python 读词向量文件

    # String embedFile
    def readEmbedFile(embedFile):
        embedId = {}
        input = open(embedFile,'r')
        lines= []
        for line in input:
            lines.append(line)
        nwords = len(lines)-1
        splits = lines[1].split(' ') #因为第一行是统计信息，所以用第二行
        dim = len(splits)-1
        embeddings = [[0 for col in range(dim)] for row in range(nwords)]

        for lineId in range(len(lines)):
            splits = lines[lineId].split(' ')
            if len(splits) > 2 :
                #embedId赋值
                embedId[splits[0]] = lineId
                #embeddings赋值
                emb = [splits[i] for i in range(1, 201)]
                embeddings.append(emb)
        return embedId, embeddings

关注点在于二维数组的初始化以及二维数组值的填充