Name	Size	Mode	Actions
base.cpython-312.pyc	4786	0644	editdlrm
classifier.cpython-312.pyc	7547	0644	editdlrm
model.cpython-312.pyc	30534	0644	editdlrm
outlier.cpython-312.pyc	8048	0644	editdlrm
regressor.cpython-312.pyc	5470	0644	editdlrm
transformer.cpython-312.pyc	6106	0644	editdlrm
__init__.cpython-312.pyc	764	0644	editdlrm

� N�j�����dZd
dl
mZmZ
d
dlZd
dlZd
dlm Z
d
dl mZ
d
dlm Z
d
dlmZ
d
dlmZ
d Zd eeej(fdeeej(ffd�ZGd �dee �Zy)z�Outlier/anomaly detection utilities for MySQL Connector/Python. Provides a scikit-learn compatible wrapper using HeatWave to score anomalies. �)�Optional�UnionN)
�OutlierMixin)
� MyBaseMLModel)
�ML_TASK)
� copy_dict)
�MySQLConnectionAbstractg�h㈵��>�prob�returnc
�|�t
j|td
tz �}
t
j|
d
|
z z�
S)z� Compute logit (logodds) for a probability, clipping to avoid numerical overflow. Args: prob: Scalar or array of probability values in (0,1). Returns: logit-transformed probabilities. �
)�np�clip�EPS�log)r �results �D/opt/nydus/tmp/pip-target-a90h98xg/lib/python/mysql/ai/ml/outlier.py�_get_logitsr0s2���W�W�T�3�
�C�� (�F� �6�6�&�A��J�'�(�(�c �D
�eZ
dZd
Z d dedeedeedeefd�Zde e jejfd ejfd �Zde e jejfd ejfd�Zde e jejfd ejfd�Zy)�MyAnomalyDetectora� MySQL HeatWave scikit-learn compatible anomaly/outlier detector. Flags samples as outliers when the probability of being an anomaly exceeds a user-tunable threshold. Includes helpers to obtain decision scores and anomaly probabilities for ranking. Args: db_connection (MySQLConnectionAbstract): Active MySQL DB connection. model_name (str, optional): Custom model name in the database. fit_extra_options (dict, optional): Extra options for fitting. score_extra_options (dict, optional): Extra options for scoring/prediction. Attributes: boundary: Decision threshold boundary in logit space. Derived from trained model's catalog info Methods: predict(X): Predict outlier/inlier labels. score_samples(X): Compute anomaly (normal class) logit scores. decision_function(X): Compute signed score above/below threshold for ranking. N� db_connection� model_name�fit_extra_options�score_extra_optionsc��t
j||
tj||�
�
t |�
|_d|_y)a2 Initialize an anomaly detector instance with threshold and extra options. Args: db_connection: Active MySQL DB connection. model_name: Optional model name in DB. fit_extra_options: Optional extra fit options. score_extra_options: Optional extra scoring options. Raises: ValueError: If outlier_threshold is not in (0,1). DatabaseError: If a database connection issue occurs. If an operational error occurs during execution. )rrN)r�__init__r�ANOMALY_DETECTIONrr�boundary)�selfrrrrs rrzMyAnomalyDetector.__init__Ws>��, ������%�%�!�/� �$-�-@�#A�� �)-�� r�
Xrc�T�t
j|j|
�
d
kdd�S)a� Predict outlier/inlier binary labels for input samples. Args: X: Samples to predict on. Returns: ndarray: Values are -1 for outliers, +1 for inliers, as per scikit-learn convention. Raises: DatabaseError: If provided options are invalid or unsupported, or if the model is not initialized, i.e., fit or import has not been called If a database connection issue occurs. If an operational error occurs during execution. DatabaseError: If provided options are invalid or unsupported, or if the model is not initialized, i.e., fit or import has not been called If a database connection issue occurs. If an operational error occurs during execution. g�����r )r�where�decision_function)r r!s r�predictzMyAnomalyDetector.predictws'��6�x�x��.�.�q�1�C�7��Q�?�?rc�
�|j
|
�
}|j�U|j�}|�td�
�
|ddj dd
�}|�td�
�
td|z �
|_
||jz S)a� Compute signed distance to the outlier threshold. Args: X: Samples to predict on. Returns: ndarray: Score > 0 means inlier, < 0 means outlier; |value| gives margin. Raises: DatabaseError: If provided options are invalid or unsupported, or if the model is not initialized, i.e., fit or import has not been called If a database connection issue occurs. If an operational error occurs during execution. ValueError: If the provided model info does not provide threshold Nz Model does not exist in catalog.�model_metadata�training_params�anomaly_detection_thresholdzzTrained model is outdated and does not support threshold. Try retraining or using an existing, trained model with MyModel.g�?)� score_samplesr�get_model_info� ValueError�getr)r r!� sample_scores� model_info� thresholds rr%z#MyAnomalyDetector.decision_function�s���.�*�*�1�-� ��=�=� ��,�,�.�J��!� �!C�D�D�"�#3�4�5F�G�K�K�-�t��I�� � �
W
���(��i��8�D�M��t�}�}�,�,rc��|jj|
|j�
�}t|dj d��
j��
S)aJ Compute normal probability logit score for each sample. Used for ranking, thresholding. Args: X: Samples to score. Returns: ndarray: Logit scores based on "normal" class probability. Raises: DatabaseError: If provided options are invalid or unsupported, or if the model is not initialized, i.e., fit or import has not been called If a database connection issue occurs. If an operational error occurs during execution. )
�options� ml_resultsc
��|d
dS)N� probabilities�normal�)
�
xs
r�z1MyAnomalyDetector.score_samples..�s��Q��/��9r)�_modelr&rr�apply�to_numpy)r r!rs rr+zMyAnomalyDetector.score_samples�sJ��,���$�$�Q��0H�0H�$�I����<� � �U�9� :� �X�Z� � r)NNN)�__name__� __module__�__qualname__�__doc__r r�str�dictrr�pd� DataFramer�ndarrayr&r%r+r8rrrr>s����6%)�,0�.2�.�.�.��S�M�.�$�D�>� .� &�d�^�.�@
@
�����r�z�z�)�*�@
� ���@
�:+-�����r�z�z�)�*�+-� ���+-�Z
 �����r�z�z�)�*� � ��� rr)rA�typingrr�numpyr�pandasrD�sklearn.baser�mysql.ai.ml.baser�mysql.ai.ml.modelr�mysql.ai.utilsr�mysql.connector.abstractsr r�floatrFrrr8rr�rP
sh�


�:
�
#���%�*�%�$�=� ��
)�e�E�2�:�:�-�.�
)�5��� � �9J�3K�
)�_
� �|�_
r