o 2h+@sdZddlZddlZddlZddlmZddlmZedGdddeZ eddd d Z ed      dddZ dS)z4Deprecated sequence preprocessing APIs from Keras 1.N) keras_export) PyDatasetz8keras._legacy.preprocessing.sequence.TimeseriesGeneratorc@sHeZdZdZ       dddZd d Zd d Zd dZddZdS)TimeseriesGeneratoralUtility class for generating batches of temporal data. DEPRECATED. 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 PyDataset instance. rNFc Cst|t|krtdt|dt|||_||_||_||_||_|||_|dur4t|d}||_||_ | |_ | |_ |j|jkrStd|jd|jddS)Nz;Data and targets have to be of same length. Data length is z while target length is rz`start_index+length=z > end_index=zU` is disallowed, as no part of the sequence would be left to be used as current step.) len ValueErrordatatargetslength sampling_ratestride start_index end_indexshufflereverse batch_size) selfr r r r r rrrrrrb/var/www/html/chatgem/venv/lib/python3.10/site-packages/keras/src/legacy/preprocessing/sequence.py__init__7s6     zTimeseriesGenerator.__init__cCs$|j|j|j|j|j|jS)N)rrrr rrrr__len__`s zTimeseriesGenerator.__len__csjrtjjjjdjd}njjj|}t|t |jjjdj}t fdd|D}t fdd|D}j rZ|ddddddf|fS||fS)Nr)sizecs$g|]}j|j|jqSr)r r r .0rowrrr ssz3TimeseriesGenerator.__getitem__..csg|]}j|qSr)r rrrrrxs.) rnprandomrandintrrrr arangeminarrayr)rindexrowsisamplesr rrr __getitem__es& zTimeseriesGenerator.__getitem__c Cs|j}t|jjtjkr|j}zt|}Wnty,}ztd||d}~ww|j }t|j jtjkr>|j }zt|}WntyY}ztd||d}~ww|||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: ) r r r r r rrrrr)r type __module__r__name__tolistjsondumps TypeErrorr r r r rrrrr)rr json_dataer json_targetsrrr get_config~s:  zTimeseriesGenerator.get_configcKs(|}|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)r4 __class__r,r.r/)rkwargsr6timeseries_generator_configrrrto_jsons  zTimeseriesGenerator.to_json)rrrNFFr) r,r+ __qualname____doc__rrr)r4r:rrrrr s. ) #rz8keras._legacy.preprocessing.sequence.make_sampling_tableh㈵>cCsVd}t|}d|d<|t||ddd|}||}td|t|S)aCGenerates a word rank-based probabilistic sampling table. DEPRECATED. 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(@)rr"logminimumsqrt)rsampling_factorgammarankinv_fqfrrrmake_sampling_tables ! "rGz.keras._legacy.preprocessing.sequence.skipgramsr>TFcsjg}g} t|D]O\} } | sq|dur|| tkrqtd| |} tt|| |d} t| | D]#}|| krV||}|s@q3|| |g|rQ| ddgq3| dq3q|dkrtt| |}dd|Dt|fddt|D7}|r| ddgg|7} n| dg|7} |r|durt dd}t |t|t |t| || fS)aGenerates skipgram word pairs. DEPRECATED. 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. NrrcSsg|]}|dqS)rr)rcrrrr,szskipgrams..cs,g|]}|ttddgqS)r)rr r!)rr'vocabulary_sizewordsrrr/sgcA) enumerater maxr#rrangeappendintrr!seed)sequencerK window_sizenegative_samplesr categoricalsampling_tablerRcoupleslabelsr'wi window_start window_endjwjnum_negative_samplesrrJr skipgramssN7        r`)r=)rHr>TFNN) r<r.r numpyrkeras.src.api_exportr3keras.src.trainers.data_adapters.py_dataset_adapterrrrGr`rrrrs&  ' )