Metadata-Version: 2.1
Name: emmv
Version: 0.0.0
Summary: Metrics for unsupervised anomaly detection models
Home-page: https://gitlab.com/chris.oleary/emmv
Author: Christian O'Leary
Author-email: christian.oleary@cit.ie
License: UNKNOWN
Description: # EMMV
        
        Implementation of EM/MV metrics based on N. Goix et al.
        
        This is a means of evaluating anomaly detection models without anomaly labels
        
        ## Installation
        
        ```shell
        pip install emmv
        ```
        
        ## Example Use
        
        ```python
        from emmv import emmv_scores
        
        test_scores = emmv_scores(model, features)
        ```
        
        - Where 'model' is your **trained** scikit-learn model
        - Where 'features' is a 2D dataframe of features (the *X* matrix)
        
        Example resulting object:
        
        ```json
        { 
            "em": 0.77586,
            "mv": 0.25367
        }
        ```
        
        ## Interpreting scores
        
        - The best model should have the **highest** Excess Mass score
        - The best model should have the **lowest** Mass Volume score
        - Probably easiest to just use one of the metrics
        
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
