bugfix

VIDA-NYU · Jun 24, 2024 · d7e00ee · d7e00ee
1 parent 4b050a4
commit d7e00ee
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/alpha_automl/automl_manager.py b/alpha_automl/automl_manager.py
@@ -14,7 +14,7 @@
 INCLUDE_PRIMITIVES = []
 NEW_PRIMITIVES = {}
 SPLITTING_STRATEGY = 'holdout'
-SAMPLE_SIZE = 50000
+SAMPLE_SIZE = 100000
 MAX_RUNNING_PROCESSES = multiprocessing.cpu_count()
 
 logger = logging.getLogger(__name__)

diff --git a/alpha_automl/data_profiler.py b/alpha_automl/data_profiler.py
@@ -33,7 +33,7 @@ def profile_data(X):
             add_nonnumeric_column(column_type, metadata, index_column, column_name)
 
         elif TEXT_COLUMN == profiled_column['structural_type']:
-            samples = X[column_name].dropna().sample(5)
+            samples = X[column_name].dropna().sample(5).astype('string')
             if samples.apply(lambda x: x.endswith(('jpg', 'png', 'jpeg', 'gif'))).all():
                 column_type = mapping_encoders[IMAGE_COLUMN]
             else: