data_reader.py

#   Copyright (c) 2018 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.

import sys
import os
import paddle


def parse_fields(fields):
    words_width = int(fields[0])
    words = fields[1:1 + words_width]
    label = fields[-1]

    return words, label


def imdb_data_feed_reader(data_dir, batch_size, buf_size):
    """ 
    Data feed reader for IMDB dataset.
    This data set has been converted from original format to a format suitable
    for AsyncExecutor
    See data.proto for data format
    """

    def reader():
        for file in os.listdir(data_dir):
            if file.endswith('.proto'):
                continue

            with open(os.path.join(data_dir, file), 'r') as f:
                for line in f:
                    fields = line.split(' ')
                    words, label = parse_fields(fields)
                    yield words, label

    test_reader = paddle.batch(
        paddle.reader.shuffle(
            reader, buf_size=buf_size), batch_size=batch_size)
    return test_reader