keras\preprocessing目录文件详解5.2(sequence.py)-keras学习笔记五

功能:用于预处理序列(例如一篇文章,句子)数据的实用工具。

keras-master\keras\preprocessing\sequence.py

建立词向量嵌入层,把输入文本转为可以进一步处理的数据格式(例如,矩阵)

Keras开发包文件目录

Keras实例文件目录

代码注释

# -*- coding: utf-8 -*-
"""Utilities for preprocessing sequence data.
用于预处理序列数据的实用工具。
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
import random
from six.moves import range


def pad_sequences(sequences, maxlen=None, dtype='int32',
                  padding='pre', truncating='pre', value=0.):
    """Pads each sequence to the same length (length of the longest sequence).
    填充使得每个序列都具有相同的长度(最长序列的长度)。

    If maxlen is provided, any sequence longer
    than maxlen is truncated to maxlen.
    如果提供了maxlen(最大长度),则任何比如果提供了maxlen长的序列都被截断到maxlen(长度)。
    Truncation happens off either the beginning (default) or
    the end of the sequence.
    截断发生在开始(默认)或序列结束时。

    Supports post-padding and pre-padding (default).
    支持后置填充和预填充(默认)。

    # Arguments
    参数
        sequences: list of lists where each element is a sequence
        sequences: 每个元素是序列的列表(列表中的每个元素是一个列表)。
        maxlen: int, maximum length
        maxlen: 整型,最大长度
        dtype: type to cast the resulting sequence.
        dtype: 生成结果序列的类型。
        padding: 'pre' or 'post', pad either before or after each sequence.
        padding: 前或后,在每个序列的前或后填充。
        truncating: 'pre' or 'post', remove values from sequences larger than
            maxlen either in the beginning or in the end of the sequence
        truncating: 前或后,在序列开始或结束时从大于maxlen的序列中移除值
        value: float, value to pad the sequences to the desired value.
        value: 浮点型,值将序列填充到期望值。

    # Returns
    返回
        x: numpy array with dimensions (number_of_sequences, maxlen)
        x: numpy数组,维度为 (number_of_sequences, maxlen)  ,其中number_of_sequences为序列数量,maxlen序列最大长度

    # Raises
    补充
        ValueError: in case of invalid values for `truncating` or `padding`,
            or in case of invalid shape for a `sequences` entry.
        ValueError: 在“truncating”或“padding”的无效值的情况下,或者对于“sequences”条目无效的形状。
    """
    if not hasattr(sequences, '__len__'):
        raise ValueError('`sequences` must be iterable.')
    lengths = []
    for x in sequences:
        if not hasattr(x, '__len__'):
            raise ValueError('`sequences` must be a list of iterables. '
                             'Found non-iterable: ' + str(x))
        lengths.append(len(x))

    num_samples = len(sequences)
    if maxlen is None:
        maxlen = np.max(lengths)

    # take the sample shape from the first non empty sequence
    # checking for consistency in the main loop below.
    # 从第一个非空序列检查中获取样本形状,以便在下面的主循环中获得一致性。
    sample_shape = tuple()
    for s in sequences:
        if len(s) > 0:
            sample_shape = np.asarray(s).shape[1:]
            break

    x = (np.ones((num_samples, maxlen) + sample_shape) * value).astype(dtype)
    for idx, s in enumerate(sequences):
        if not len(s):
            continue  # empty list/array was found
        if truncating == 'pre':
            trunc = s[-maxlen:]
        elif truncating == 'post':
            trunc = s[:maxlen]
        else:
            raise ValueError('Truncating type "%s" not understood' % truncating)

        # check `trunc` has expected shape
        # 检查“trunc”是否具有预期形状
        trunc = np.asarray(trunc, dtype=dtype)
        if trunc.shape[1:] != sample_shape:
            raise ValueError('Shape of sample %s of sequence at position %s is different from expected shape %s' %
                             (trunc.shape[1:], idx, sample_shape))

        if padding == 'post':
            x[idx, :len(trunc)] = trunc
        elif padding == 'pre':
            x[idx, -len(trunc):] = trunc
        else:
            raise ValueError('Padding type "%s" not understood' % padding)
    return x


def make_sampling_table(size, sampling_factor=1e-5):
    """Generates a word rank-based probabilistic sampling table.
    生成基于词秩的概率抽样表。

    This generates an array where the ith element
    is the probability that a word of rank i would be sampled,
    according to the sampling distribution used in word2vec.
    这就产生了一个数组,其中第i个元素是根据word2vec中使用的采样分布来对秩i进行采样的概率。

    The word2vec formula is:
    word2vec公式为:
        p(word) = min(1, sqrt(word.frequency/sampling_factor) / (word.frequency/sampling_factor))

    We assume that the word frequencies follow Zipf's law (s=1) to derive
    我们假设词频遵循Zipf定律(s=1)来推导。
    a numerical approximation of frequency(rank):
    频率(秩)的数值逼近:
       frequency(rank) ~ 1/(rank * (log(rank) + gamma) + 1/2 - 1/(12*rank))
        where gamma is the Euler-Mascheroni constant.
        其中Gamma是Euler-Mascheroni常数。

     Zipf's law(齐夫定律):https://en.wikipedia.org/wiki/Zipf%27s_law
     https://www.cnblogs.com/sddai/p/6081447.html


    # Arguments
    参数
        size: int, number of possible words to sample.
        size: 整型,可能的采样单词数。
        sampling_factor: the sampling factor in the word2vec formula.
        sampling_factor: word2vec公式中的采样因子。

    # Returns
    返回
        A 1D Numpy array of length `size` where the ith entry
        is the probability that a word of rank i should be sampled.
        长度为“size”的一维Numpy数组,其中第i个条目是应该对等级I进行采样的概率。
    """
    gamma = 0.577
    rank = np.arange(size)
    rank[0] = 1
    inv_fq = rank * (np.log(rank) + gamma) + 0.5 - 1. / (12. * rank)
    f = sampling_factor * inv_fq

    return np.minimum(1., f / np.sqrt(f))


def skipgrams(sequence, vocabulary_size,
              window_size=4, negative_samples=1., shuffle=True,
              categorical=False, sampling_table=None, seed=None):
    """Generates skipgram word pairs.
    生成skipgram单词对。
    skipgram:https://blog.csdn.net/u010665216/article/details/78721354?locationNum=7&fps=1

    Takes a sequence (list of indexes of words),
    returns couples of [word_index, other_word index] and labels (1s or 0s),
    where label = 1 if 'other_word' belongs to the context of 'word',
    and label=0 if 'other_word' is randomly sampled
    取一个序列(单词索引的列表),返回[word_index, other_word index]和标签(1s或0)的对,其中标签label = 1如
    果 'other_word' 属于'word'的上下文,同时标签label=0,如果'other_word'是随机抽样的。

    # Arguments
    参数
        sequence: a word sequence (sentence), encoded as a list
            of word indices (integers). If using a `sampling_table`,
            word indices are expected to match the rank
            of the words in a reference dataset (e.g. 10 would encode
            the 10-th most frequently occurring token).
            Note that index 0 is expected to be a non-word and will be skipped.
        sequence:一个单词序列(句子),被编码为单词索引(整数)的列表。如果使用“sampling_table”,则期
        望单词索引与参考数据集中的单词的等级相匹配(例如,10将编码第10个最频繁出现的分词)。
        注意,索引0预期为非单词,将被跳过。
        vocabulary_size: int. maximum possible word index + 1
        vocabulary_size: 整型。最大(值)可能是  word index + 1  (第一个词索引是0)
        window_size: int. actually half-window.
            The window of a word wi will be [i-window_size, i+window_size+1]
        window_size:整型。实际上是半窗口。
            一个单词Wi的窗口将是 [i-window_size, i+window_size+1]。
        negative_samples: float >= 0. 0 for no negative (=random) samples.
            1 for same number as positive samples. etc.
        negative_samples: 浮点数 >= 0。 0表示没有负(随机)样本。1表示和正样本相同数量。
        shuffle: whether to shuffle the word couples before returning them.
        shuffle: 在返回之前,是否重新整理(排序)词对。
        categorical: bool. if False, labels will be
            integers (eg. [0, 1, 1 .. ]),
            if True labels will be categorical eg. [[1,0],[0,1],[0,1] .. ]
        sampling_table: 1D array of size `vocabulary_size` where the entry i
            encodes the probability to sample a word of rank i.
        sampling_table:  `vocabulary_size` 大小的一维数组,其中条目i编码i等级词的采样概率。
        seed: random seed.
        seed: 随机种子

    # Returns
    返回
        couples, labels: where `couples` are int pairs and
            `labels` are either 0 or 1.
        couples, labels:`couples`是整数对,`labels`是 0 或者 1。

    # Note
    注意
        By convention, index 0 in the vocabulary is
        a non-word and will be skipped.
        按照惯例,词汇表中的索引0是非单词,将被跳过。
    """
    couples = []
    labels = []
    for i, wi in enumerate(sequence):
        if not wi:
            continue
        if sampling_table is not None:
            if sampling_table[wi] < random.random():
                continue

        window_start = max(0, i - window_size)
        window_end = min(len(sequence), i + window_size + 1)
        for j in range(window_start, window_end):
            if j != i:
                wj = sequence[j]
                if not wj:
                    continue
                couples.append([wi, wj])
                if categorical:
                    labels.append([0, 1])
                else:
                    labels.append(1)

    if negative_samples > 0:
        num_negative_samples = int(len(labels) * negative_samples)
        words = [c[0] for c in couples]
        random.shuffle(words)

        couples += [[words[i % len(words)],
                    random.randint(1, vocabulary_size - 1)] for i in range(num_negative_samples)]
        if categorical:
            labels += [[1, 0]] * num_negative_samples
        else:
            labels += [0] * num_negative_samples

    if shuffle:
        if seed is None:
            seed = random.randint(0, 10e6)
        random.seed(seed)
        random.shuffle(couples)
        random.seed(seed)
        random.shuffle(labels)

    return couples, labels


def _remove_long_seq(maxlen, seq, label):
    """Removes sequences that exceed the maximum length.
    移除超过最大长度的序列。

    # Arguments
    参数
        maxlen: int, maximum length
        maxlen: 整型,最大的长度
        seq: list of lists where each sublist is a sequence
        seq: 每个子列表是序列的序列列表
        label: list where each element is an integer
        label: 每个元素是整数的列表

    # Returns
    返回
        new_seq, new_label: shortened lists for `seq` and `label`.
        new_seq, new_label: `seq` 和 `label`.的缩短列表。
    """
    new_seq, new_label = [], []
    for x, y in zip(seq, label):
        if len(x) < maxlen:
            new_seq.append(x)
            new_label.append(y)
    return new_seq, new_label

代码执行

Keras详细介绍

英文:https://keras.io/

中文:http://keras-cn.readthedocs.io/en/latest/

实例下载

https://github.com/keras-team/keras

https://github.com/keras-team/keras/tree/master/examples

完整项目下载

方便没积分童鞋,请加企鹅452205574,共享文件夹。

包括:代码、数据集合(图片)、已生成model、安装库文件等。

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值