added explicit classifier column to scoring dataframes and updated ga…

…ther results accordingly
uhlmanngroup · Oct 21, 2024 · 099b666 · 099b666
1 parent 74fe9d0
commit 099b666
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/scripts/shapeembed/evaluation.py b/scripts/shapeembed/evaluation.py
@@ -105,7 +105,8 @@ def score_dataframe( df, name
     # Put the results into a DataFrame
     df = pandas.DataFrame(cv_results)
     df = df.drop(["fit_time", "score_time"], axis=1)
-    df.insert(loc=0, column='trial', value=f'{name}_{pipename}')
+    df.insert(loc=0, column='classifier', value=pipename)
+    df.insert(loc=0, column='trial', value=name)
     tag_columns.reverse()
     for tag_col_name, tag_col_value in tag_columns:
       df.insert(loc=0, column=tag_col_name, value=tag_col_value)

diff --git a/scripts/shapeembed/gather_run_results.py b/scripts/shapeembed/gather_run_results.py
@@ -142,7 +142,7 @@ def main_process(clargs, logger=logging.getLogger(__name__)):
   # function for finding total
   def keep_first_fname(series): 
     return functools.reduce(lambda x, y: y if str(x) == 'nofile' else x, series)
-  idx_cols = ['trial', 'dataset', 'model', 'compression_factor', 'latent_dim', 'batch_size']
+  idx_cols = ['trial', 'classifier', 'dataset', 'model', 'compression_factor', 'latent_dim', 'batch_size']
   df.set_index(idx_cols, inplace=True)
   df.sort_index(inplace=True)
   #df = df.groupby(level=['trial', 'dataset', 'model', 'compression_factor', 'latent_dim', 'batch_size']).agg({