utils.py 10.1 KB
Newer Older
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 40
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
#   Copyright (c) 2019 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 unicode_literals
import sys
import os
import random
import paddle
import logging
import paddle.fluid as fluid
import numpy as np
import collections
import six
import codecs
try:
    import configparser as cp
except ImportError:
    import ConfigParser as cp

random_seed = 7
logger = logging.getLogger()
format = "%(asctime)s - %(name)s - %(levelname)s -%(filename)s-%(lineno)4d -%(message)s"
# format = "%(levelname)8s: %(asctime)s: %(filename)s:%(lineno)4d %(message)s"
logging.basicConfig(format=format)
logger.setLevel(logging.INFO)
41
logger = logging.getLogger('Paddle-DDC')
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78


def str2bool(v):
    """[ because argparse does not support to parse "true, False" as python
     boolean directly]
    Arguments:
        v {[type]} -- [description]
    Returns:
        [type] -- [description]
    """
    return v.lower() in ("true", "t", "1")


def to_lodtensor(data, place):
    """
    convert ot LODtensor
    """
    seq_lens = [len(seq) for seq in data]
    cur_len = 0
    lod = [cur_len]
    for l in seq_lens:
        cur_len += l
        lod.append(cur_len)
    flattened_data = np.concatenate(data, axis=0).astype("int64")
    flattened_data = flattened_data.reshape([len(flattened_data), 1])
    res = fluid.LoDTensor()
    res.set(flattened_data, place)
    res.set_lod([lod])
    return res


class ArgumentGroup(object):
    """[ArgumentGroup]
    
    Arguments:
        object {[type]} -- [description]
    """
79

80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
    def __init__(self, parser, title, des):
        self._group = parser.add_argument_group(title=title, description=des)

    def add_arg(self, name, type, default, help, **kwargs):
        """[add_arg]
        
        Arguments:
            name {[type]} -- [description]
            type {[type]} -- [description]
            default {[type]} -- [description]
            help {[type]} -- [description]
        """
        type = str2bool if type == bool else type
        self._group.add_argument(
            "--" + name,
            default=default,
            type=type,
            help=help + ' Default: %(default)s.',
            **kwargs)


class DataReader(object):
    """[get data generator for dataset]
    
    Arguments:
        object {[type]} -- [description]
    
    Returns:
        [type] -- [description]
    """
110

111 112 113 114 115 116 117 118
    def __init__(self, char_vocab, intent_dict, max_len):
        self._char_vocab = char_vocab
        self._intent_dict = intent_dict
        self._oov_id = 0
        self.intent_size = len(intent_dict)
        self.all_data = []
        self.max_len = max_len
        self.padding_id = 0
119

120 121
    def _get_num_examples(self):
        return len(self.all_data)
122

123 124 125 126 127 128 129 130 131
    def prepare_data(self, data_path, batch_size, mode):
        """
        prepare data
        """
        # print word_dict_path
        # assert os.path.exists(
        #     word_dict_path), "The given word dictionary dose not exist."
        assert os.path.exists(data_path), "The given data file does not exist."
        if mode == "train":
132 133 134 135 136 137
            train_reader = fluid.io.batch(
                paddle.reader.shuffle(
                    self.data_reader(
                        data_path, self.max_len, shuffle=True),
                    buf_size=batch_size * 100),
                batch_size)
138 139 140
            # train_reader = fluid.io.batch(self.data_reader(data_path), batch_size)                   
            return train_reader
        else:
141 142
            test_reader = fluid.io.batch(
                self.data_reader(data_path, self.max_len), batch_size)
143 144 145 146 147 148 149
            return test_reader

    def data_reader(self, file_path, max_len, shuffle=False):
        """
        Convert query into id list
        use fixed voc
        """
150

151 152 153 154 155 156 157 158
        for line in codecs.open(file_path, "r", encoding="utf8"):
            line = line.strip()
            if isinstance(line, six.binary_type):
                line = line.decode("utf8", errors="ignore")
            query, intent = line.split("\t")
            char_id_list = list(map(lambda x: 0 if x not in self._char_vocab else int(self._char_vocab[x]), \
                            list(query)))
            if len(char_id_list) < max_len:
159 160
                char_id_list.extend([self.padding_id] *
                                    (max_len - len(char_id_list)))
161 162 163 164 165 166 167 168
            char_id_list = char_id_list[:max_len]
            intent_id_list = [self.padding_id] * self.intent_size
            for item in intent.split('\2'):
                intent_id_list[int(self._intent_dict[item])] = 1
            self.all_data.append([char_id_list, intent_id_list])
        if shuffle:
            random.seed(random_seed)
            random.shuffle(self.all_data)
169

170 171 172 173 174 175 176
        def reader():
            """
            reader
            """
            for char_id_list, intent_id_list in self.all_data:
                # print char_id_list, intent_id
                yield char_id_list, intent_id_list
177

178 179 180 181 182 183 184 185 186 187 188 189
        return reader


class DataProcesser(object):
    """[file process methods]
    
    Arguments:
        object {[type]} -- [description]
    
    Returns:
        [type] -- [description]
    """
190

191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
    @staticmethod
    def read_dict(filename):
        """
        read_dict: key\2value
        """
        res_dict = {}
        for line in codecs.open(filename, encoding="utf8"):
            try:
                if isinstance(line, six.binary_type):
                    line = line.strip().decode("utf8")
                line = line.strip()
                key, value = line.strip().split("\2")
                res_dict[key] = value
            except Exception as err:
                logger.error(str(err))
                logger.error("read dict[%s] failed" % filename)
        return res_dict

    @staticmethod
    def build_dict(filename, save_dir, min_num_char=2, min_num_intent=2):
        """[build_dict  from file]
        
        Arguments:
            filename {[type]} -- [description]
            save_dir {[type]} -- [description]
        
        Keyword Arguments:
            min_num_char {int} -- [description] (default: {2})
            min_num_intent {int} -- [description] (default: {2})
        """
        char_dict = {}
        intent_dict = {}
        # readfile
224
        for line in codecs.open(filename):
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
            line = line.strip()
            if isinstance(line, six.binary_type):
                line = line.strip().decode("utf8", errors="ignore")
            query, intents = line.split("\t")
            # read query
            for char_item in list(query):
                if char_item not in char_dict:
                    char_dict[char_item] = 0
                char_dict[char_item] += 1
            # read intents
            for intent in intents.split('\002'):
                if intent not in intent_dict:
                    intent_dict[intent] = 0
                intent_dict[intent] += 1
        #   save char dict
240 241
        with codecs.open(
                "%s/char.dict" % save_dir, "w", encoding="utf8") as f_out:
242 243 244 245 246 247 248 249 250 251
            f_out.write("PAD\0020\n")
            f_out.write("OOV\0021\n")
            char_id = 2
            for key, value in char_dict.items():
                if value >= min_num_char:
                    if isinstance(key, six.binary_type):
                        key = key.encode("utf8")
                    f_out.write("%s\002%d\n" % (key, char_id))
                    char_id += 1
        #   save intent dict
252 253
        with codecs.open(
                "%s/domain.dict" % save_dir, "w", encoding="utf8") as f_out:
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299
            f_out.write("SYS_OTHER\0020\n")
            intent_id = 1
            for key, value in intent_dict.items():
                if value >= min_num_intent and key != u'SYS_OTHER':
                    if isinstance(key, six.binary_type):
                        key = key.encode("utf8")
                    f_out.write("%s\002%d\n" % (key, intent_id))
                    intent_id += 1


class ConfigReader(object):
    """[read model config file]
    
    Arguments:
        object {[type]} -- [description]
    
    Returns:
        [type] -- [description]
    """

    @staticmethod
    def read_conf(conf_file):
        """[read_conf]
        
        Arguments:
            conf_file {[type]} -- [description]
        
        Returns:
            [type] -- [description]
        """
        flow_data = collections.defaultdict(lambda: {})
        class2key = set(["model"])
        param_conf = cp.ConfigParser()
        param_conf.read(conf_file)
        for section in param_conf.sections():
            if section not in class2key:
                continue
            for option in param_conf.items(section):
                flow_data[section][option[0]] = eval(option[1])
        return flow_data


def init_checkpoint(exe, init_checkpoint_path, main_program):
    """
    Init CheckPoint
    """
300 301
    fluid.load(main_program, init_checkpoint_path, exe)
    print("Load model from {}".format(init_checkpoint_path))
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327


def print_arguments(args):
    """
    Print Arguments
    """
    print('-----------  Configuration Arguments -----------')
    for arg, value in sorted(six.iteritems(vars(args))):
        print('%s: %s' % (arg, value))
    print('------------------------------------------------')


def check_version(version='1.6.0'):
    """
    Log error and exit when the installed version of paddlepaddle is
    not satisfied.
    """
    err = "PaddlePaddle version 1.6 or higher is required, " \
          "or a suitable develop version is satisfied as well. \n" \
          "Please make sure the version is good with your code." \

    try:
        fluid.require_version(version)
    except Exception as e:
        logger.error(err)
        sys.exit(1)