self.vocabulary()))
def dim(self):
return self.vdim
model.skipgram(input="./clean_corpus", output='model', epoch=100, lr=0.7)
print(model.nwords)
'''
#model = fasttext.load_model('../data/model.bin')
model = FastText('../data/model.bin')
def get_set(filepath):
result = set()
with open(filepath, 'r') as file_in:
for line in file_in:
result.add(line.strip())
return result
vocab_in = get_set("../data/vocab_in")
vocab_out = get_set("../data/vocab_out")
in2out_file = open("../data/in2out_map", 'w')
for word in vocab_out:
candi_list = model.nearest_neighbors(word, k=10)
mark = False
for temp in candi_list:
if (temp[0] in vocab_in):
in2out_file.write("\t".join([word, temp[0]]) + "\n")
mark = True
break
if (not mark):
in2out_file.write("\t".join([word, "none"]) + "\n")
in2out_file.close()
if word_lst[j]=='ළ':
if len(i)<=1:
per_word = word_lst.copy()
per_word[j] = 'ල'
concat = ''
for k in per_word:
concat+=k
permutated_words.append(concat)
return permutated_words
model = FastText('sinhala_all.bin')
#print(model.similarity('බල්ල', 'බල්ලා'))
sin_word = 'බළ්ළාට'
permutated_sin_word = NanaLala(sin_word)
words = model.nearest_neighbors(sin_word, k=10000)
suggested_words = []
for i in words:
suggested_words.append(i[0])
copy_suggested_words = suggested_words.copy()
for i in suggested_words:
if i in permutated_sin_word:
copy_suggested_words.remove(i)
copy_suggested_words.insert(0,i)
print(copy_suggested_words[:5])
def evaluate():
model = FastText("debate2vec.bin")
#print(model.similarity('dog', 'cat'))
pprint.pprint(model.nearest_neighbors('praxis', k=30))
start = time.time()
model = FastText('output.bin')
with open("testDataMasked.txt", encoding="utf8") as f:
contentData = f.readlines()
contentData = [x.strip() for x in contentData]
lineIndex = 1
with open("FastTextResult.txt", 'a', encoding="utf8") as fastTextResultFile:
for line in contentData:
tmpArray = line.split()
vectors = []
maskedIndex = tmpArray.index('[MASK]')
similiarsLeft = model.nearest_neighbors(tmpArray[maskedIndex - 1],
k=1000)
if (maskedIndex < len(tmpArray) - 1):
similiarsRight = model.nearest_neighbors(tmpArray[maskedIndex + 1],
k=1000)
predictions = []
if (maskedIndex < len(tmpArray) - 1):
for simL in similiarsLeft:
index = 0
for simR in similiarsRight:
if (simL[0] == simR[0]):
predictions.append(simL[0])
else:
for simL in similiarsLeft:
predictions.append(simL[0])
output='skip_gram_model',
epoch=100,
lr=0.7)
print(skip_gram_model['贷款'])
# print(skip_gram_model.get_numpy_vector('贷款'))
# print(skip_gram_model.get_numpy_vector('贷款', normalized=True))
var1 = skip_gram_model.get_numpy_vector('人民币')
var2 = skip_gram_model.get_numpy_vector('贷款')
var3 = skip_gram_model.get_numpy_vector('外币')
skip_gram_model.words_for_vector(var1 + var2 - var3, k=1)
# for word in skip_gram_model.words:
# print(word, skip_gram_model[word])
print(skip_gram_model.nearest_neighbors('贷款', k=2))
# test data is stored inside a file, use this:
# skip_gram_model.predict_proba_file('./test.txt', k=2)
print("\n")
##################
# 使用cbow模型训练 #
##################
cbow_model = FastText()
cbow_model.cbow(input='./train.txt', output='cbow_model', epoch=100, lr=0.7)
print(cbow_model['贷款'])
# print(cbow_model.get_numpy_vector('贷款'))
# print(cbow_model.get_numpy_vector('贷款', normalized=True))
def lemma(girdi):
istek = {"text": girdi, "fields": "lemma"}
lemmas = ((requests.post(url, istek, headers)).text)
sonuc = lemmas.strip(punctuations)
cikti = re.sub(r'^.*\"', '', sonuc)
if cikti == "No_Lemma":
cikti = girdi
else:
cikti == sonuc
return cikti
# Load model and set query key
primary = (model.nearest_neighbors(key, k=25))
my_dict = dict(primary)
# Empty list for first cycle
f_cycle = []
f_second_input = []
# Create first cycle data
for word, weight in my_dict.items():
word = word.lower()
weight = format(weight, '.3f')
if word != key and not word.startswith(key):
word = lemma(word)
f_second_input.append(word)
# sonuc = (f"{key},{word},{weight}")
sonuc = key, word, weight
class WordModel:
def __init__(self):
self.model_name = None
self.model = None
self.model_path = None
def get_vector(self, word):
try:
vector = self.model[word]
except KeyError:
vector = None
return vector
def get_full_path(self, relative_path):
pwd = os.path.dirname(os.path.abspath(__file__))
pwd = os.path.join(pwd, relative_path)
return pwd
def path_exists(self, relative_path):
full_path = self.get_full_path(relative_path)
return os.path.exists(full_path)
def validate_model_path(self, path):
if path is None or not self.path_exists(path):
if self.model_name == 'fasttext':
default_path = self.get_full_path(
'models/fasttext_skipgram_model.bin')
else:
default_path = self.get_full_path(
'models/word2vec_skipgram.w2v')
return default_path
else:
path = self.get_full_path(path)
return path
def validate_model_name(self, name):
if name is not None and name in ['fasttext', 'word2vec']:
correct_name = name
else:
correct_name = 'fasttext'
return correct_name
def get_numpy_vector(self, word):
if self.model_name == 'fasttext':
return self.model.get_numpy_vector(word, normalized=True)
else:
try:
np_vector = self.model.wv[word]
except KeyError:
np_vector = None
return np_vector
def load_model(self):
if not os.path.exists(self.model_path):
raise FileNotFoundError('model file not found!')
if self.model_name == 'fasttext':
self.model = FastText(self.model_path)
else:
self.model = gensim.models.Word2Vec.load(self.model_path, mmap='r')
def get_most_similar_words(self, word, k=5):
if self.model_name == 'fasttext':
return self.model.nearest_neighbors(word, k=k)
else:
try:
similar_words = self.model.similar_by_word(word, topn=k)
except KeyError:
similar_words = []
return similar_words
def get_words_for_vector(self, vector, k=3):
if self.model_name == 'fasttext':
return self.model.words_for_vector(vector, k)
else:
try:
similar_words = self.model.similar_by_vector(vector, topn=k)
except KeyError:
similar_words = []
return similar_words
def similarity(self, word_1, word_2):
if self.model_name == 'fasttext':
return self.model.similarity(word_1, word_2)
else:
try:
sim = self.model.wv.similarity(word_1, word_2)
except KeyError:
sim = 0
return sim
def word_analogies(self, words, k=3):
word_list = words.split()
if len(word_list) == 3:
word_vec_1 = self.get_numpy_vector(word_list[0])
word_vec_2 = self.get_numpy_vector(word_list[1])
word_vec_3 = self.get_numpy_vector(word_list[2])
word_vec_4 = word_vec_3 - word_vec_1 + word_vec_2
return self.get_words_for_vector(word_vec_4, k)
def odd_one_out(self, words):
word_list = words.split()
if len(word_list) == 4:
scores = [0.0, 0.0, 0.0, 0.0]
for index in range(len(word_list)):
for another_word in word_list:
if another_word != word_list[index]:
scores[index] += self.similarity(
word_list[index], another_word)**2
scores[index] = sqrt(scores[index] / 3.0)
min_index = scores.index(min(scores))
result = f'{word_list[min_index]}\n'
result += '\n'
scores, word_list = zip(*sorted(zip(scores, word_list)))
for word, score in zip(word_list, scores):
result += f'{word}: {score}\t'
return result
def main():
model = FastText('model_text8.bin')
target_word = 'deep'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
print('Embedding shape:', target_word_embedding.shape)
print('Embedding:', target_word_embedding[0:15], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'president'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'self'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'insult'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'general'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'inclined'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'property'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'international'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'many'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'imprisoned'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'branches'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'communist'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'france'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'strict'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'earthly'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
terget_word = "zero"
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'feminism'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'ideas'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'theory'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
target_word = 'writings'
# get embedding
target_word_embedding = model.get_numpy_vector(target_word)
print('Target word:', target_word)
#print('Embedding shape:', target_word_embedding.shape)
#print('Embedding:', target_word_embedding[0:10], '...')
# find closest words
closest_words = model.nearest_neighbors(target_word, k=15)
closest_word_embeddings = []
numw = 0
for word, similarity in closest_words:
print('Word:', word, 'similarity:', similarity)
closest_word_embeddings.append(model.get_numpy_vector(word))
kmeans = cluster.KMeans(n_clusters=3)
kmeans.fit(closest_word_embeddings)
labels = kmeans.labels_
print ('Cluster id labels for inputted data')
print (labels)
cluster1 = []
cluster2 = []
cluster3 = []
for i in range(0,15):
if labels[i] == 0:
cluster1.append(closest_words[i][0])
if labels[i] == 1:
cluster2.append(closest_words[i][0])
if labels[i] == 2:
cluster3.append(closest_words[i][0])
print("cluster #1 : ", cluster1)
print("cluster #2 : ", cluster2)
print("cluster #3 : ", cluster3)
