a
    Sic*                     @   sb   d Z ddlZddlm  mZ ddlmZ ddl	m
Z
 e
ddg ddddZdd Zdd ZdS )z(Keras text dataset generation utilities.    N)dataset_utils)keras_exportz'keras.utils.text_dataset_from_directoryz/keras.preprocessing.text_dataset_from_directory)v1inferredint    TFc              	   C   sp  |dvr<t |ttfs$td| |r<td| d| |dvrRtd| |du sb|du rjd}d}t||	|| |du rtjd}tj	| |d	||||
d
\}}}|dkrt
|dkrtd| |	dkrt|||d\}}t|||d\}}|std|  d|s,td|  dt|||t
||d}t|||t
||d}|tjj}|tjj}|dur|r|j|d |d}||}||}n|r|jd|d}||_||_||g}nt||||	\}}|s td|  dt|||t
||d}|tjj}|durR|rF|j|d |d}||}n|rf|jd|d}||_|S )a  Generates 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. Default: 32.
        If `None`, the data will not be batched
        (the dataset will yield individual samples).
      max_length: Maximum size of a text string. Texts longer than this will
        be truncated to `max_length`.
      shuffle: Whether to shuffle the data. Default: True.
          If set to False, sorts the data in alphanumeric order.
      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.

    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.
    )r   Na`  `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=>   categoricalNr   binaryzc`label_mode` argument must be one of "int", "categorical", "binary", or None. Received: label_mode=Ng    .A)z.txt)formatsclass_namesshuffleseedfollow_linksr	      z_When passing `label_mode="binary"`, there must be exactly 2 class_names. Received: class_names=bothtraining
validationz*No training text files found in directory z. Allowed format: .txtz,No validation text files found in directory )
file_pathslabels
label_modenum_classes
max_length   )buffer_sizer   i   z!No text files found in directory )
isinstancelisttuple
ValueErrorr   check_validation_split_argnprandomrandintindex_directorylen get_training_or_validation_splitpaths_and_labels_to_datasetprefetchtfdataAUTOTUNEr   batchr   )	directoryr   r   r   
batch_sizer   r   r   validation_splitsubsetr   r   file_paths_trainlabels_trainfile_paths_val
labels_valtrain_datasetval_datasetdataset r6   T/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/utils/text_dataset.pytext_dataset_from_directory   s    d	








r8   c                    sP   t jj| }|j fddt jjd}|rLt|||}t jj||f}|S )z0Constructs a dataset of text strings and labels.c                    s
   t |  S )N)path_to_string_content)xr   r6   r7   <lambda>      z-paths_and_labels_to_dataset.<locals>.<lambda>)num_parallel_calls)	r'   r(   Datasetfrom_tensor_slicesmapr)   r   labels_to_datasetzip)r   r   r   r   r   path_dsZ	string_dslabel_dsr6   r;   r7   r%     s    
r%   c                 C   s,   t j| }|d ur(t jjj|d|}|S )Nr   )r'   io	read_filecompatr   stringssubstr)pathr   txtr6   r6   r7   r9     s    r9   )
r   r   Nr   NTNNNF)__doc__numpyr   tensorflow.compat.v2rH   v2r'   keras.utilsr    tensorflow.python.util.tf_exportr   r8   r%   r9   r6   r6   r6   r7   <module>   s.              g