[source]

TimeseriesGenerator

  1. keras.preprocessing.sequence.TimeseriesGenerator(data, targets, length, sampling_rate=1, stride=1, start_index=0, end_index=None, shuffle=False, reverse=False, batch_size=128)

Utility class for generating batches of temporal data.

This class takes in a sequence of data-points gathered atequal intervals, along with time series parameters such asstride, length of history, etc., to produce batches fortraining/validation.

Arguments

  • data: Indexable generator (such as list or Numpy array) containing consecutive data points (timesteps). The data should be at 2D, and axis 0 is expected to be the time dimension.
  • targets: Targets corresponding to timesteps in data. It should have same length as data.
  • length: Length of the output sequences (in number of timesteps).
  • sampling_rate: Period between successive individual timesteps within sequences. For rate r, timesteps data[i], data[i-r], … data[i - length] are used for create a sample sequence.
  • stride: Period between successive output sequences. For stride s, consecutive output samples would be centered around data[i], data[i+s], data[i+2*s], etc.
  • start_index: Data points earlier than start_index will not be used in the output sequences. This is useful to reserve part of the data for test or validation.
  • end_index: Data points later than end_index will not be used in the output sequences. This is useful to reserve part of the data for test or validation.
  • shuffle: Whether to shuffle output samples, or instead draw them in chronological order.
  • reverse: Boolean: if true, timesteps in each output sample will be in reverse chronological order.
  • batch_size: Number of timeseries samples in each batch (except maybe the last one).

Returns

A Sequence instance.

Examples

  1. from keras.preprocessing.sequence import TimeseriesGenerator
  2. import numpy as np
  4. data = np.array([[i] for i in range(50)])
  5. targets = np.array([[i] for i in range(50)])
  7. data_gen = TimeseriesGenerator(data, targets,
  8.                                length=10, sampling_rate=2,
  9.                                batch_size=2)
  10. assert len(data_gen) == 20
  12. batch_0 = data_gen[0]
  13. x, y = batch_0
  14. assert np.array_equal(x,
  15.                       np.array([[[0], [2], [4], [6], [8]],
  16.                                 [[1], [3], [5], [7], [9]]]))
  17. assert np.array_equal(y,
  18.                       np.array([[10], [11]]))

pad_sequences

  1. keras.preprocessing.sequence.pad_sequences(sequences, maxlen=None, dtype='int32', padding='pre', truncating='pre', value=0.0)

Pads sequences to the same length.

This function transforms a list ofnum_samples sequences (lists of integers)into a 2D Numpy array of shape (num_samples, num_timesteps).num_timesteps is either the maxlen argument if provided,or the length of the longest sequence otherwise.

Sequences that are shorter than num_timestepsare padded with value at the end.

Sequences longer than num_timesteps are truncatedso that they fit the desired length.The position where padding or truncation happens is determined bythe arguments padding and truncating, respectively.

Pre-padding is the default.

Arguments

  • sequences: List of lists, where each element is a sequence.
  • maxlen: Int, maximum length of all sequences.
  • dtype: Type of the output sequences. To pad sequences with variable length strings, you can use object.
  • padding: String, 'pre' or 'post': pad either before or after each sequence.
  • truncating: String, 'pre' or 'post': remove values from sequences larger than maxlen, either at the beginning or at the end of the sequences.
  • value: Float or String, padding value.

Returns

  • x: Numpy array with shape (len(sequences), maxlen)

Raises

  • ValueError: In case of invalid values for truncating or padding, or in case of invalid shape for a sequences entry.

skipgrams

  1. keras.preprocessing.sequence.skipgrams(sequence, vocabulary_size, window_size=4, negative_samples=1.0, shuffle=True, categorical=False, sampling_table=None, seed=None)

Generates skipgram word pairs.

This function transforms a sequence of word indexes (list of integers)into tuples of words of the form:

  • (word, word in the same window), with label 1 (positive samples).
  • (word, random word from the vocabulary), with label 0 (negative samples).

Read more about Skipgram in this gnomic paper by Mikolov et al.:Efficient Estimation of Word Representations inVector Space

Arguments

  • 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.
  • vocabulary_size: Int, maximum possible word index + 1
  • window_size: Int, size of sampling windows (technically half-window). The window of a word w_i will be [i - window_size, i + window_size+1].
  • negative_samples: Float >= 0. 0 for no negative (i.e. random) samples. 1 for same number as positive samples.
  • shuffle: Whether to shuffle the word couples before returning them.
  • categorical: bool. if False, labels will be integers (eg. [0, 1, 1 .. ]), if True, labels will be categorical, e.g. [[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.
  • seed: Random seed.

Returns

couples, labels: where couples are int pairs and labels are either 0 or 1.

Note

By convention, index 0 in the vocabulary isa non-word and will be skipped.

make_sampling_table

  1. keras.preprocessing.sequence.make_sampling_table(size, sampling_factor=1e-05)

Generates a word rank-based probabilistic sampling table.

Used for generating the sampling_table argument for skipgrams.sampling_table[i] is the probability of samplingthe word i-th most common word in a dataset(more common words should be sampled less frequently, for balance).

The sampling probabilities are generated accordingto the sampling distribution used in word2vec:

  1. p(word) = (min(1, sqrt(word_frequency / sampling_factor) /
  2.     (word_frequency / sampling_factor)))

We assume that the word frequencies follow Zipf's law (s=1) to derivea numerical approximation of frequency(rank):

frequency(rank) ~ 1/(rank (log(rank) + gamma) + 1/2 - 1/(12rank))where gamma is the Euler-Mascheroni constant.

Arguments

  • size: Int, number of possible words to sample.
  • sampling_factor: The sampling factor in the word2vec formula.

Returns

A 1D Numpy array of length size where the ith entryis the probability that a word of rank i should be sampled.