sdgym 0.14.5.dev0__tar.gz → 0.15.1.dev0__tar.gz

{sdgym-0.14.5.dev0/sdgym.egg-info → sdgym-0.15.1.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdgym
-Version: 0.14.5.dev0
+Version: 0.15.1.dev0
 Summary: Benchmark tabular synthetic data generators using a variety of datasets
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License-Expression: BUSL-1.1

{sdgym-0.14.5.dev0 → sdgym-0.15.1.dev0}/pyproject.toml

@@ -168,7 +168,7 @@ namespaces = false
 version = {attr = 'sdgym.__version__'}
 
 [tool.bumpversion]
-current_version = "0.14.5.dev0"
+current_version = "0.15.1.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',

{sdgym-0.14.5.dev0 → sdgym-0.15.1.dev0}/sdgym/__init__.py

@@ -8,7 +8,7 @@ __author__ = 'DataCebo, Inc.'
 __copyright__ = 'Copyright (c) 2022 DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
 __license__ = 'BSL-1.1'
-__version__ = '0.14.5.dev0'
+__version__ = '0.15.1.dev0'
 
 import logging
 

{sdgym-0.14.5.dev0 → sdgym-0.15.1.dev0}/sdgym/datasets.py

@@ -187,14 +187,12 @@ def get_data_and_metadata_from_path(dataset_path, modality):
     metadata_dict = None
     data = None
     for file_name in dataset_path.iterdir():
-        if 'metadata' in file_name.stem and file_name.suffix == '.json':
+        is_metadata = 'metadata' in file_name.stem and file_name.suffix == '.json'
+        if (is_metadata and metadata_dict is None) or file_name.name == 'metadata.json':
             metadata_dict = _read_metadata_json(file_name)
         elif 'data' in file_name.stem and file_name.suffix == '.zip':
             data = _read_zipped_data(zip_file_path=(file_name), modality=modality)
 
-        if data is not None and metadata_dict is not None:
-            break
-
     return data, metadata_dict
 
 

{sdgym-0.14.5.dev0 → sdgym-0.15.1.dev0}/sdgym/run_benchmark/upload_benchmark_results.py

@@ -33,17 +33,7 @@ from sdgym.s3 import S3_REGION, load_pickle_from_s3, parse_s3_path
 from sdgym.utils import _set_column_width
 
 LOGGER = logging.getLogger(__name__)
-SYNTHESIZER_TO_GLOBAL_POSITION = {
-    'CTGAN': 'middle right',
-    'TVAE': 'middle left',
-    'GaussianCopula': 'bottom center',
-    'Uniform': 'top center',
-    'Column': 'top center',
-    'CopulaGAN': 'top center',
-    'RealTabFormer': 'bottom center',
-    'HSA': 'bottom center',
-    'Independent': 'top center',
-}
+
 SDGYM_RUNS_FILENAME = 'SDGym_Runs.xlsx'
 MODEL_DETAILS_FILENAME = 'Model_Details.xlsx'
 DATASET_DETAILS_FILENAME = 'Dataset_Details.xlsx'

{sdgym-0.14.5.dev0 → sdgym-0.15.1.dev0}/sdgym/synthesizer_descriptions.yaml

@@ -134,3 +134,22 @@ XGCSynthesizer:
     to train a model and generate synthetic data similar to the GaussianCopulaSynthesizer.
     However, it contains some additional features for higher quality modeling.
 
+TabDDOMSynthesizer:
+  library: sdgym
+  organization: Yandex
+  modality: single_table
+  type: Deep Learning
+  description: >
+    The TabDDPM model is a denoising diffusion probabilistic model for tabular datasets.
+    It uses the multinomial diffusion to model the categorical and binary features, and
+    the Gaussian diffusion to model the numerical ones.
+
+ClavaDDPMSynthesizer:
+  library: sdgym
+  organization: University of Waterloo, Vector Institute, Royal Bank of Canada
+  modality: multi_table
+  type: Deep Learning
+  description: >
+    The ClavaDDPM model is an extension of the TabDDPM model to handle multi-table datasets.
+    It is based on clustering labels as intermediaries to model relationships between tables,
+    specifically focusing on foreign key constraints.

{sdgym-0.14.5.dev0 → sdgym-0.15.1.dev0/sdgym.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdgym
-Version: 0.14.5.dev0
+Version: 0.15.1.dev0
 Summary: Benchmark tabular synthetic data generators using a variety of datasets
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License-Expression: BUSL-1.1