a SicM6@s~dZddlZddlZddlZddlmZddlmZddZ edGdd d ej Z ed dd d Z eddddZ 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_exportcCsFgg}}t||D](\}}t||kr||||q||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)maxlenseqlabelZnew_seq new_labelxyr X/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/preprocessing/sequence.py_remove_long_seq$s    rz0keras.preprocessing.sequence.TimeseriesGeneratorc@s:eZdZdZdddZd d Zd d Zd dZddZdS)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 Cst|t|kr4tddt|dt|||_||_||_||_||_|||_|durpt|d}||_ ||_ | |_ | |_ |j|j krtd|j|j fdS)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 ValueErrorformatdatatargetslength sampling_ratestride start_index end_indexshufflereverse batch_size) selfrrrrrrrrrrr r r__init__{s4     zTimeseriesGenerator.__init__cCs$|j|j|j|j|j|jS)N)rrrrrr r r__len__s zTimeseriesGenerator.__len__csjr$tjjjjdjd}n>jjj|}t|t |jjjdj}t fdd|D}t fdd|D}j r|ddddddf|fS||fS)Nr)sizecs$g|]}j|j|jqSr )rrr.0rowr!r r sz3TimeseriesGenerator.__getitem__..csg|]}j|qSr )rr$r!r rr'.) rnprandomrandintrrrrarangeminarrayr)rindexrowsisamplesrr r!r __getitem__s& zTimeseriesGenerator.__getitem__c Cs|j}t|jjtjkr"|j}zt|}Wn0ty`}ztd||WYd}~n d}~00|j }t|j jtjkr|j }zt|}Wn0ty}ztd||WYd}~n d}~00|||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:) rrrrrrrrrr)rtype __module__r*__name__tolistjsondumps TypeErrorrrrrrrrrr)rrZ json_dataerZ json_targetsr r r get_configs2 " "zTimeseriesGenerator.get_configcKs(|}|jj|d}tj|fi|S)aReturns a JSON string containing the timeseries generator configuration. Args: **kwargs: Additional keyword arguments to be passed to `json.dumps()`. Returns: A JSON string containing the tokenizer configuration. ) class_nameconfig)r= __class__r7r9r:)rkwargsr?Ztimeseries_generator_configr r rto_jsons zTimeseriesGenerator.to_json)rrrNFFr) r7r6 __qualname____doc__r r"r4r=rBr r r rr7sG *#rz0keras.preprocessing.sequence.make_sampling_tableh㈵>cCsVd}t|}d|d<|t||ddd|}||}td|t|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(@)r*r-logminimumsqrt)r#Zsampling_factorgammarankZinv_fqfr r rmake_sampling_tables  "rMz&keras.preprocessing.sequence.skipgramsrFTFcsrg}g} t|D]\} } | sq|dur8|| tkr8qtd| |} tt|| |d} t| | D]F}|| krf||}|sqf|| |g|r| ddgqf| dqfq|dkr&tt| |}dd|Dt|fddt|D7}|r| ddgg|7} n| dg|7} |rj|durBt dd}t |t|t |t| || 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. NrrcSsg|] }|dqS)rr )r%cr r rr'lr(zskipgrams..cs,g|]$}|ttddgqS)r)rr+r,)r%r2vocabulary_sizewordsr rr'osgcA) enumerater+maxr.rrangerintrr,seed)sequencerQ window_sizeZnegative_samplesr categoricalZsampling_tablerWZcoupleslabelsr2wiZ window_startZ window_endjZwjZnum_negative_samplesr rPr skipgramssJ5        r^)rE)rNrFTFNN)rDr9r+numpyr* keras.utilsr tensorflow.python.util.tf_exportrrSequencerrMr^r r r rs&   @ '