fix bug - cleaned data files have different layer names such as Patient_Segment_A

MIND_utils.py

@@ -1,20 +1,33 @@
-import numpy as np, pandas as pd, json
-
 dimensions = ["A", "B-S", "B-O", "C-S", "C-O", "D"]
-dimension_to_layer_name = {
+dimension_to_layer_name_raw = { # in raw annotation files (Ayal's outputs)
+    "A": "Segment Patient Affect (A)",
     "B-S": "Segment Patient B-S",
+    "B-O": "Segment Patient B-O",
     "C-S": "Segment Patient C-S",
-    "D": "Segment Patient Desire (D)",
     "C-O": "Segment Patient C-O",
-    "B-O": "Segment Patient B-O",
-    "A": "Segment Patient Affect (A)",
+    "D": "Segment Patient Desire (D)",
 }
+dimension_to_layer_name_cleaned = { # in cleaned annotation files (Yael's outputs)
+    "A": "Segment_Patient_A",
+    "B-S": "Segment_Patient_B-S",
+    "B-O": "Segment_Patient_B-O",
+    "C-S": "Segment_Patient_C-S",
+    "C-O": "Segment_Patient_C-O",
+    "D": "Segment_Patient_D",
+}
+
         
 def df_to_self_states_json(df, doc_name, annotator = None):
     """Convert a dataframe into a json object that can be more easily used for visualization."""
     # df is the dataframe of annotations
     # doc_name is the name of the document
     # annotator is the name of the annotator (optional)
+    # select dimension_to_layer_name
+    if 'Segment_Patient_A' in df.layer.unique():
+        dimension_to_layer_name = dimension_to_layer_name_cleaned
+    else:
+        dimension_to_layer_name = dimension_to_layer_name_raw
+    
     def get_evidence_obj(evidence_df):
         "Assume that the evidence_df is a partial dataframe including only annotation of a single evidence span."
         evidence_obj = {k: v.value.iloc[0] for k, v in evidence_df.groupby("feature")}