Merge pull request #337 from CogStack/master

v1.8.0 Release PR

README.md

@@ -1,4 +1,4 @@
-# Medical  <img src="https://github.com/CogStack/MedCAT/blob/master/media/cat-logo.png" width=45> oncept Annotation Tool
+# Medical  <img src="https://raw.githubusercontent.com/CogStack/MedCAT/master/media/cat-logo.png" width=45> oncept Annotation Tool
 
 [![Build Status](https://github.com/CogStack/MedCAT/actions/workflows/main.yml/badge.svg?branch=master)](https://github.com/CogStack/MedCAT/actions/workflows/main.yml?query=branch%3Amaster)
 [![Documentation Status](https://readthedocs.org/projects/medcat/badge/?version=latest)](https://medcat.readthedocs.io/en/latest/?badge=latest)
@@ -50,7 +50,6 @@ Since MedCAT is primarily a library, logging has been effectively disabled by de
 The idea is that the user can directly modify the logging behaviour of either the entire library or a certain set of modules within as they wish. We have provided a convenience method to add default handlers that log into the console as well as _medcat.log_ (`medcat.add_default_log_handlers`).
 
 Some details as to how one can configure the logging are described in the [MedCAT Tutorials](https://github.com/CogStack/MedCATtutorials).
-PS: Currently (temporarily!) the tutorial is in the `tutorials` folder.
 
 ## Acknowledgements
 Entity extraction was trained on [MedMentions](https://github.com/chanzuckerberg/MedMentions) In total it has ~ 35K entites from UMLS

docs/requirements.txt

@@ -3,4 +3,4 @@ sphinx-rtd-theme~=1.0
 myst-parser~=0.17
 sphinx-autoapi~=1.8
 setuptools>=60.0
-aiohttp==3.8.3
+aiohttp==3.8.5

medcat/cat.py

@@ -534,10 +534,14 @@ def _print_stats(self,
                             anns_norm.append((ann['start'], cui))
                             anns_examples.append({"text": doc['text'][max(0, ann['start']-60):ann['end']+60],
                                                   "cui": cui,
+                                                  "start": ann['start'],
+                                                  "end": ann['end'],
                                                   "source value": ann['value'],
                                                   "acc": 1,
                                                   "project name": project.get('name'),
-                                                  "document name": doc.get('name')})
+                                                  "document name": doc.get('name'),
+                                                  "project id": project.get('id'),
+                                                  "document id": doc.get('id')})
                         elif ann.get('validated', True) and (ann.get('killed', False) or ann.get('deleted', False)):
                             anns_norm_neg.append((ann['start'], cui))
 
@@ -556,11 +560,14 @@ def _print_stats(self,
                     p_anns_norm.append((ann.start_char, cui))
                     p_anns_examples.append({"text": doc['text'][max(0, ann.start_char-60):ann.end_char+60],
                                             "cui": cui,
+                                            "start": ann.start_char,
+                                            "end": ann.end_char,
                                             "source value": ann.text,
                                             "acc": float(ann._.context_similarity),
                                             "project name": project.get('name'),
-                                            "document name": doc.get('name')})
-
+                                            "document name": doc.get('name'),
+                                            "project id": project.get('id'),
+                                            "document id": doc.get('id')})
                 for iann, ann in enumerate(p_anns_norm):
                     cui = ann[1]
                     if ann in anns_norm:

setup.py

@@ -42,7 +42,7 @@
         'pydantic>=1.10.0,<2.0', # for spacy compatibility; avoid 2.0 due to breaking changes
         # the following are not direct dependencies of MedCAT but needed for docs/building
         # hopefully will no longer need the transitive dependencies
-        'aiohttp==3.8.3', # 3.8.3 is needed for compatibility with fsspec <- datasets <- medcat
+        'aiohttp==3.8.5', # 3.8.3 is needed for compatibility with fsspec <- datasets <- medcat
         'blis<0.8.0,>=0.7.8', # as required by thinc <- spacy <- medcat
         # 'smart-open==5.2.1', # 5.2.1 is needed for compatibility with pathy
         # 'joblib~=1.2',