~Wh26dZddlZddlZddlZddlmZddlmZdZ edGddej Z ed dd Z ed  ddZ dS)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]B\}}t||kr*||||C||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 b/var/www/html/movieo_spanner_bot/venv/lib/python3.11/site-packages/keras/preprocessing/sequence.py_remove_long_seqr$siRYGC  1 q66F?? NN1      Q    I z0keras.preprocessing.sequence.TimeseriesGeneratorc@eZdZdZ d dZdZd Zd Zd ZdS) 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/keras/utils/Sequence) instance. Examples: ```python from keras.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]])) ``` rNFc t|t|kr5tddt|zdt|z||_||_||_||_||_||z|_|t|dz }||_||_ | |_ | |_ |j|jkrtd|j|jfzdS)NzData and targets have to bez of same length. Data length is z while target length is rzz`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) selfrrrrrrrr r!r"s r__init__zTimeseriesGenerator.__init__{s t99G $ $-@SYY@@A;S\\;;<     * &/  D A I"  $  dn , ,<#T^45  - ,rc`|j|jz |j|jzz|j|jzzS)N)rrr"r)r#s r__len__zTimeseriesGenerator.__len__s3 NT- -$+0M Mo +- -rcjr5tjjjdzj}n[jjjz|zz}tj|t|jjzzjdzj}tj fd|D}tj fd|D}j r|ddddddf|fS||fS)Nr)sizecJg|]}j|jz |j S)rrr.0rowr#s r z3TimeseriesGenerator.__getitem__..sA    # +cD4FFG   rc*g|]}j|Sr*)rr+s rr.z3TimeseriesGenerator.__getitem__..s >>>#DL->>>r.) r nprandomrandintrrr"rarangeminarrayr!)r#indexrowsisamplesrs` r __getitem__zTimeseriesGenerator.__getitem__s* < 9$$ $.1"44?%DD 4?T[#@5#HHA9A$+55t~7IJJ D (          (>>>>>>>?? < 2111dddC<('1 1rc l|j}t|jjtjkr|j} t j|}n##t$r}td||d}~wwxYw|j }t|j jtjkr|j } t j|}n##t$r}td||d}~wwxYw|||j |j |j |j |j|j|j|jd S)zReturns the TimeseriesGenerator configuration as Python dictionary. Returns: A Python dictionary with the TimeseriesGenerator configuration. zData not JSON Serializable:NzTargets not JSON Serializable:) rrrrrrrr r!r")rtype __module__r1__name__tolistjsondumps TypeErrorrrrrrrr r!r")r#r json_dataer json_targetss r get_configzTimeseriesGenerator.get_configsG y  ?? % 4 49##%%D H 4((II H H H94@@a G H,    (BK 7 7l))++G N:g..LL N N N(A99A> C C>(C99C>c l|}|jj|d}tj|fi|S)aReturns a JSON string containing the generator's configuration. Args: **kwargs: Additional keyword arguments to be passed to `json.dumps()`. Returns: A JSON string containing the tokenizer configuration. ) class_nameconfig)rG __class__r?rArB)r#kwargsrJtimeseries_generator_configs rto_jsonzTimeseriesGenerator.to_jsonsF"".1' ' #z5@@@@@r)rrrNFFr) r?r> __qualname____doc__r$r&r;rGrNr*rrrr7s@@N((((T---    2! ! ! FAAAAArrz0keras.preprocessing.sequence.make_sampling_tableh㈵>cd}tj|}d|d<|tj||zzdzdd|zz z }||z}tjd|tj|z S)a2Generates a word rank-based probabilistic sampling table. Used for generating the `sampling_table` argument for `skipgrams`. `sampling_table[i]` is the probability of sampling the word i-th most common word in a dataset (more common words should be sampled less frequently, for balance). The sampling probabilities are generated according to the sampling distribution used in word2vec: ``` 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 a numerical approximation of frequency(rank): `frequency(rank) ~ 1/(rank * (log(rank) + gamma) + 1/2 - 1/(12*rank))` where `gamma` is the Euler-Mascheroni constant. Args: 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 entry is the probability that a word of rank i should be sampled. gX9v?rrg??g(@)r1r4logminimumsqrt)r(sampling_factorgammarankinv_fqfs rmake_sampling_tabler\sq> E 9T??DDG RVD\\E) *S 03$+3F FF& A :c1rwqzz> * **rz&keras.preprocessing.sequence.skipgramsrSTFcg}g} t|D]\} } | s||| tjkr(td| |z } tt || |zdz} t | | D]Y}|| krQ||}|s|| |g|r| ddgD| dZ|dkrutt | |z}d|Dtj|fdt |Dz }|r | ddgg|zz } n | dg|zz } |rg|tj dd}tj |tj|tj |tj| || fS)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. Nrrcg|] }|d S)rr*)r,cs rr.zskipgrams..ms'''!1'''rcpg|]2}|tztjddz g3S)r)rr2r3)r,r9vocabulary_sizewordss rr.zskipgrams..psN   1s5zz> "FN1o6I$J$J K   rgcA) enumerater2maxr5rrangerintr r3seed)sequencerb window_sizenegative_samplesr categoricalsampling_tablerhcoupleslabelsr9wi window_start window_endjwjnum_negative_samplesrcs ` @r skipgramsrv s0jG F8$$%%2    %b!FMOO331a+o.. XK!(;<< |Z00 % %AAvva[Bx(((%MM1a&))))MM!$$$ %!"3v;;1A#ABB''w'''u     /00      1 1vh!55 5FF qc00 0F <>!T**D Dw Dv F?r)rQ)r]rSTFNN)rPrAr2numpyr1 keras.utilsr tensorflow.python.util.tf_exportrrSequencerr\rvr*rrr{s9 """""":99999&@AA}A}A}A}A}A*-}A}ABA}A@@AA$+$+$+BA$+N677  ```87```r