嵌入时出错：无法将字符串转换为浮点数：'ng'

Question

我正在使用 GloVe 方法处理预训练的词向量。数据包含维基百科数据上的向量。在嵌入数据时，我收到错误，指出无法将字符串转换为浮点数：'ng'我尝试浏览数据，但在那里我找不到符号“ng”# load embedding as a dictdef load_embedding(filename):    # load embedding into memory, skip first line    file = open(filename,'r', errors = 'ignore')    # create a map of words to vectors    embedding = dict()    for line in file:        parts = line.split()        # key is string word, value is numpy array for vector        embedding[parts[0]] = np.array(parts[1:], dtype='float32')    file.close()    return embedding这是错误报告。请进一步指导我。runfile('C:/Users/AKSHAY/Desktop/NLP/Pre-trained GloVe.py', wdir='C:/Users/AKSHAY/Desktop/NLP')C:\Users\AKSHAY\AppData\Local\conda\conda\envs\py355\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.  from ._conv import register_converters as _register_convertersUsing TensorFlow backend.Traceback (most recent call last):  File "<ipython-input-1-d91aa5ebf9f8>", line 1, in <module>    runfile('C:/Users/AKSHAY/Desktop/NLP/Pre-trained GloVe.py', wdir='C:/Users/AKSHAY/Desktop/NLP')  File "C:\Users\AKSHAY\AppData\Local\conda\conda\envs\py355\lib\site-packages\spyder\utils\site\sitecustomize.py", line 705, in runfile    execfile(filename, namespace)  File "C:\Users\AKSHAY\AppData\Local\conda\conda\envs\py355\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile    exec(compile(f.read(), filename, 'exec'), namespace)  File "C:/Users/AKSHAY/Desktop/NLP/Pre-trained GloVe.py", line 123, in <module>    raw_embedding = load_embedding('glove.6B.50d.txt')  File "C:/Users/AKSHAY/Desktop/NLP/Pre-trained GloVe.py", line 67, in load_embedding    embedding[parts[0]] = np.array(parts[1:], dtype='float32')ValueError: could not convert string to float: 'ng'

Answer 1

ValueError: 无法将字符串转换为浮点数：'ng'

为了解决上述问题，在函数中添加encoding='utf8'如下：

file = open(filename,'r', errors = 'ignore', encoding='utf8')

Answer 2

这似乎工作正常：

embedding_model = {}

f = open(r'dataset/glove.840B.300d.txt', encoding="utf8", "r")

for line in f:

    values = line.split()

    word = ''.join(values[:-300])

    coefs = np.asarray(values[-300:], dtype='float32')

    embedding_model[word] = coefs

f.close()

Answer 3

看起来 'ng' 是您文件中的一个单词（令牌），您正试图为其获取单词向量。手套预训练向量可能没有导致错误的“ng”向量。所以，你需要检查这个词在 Glove 嵌入中是否有一个向量。