embedding.py 文件源码

def __init__(self, path, words=[], dim=300, normalize=True, **kwargs):
        seen = []
        vs = {}
        for line in open(path):
            split = line.split()
            w = split[0]
            if words == [] or w in words:
                if len(split) != dim+1:
                    continue
                seen.append(w)
                vs[w] = np.array(map(float, split[1:]), dtype='float32')
        self.iw = seen
        self.wi = {w:i for i,w in enumerate(self.iw)}
        self.m = np.vstack(vs[w] for w in self.iw)
        if normalize:
            self.normalize()