Merge pull request #88 from chenyangkang/debug

fix #87; compatibility with pandas 3.0

Author: chenyangkang

.github/workflows/run_pytest.yml

@@ -11,7 +11,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        python-version: ["3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.11", "3.12", "3.13"] #future: "3.14"
     steps:
     - name: Set Swap Space
       uses: pierotofy/set-swap-space@master

setup.py

@@ -46,9 +46,9 @@
         "Development Status :: 5 - Production/Stable",
         "Programming Language :: Python :: 3",
         "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
         "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
         "Operating System :: Unix",
         "Operating System :: MacOS :: MacOS X",
         "Operating System :: Microsoft :: Windows",

stemflow/model/AdaSTEM.py

@@ -944,13 +944,13 @@ def find_belonged_points_and_predict(df, st_indexes_df, X_df):
                             "stixel_calibration_point_transformed_upper_bound",
                         ]
                     ]
-                    .groupby(["ensemble_index", "unique_stixel_id"], as_index=False)
+                    .groupby(["ensemble_index", "unique_stixel_id"], as_index=False, group_keys=False)
                     .pipe(lambda x: x[x.obj.columns]) # Explicitly select all the columns in the original df to include. To overcome the include_groups=True deprecation warning
                     .apply(find_belonged_points_and_predict, st_indexes_df=window_X_df_indexes_only, X_df=window_X_df, include_groups=False) # although ["ensemble_index", "unique_stixel_id"] will be passed into `find_belonged_points` due to `.pipe(lambda x: x[x.obj.columns])`, the output will not have them so we still set `as_index=True` in `groupby`
                 )
 
-                if len(res)>0:
-                    res = res.droplevel(0) # If using as_index=False duing groupby, pandas will automatically generate a group indexing column, so drop the indexing of the new groups
+                # if len(res)>0:
+                #     res = res.droplevel(0) # If using as_index=False duing groupby, pandas will automatically generate a group indexing column, so drop the indexing of the new groups
 
                 window_prediction_list.append(res)
 

stemflow/model/SphereAdaSTEM.py

@@ -513,17 +513,18 @@ def find_belonged_points(df, st_indexes_df, X_df):
             window_prediction = (
                 query_results
                 .dropna(subset="unique_stixel_id")
-                .groupby("unique_stixel_id", as_index=False)
+                .groupby("unique_stixel_id", as_index=False, group_keys=False)
                 .pipe(lambda x: x[x.obj.columns])
                 .apply(lambda stixel: self.stixel_predict(stixel), include_groups=False)
-                .droplevel(0)
             )
             # print('window_prediction:',window_prediction)
             window_prediction_list.append(window_prediction)
 
         if any([i is not None for i in window_prediction_list]):
             ensemble_prediction = pd.concat(window_prediction_list, axis=0)
-            ensemble_prediction = ensemble_prediction.groupby("index").mean().reset_index(drop=False)
+            ensemble_prediction = ensemble_prediction.groupby(level=0).mean()
+            ensemble_prediction.index.name = "index"
+            ensemble_prediction = ensemble_prediction.reset_index(drop=False)
         else:
             ensmeble_index = list(window_single_ensemble_df["ensemble_index"])[0]
             warnings.warn(f"No prediction for this ensemble: {ensmeble_index}")