sequenceGen.py 2.3 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 23 24
def hook(settings, dict_file, **kwargs):
    settings.word_dict = dict_file
    settings.input_types = [integer_value_sequence(len(settings.word_dict)), 
                            integer_value_sequence(3)]
    settings.logger.info('dict len : %d' % (len(settings.word_dict)))
Z
zhangjinchao01 已提交
25

26 27
@provider(init_hook=hook)
def process(settings, file_name):
Z
zhangjinchao01 已提交
28 29 30 31 32
    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()
33
            word_slot = [settings.word_dict[w] for w in words if w in settings.word_dict]
Z
zhangjinchao01 已提交
34 35 36
            yield word_slot, [label]

## for hierarchical sequence network
37 38 39 40 41 42 43 44
def hook2(settings, dict_file, **kwargs):
    settings.word_dict = dict_file
    settings.input_types = [integer_value_sub_sequence(len(settings.word_dict)),
                            integer_value_sub_sequence(3)]
    settings.logger.info('dict len : %d' % (len(settings.word_dict)))

@provider(init_hook=hook2)
def process2(settings, file_name):
Z
zhangjinchao01 已提交
45 46 47 48 49 50 51 52
    with open(file_name) as fdata:
        label_list = []
        word_slot_list = []
        for line in fdata:
            if (len(line)) > 1:
                label,comment = line.strip().split('\t')
                label = int(''.join(label.split()))
                words = comment.split()
53
                word_slot = [settings.word_dict[w] for w in words if w in settings.word_dict]
Z
zhangjinchao01 已提交
54 55 56 57 58 59
                label_list.append([label])
                word_slot_list.append(word_slot)
            else:
                yield word_slot_list, label_list
                label_list = []
                word_slot_list = []