Ë
|
Wñúhï ã óÌ d Z ddlmZmZ ddlZddlZddlm Z ddl
|
m Z ddl m Z ddlmZ ddlmZ d Zd
|
eeej( f d eeej( f fd Z G d de e « Zy)zOutlier/anomaly detection utilities for MySQL Connector/Python.
|
|
Provides a scikit-learn compatible wrapper using HeatWave to score anomalies.
|
é )ÚOptionalÚUnionN)Ú OutlierMixin)Ú MyBaseMLModel)ÚML_TASK)Ú copy_dict)ÚMySQLConnectionAbstractgñhãµøä>ÚprobÚreturnc ó| t j | t dt z
|
« }t j |d|z
|
z « S )zÚ
|
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.
|
é )ÚnpÚclipÚEPSÚlog)r
|
Úresults úFH:\Change_password\venv_build\Lib\site-packages\mysql/ai/ml/outlier.pyÚ _get_logitsr 0 s2 ô WWT3 ¤C¡Ó (FÜ 66&A JÑ'Ó (Ð(ó c
|
óD e Zd ZdZ d dedee dee dee fdZde e
|
j e j f d e j fd
|
Zde e
|
j e j f d e j fd Zde e
|
j e j f d e j fd Zy)ÚMyAnomalyDetectora¯
|
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.
|
NÚ db_connectionÚ
|
model_nameÚfit_extra_optionsÚscore_extra_optionsc ó t j | |t j ||¬« 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.
|
)r r N)r Ú__init__r ÚANOMALY_DETECTIONr r Úboundary)Úselfr r r r s r r zMyAnomalyDetector.__init__W s> ô, × Ñ Ø Ø Ü × %Ñ %Ø!Ø /õ
|
ô $-Ð-@Ó#AÔ Ø)- r ÚXr c óT t j | j |« dk dd« 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 éÿÿÿÿr )r ÚwhereÚdecision_function)r r! s r ÚpredictzMyAnomalyDetector.predictw s' ô6 xx×.Ñ.¨qÓ1°CÑ7¸¸QÓ?Ð?r c ó | j |« }| j U| j « }| t d« |d d j dd« }| t d« t d|z
|
« | _ || j z
|
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.Úmodel_metadataÚtraining_paramsÚanomaly_detection_thresholdzzTrained model is outdated and does not support threshold. Try retraining or using an existing, trained model with MyModel.g ð?)Ú score_samplesr Úget_model_infoÚ
|
ValueErrorÚgetr )r r! Ú sample_scoresÚ
|
model_infoÚ thresholds r r% z#MyAnomalyDetector.decision_function s ð. ×*Ñ*¨1Ó- à ==Ð Ø ×,Ñ,Ó.JØÐ!Ü Ð!CÓDÐDà"Ð#3Ñ4Ð5FÑG×KÑKØ-¨tóIð Ð Ü ðWóð ô (¨¨i©Ó 8DMà t}}Ñ,Ð,r c ó¨ | j j || j ¬« }t |d j 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.
|
)ÚoptionsÚ
|
ml_resultsc ó | d d S )NÚ probabilitiesÚnormal© )Úxs r ú<lambda>z1MyAnomalyDetector.score_samples.<locals>.<lambda>Û s QÑ /°Ñ 9 r )Ú_modelr& r r ÚapplyÚto_numpy)r r! r s r r+ z MyAnomalyDetector.score_samplesÁ sJ ð, ×$Ñ$ Q°×0HÑ0HÐ$ÓIäØ <Ñ ß UÑ9Ó :ß XZó
|
ð
|
r )NNN)Ú__name__Ú
|
__module__Ú __qualname__Ú__doc__r r ÚstrÚdictr r ÚpdÚ DataFramer Úndarrayr& r% r+ r8 r r r r > sÕ ñð6 %)Ø,0Ø.2ñ .à.ð .ð SMð .ð $ D>ð .ð
|
& d^ó .ð@@à rzzÐ)Ñ *ð@ð
|
ó@ð:+-à rzzÐ)Ñ *ð+-ð
|
ó+-ðZ
|
à rzzÐ)Ñ *ð
|
ð
|
ô
|
r r )rA Útypingr r Únumpyr ÚpandasrD Ú sklearn.baser Úmysql.ai.ml.baser Úmysql.ai.ml.modelr Úmysql.ai.utilsr Úmysql.connector.abstractsr r ÚfloatrF r r r8 r r ú<module>rP sh ðñ:÷ #ã Û Ý %å *Ý %Ý $å =à
|
ð )eE 2§:¡:Ð -Ñ.ð )°5¸ÀÇ
|
Á
|
Ð9JÑ3Kó )ô _
|
|õ _
|
r
|
