Bokeh figure - added symbol for "ensemble" model type

analyze_winscore.py

@@ -74,19 +74,32 @@ def create_scatter_plot_with_curve_with_variances_named(category, variance_acros
     def get_variance_for_model(model_name):
         return variance_across_categories.get(model_name, 0)  # Default to 0 if model not found
 
+    # Get markers
+    filtered_markers = np.array(model_names)[np.in1d(x, x_filtered)]
+    outlier_markers = np.array(model_names)[np.in1d(x, x_outliers)]
+
     # Get marker sizes and variances for the filtered data
-    filtered_variances = [get_variance_for_model(mname) for mname in np.array(model_names)[np.in1d(x, x_filtered)]]
+    filtered_variances = [get_variance_for_model(mname) for mname in filtered_markers]
     marker_sizes_filtered = [scale_variance_to_size(var) for var in filtered_variances]
     
     # Get marker sizes and variances for the outlier data
-    outlier_variances = [get_variance_for_model(mname) for mname in np.array(model_names)[np.in1d(x, x_outliers)]]
+    outlier_variances = [get_variance_for_model(mname) for mname in outlier_markers]
     marker_sizes_outliers = [scale_variance_to_size(var) for var in outlier_variances]
 
-    # Randomly assign symbols to the filtered data points
-    filtered_symbols = ['circle' if ldb_records[mname]['Type'] == 'chat' else 'triangle' for mname in np.array(model_names)[np.in1d(x, x_filtered)]]
+    # Assign symbols to the model types
+    # https://docs.bokeh.org/en/latest/docs/examples/basic/scatters/markers.html
+    _model_type2symbol = {
+        'chat': 'circle',
+        'pretrained': 'triangle',
+        'ensemble': 'star',
+    }
+    model_type2symbol = lambda model_type: _model_type2symbol.get(model_type, 'diamond')
+    
+    # Assign symbols to the filtered data points
+    filtered_symbols = [model_type2symbol(ldb_records[mname]['Type']) for mname in filtered_markers]
     
-    # Randomly assign symbols to the outlier data points
-    outlier_symbols = ['circle' if ldb_records[mname]['Type'] == 'chat' else 'triangle' for mname in np.array(model_names)[np.in1d(x, x_outliers)]]
+    # Assign symbols to the outlier data points
+    outlier_symbols = [model_type2symbol(ldb_records[mname]['Type']) for mname in outlier_markers]
     
     # Define a color palette with enough colors
     stride = len(Turbo256) // len(model_names)