sequenceGen.py 2.4 KB
Newer Older
Z
zhangjinchao01 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
# Copyright (c) 2016 Baidu, Inc. 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 os
import sys

18
from paddle.trainer.PyDataProvider2 import *
Z
zhangjinchao01 已提交
19

20

21 22
def hook(settings, dict_file, **kwargs):
    settings.word_dict = dict_file
23
    settings.input_types = [integer_value_sequence(len(settings.word_dict)),
24
                            integer_value(3)]
25
    settings.logger.info('dict len : %d' % (len(settings.word_dict)))
Z
zhangjinchao01 已提交
26

27 28

@provider(init_hook=hook, should_shuffle=False)
29
def process(settings, file_name):
Z
zhangjinchao01 已提交
30 31 32 33 34
    with open(file_name, 'r') as fdata:
        for line in fdata:
            label, comment = line.strip().split('\t')
            label = int(''.join(label.split()))
            words = comment.split()
35 36
            word_slot = [settings.word_dict[w] for w in words if
                         w in settings.word_dict]
37
            yield word_slot, label
Z
zhangjinchao01 已提交
38

39

Z
zhangjinchao01 已提交
40
## for hierarchical sequence network
41 42 43
def hook2(settings, dict_file, **kwargs):
    settings.word_dict = dict_file
    settings.input_types = [integer_value_sub_sequence(len(settings.word_dict)),
44
                            integer_value_sequence(3)]
45 46
    settings.logger.info('dict len : %d' % (len(settings.word_dict)))

47 48

@provider(init_hook=hook2, should_shuffle=False)
49
def process2(settings, file_name):
Z
zhangjinchao01 已提交
50 51 52 53 54
    with open(file_name) as fdata:
        label_list = []
        word_slot_list = []
        for line in fdata:
            if (len(line)) > 1:
55
                label, comment = line.strip().split('\t')
Z
zhangjinchao01 已提交
56 57
                label = int(''.join(label.split()))
                words = comment.split()
58 59
                word_slot = [settings.word_dict[w] for w in words if
                             w in settings.word_dict]
60
                label_list.append(label)
Z
zhangjinchao01 已提交
61 62 63 64 65
                word_slot_list.append(word_slot)
            else:
                yield word_slot_list, label_list
                label_list = []
                word_slot_list = []