Dataset.py 文件源码

def bin_count(hdf_data_dir, file_prefix, num_of_parts):
        """
        count positive/negative samples
        :param hdf_data_dir: 
        :param file_prefix: see this param in feature_to_hdf()
        :param num_of_parts: 
        :return: size of a dataset, positive samples, negative samples, positive ratio
        """
        size = 0
        num_of_pos = 0
        num_of_neg = 0
        for part in range(num_of_parts):
            _y = pd.read_hdf(os.path.join(hdf_data_dir, file_prefix + '_output_part_' + str(part) + '.h5'), mode='r')
            part_pos_num = _y.loc[_y.iloc[:, 0] == 1].shape[0]
            part_neg_num = _y.shape[0] - part_pos_num
            size += _y.shape[0]
            num_of_pos += part_pos_num
            num_of_neg += part_neg_num
        pos_ratio = 1.0 * num_of_pos / (num_of_pos + num_of_neg)
        return size, num_of_pos, num_of_neg, pos_ratio