Merge branch 'main' into issue-2708-missing_values_proportion-invalid-key

Author: frances-h

pyproject.toml

@@ -38,7 +38,7 @@ dependencies = [
     'copulas>=0.12.1',
     'ctgan>=0.11.0',
     'deepecho>=0.7.0',
-    'rdt>=1.17.0',
+    'rdt>=1.18.2',
     'sdmetrics>=0.21.0',
     'platformdirs>=4.0',
     'pyyaml>=6.0.1',

sdv/single_table/_dayz_utils.py

@@ -42,8 +42,8 @@ def detect_column_parameters(data, metadata, table_name):
         if sdtype == 'numerical':
             column_parameters[column_name] = {
                 'num_decimal_digits': learn_rounding_digits(data[column_name]),
-                'min_value': data[column_name].min().item(),
-                'max_value': data[column_name].max().item(),
+                'min_value': data[column_name].min(),
+                'max_value': data[column_name].max(),
             }
         elif sdtype == 'datetime':
             datetime_format = column_metadata.get('datetime_format', None)
@@ -63,12 +63,12 @@ def detect_column_parameters(data, metadata, table_name):
                 'start_timestamp': start_timestamp,
                 'end_timestamp': end_timestamp,
             }
-        elif sdtype in ['categorical', 'boolean']:
+        elif sdtype == 'categorical':
             column_parameters[column_name] = {
                 'category_values': data[column_name].dropna().unique().tolist()
             }
 
-        column_parameters[column_name]['missing_values_proportion'] = (
+        column_parameters[column_name]['missing_values_proportion'] = float(
             data[column_name].isna().mean()
         )
 

tasks.py

@@ -13,7 +13,9 @@
 from packaging.version import Version
 
 COMPARISONS = {'>=': operator.ge, '>': operator.gt, '<': operator.lt, '<=': operator.le}
-
+EXTERNAL_DEPENDENCY_CAPS = {
+    'torch': '2.9.0'
+}
 
 if not hasattr(inspect, 'getargspec'):
     inspect.getargspec = inspect.getfullargspec
@@ -86,6 +88,8 @@ def install_minimum(c):
     if minimum_versions:
         install_deps = ' '.join(minimum_versions)
         c.run(f'python -m pip install {install_deps}')
+        for dep, cap in EXTERNAL_DEPENDENCY_CAPS.items():
+            c.run(f'python -m pip install "{dep}<{cap}"')
 
 
 @task

tests/integration/multi_table/test_dayz.py

@@ -24,7 +24,6 @@ def test_create_parameters_end_to_end(self):
                         'guest_email': {'missing_values_proportion': 0.0},
                         'hotel_id': {'missing_values_proportion': 0.0},
                         'has_rewards': {
-                            'category_values': [False, True],
                             'missing_values_proportion': 0.0,
                         },
                         'room_type': {

tests/integration/single_table/test_dayz.py

@@ -23,7 +23,6 @@ def test_create_parameters_end_to_end(self):
                     'columns': {
                         'guest_email': {'missing_values_proportion': 0.0},
                         'has_rewards': {
-                            'category_values': [False, True],
                             'missing_values_proportion': 0.0,
                         },
                         'room_type': {