rsc15_reader.py 1.4 KB
Newer Older
Z
zhangwenhui03 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13
#   Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
T
tangwei 已提交
14

Z
zhangwenhui03 已提交
15 16
from __future__ import print_function

C
Chengmo 已提交
17
from paddlerec.core.reader import ReaderBase
Z
zhangwenhui03 已提交
18 19


C
Chengmo 已提交
20
class Reader(ReaderBase):
Z
zhangwenhui03 已提交
21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39
    def init(self):
        pass

    def generate_sample(self, line):
        """
        Read the data line by line and process it as a dictionary
        """

        def reader():
            """
            This function needs to be implemented by the user, based on data format
            """
            l = line.strip().split()
            l = [w for w in l]
            src_seq = l[:len(l) - 1]
            src_seq = [int(e) for e in src_seq]
            trg_seq = l[1:]
            trg_seq = [int(e) for e in trg_seq]
            feature_name = ["src_wordseq", "dst_wordseq"]
X
xujiaqi01 已提交
40
            yield list(zip(feature_name, [src_seq] + [trg_seq]))
Z
zhangwenhui03 已提交
41 42

        return reader