fix exclusion imlementation and fix FutureWarning and DeprecationWarning

Author: staskh

README.md

@@ -33,7 +33,7 @@ Unless noted, iglu-r test is considered successful if it achieves precision of 0
 | cv_glu | ✅ |
 | cv_measures | ✅ |
 | ea1c | ✅ |
-| episode_calculation |  🟡  need fix in excl| || no match in lv1_hypo_excl and lv1_hyper_excl|
+| episode_calculation |  ✅| || no match in lv1_hypo_excl and lv1_hyper_excl|
 | gmi | ✅ |
 | grade_eugly | ✅ |
 | grade_hyper | ✅ |

iglu_python/episode_calculation.py

@@ -168,8 +168,15 @@ def episode_calculation(
         subject_episode_data['id'] = subject_id
 
         # Append to main dataframes
-        episode_data_df = pd.concat([episode_data_df, subject_episode_data], ignore_index=True)
-        episode_summary_df = pd.concat([episode_summary_df, subject_summary], ignore_index=True)
+        if episode_data_df.empty:
+            episode_data_df = subject_episode_data
+        else:
+            episode_data_df = pd.concat([episode_data_df, subject_episode_data], ignore_index=True)
+        
+        if episode_summary_df.empty:
+            episode_summary_df = subject_summary
+        else:
+            episode_summary_df = pd.concat([episode_summary_df, subject_summary], ignore_index=True)
 
 
 
@@ -238,7 +245,7 @@ def episode_single(
             day_one = day_one.tz_convert(local_tz)
         ndays = len(gd2d_tuple[1])
         # generate grid times by starting from day one and cumulatively summing
-        time_ip =  pd.date_range(start=day_one + pd.Timedelta(minutes=dt0), periods=ndays * 24 * 60 /dt0, freq=f"{dt0}min")
+        time_ip =  pd.date_range(start=day_one + pd.Timedelta(minutes=dt0), periods=int(ndays * 24 * 60 /dt0), freq=f"{dt0}min")
         data_ip = gd2d_tuple[0].flatten().tolist()
         new_data = pd.DataFrame({
             "time": time_ip,
@@ -305,22 +312,17 @@ def episode_single(
     )
 
 
-    # Add exclusive labels
-    def hypo_exclusion_logic(group_df):
-        # group_df is a DataFrame with all columns for the current group
-        if (group_df['lv2_hypo'] > 0).any():
-            return pd.Series([0] * len(group_df), index=group_df.index)
-        else:
-            return group_df['lv1_hypo']
-    ep_per_seg['lv1_hypo_excl'] = ep_per_seg.groupby(['segment', 'lv1_hypo']).apply(hypo_exclusion_logic, include_groups=True).reset_index(level=[0,1], drop=True).values.flatten()
-
-    def hyper_exclusion_logic(group_df):
-        # group_df is a DataFrame with all columns for the current group
-        if (group_df['lv2_hyper'] > 0).any():
-            return pd.Series([0] * len(group_df), index=group_df.index)
-        else:
-            return group_df['lv1_hyper']
-    ep_per_seg['lv1_hyper_excl'] = ep_per_seg.groupby(['segment', 'lv1_hyper']).apply(hyper_exclusion_logic, include_groups=True).reset_index(level=[0,1], drop=True).values.flatten()
+    # Add exclusive labels using the correct original logic without DeprecationWarning
+    # For hypo exclusion: group by both segment and lv1_hypo, set to 0 if any lv2_hypo > 0 in that group
+    def calculate_exclusion(df, lv1_col, lv2_col):
+        """Calculate exclusion labels for lv1 episodes based on lv2 episodes in same group"""
+        df = df.copy()
+        df['group_id'] = df.groupby(['segment', lv1_col]).ngroup()
+        group_has_lv2 = df.groupby('group_id')[lv2_col].transform(lambda x: (x > 0).any())
+        return df[lv1_col].where(~group_has_lv2, 0)
+    
+    ep_per_seg['lv1_hypo_excl'] = calculate_exclusion(ep_per_seg, 'lv1_hypo', 'lv2_hypo')
+    ep_per_seg['lv1_hyper_excl'] = calculate_exclusion(ep_per_seg, 'lv1_hyper', 'lv2_hyper')
 
     full_segment_df = pd.concat([segment_data, ep_per_seg.drop(["segment"], axis=1)], axis=1)
 

tests/test_episode_calculation.py

@@ -63,8 +63,8 @@ def test_episode_calculation_iglu_r_compatible(scenario):
 
         # ToDo : find why no match in lv1_hypo_excl and lv1_hyper_excl
         pd.testing.assert_frame_equal(
-            result_data_df[['id', 'time', 'gl', 'segment', 'lv1_hypo', 'lv2_hypo', 'lv1_hyper', 'lv2_hyper', 'ext_hypo']],
-            expected_data_df[['id', 'time', 'gl', 'segment', 'lv1_hypo', 'lv2_hypo', 'lv1_hyper', 'lv2_hyper', 'ext_hypo']],
+            result_data_df,
+            expected_data_df,
             check_dtype=False,  # Don't check dtypes since we might have different numeric types
             check_index_type=True,
             check_column_type=True,