Util.py 文件源码

def quantize_data(x, y, wc=None, continuous_rate=0.1, separate=False):
        if isinstance(x, list):
            xt = map(list, zip(*x))
        else:
            xt = x.T
        features = [set(feat) for feat in xt]
        if wc is None:
            wc = np.array([len(feat) >= int(continuous_rate * len(y)) for feat in features])
        else:
            wc = np.asarray(wc)
        feat_dics = [{_l: i for i, _l in enumerate(feats)} if not wc[i] else None
                     for i, feats in enumerate(features)]
        if not separate:
            if np.all(~wc):
                dtype = np.int
            else:
                dtype = np.double
            x = np.array([[feat_dics[i][_l] if not wc[i] else _l for i, _l in enumerate(sample)]
                          for sample in x], dtype=dtype)
        else:
            x = np.array([[feat_dics[i][_l] if not wc[i] else _l for i, _l in enumerate(sample)]
                          for sample in x], dtype=np.double)
            x = (x[:, ~wc].astype(np.int), x[:, wc])
        label_dic = {_l: i for i, _l in enumerate(set(y))}
        y = np.array([label_dic[yy] for yy in y], dtype=np.int8)
        label_dic = {i: _l for _l, i in label_dic.items()}
        return x, y, wc, features, feat_dics, label_dic