Merge pull request CogStack#243 from CogStack/more-doc-improvements

CU-26gtw2r: improve docs of MetaCAT, include the CUIs filter into the…

medcat/meta_cat.py

@@ -22,7 +22,23 @@
 
 
 class MetaCAT(PipeRunner):
-    r""" TODO: Add documentation
+    r"""
+    The MetaCAT class used for training 'Meta-Annotation' models, i.e. annotations of clinical
+    concept annotations. These are also known as properties or attributes of recognise entities
+    in similar tools such as MetaMap and cTakes.
+
+    This is a flexible model agnostic class that can learns any meta-annotation task, i.e. any
+    multi-class classification task for recognised terms.
+
+    Args:
+        tokenizer (TokenizerWrapperBase):
+            The Huggingface tokenizer instance. This can be a pre-trained tokenzier instance from
+            a BERT-style model, or trained from scratch for the Bi-LSTM (w. attention) model that
+            is currently used in most deployments.
+        embeddings (Tensor, numpy.ndarray):
+            embedding mapping (sub)word input id n-dim (sub)word embedding.
+        config (ConfigMetaCAT):
+            the configuration for MetaCAT. Param descriptions available in ConfigMetaCAT docs.
     """
 
     # Custom pipeline component name

medcat/utils/helpers.py

@@ -18,6 +18,10 @@ def get_important_config_parameters(config):
                 'value': config.linking['similarity_threshold'],
                 'description': "If the confidence of the model is lower than this a detection will be ignore."
                 },
+            "config.linking['filters']['cuis']": {
+                'value': len(config.linking['filters']['cuis']),
+                'description': "Length of the CUIs filter to be included in outputs. If this is not 0 (i.e. not empty) its best to check what is included before using the model"
+            },
             "config.general['spell_check']": {
                 'value': config.general['spell_check'],
                 'description': "Is spell checking enabled."