hhM6dZddlZddlZddlZddlmZddlmZdZ edGddejZ ed d d Z ed  dd Z y)aiUtilities for preprocessing sequence data. Deprecated: `tf.keras.preprocessing.sequence` APIs are not recommended for new code. Prefer `tf.keras.utils.timeseries_dataset_from_array` and the `tf.data` APIs which provide a much more flexible mechanisms for dealing with sequences. See the [tf.data guide](https://www.tensorflow.org/guide/data) for more details. N) data_utils) keras_exportcgg}}t||D]6\}}t||ks|j||j|8||fS)aCRemoves sequences that exceed the maximum length. Args: maxlen: Int, maximum length of the output sequences. seq: List of lists, where each sublist is a sequence. label: List where each element is an integer. Returns: new_seq, new_label: shortened lists for `seq` and `label`. )ziplenappend)maxlenseqlabelnew_seq new_labelxys a/var/www/html/dev/engine/venv/lib/python3.12/site-packages/tf_keras/src/preprocessing/sequence.py_remove_long_seqr$sXRYGC 1 q6F? NN1    Q   I z0keras.preprocessing.sequence.TimeseriesGeneratorc>eZdZdZ ddZdZdZdZdZy) TimeseriesGeneratora$ Utility class for generating batches of temporal data. Deprecated: `tf.keras.preprocessing.sequence.TimeseriesGenerator` does not operate on tensors and is not recommended for new code. Prefer using a `tf.data.Dataset` which provides a more efficient and flexible mechanism for batching, shuffling, and windowing input. See the [tf.data guide](https://www.tensorflow.org/guide/data) for more details. This class takes in a sequence of data-points gathered at equal intervals, along with time series parameters such as stride, length of history, etc., to produce batches for training/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]( https://www.tensorflow.org/api_docs/python/tf/tf_keras/utils/Sequence) instance. Examples: ```python from tf_keras.src.preprocessing.sequence import TimeseriesGenerator import numpy as np data = np.array([[i] for i in range(50)]) targets = np.array([[i] for i in range(50)]) data_gen = TimeseriesGenerator(data, targets, length=10, sampling_rate=2, batch_size=2) assert len(data_gen) == 20 batch_0 = data_gen[0] x, y = batch_0 assert np.array_equal(x, np.array([[[0], [2], [4], [6], [8]], [[1], [3], [5], [7], [9]]])) assert np.array_equal(y, np.array([[10], [11]])) ``` Nc t|t|k7r)tddt|zdt|z||_||_||_||_||_||z|_|t|dz }||_||_ | |_ | |_ |j|jkDr$td|j|jfzy)NzData and targets have to bez of same length. Data length is z while target length is zz`start_index+length=%i > end_index=%i` is disallowed, as no part of the sequence would be left to be used as current step.) r ValueErrordatatargetslength sampling_ratestride start_index end_indexshufflereverse batch_size) selfrrrrrrrrr r!s r__init__zTimeseriesGenerator.__init__{s t9G $-4SYK@A,S\N;<     * &/  D A I"  $   dnn ,<##T^^45  -rc|j|jz |j|jzz|j|jzzS)N)rrr!r)r"s r__len__zTimeseriesGenerator.__len__s@ NNT-- -$++0M Moo +- -rc |jrDtjj|j|j dz|j }n{|j|j |jz|zz}tj|t||j |jzz|j dz|j}tj|Dcgc]+}|j||jz ||j-c}}tj|Dcgc]}|j|c}}|jr|ddddddf|fS||fScc}wcc}w)Nr)size.)rnprandomrandintrrr!rarangeminarrayrrrrr )r"indexrowsirowsamplesrs r __getitem__zTimeseriesGenerator.__getitem__s> <<99$$  $..1"44??%D  4??T[[#@5#HHA99A$++55t~~7IJ D ((   # +cD4F4FFG   ((>#DLL->? <<1ddC<('1 1  ?s 0E%)E*c |j}t|jjtjk(r|jj } t j|}|j}t|jjtjk(r|jj } t j|}|||j|j|j|j|j|j|j |j"d S#t$r}td||d}~wwxYw#t$r}td||d}~wwxYw)zReturns the TimeseriesGenerator configuration as Python dictionary. Returns: A Python dictionary with the TimeseriesGenerator configuration. zData not JSON Serializable:NzTargets not JSON Serializable:) rrrrrrrrr r!)rtype __module__r)__name__tolistjsondumps TypeErrorrrrrrrrr r!)r"r json_dataer json_targetss r get_configzTimeseriesGenerator.get_configs. yy  ? % % 499##%D H 4(I,,   ( (BKK 7ll))+G N::g.L #kk!//kk++||||//   H94@a G H N E 99T?DDG RVVD\E) *S 03$+3F FF& A ::c1rwwqz> **rz&keras.preprocessing.sequence.skipgramsc g}g} t|D]\} } | s ||| tjkr&td| |z } tt || |zdz} t | | D]J}|| k7s ||}|s|j | |g|r| j ddg:| j dL|dkDrtt | |z}|Dcgc]}|d }}tj||t |D cgc]5} || t |ztjdt|dz g7c} z }|r | ddgg|zz } n | dg|zz } |ru|tjdtd}tj|tj|tj|tj| || fScc}wcc} w)asGenerates 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 in Vector Space](http://arxiv.org/pdf/1301.3781v3.pdf) Args: 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 is a non-word and will be skipped. rrgcA) enumerater*maxr-rrangerintrr+seed)sequencevocabulary_size window_sizenegative_samplesr categoricalsampling_tabler\coupleslabelsr1wi window_start window_endjwjnum_negative_samplescwordss r skipgramsrmsjG F8$%2   %b!FMMO31a+o. XK!(;< |Z0 %AAva[Bx(MM1a&)MM!$ %%(!"3v;1A#AB&'!1''u/0 1s5z> "FNN1c/A:M6N$O P    1vh!55 5F qc00 0F <>>!SY/D Dw Dv F?)( s  G :G")gh㈵>)rMTFNN)rJr:r*numpyr)tf_keras.src.utilsr tensorflow.python.util.tf_exportrrSequencerrVrmrKrrrss ):&@A|A*--|AB|A~@A$+B$+N67  `8`r