test_reader.py 1.3 KB
Newer Older
Y
yinhaofeng 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39
#   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.
from __future__ import print_function

from paddlerec.core.reader import ReaderBase


class Reader(ReaderBase):
    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
            """

            features = line.strip('\n').split('\t')
            doc1 = [int(word_id) for word_id in features[0].split(",")]
            doc2 = [int(word_id) for word_id in features[1].split(",")]
            features_name = ["doc1", "doc2"]
            yield zip(features_name, [doc1] + [doc2])

        return reader