2Vh)|ddlZddlmZddlmZddlmZeddg d dZ d dZ d Z y) N) keras_export) dataset_utils) tensorflowz'keras.utils.text_dataset_from_directoryz/keras.preprocessing.text_dataset_from_directoryc $|dvr7t|ttfstd||rtd|d||dvrtd|||d}d}t j || |||t jjd}t j||d |||| | \} }}|d k(rt|d k7rtd |||dz} nd} | dk(r t j| ||d\}}t j| ||d\}}|std|d|std|dt||||r t|nd||| |}t||||r t|nd|d}|"|j|}|j|}|jtj j"}|jtj j"}||_||_||g}|St j| ||| \} }| std|dt| |||r t|nd||| |}||j|}|jtj j"}||_|S)aGenerates a `tf.data.Dataset` from text files in a directory. If your directory structure is: ``` main_directory/ ...class_a/ ......a_text_1.txt ......a_text_2.txt ...class_b/ ......b_text_1.txt ......b_text_2.txt ``` Then calling `text_dataset_from_directory(main_directory, labels='inferred')` will return a `tf.data.Dataset` that yields batches of texts from the subdirectories `class_a` and `class_b`, together with labels 0 and 1 (0 corresponding to `class_a` and 1 corresponding to `class_b`). Only `.txt` files are supported at this time. Args: directory: Directory where the data is located. If `labels` is `"inferred"`, it should contain subdirectories, each containing text files for a class. Otherwise, the directory structure is ignored. labels: Either `"inferred"` (labels are generated from the directory structure), `None` (no labels), or a list/tuple of integer labels of the same size as the number of text files found in the directory. Labels should be sorted according to the alphanumeric order of the text file paths (obtained via `os.walk(directory)` in Python). label_mode: String describing the encoding of `labels`. Options are: - `"int"`: means that the labels are encoded as integers (e.g. for `sparse_categorical_crossentropy` loss). - `"categorical"` means that the labels are encoded as a categorical vector (e.g. for `categorical_crossentropy` loss). - `"binary"` means that the labels (there can be only 2) are encoded as `float32` scalars with values 0 or 1 (e.g. for `binary_crossentropy`). - `None` (no labels). class_names: Only valid if `"labels"` is `"inferred"`. This is the explicit list of class names (must match names of subdirectories). Used to control the order of the classes (otherwise alphanumerical order is used). batch_size: Size of the batches of data. If `None`, the data will not be batched (the dataset will yield individual samples). Defaults to `32`. max_length: Maximum size of a text string. Texts longer than this will be truncated to `max_length`. shuffle: Whether to shuffle the data. If set to `False`, sorts the data in alphanumeric order. Defaults to `True`. seed: Optional random seed for shuffling and transformations. validation_split: Optional float between 0 and 1, fraction of data to reserve for validation. subset: Subset of the data to return. One of `"training"`, `"validation"` or `"both"`. Only used if `validation_split` is set. When `subset="both"`, the utility returns a tuple of two datasets (the training and validation datasets respectively). follow_links: Whether to visits subdirectories pointed to by symlinks. Defaults to `False`. verbose: Whether to display number information on classes and number of files found. Defaults to `True`. Returns: A `tf.data.Dataset` object. - If `label_mode` is `None`, it yields `string` tensors of shape `(batch_size,)`, containing the contents of a batch of text files. - Otherwise, it yields a tuple `(texts, labels)`, where `texts` has shape `(batch_size,)` and `labels` follows the format described below. Rules regarding labels format: - if `label_mode` is `int`, the labels are an `int32` tensor of shape `(batch_size,)`. - if `label_mode` is `binary`, the labels are a `float32` tensor of 1s and 0s of shape `(batch_size, 1)`. - if `label_mode` is `categorical`, the labels are a `float32` tensor of shape `(batch_size, num_classes)`, representing a one-hot encoding of the class index. )inferredNa``labels` argument should be a list/tuple of integer labels, of the same size as the number of text files in the target directory. If you wish to infer the labels from the subdirectory names in the target directory, pass `labels="inferred"`. If you wish to get a dataset that only contains text samples (no labels), pass `labels=None`. Received: labels=zIYou can only pass `class_names` if `labels="inferred"`. Received: labels=z, and class_names=>Nintbinary categoricalzc`label_mode` argument must be one of "int", "categorical", "binary", or None. Received: label_mode=Ng.A)z.txt)formats class_namesshuffleseed follow_linksverboser z_When passing `label_mode="binary"`, there must be exactly 2 class_names. Received: class_names=bothtraining validationz*No training text files found in directory z. Allowed format: .txtz,No validation text files found in directory r) file_pathslabels label_mode num_classes max_lengthr shuffle_buffer_sizerF)rrrrrr z!No text files found in directory ) isinstancelisttuple ValueErrorrcheck_validation_split_argnprandomrandintindex_directorylen get_training_or_validation_splitpaths_and_labels_to_datasetbatchprefetchtfdataAUTOTUNEr ) directoryrrr batch_sizerr rvalidation_splitsubsetrrrrfile_paths_train labels_trainfile_paths_val labels_val train_dataset val_datasetdatasets R/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/utils/text_dataset_utils.pytext_dataset_from_directoryr:spZ''&4-0E FLH N  99?A*m-  ?? --7L :  ~+ ,,&'4 |yy  %&3&C&C ! '#J X#k"2a"7 22= @  (1n"   : :  0*     : :  0,    ykJ'' 4'!,7K(Q! 3  2%!,7K(Q!    !)// ;M%++J7K%..rww/?/?@ !**277+;+;< %0 !"-  +.4 N1+KK  0&  F3I;?'' .!!,7K(Q! 3    !mmJ/G""277#3#34* Nctjjj|}|rCt j |||} tjjj || f} n|} |r| j|xsd|} |r0| jfdtjj} | S| jfdtjj} | S)z0Constructs a dataset of text strings and labels.r) buffer_sizerc t||fSNpath_to_string_content)xyrs r9z-paths_and_labels_to_dataset..s0J?Cr;)num_parallel_callsct|Sr?r@)rBrs r9rDz-paths_and_labels_to_dataset..s,Q ;r;) r+r,Datasetfrom_tensor_slicesrlabels_to_datasetzipr mapr-) rrrrrr rrpath_dslabel_dsdss ` r9r(r(sggoo00r\sq-)919     j  jf  !Hr;