lower numpy version

setup.cfg

@@ -46,7 +46,7 @@ install_requires =
     pymesh
     torchsummary
     statsmodels
-    numpy<=1.25.0
+    numpy<=1.24.0
 
 
 python_requires = >=3.8

src/napatrackmater/Trackmate.py

@@ -2046,7 +2046,7 @@ def _update_spot_fate(self, TrackIds, fate_label):
                         {self.fate_key: fate_label}
                     )
 
-    def _get_trackmate_ids_by_location(self, dataframe):
+    def _get_trackmate_ids_by_location(self, dataframe, tracklet_length = None):
         trackmate_track_ids = []
         t = int(self.tend)
         for index, row in dataframe.iterrows():
@@ -2070,7 +2070,12 @@ def _get_trackmate_ids_by_location(self, dataframe):
                 spot_properties_dict = self.unique_spot_properties[spot_id]
                 if self.trackid_key in spot_properties_dict.keys():
                     trackmate_track_id = spot_properties_dict[self.trackid_key]
-                    trackmate_track_ids.append(trackmate_track_id)
+                    if tracklet_length is None:
+                       trackmate_track_ids.append(trackmate_track_id)
+                    else:
+                           track_duration = spot_properties_dict[self.track_duration_key]
+                           if track_duration > tracklet_length:
+                               trackmate_track_ids.append(trackmate_track_id)
 
         return trackmate_track_ids
 

src/napatrackmater/Trackvector.py

@@ -4103,7 +4103,7 @@ def get_most_frequent_prediction(predictions):
         return "UnClassified"
 
 
-def save_cell_type_predictions(tracks_dataframe, cell_map, predictions, save_dir):
+def save_cell_type_predictions(tracks_dataframe, cell_map, predictions, save_dir, channel):
 
     cell_type = {}
     for value in cell_map.values():
@@ -4129,11 +4129,11 @@ def save_cell_type_predictions(tracks_dataframe, cell_map, predictions, save_dir
         save_name = f"{value}_inception"
 
         if "Goblet" in value:
-            save_name = "goblet_cells_annotations_inception"
+            save_name = f"goblet_cells_{channel}annotations_inception"
         if "Radial" in value:
-            save_name = "radially_intercalating_cells_annotations_inception"
+            save_name = f"radially_intercalating_cells_{channel}annotations_inception"
         if "Basal" in value:
-            save_name = "basal_cells_annotations_inception"
+            save_name = f"basal_cells_{channel}annotations_inception"
 
         filename = os.path.join(save_dir, f"{save_name}.csv")
         df.to_csv(filename, index=True)