python获取txt文件词向量过程详解

代码1:
try:
lines=np.loadtxt(filepath)
catch:
感觉这块不会写了咦，，，
  print(ValueError)
但这样的话，它就不会继续循环去读上边的txt了呢

代码2：
lines=[]
with open(filepath) as f:
  for line in f:
    lines.append(line)
np.save(filepath,lines)

代码3
 
def readEmbedFile(embedFile):
#   embedId = {}
#   input = open(embedFile,'r',encoding="utf-8")
#   lines = []
#   a=0
#   for line in input:
#     lines.append(line)
#     a=a+1
#     print(a)
#   nwords = len(lines) - 1
#   splits = lines[1].strip().split(' ') # 因为第一行是统计信息，所以用第二行
#   dim = len(splits) - 1
#   embeddings=[]
#   # embeddings = [[0 for col in range(dim)] for row in range(nwords)]
#   b=0
#   for lineId in range(len(lines)):
#     b=b+1
#     print(b)
#     splits = lines[lineId].split(' ')
#     if len(splits) > 2:
#       # embedId赋值
#       embedId[splits[0]] = lineId
#       # embeddings赋值
#       emb = [float(splits[i]) for i in range(1, 300)]
#       embeddings.append(emb)
#   return embedId, embeddings

代码4：
def load_txt(filename):
  lines=[]
  vec_dict={}
  with open(filename,r) as f:
    for line in f:
    list=line.strip()
    lines.append(line)
  for i, line in emuate(lines):
    if i=0:
      continue
    line=line.split(" ")
    wordID=line[0]
    wordvec=[float line[i] for i in range(1,300)]
  vec_dict[wordId]=np.array(wordvec)  
 
  return vec_dict

print("str",sys.getsizeof(""))
print("float",sys.getsizeof(1.1))
print("int",sys.getsizeof(1))
print("list",sys.getsizeof([]))
print("tuple",sys.getsizeof(()))
print("dic",sys.getsizeof([]))

str 49
float 24
int 28
list 64
tuple 48
dic 64