Merge pull request #29 from smart-on-fhir/mikix/bump

Change "κ" to "Kappa" and bump version to 1.1.0
smart-on-fhir · Apr 29, 2024 · 08c726b · 08c726b
2 parents 492540b + 61e77c4
commit 08c726b
Show file tree

Hide file tree

Showing 6 changed files with 18 additions and 18 deletions.
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 # Chart Review
 
-**Measure agreement between chart annotators.**
+**Measure agreement between chart reviewers.**
 
 Whether your chart annotations come from humans, machine-learning, or coded data like ICD-10,
 `chart-review` can compare them to reveal interesting statistics like:
@@ -28,13 +28,13 @@ For guides on installing & using Chart Review,
 $ ls
 config.yaml  labelstudio-export.json
 
-$ chart-review accuracy jane john
-accuracy-jane-john:
-F1     Sens  Spec  PPV  NPV  TP  FN  TN  FP  Label
-0.889  0.8   1.0   1.0  0.5  4   1   1   0   *
-1.0    1.0   1.0   1.0  1.0  1   0   1   0   Cough
-0      0     0     0    0    2   0   0   0   Fatigue
-0      0     0     0    0    1   1   0   0   Headache
+$ chart-review accuracy jill jane
+accuracy-jill-jane:
+F1     Sens  Spec  PPV  NPV   Kappa  TP  FN  TN  FP  Label   
+0.667  0.75  0.6   0.6  0.75  0.341  3   1   3   2   *       
+0.667  0.5   1.0   1.0  0.5   0.4    1   1   1   0   Cough   
+1.0    1.0   1.0   1.0  1.0   1.0    2   0   1   0   Fatigue 
+0      0     0     0    0     0      0   0   1   2   Headache
 ```
 
 ## Contributing

diff --git a/chart_review/__init__.py b/chart_review/__init__.py
@@ -1,3 +1,3 @@
 """Chart Review public entry point"""
 
-__version__ = "1.0.0"
+__version__ = "1.1.0"
diff --git a/chart_review/agree.py b/chart_review/agree.py
@@ -143,7 +143,7 @@ def score_matrix(matrix: dict, sig_digits=3) -> dict:
         "Spec": round(spec, sig_digits),
         "PPV": round(ppv, sig_digits),
         "NPV": round(npv, sig_digits),
-        "κ": round(kappa, sig_digits),
+        "Kappa": round(kappa, sig_digits),
         "TP": true_pos,
         "FP": false_pos,
         "FN": false_neg,
@@ -200,7 +200,7 @@ def csv_header(pick_label=False, as_string=False):
     :param pick_label: default= None
     :return: header
     """
-    as_list = ["F1", "Sens", "Spec", "PPV", "NPV", "κ", "TP", "FN", "TN", "FP"]
+    as_list = ["F1", "Sens", "Spec", "PPV", "NPV", "Kappa", "TP", "FN", "TN", "FP"]
 
     if not as_string:
         return as_list

diff --git a/docs/accuracy.md b/docs/accuracy.md
@@ -19,7 +19,7 @@ your accuracy scores will be printed to the console.
 ```shell
 $ chart-review accuracy jill jane
 accuracy-jill-jane:
-F1     Sens  Spec  PPV  NPV   κ      TP  FN  TN  FP  Label   
+F1     Sens  Spec  PPV  NPV   Kappa  TP  FN  TN  FP  Label   
 0.667  0.75  0.6   0.6  0.75  0.341  3   1   3   2   *       
 0.667  0.5   1.0   1.0  0.5   0.4    1   1   1   0   Cough   
 1.0    1.0   1.0   1.0  1.0   1.0    2   0   1   0   Fatigue 

diff --git a/docs/index.md b/docs/index.md
@@ -7,7 +7,7 @@ has_children: true
 
 # Chart Review
 
-**Measure agreement between chart annotators.**
+**Measure agreement between chart reviewers.**
 
 Whether your chart annotations come from humans, machine-learning, or coded data like ICD-10,
 Chart Review can compare them to reveal interesting statistics like:

diff --git a/tests/test_cli.py b/tests/test_cli.py
@@ -30,7 +30,7 @@ def test_accuracy(self):
                     "Spec": 0.6,
                     "PPV": 0.6,
                     "NPV": 0.75,
-                    "κ": 0.341,
+                    "Kappa": 0.341,
                     "TP": 3,
                     "FN": 1,
                     "TN": 3,
@@ -45,7 +45,7 @@ def test_accuracy(self):
                         "Spec": 1.0,
                         "TN": 1,
                         "TP": 1,
-                        "κ": 0.4,
+                        "Kappa": 0.4,
                     },
                     "Fatigue": {
                         "F1": 1.0,
@@ -57,7 +57,7 @@ def test_accuracy(self):
                         "Spec": 1.0,
                         "TN": 1,
                         "TP": 2,
-                        "κ": 1.0,
+                        "Kappa": 1.0,
                     },
                     "Headache": {
                         "F1": 0,
@@ -69,15 +69,15 @@ def test_accuracy(self):
                         "Spec": 0,
                         "TN": 1,
                         "TP": 0,
-                        "κ": 0,
+                        "Kappa": 0,
                     },
                 },
                 accuracy_json,
             )
 
             accuracy_csv = common.read_text(f"{tmpdir}/accuracy-jill-jane.csv")
             self.assertEqual(
-                """F1	Sens	Spec	PPV	NPV	κ	TP	FN	TN	FP	Label
+                """F1	Sens	Spec	PPV	NPV	Kappa	TP	FN	TN	FP	Label
 0.667	0.75	0.6	0.6	0.75	0.341	3	1	3	2	*
 0.667	0.5	1.0	1.0	0.5	0.4	1	1	1	0	Cough
 1.0	1.0	1.0	1.0	1.0	1.0	2	0	1	0	Fatigue