def generate_vocab(walks):
index2word = []
raw_vocab = defaultdict(int)
for walk in walks:
for word in walk:
raw_vocab[word] += 1
vocab = {}
for word, v in iteritems(raw_vocab):
vocab[word] = Vocab(count=v, index=len(index2word))
index2word.append(word)
index2word.sort(key=lambda word: vocab[word].count, reverse=True)
for i, word in enumerate(index2word):
vocab[word].index = i
return vocab, index2word
def generate_vocab(all_walks):
index2word = []
raw_vocab = defaultdict(int)
for walks in all_walks: # 遍历每一层walks
for walk in walks:
for word in walk:
raw_vocab[word] += 1 # 统计一下word（node）出现的次数
vocab = {}
for word, v in iteritems(raw_vocab): # 构建词袋，给word一个编码，按照出现的次数进行排序
vocab[word] = Vocab(count=v, index=len(index2word))
index2word.append(word)
index2word.sort(key=lambda word: vocab[word].count,
reverse=True) # 按照词袋的数量从大到小进行排序
for i, word in enumerate(index2word):
vocab[word].index = i # 词袋的index重新排序
return vocab, index2word
def generate_vocab(all_walks):
index2word = []
raw_vocab = defaultdict(int)
for walks in all_walks:
for walk in walks:
for word in walk:
raw_vocab[word] += 1
vocab = {}
for word, v in iteritems(raw_vocab):
vocab[word] = Vocab(count=v, index=len(index2word))
index2word.append(word)
# 按照每个单词出现的频次进行从大到小排序在vocab中
index2word.sort(key=lambda word: vocab[word].count, reverse=True)
for i, word in enumerate(index2word):
vocab[word].index = i
# vocab是一个按照walks中所有节点出现的频率从大到小排序后的单词表
# index2word是节点集合
return vocab, index2word
def generate_vocab(all_walks):
index2word = []
raw_vocab = defaultdict(
int) # stores the count of a word appearing in the walk
for walks in all_walks:
for walk in walks:
for word in walk:
raw_vocab[word] += 1
# compute count, then to sort based on count, at last set index after sort
vocab = {}
for word, v in iteritems(raw_vocab):
vocab[word] = Vocab(
count=v, index=len(index2word)) # vocab[word] = (count, index)
index2word.append(word) # index2word[index] == word
index2word.sort(key=lambda word: vocab[word].count,
reverse=True) # decending order
for i, word in enumerate(index2word):
vocab[word].index = i # word2inedx
return vocab, index2word # vocab: