keras_tokenizer.py

# -*- coding: utf-8 -*-
"""Utilities for text input preprocessing.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import string
import sys
import warnings
from collections import OrderedDict
from collections import defaultdict
from hashlib import md5
import json

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

if sys.version_info < (3,):
    maketrans = string.maketrans
else:
    maketrans = str.maketrans


def text_to_word_sequence(text,
                          filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n',
                          lower=True, split=" "):
    """Converts a text to a sequence of words (or tokens).

    # Arguments
        text: Input text (string).
        filters: list (or concatenation) of characters to filter out, such as
            punctuation. Default: ``!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\\t\\n``,
            includes basic punctuation, tabs, and newlines.
        lower: boolean. Whether to convert the input to lowercase.
        split: str. Separator for word splitting.

    # Returns
        A list of words (or tokens).
    """
    if lower:
        text = text.lower()

    if sys.version_info < (3,):
        if isinstance(text, unicode):  # noqa: F821
            translate_map = {
                ord(c): unicode(split) for c in filters  # noqa: F821
            }
            text = text.translate(translate_map)
        elif len(split) == 1:
            translate_map = maketrans(filters, split * len(filters))
            text = text.translate(translate_map)
        else:
            for c in filters:
                text = text.replace(c, split)
    else:
        translate_dict = {c: split for c in filters}
        translate_map = maketrans(translate_dict)
        text = text.translate(translate_map)

    seq = text.split(split)
    return [i for i in seq if i]


def one_hot(text, n,
            filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n',
            lower=True,
            split=' ',
            analyzer=None):
    """One-hot encodes a text into a list of word indexes of size n.

    This is a wrapper to the `hashing_trick` function using `hash` as the
    hashing function; unicity of word to index mapping non-guaranteed.

    # Arguments
        text: Input text (string).
        n: int. Size of vocabulary.
        filters: list (or concatenation) of characters to filter out, such as
            punctuation. Default: ``!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\\t\\n``,
            includes basic punctuation, tabs, and newlines.
        lower: boolean. Whether to set the text to lowercase.
        split: str. Separator for word splitting.
        analyzer: function. Custom analyzer to split the text

    # Returns
        List of integers in [1, n]. Each integer encodes a word
        (unicity non-guaranteed).
    """
    return hashing_trick(text, n,
                         hash_function=hash,
                         filters=filters,
                         lower=lower,
                         split=split,
                         analyzer=analyzer)


def hashing_trick(text, n,
                  hash_function=None,
                  filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n',
                  lower=True,
                  split=' ',
                  analyzer=None):
    """Converts a text to a sequence of indexes in a fixed-size hashing space.

    # Arguments
        text: Input text (string).
        n: Dimension of the hashing space.
        hash_function: defaults to python `hash` function, can be 'md5' or
            any function that takes in input a string and returns a int.
            Note that 'hash' is not a stable hashing function, so
            it is not consistent across different runs, while 'md5'
            is a stable hashing function.
        filters: list (or concatenation) of characters to filter out, such as
            punctuation. Default: ``!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\\t\\n``,
            includes basic punctuation, tabs, and newlines.
        lower: boolean. Whether to set the text to lowercase.
        split: str. Separator for word splitting.
        analyzer: function. Custom analyzer to split the text

    # Returns
        A list of integer word indices (unicity non-guaranteed).

    `0` is a reserved index that won't be assigned to any word.

    Two or more words may be assigned to the same index, due to possible
    collisions by the hashing function.
    The [probability](
        https://en.wikipedia.org/wiki/Birthday_problem#Probability_table)
    of a collision is in relation to the dimension of the hashing space and
    the number of distinct objects.
    """
    if hash_function is None:
        hash_function = hash
    elif hash_function == 'md5':
        def hash_function(w):
            return int(md5(w.encode()).hexdigest(), 16)

    if analyzer is None:
        seq = text_to_word_sequence(text,
                                    filters=filters,
                                    lower=lower,
                                    split=split)
    else:
        seq = analyzer(text)

    return [(hash_function(w) % (n - 1) + 1) for w in seq]


class Tokenizer(object):
    """Text tokenization utility class.

    This class allows to vectorize a text corpus, by turning each
    text into either a sequence of integers (each integer being the index
    of a token in a dictionary) or into a vector where the coefficient
    for each token could be binary, based on word count, based on tf-idf...

    # Arguments
        num_words: the maximum number of words to keep, based
            on word frequency. Only the most common `num_words-1` words will
            be kept.
        filters: a string where each element is a character that will be
            filtered from the texts. The default is all punctuation, plus
            tabs and line breaks, minus the `'` character.
        lower: boolean. Whether to convert the texts to lowercase.
        split: str. Separator for word splitting.
        char_level: if True, every character will be treated as a token.
        oov_token: if given, it will be added to word_index and used to
            replace out-of-vocabulary words during text_to_sequence calls
        analyzer: function. Custom analyzer to split the text.
            The default analyzer is text_to_word_sequence

    By default, all punctuation is removed, turning the texts into
    space-separated sequences of words
    (words maybe include the `'` character). These sequences are then
    split into lists of tokens. They will then be indexed or vectorized.

    `0` is a reserved index that won't be assigned to any word.
    """

    def __init__(self, num_words=None,
                 filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n',
                 lower=True,
                 split=' ',
                 char_level=False,
                 oov_token=None,
                 document_count=0,
                 analyzer=None,
                 **kwargs):
        # Legacy support
        if 'nb_words' in kwargs:
            warnings.warn('The `nb_words` argument in `Tokenizer` '
                          'has been renamed `num_words`.')
            num_words = kwargs.pop('nb_words')
        if kwargs:
            raise TypeError('Unrecognized keyword arguments: ' + str(kwargs))

        self.word_counts = OrderedDict()
        self.word_docs = defaultdict(int)
        self.filters = filters
        self.split = split
        self.lower = lower
        self.num_words = num_words
        self.document_count = document_count
        self.char_level = char_level
        self.oov_token = oov_token
        self.index_docs = defaultdict(int)
        self.word_index = {}
        self.index_word = {}
        self.analyzer = analyzer

    def fit_on_texts(self, texts):
        """Updates internal vocabulary based on a list of texts.

        In the case where texts contains lists,
        we assume each entry of the lists to be a token.

        Required before using `texts_to_sequences` or `texts_to_matrix`.

        # Arguments
            texts: can be a list of strings,
                a generator of strings (for memory-efficiency),
                or a list of list of strings.
        """
        for text in texts:
            self.document_count += 1
            if self.char_level or isinstance(text, list):
                if self.lower:
                    if isinstance(text, list):
                        text = [text_elem.lower() for text_elem in text]
                    else:
                        text = text.lower()
                seq = text
            else:
                if self.analyzer is None:
                    seq = text_to_word_sequence(text,
                                                filters=self.filters,
                                                lower=self.lower,
                                                split=self.split)
                else:
                    seq = self.analyzer(text)
            for w in seq:
                if w in self.word_counts:
                    self.word_counts[w] += 1
                else:
                    self.word_counts[w] = 1
            for w in set(seq):
                # In how many documents each word occurs
                self.word_docs[w] += 1

        wcounts = list(self.word_counts.items())
        wcounts.sort(key=lambda x: x[1], reverse=True)
        # forcing the oov_token to index 1 if it exists
        if self.oov_token is None:
            sorted_voc = []
        else:
            sorted_voc = [self.oov_token]
        sorted_voc.extend(wc[0] for wc in wcounts)

        # note that index 0 is reserved, never assigned to an existing word
        self.word_index = dict(
            zip(sorted_voc, list(range(1, len(sorted_voc) + 1))))

        self.index_word = {c: w for w, c in self.word_index.items()}

        for w, c in list(self.word_docs.items()):
            self.index_docs[self.word_index[w]] = c

    def fit_on_sequences(self, sequences):
        """Updates internal vocabulary based on a list of sequences.

        Required before using `sequences_to_matrix`
        (if `fit_on_texts` was never called).

        # Arguments
            sequences: A list of sequence.
                A "sequence" is a list of integer word indices.
        """
        self.document_count += len(sequences)
        for seq in sequences:
            seq = set(seq)
            for i in seq:
                self.index_docs[i] += 1

    def texts_to_sequences(self, texts):
        """Transforms each text in texts to a sequence of integers.

        Only top `num_words-1` most frequent words will be taken into account.
        Only words known by the tokenizer will be taken into account.

        # Arguments
            texts: A list of texts (strings).

        # Returns
            A list of sequences.
        """
        return list(self.texts_to_sequences_generator(texts))

    def texts_to_sequences_generator(self, texts):
        """Transforms each text in `texts` to a sequence of integers.

        Each item in texts can also be a list,
        in which case we assume each item of that list to be a token.

        Only top `num_words-1` most frequent words will be taken into account.
        Only words known by the tokenizer will be taken into account.

        # Arguments
            texts: A list of texts (strings).

        # Yields
            Yields individual sequences.
        """
        num_words = self.num_words
        oov_token_index = self.word_index.get(self.oov_token)
        for text in texts:
            if self.char_level or isinstance(text, list):
                if self.lower:
                    if isinstance(text, list):
                        text = [text_elem.lower() for text_elem in text]
                    else:
                        text = text.lower()
                seq = text
            else:
                if self.analyzer is None:
                    seq = text_to_word_sequence(text,
                                                filters=self.filters,
                                                lower=self.lower,
                                                split=self.split)
                else:
                    seq = self.analyzer(text)
            vect = []
            for w in seq:
                i = self.word_index.get(w)
                if i is not None:
                    if num_words and i >= num_words:
                        if oov_token_index is not None:
                            vect.append(oov_token_index)
                    else:
                        vect.append(i)
                elif self.oov_token is not None:
                    vect.append(oov_token_index)
            yield vect

    def sequences_to_texts(self, sequences):
        """Transforms each sequence into a list of text.

        Only top `num_words-1` most frequent words will be taken into account.
        Only words known by the tokenizer will be taken into account.

        # Arguments
            sequences: A list of sequences (list of integers).

        # Returns
            A list of texts (strings)
        """
        return list(self.sequences_to_texts_generator(sequences))

    def sequences_to_texts_generator(self, sequences):
        """Transforms each sequence in `sequences` to a list of texts(strings).

        Each sequence has to a list of integers.
        In other words, sequences should be a list of sequences

        Only top `num_words-1` most frequent words will be taken into account.
        Only words known by the tokenizer will be taken into account.

        # Arguments
            sequences: A list of sequences.

        # Yields
            Yields individual texts.
        """
        num_words = self.num_words
        oov_token_index = self.word_index.get(self.oov_token)
        for seq in sequences:
            vect = []
            for num in seq:
                word = self.index_word.get(num)
                if word is not None:
                    if num_words and num >= num_words:
                        if oov_token_index is not None:
                            vect.append(self.index_word[oov_token_index])
                    else:
                        vect.append(word)
                elif self.oov_token is not None:
                    vect.append(self.index_word[oov_token_index])
            vect = ' '.join(vect)
            yield vect

    def texts_to_matrix(self, texts, mode='binary'):
        """Convert a list of texts to a Numpy matrix.

        # Arguments
            texts: list of strings.
            mode: one of "binary", "count", "tfidf", "freq".

        # Returns
            A Numpy matrix.
        """
        sequences = self.texts_to_sequences(texts)
        return self.sequences_to_matrix(sequences, mode=mode)

    def sequences_to_matrix(self, sequences, mode='binary'):
        """Converts a list of sequences into a Numpy matrix.

        # Arguments
            sequences: list of sequences
                (a sequence is a list of integer word indices).
            mode: one of "binary", "count", "tfidf", "freq"

        # Returns
            A Numpy matrix.

        # Raises
            ValueError: In case of invalid `mode` argument,
                or if the Tokenizer requires to be fit to sample data.
        """
        if not self.num_words:
            if self.word_index:
                num_words = len(self.word_index) + 1
            else:
                raise ValueError('Specify a dimension (`num_words` argument), '
                                 'or fit on some text data first.')
        else:
            num_words = self.num_words

        if mode == 'tfidf' and not self.document_count:
            raise ValueError('Fit the Tokenizer on some data '
                             'before using tfidf mode.')

        x = np.zeros((len(sequences), num_words))
        for i, seq in enumerate(sequences):
            if not seq:
                continue
            counts = defaultdict(int)
            for j in seq:
                if j >= num_words:
                    continue
                counts[j] += 1
            for j, c in list(counts.items()):
                if mode == 'count':
                    x[i][j] = c
                elif mode == 'freq':
                    x[i][j] = c / len(seq)
                elif mode == 'binary':
                    x[i][j] = 1
                elif mode == 'tfidf':
                    # Use weighting scheme 2 in
                    # https://en.wikipedia.org/wiki/Tf%E2%80%93idf
                    tf = 1 + np.log(c)
                    idf = np.log(1 + self.document_count /
                                 (1 + self.index_docs.get(j, 0)))
                    x[i][j] = tf * idf
                else:
                    raise ValueError('Unknown vectorization mode:', mode)
        return x

    def get_config(self):
        '''Returns the tokenizer configuration as Python dictionary.
        The word count dictionaries used by the tokenizer get serialized
        into plain JSON, so that the configuration can be read by other
        projects.

        # Returns
            A Python dictionary with the tokenizer configuration.
        '''
        json_word_counts = json.dumps(self.word_counts)
        json_word_docs = json.dumps(self.word_docs)
        json_index_docs = json.dumps(self.index_docs)
        json_word_index = json.dumps(self.word_index)
        json_index_word = json.dumps(self.index_word)

        return {
            'num_words': self.num_words,
            'filters': self.filters,
            'lower': self.lower,
            'split': self.split,
            'char_level': self.char_level,
            'oov_token': self.oov_token,
            'document_count': self.document_count,
            'word_counts': json_word_counts,
            'word_docs': json_word_docs,
            'index_docs': json_index_docs,
            'index_word': json_index_word,
            'word_index': json_word_index
        }

    def to_json(self, **kwargs):
        """Returns a JSON string containing the tokenizer configuration.
        To load a tokenizer from a JSON string, use
        `keras.preprocessing.text.tokenizer_from_json(json_string)`.

        # Arguments
            **kwargs: Additional keyword arguments
                to be passed to `json.dumps()`.

        # Returns
            A JSON string containing the tokenizer configuration.
        """
        config = self.get_config()
        tokenizer_config = {
            'class_name': self.__class__.__name__,
            'config': config
        }
        return json.dumps(tokenizer_config, **kwargs)


def tokenizer_from_json(json_string):
    """Parses a JSON tokenizer configuration file and returns a
    tokenizer instance.

    # Arguments
        json_string: JSON string encoding a tokenizer configuration.

    # Returns
        A Keras Tokenizer instance
    """
    tokenizer_config = json.loads(json_string)
    config = tokenizer_config.get('config')

    word_counts = json.loads(config.pop('word_counts'))
    word_docs = json.loads(config.pop('word_docs'))
    index_docs = json.loads(config.pop('index_docs'))
    # Integer indexing gets converted to strings with json.dumps()
    index_docs = {int(k): v for k, v in index_docs.items()}
    index_word = json.loads(config.pop('index_word'))
    index_word = {int(k): v for k, v in index_word.items()}
    word_index = json.loads(config.pop('word_index'))

    tokenizer = Tokenizer(**config)
    tokenizer.word_counts = word_counts
    tokenizer.word_docs = word_docs
    tokenizer.index_docs = index_docs
    tokenizer.word_index = word_index
    tokenizer.index_word = index_word

    return tokenizer