Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detector

Predict raw anomaly score of X using the fitted detector. For consistency, outliers are assigned with larger anomaly scores. Paramete

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detecto

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detecto

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detecto

Not supported (transductive detector). Raises ------ NotImplementedError

Predict raw anomaly scores for time series X. Parameters ---------- X : array-like of shape (n_timestamps,) or (n_timestamps,

Not supported (transductive detector).

Predict raw anomaly scores for time series X. Parameters ---------- X : array-like of shape (n_timestamps,) or (n_timestamps,

Predict raw anomaly score of X using the fitted detector. For consistency, outliers are assigned with larger anomaly scores. Paramete

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detecto

Not supported (transductive detector).

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detecto

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detecto

Predict raw anomaly score of X using the fitted detector. Parameters ---------- X : numpy.ndarray The input sampl

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detecto

Predict raw anomaly score of X using the fitted detector. The anomaly score of an input sample is computed based on different detecto

Predict raw anomaly scores for time series X. Parameters ---------- X : array-like of shape (n_timestamps,) or (n_timestamps,

Not supported (transductive detector).

Predict raw anomaly scores for time series X. Parameters ---------- X : array-like of shape (n_timestamps,) or (n_timestamps,

For any additional operations after each decision function call.

Z-score-based deviation loss translated to PyTorch.

Construct the deviation network-based detection model in PyTorch style

This is a helper function for computing the ecdf of an array. It has been outsourced from the original function in order to be able to use th

Source: https://github.com/ChongYou/subspace-clustering/blob/master/cluster/selfrepresentation.py Elastic net subspace clust

Encode text strings to embeddings. Parameters ---------- X : list of str Text strings to encode. batch_s

For any additional operations after each epoch.

Evaluate a single condition predicate. Supported operators: ``'eq'`` (equality), ``'lt'``, ``'lte'``, ``'gt'``, ``'gte'`` (numeric comparison

Evaluate routing rules against a data profile. Walks every rule in the KB's routing-rules table; for each rule whose conditions match the pro

Forward pass for evaluating the model. Abstract method to be implemented. Parameters ---------- batch_data :

Plot dimensional outlier graph for a given data point within the dataset. Parameters ---------- ind : int

Explain top anomalies from the best detector.

Compute per-feature z-score, value, and direction for a sample. Returns the top-5 features by absolute z-score for the row at `idx`. Each ent

Map a UCI Ionosphere feature index to a readable pulse name.

Fit detector. y is ignored in unsupervised methods. Parameters ---------- X : numpy array of shape (n_samples, n_features)

Fit detector. y is ignored in unsupervised methods. Parameters ---------- X : numpy array of shape (n_samples, n_features)

Fit detector. y is ignored in unsupervised methods. Parameters ---------- X : numpy array of shape (n_samples, n_features)

Draw randomly sampled indices. Internal use only. See sklearn/ensemble/bagging.py Parameters ---------- random_state : RandomState

Find the multivariate geometric L1-median by applying Vardi and Zhang algorithm. Parameters ---------- x : array-like, the data

Imports the library of the selected model and initializes the classifier. Returns ------- clf : object

Copy a packaged skill (with references/) into a Claude Code skill directory. The skill is installed at ``target_dir / <install-dirname>/`` as a

Download UCI Ionosphere and return X plus held-out labels.

Unified `pyod` CLI entry point.

Entry point for `python -m pyod.mcp_server` and `pyod mcp serve`. Creates the FastMCP instance, registers every tool function, and blocks on

Combination method to merge the scores from multiple estimators by majority vote. Parameters ---------- scores : numpy array of shape

Not supported (transductive detector).

Not supported (transductive detector).

Not supported (transductive detector).

Not supported (transductive detector).

Not supported (transductive detector). Raises ------ NotImplementedError

Not supported (transductive detector).

Not supported (transductive detector).

Not supported (transductive detector).

Predict the probability of a sample being an outlier. Overrides the base implementation to handle list inputs (raw data such as text

Regenerate every skill file. Returns the number of files modified.

Regenerate every KB-DERIVED block in a single file in place. Returns True if the file was modified, False if it was already up to date.

Check if all conditions in a rule match the profile. Each rule's ``conditions`` list is treated as a logical AND. A condition's ``field`` is

Run a complete agentic flow on external data.

Scale all angles in which angles <= 90 degree will be scaled within [0 - 54.7] and angles > 90 will be scaled within [90 - 126] Para

Select best detector via Spearman with consensus. Fallback chain (per spec): 1. Highest finite Spearman correlation against consensus. 2

Return od-expert adaptive triggers fired after analysis.

Apply the od-expert skill's tabular pre-run checklist.

Compute the SVM decision function. Parameters ---------- rff_features : torch.Tensor Random Fourier features.

Additional edge case tests for HBOS with auto bins.

Test HBOS with n_bins='auto' when test data exceeds training range. This test reproduces the IndexError that occurred when test values

Compare behavior between auto and static bins to ensure consistency.

This function allows the researcher to perform extra training instead of the fixed number determined by the fit() function.

Forward pass for training the model. Abstract method to be implemented. Parameters ---------- batch_data : t

Returns the index'th estimator in the ensemble.

Initializes the AutoModelSelector with a dataset, additional notes, and an OpenAI API key. Parameters ----------