ssr_reader.py 1.5 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 17 18
from __future__ import print_function

import random

C
Chengmo 已提交
19
from paddlerec.core.reader import ReaderBase
T
tangwei 已提交
20 21


C
Chengmo 已提交
22
class Reader(ReaderBase):
Z
zhangwenhui03 已提交
23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47
    def init(self):
        pass

    def sample_neg_from_seq(self, seq):
        return seq[random.randint(0, len(seq) - 1)]

    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
            """
            ids = line.strip().split()
            conv_ids = [int(i) for i in ids]
            boundary = len(ids) - 1
            src = conv_ids[:boundary]
            pos_tgt = [conv_ids[boundary]]
            neg_tgt = [self.sample_neg_from_seq(src)]
            feature_name = ["user", "p_item", "n_item"]
            yield zip(feature_name, [src] + [pos_tgt] + [neg_tgt])

        return reader