Module keras.api.keras.datasets.imdb

Public API for tf.keras.datasets.imdb namespace.

Expand source code
# This file is MACHINE GENERATED! Do not edit.
# Generated by: tensorflow/python/tools/api/generator/create_python_api.py script.
"""Public API for tf.keras.datasets.imdb namespace.
"""

from __future__ import print_function as _print_function

import sys as _sys

from keras.datasets.imdb import get_word_index
from keras.datasets.imdb import load_data

del _print_function

from tensorflow.python.util import module_wrapper as _module_wrapper

if not isinstance(_sys.modules[__name__], _module_wrapper.TFModuleWrapper):
  _sys.modules[__name__] = _module_wrapper.TFModuleWrapper(
      _sys.modules[__name__], "keras.datasets.imdb", public_apis=None, deprecation=True,
      has_lite=False)

Functions

def get_word_index(path='imdb_word_index.json')

Retrieves a dict mapping words to their index in the IMDB dataset.

Args

path
where to cache the data (relative to ~/.keras/dataset).

Returns

The word index dictionary. Keys are word strings, values are their index. Example:

# Retrieve the training sequences.
(x_train, _), _ = keras.datasets.imdb.load_data()
# Retrieve the word index file mapping words to indices
word_index = keras.datasets.imdb.get_word_index()
# Reverse the word index to obtain a dict mapping indices to words
inverted_word_index = dict((i, word) for (word, i) in word_index.items())
# Decode the first sequence in the dataset
decoded_sequence = " ".join(inverted_word_index[i] for i in x_train[0])
Expand source code
@keras_export('keras.datasets.imdb.get_word_index')
def get_word_index(path='imdb_word_index.json'):
  """Retrieves a dict mapping words to their index in the IMDB dataset.

  Args:
      path: where to cache the data (relative to `~/.keras/dataset`).

  Returns:
      The word index dictionary. Keys are word strings, values are their index.

  Example:

  ```python
  # Retrieve the training sequences.
  (x_train, _), _ = keras.datasets.imdb.load_data()
  # Retrieve the word index file mapping words to indices
  word_index = keras.datasets.imdb.get_word_index()
  # Reverse the word index to obtain a dict mapping indices to words
  inverted_word_index = dict((i, word) for (word, i) in word_index.items())
  # Decode the first sequence in the dataset
  decoded_sequence = " ".join(inverted_word_index[i] for i in x_train[0])
  ```
  """
  origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
  path = get_file(
      path,
      origin=origin_folder + 'imdb_word_index.json',
      file_hash='bfafd718b763782e994055a2d397834f')
  with open(path) as f:
    return json.load(f)
def load_data(path='imdb.npz', num_words=None, skip_top=0, maxlen=None, seed=113, start_char=1, oov_char=2, index_from=3, **kwargs)

Loads the IMDB dataset.

This is a dataset of 25,000 movies reviews from IMDB, labeled by sentiment (positive/negative). Reviews have been preprocessed, and each review is encoded as a list of word indexes (integers). For convenience, words are indexed by overall frequency in the dataset, so that for instance the integer "3" encodes the 3rd most frequent word in the data. This allows for quick filtering operations such as: "only consider the top 10,000 most common words, but eliminate the top 20 most common words".

As a convention, "0" does not stand for a specific word, but instead is used to encode any unknown word.

Args

path
where to cache the data (relative to ~/.keras/dataset).
num_words
integer or None. Words are ranked by how often they occur (in the training set) and only the num_words most frequent words are kept. Any less frequent word will appear as oov_char value in the sequence data. If None, all words are kept. Defaults to None, so all words are kept.
skip_top
skip the top N most frequently occurring words (which may not be informative). These words will appear as oov_char value in the dataset. Defaults to 0, so no words are skipped.
maxlen
int or None. Maximum sequence length. Any longer sequence will be truncated. Defaults to None, which means no truncation.
seed
int. Seed for reproducible data shuffling.
start_char
int. The start of a sequence will be marked with this character. Defaults to 1 because 0 is usually the padding character.
oov_char
int. The out-of-vocabulary character. Words that were cut out because of the num_words or skip_top limits will be replaced with this character.
index_from
int. Index actual words with this index and higher.
**kwargs
Used for backwards compatibility.

Returns

Tuple of Numpy arrays
(x_train, y_train), (x_test, y_test).

x_train, x_test: lists of sequences, which are lists of indexes (integers). If the num_words argument was specific, the maximum possible index value is num_words - 1. If the maxlen argument was specified, the largest possible sequence length is maxlen.

y_train, y_test: lists of integer labels (1 or 0).

Raises

ValueError
in case maxlen is so low that no input sequence could be kept.

Note that the 'out of vocabulary' character is only used for words that were present in the training set but are not included because they're not making the num_words cut here. Words that were not seen in the training set but are in the test set have simply been skipped.

Expand source code
@keras_export('keras.datasets.imdb.load_data')
def load_data(path='imdb.npz',
              num_words=None,
              skip_top=0,
              maxlen=None,
              seed=113,
              start_char=1,
              oov_char=2,
              index_from=3,
              **kwargs):
  """Loads the [IMDB dataset](https://ai.stanford.edu/~amaas/data/sentiment/).

  This is a dataset of 25,000 movies reviews from IMDB, labeled by sentiment
  (positive/negative). Reviews have been preprocessed, and each review is
  encoded as a list of word indexes (integers).
  For convenience, words are indexed by overall frequency in the dataset,
  so that for instance the integer "3" encodes the 3rd most frequent word in
  the data. This allows for quick filtering operations such as:
  "only consider the top 10,000 most
  common words, but eliminate the top 20 most common words".

  As a convention, "0" does not stand for a specific word, but instead is used
  to encode any unknown word.

  Args:
    path: where to cache the data (relative to `~/.keras/dataset`).
    num_words: integer or None. Words are
        ranked by how often they occur (in the training set) and only
        the `num_words` most frequent words are kept. Any less frequent word
        will appear as `oov_char` value in the sequence data. If None,
        all words are kept. Defaults to None, so all words are kept.
    skip_top: skip the top N most frequently occurring words
        (which may not be informative). These words will appear as
        `oov_char` value in the dataset. Defaults to 0, so no words are
        skipped.
    maxlen: int or None. Maximum sequence length.
        Any longer sequence will be truncated. Defaults to None, which
        means no truncation.
    seed: int. Seed for reproducible data shuffling.
    start_char: int. The start of a sequence will be marked with this
        character. Defaults to 1 because 0 is usually the padding character.
    oov_char: int. The out-of-vocabulary character.
        Words that were cut out because of the `num_words` or
        `skip_top` limits will be replaced with this character.
    index_from: int. Index actual words with this index and higher.
    **kwargs: Used for backwards compatibility.

  Returns:
    Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.

  **x_train, x_test**: lists of sequences, which are lists of indexes
    (integers). If the num_words argument was specific, the maximum
    possible index value is `num_words - 1`. If the `maxlen` argument was
    specified, the largest possible sequence length is `maxlen`.

  **y_train, y_test**: lists of integer labels (1 or 0).

  Raises:
    ValueError: in case `maxlen` is so low
        that no input sequence could be kept.

  Note that the 'out of vocabulary' character is only used for
  words that were present in the training set but are not included
  because they're not making the `num_words` cut here.
  Words that were not seen in the training set but are in the test set
  have simply been skipped.
  """
  # Legacy support
  if 'nb_words' in kwargs:
    logging.warning('The `nb_words` argument in `load_data` '
                    'has been renamed `num_words`.')
    num_words = kwargs.pop('nb_words')
  if kwargs:
    raise TypeError('Unrecognized keyword arguments: ' + str(kwargs))

  origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
  path = get_file(
      path,
      origin=origin_folder + 'imdb.npz',
      file_hash=
      '69664113be75683a8fe16e3ed0ab59fda8886cb3cd7ada244f7d9544e4676b9f')
  with np.load(path, allow_pickle=True) as f:  # pylint: disable=unexpected-keyword-arg
    x_train, labels_train = f['x_train'], f['y_train']
    x_test, labels_test = f['x_test'], f['y_test']

  rng = np.random.RandomState(seed)
  indices = np.arange(len(x_train))
  rng.shuffle(indices)
  x_train = x_train[indices]
  labels_train = labels_train[indices]

  indices = np.arange(len(x_test))
  rng.shuffle(indices)
  x_test = x_test[indices]
  labels_test = labels_test[indices]

  if start_char is not None:
    x_train = [[start_char] + [w + index_from for w in x] for x in x_train]
    x_test = [[start_char] + [w + index_from for w in x] for x in x_test]
  elif index_from:
    x_train = [[w + index_from for w in x] for x in x_train]
    x_test = [[w + index_from for w in x] for x in x_test]

  if maxlen:
    x_train, labels_train = _remove_long_seq(maxlen, x_train, labels_train)
    x_test, labels_test = _remove_long_seq(maxlen, x_test, labels_test)
    if not x_train or not x_test:
      raise ValueError('After filtering for sequences shorter than maxlen=' +
                       str(maxlen) + ', no sequence was kept. '
                       'Increase maxlen.')

  xs = x_train + x_test
  labels = np.concatenate([labels_train, labels_test])

  if not num_words:
    num_words = max(max(x) for x in xs)

  # by convention, use 2 as OOV word
  # reserve 'index_from' (=3 by default) characters:
  # 0 (padding), 1 (start), 2 (OOV)
  if oov_char is not None:
    xs = [
        [w if (skip_top <= w < num_words) else oov_char for w in x] for x in xs
    ]
  else:
    xs = [[w for w in x if skip_top <= w < num_words] for x in xs]

  idx = len(x_train)
  x_train, y_train = np.array(xs[:idx], dtype='object'), labels[:idx]
  x_test, y_test = np.array(xs[idx:], dtype='object'), labels[idx:]
  return (x_train, y_train), (x_test, y_test)