sdgym 0.10.0.dev0__tar.gz → 0.10.1.dev0__tar.gz

{sdgym-0.10.0.dev0/sdgym.egg-info → sdgym-0.10.1.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: sdgym
-Version: 0.10.0.dev0
+Version: 0.10.1.dev0
 Summary: Benchmark tabular synthetic data generators using a variety of datasets
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -15,13 +15,13 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: Free for non-commercial use
 Classifier: Natural Language :: English
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: <3.13,>=3.8
+Requires-Python: <3.14,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: appdirs>=1.3
@@ -29,59 +29,66 @@ Requires-Dist: boto3<2,>=1.28
 Requires-Dist: botocore<2,>=1.31
 Requires-Dist: cloudpickle>=2.1.0
 Requires-Dist: compress-pickle>=1.2.0
-Requires-Dist: humanfriendly>=8.2
-Requires-Dist: numpy>=1.21.6; python_version < "3.10"
-Requires-Dist: numpy>=1.23.3; python_version >= "3.10" and python_version < "3.12"
-Requires-Dist: numpy>=1.26.0; python_version >= "3.12"
+Requires-Dist: humanfriendly>=10.0
+Requires-Dist: numpy>=1.22.2; python_version < "3.10"
+Requires-Dist: numpy>=1.24.0; python_version >= "3.10" and python_version < "3.12"
+Requires-Dist: numpy>=1.26.0; python_version >= "3.12" and python_version < "3.13"
+Requires-Dist: numpy>=2.1.0; python_version >= "3.13"
 Requires-Dist: pandas>=1.4.0; python_version < "3.11"
 Requires-Dist: pandas>=1.5.0; python_version >= "3.11" and python_version < "3.12"
-Requires-Dist: pandas>=2.1.1; python_version >= "3.12"
+Requires-Dist: pandas>=2.1.1; python_version >= "3.12" and python_version < "3.13"
+Requires-Dist: pandas>=2.2.3; python_version >= "3.13"
 Requires-Dist: psutil>=5.7
 Requires-Dist: scikit-learn>=1.0.2; python_version < "3.10"
 Requires-Dist: scikit-learn>=1.1.0; python_version >= "3.10" and python_version < "3.11"
 Requires-Dist: scikit-learn>=1.1.3; python_version >= "3.11" and python_version < "3.12"
-Requires-Dist: scikit-learn>=1.3.1; python_version >= "3.12"
+Requires-Dist: scikit-learn>=1.3.1; python_version >= "3.12" and python_version < "3.13"
+Requires-Dist: scikit-learn>=1.5.2; python_version >= "3.13"
 Requires-Dist: scipy>=1.7.3; python_version < "3.10"
 Requires-Dist: scipy>=1.9.2; python_version >= "3.10" and python_version < "3.12"
-Requires-Dist: scipy>=1.12.0; python_version >= "3.12"
+Requires-Dist: scipy>=1.12.0; python_version >= "3.12" and python_version < "3.13"
+Requires-Dist: scipy>=1.14.1; python_version >= "3.13"
 Requires-Dist: tabulate<0.9,>=0.8.3
-Requires-Dist: torch>=1.12.1; python_version < "3.10"
-Requires-Dist: torch>=2.0.0; python_version >= "3.10" and python_version < "3.12"
-Requires-Dist: torch>=2.2.0; python_version >= "3.12"
+Requires-Dist: torch>=2.6.0
 Requires-Dist: tqdm>=4.66.3
 Requires-Dist: XlsxWriter>=1.2.8
-Requires-Dist: rdt>=1.13.1
-Requires-Dist: sdmetrics>=0.17.0
-Requires-Dist: sdv>=1.17.2
+Requires-Dist: rdt>=1.17.0
+Requires-Dist: sdmetrics>=0.20.1
+Requires-Dist: sdv>=1.21.0
 Provides-Extra: dask
 Requires-Dist: dask; extra == "dask"
 Requires-Dist: distributed; extra == "dask"
 Provides-Extra: realtabformer
-Requires-Dist: realtabformer>=0.2.2; extra == "realtabformer"
-Requires-Dist: torch>=2.0.0; (python_version >= "3.8" and python_version < "3.12") and extra == "realtabformer"
-Requires-Dist: torch>=2.2.0; python_version >= "3.12" and extra == "realtabformer"
+Requires-Dist: realtabformer>=0.2.3; extra == "realtabformer"
+Requires-Dist: torch>=2.6.0; extra == "realtabformer"
+Requires-Dist: transformers<4.51; extra == "realtabformer"
 Provides-Extra: test
 Requires-Dist: sdgym[realtabformer]; extra == "test"
 Requires-Dist: pytest>=6.2.5; extra == "test"
 Requires-Dist: pytest-cov>=2.6.0; extra == "test"
 Requires-Dist: jupyter<2,>=1.0.0; extra == "test"
-Requires-Dist: rundoc<0.5,>=0.4.3; extra == "test"
 Requires-Dist: tomli<3,>=2.0.0; extra == "test"
+Requires-Dist: slack-sdk<4.0,>=3.23; extra == "test"
+Requires-Dist: openpyxl>=3.0.0; python_version < "3.9" and extra == "test"
+Requires-Dist: openpyxl>=3.1.2; python_version >= "3.9" and extra == "test"
+Requires-Dist: pydrive2<2.0.0,>=1.4.0; extra == "test"
 Provides-Extra: dev
 Requires-Dist: sdgym[dask,test]; extra == "dev"
 Requires-Dist: build<2,>=1.0.0; extra == "dev"
-Requires-Dist: bump-my-version<1,>=0.18.3; extra == "dev"
+Requires-Dist: bump-my-version>=0.18.3; extra == "dev"
 Requires-Dist: pip>=9.0.1; extra == "dev"
 Requires-Dist: watchdog<5,>=1.0.1; extra == "dev"
 Requires-Dist: ruff<1,>=0.4.5; extra == "dev"
-Requires-Dist: twine<6,>=1.10.0; extra == "dev"
+Requires-Dist: twine>=1.10.0; extra == "dev"
 Requires-Dist: wheel>=0.30.0; extra == "dev"
 Requires-Dist: coverage<8,>=4.5.12; extra == "dev"
-Requires-Dist: tox<5,>=2.9.1; extra == "dev"
 Requires-Dist: importlib-metadata>=3.6; extra == "dev"
 Requires-Dist: invoke; extra == "dev"
+Provides-Extra: readme
+Requires-Dist: rundoc<0.5,>=0.4.3; extra == "readme"
 Provides-Extra: all
 Requires-Dist: sdgym[dask,dev,test]; extra == "all"
+Dynamic: license-file
 
 <div align="center">
 <br/>

{sdgym-0.10.0.dev0 → sdgym-0.10.1.dev0}/pyproject.toml

@@ -8,17 +8,17 @@ classifiers = [
     'License :: Free for non-commercial use',
     'Natural Language :: English',
     'Programming Language :: Python :: 3',
-    'Programming Language :: Python :: 3.8',
     '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',
     'Topic :: Scientific/Engineering :: Artificial Intelligence',
 ]
 keywords = ['machine learning', 'synthetic data generation', 'benchmark', 'generative models']
 dynamic = ['version']
 license = { text = 'BSL-1.1' }
-requires-python = '>=3.8,<3.13'
+requires-python = '>=3.9,<3.14'
 readme = 'README.md'
 dependencies = [
     'appdirs>=1.3',
@@ -26,30 +26,32 @@ dependencies = [
     'botocore>=1.31,<2',
     'cloudpickle>=2.1.0',
     'compress-pickle>=1.2.0',
-    'humanfriendly>=8.2',
-    "numpy>=1.21.6;python_version<'3.10'",
-    "numpy>=1.23.3;python_version>='3.10' and python_version<'3.12'",
-    "numpy>=1.26.0;python_version>='3.12'",
+    'humanfriendly>=10.0',
+    "numpy>=1.22.2;python_version<'3.10'",
+    "numpy>=1.24.0;python_version>='3.10' and python_version<'3.12'",
+    "numpy>=1.26.0;python_version>='3.12' and python_version<'3.13'",
+    "numpy>=2.1.0;python_version>='3.13'",
     "pandas>=1.4.0;python_version<'3.11'",
     "pandas>=1.5.0;python_version>='3.11' and python_version<'3.12'",
-    "pandas>=2.1.1;python_version>='3.12'",
+    "pandas>=2.1.1;python_version>='3.12' and python_version<'3.13'",
+    "pandas>=2.2.3;python_version>='3.13'",
     'psutil>=5.7',
     "scikit-learn>=1.0.2;python_version<'3.10'",
     "scikit-learn>=1.1.0;python_version>='3.10' and python_version<'3.11'",
     "scikit-learn>=1.1.3;python_version>='3.11' and python_version<'3.12'",
-    "scikit-learn>=1.3.1;python_version>='3.12'",
+    "scikit-learn>=1.3.1;python_version>='3.12' and python_version<'3.13'",
+    "scikit-learn>=1.5.2;python_version>='3.13'",
     "scipy>=1.7.3;python_version<'3.10'",
     "scipy>=1.9.2;python_version>='3.10' and python_version<'3.12'",
-    "scipy>=1.12.0;python_version>='3.12'",
+    "scipy>=1.12.0;python_version>='3.12' and python_version<'3.13'",
+    "scipy>=1.14.1;python_version>='3.13'",
     'tabulate>=0.8.3,<0.9',
-    "torch>=1.12.1;python_version<'3.10'",
-    "torch>=2.0.0;python_version>='3.10' and python_version<'3.12'",
-    "torch>=2.2.0;python_version>='3.12'",
+    "torch>=2.6.0",
     'tqdm>=4.66.3',
     'XlsxWriter>=1.2.8',
-    'rdt>=1.13.1',
-    'sdmetrics>=0.17.0',
-    'sdv>=1.17.2',
+    'rdt>=1.17.0',
+    'sdmetrics>=0.20.1',
+    'sdv>=1.21.0',
 ]
 
 [project.urls]
@@ -65,24 +67,27 @@ sdgym = { main = 'sdgym.cli.__main__:main' }
 [project.optional-dependencies]
 dask = ['dask', 'distributed']
 realtabformer = [
-    'realtabformer>=0.2.2',
-    "torch>=2.0.0;python_version>='3.8' and python_version<'3.12'",
-    "torch>=2.2.0;python_version>='3.12'",
+    'realtabformer>=0.2.3',
+    "torch>=2.6.0",
+    'transformers<4.51',
 ]
 test = [
     'sdgym[realtabformer]',
     'pytest>=6.2.5',
     'pytest-cov>=2.6.0',
     'jupyter>=1.0.0,<2',
-    'rundoc>=0.4.3,<0.5',
     'tomli>=2.0.0,<3',
+    'slack-sdk>=3.23,<4.0',
+    "openpyxl>=3.0.0; python_version<'3.9'",
+    "openpyxl>=3.1.2; python_version>='3.9'",
+    'pydrive2>=1.4.0,<2.0.0'
 ]
 dev = [
     'sdgym[dask, test]',
 
     # general
     'build>=1.0.0,<2',
-    'bump-my-version>=0.18.3,<1',
+    'bump-my-version>=0.18.3',
     'pip>=9.0.1',
     'watchdog>=1.0.1,<5',
 
@@ -90,17 +95,17 @@ dev = [
     'ruff>=0.4.5,<1',
 
     # distribute on PyPI
-    'twine>=1.10.0,<6',
+    'twine>=1.10.0',
     'wheel>=0.30.0',
 
     # Advanced testing
     'coverage>=4.5.12,<8',
-    'tox>=2.9.1,<5',
     'importlib-metadata>=3.6',
 
     # Invoke
     'invoke',
 ]
+readme = ['rundoc>=0.4.3,<0.5',]
 all = [
     'sdgym[dask, test, dev]',
 ]
@@ -140,7 +145,7 @@ namespaces = false
 version = {attr = 'sdgym.__version__'}
 
 [tool.bumpversion]
-current_version = "0.10.0.dev0"
+current_version = "0.10.1.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',
@@ -188,6 +193,8 @@ exclude = [
     "__pycache__",
     ".ipynb_checkpoints",
     "tasks.py",
+    "static_code_analysis.txt",
+    "*.ipynb"
 ]
 
 [tool.ruff.lint]
@@ -212,7 +219,6 @@ ignore = [
     # pydocstyle
     "D107",  # Missing docstring in __init__
     "D417",   # Missing argument descriptions in the docstring, this is a bug from pydocstyle: https://github.com/PyCQA/pydocstyle/issues/449
-    "PD901",
     "PD101",
 ]
 
@@ -237,4 +243,4 @@ convention = "google"
 
 [tool.ruff.lint.pycodestyle]
 max-doc-length = 100
-max-line-length = 100
+max-line-length = 100

{sdgym-0.10.0.dev0 → sdgym-0.10.1.dev0}/sdgym/__init__.py

@@ -8,26 +8,30 @@ __author__ = 'DataCebo, Inc.'
 __copyright__ = 'Copyright (c) 2022 DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
 __license__ = 'BSL-1.1'
-__version__ = '0.10.0.dev0'
+__version__ = '0.10.1.dev0'
 
 import logging
 
 from sdgym.benchmark import benchmark_single_table
 from sdgym.cli.collect import collect_results
 from sdgym.cli.summary import make_summary_spreadsheet
+from sdgym.dataset_explorer import DatasetExplorer
 from sdgym.datasets import get_available_datasets, load_dataset
 from sdgym.synthesizers import create_sdv_synthesizer_variant, create_single_table_synthesizer
+from sdgym.result_explorer import ResultsExplorer
 
 # Clear the logging wrongfully configured by tensorflow/absl
 list(map(logging.root.removeHandler, logging.root.handlers))
 list(map(logging.root.removeFilter, logging.root.filters))
 
 __all__ = [
-    'load_dataset',
-    'collect_results',
-    'make_summary_spreadsheet',
+    'DatasetExplorer',
+    'ResultsExplorer',
     'benchmark_single_table',
-    'get_available_datasets',
+    'collect_results',
     'create_sdv_synthesizer_variant',
     'create_single_table_synthesizer',
+    'get_available_datasets',
+    'load_dataset',
+    'make_summary_spreadsheet',
 ]

sdgym-0.10.1.dev0/sdgym/_dataset_utils.py

@@ -0,0 +1,107 @@
+"""Utility functions for handling datasets."""
+
+import json
+import logging
+from pathlib import Path
+from zipfile import ZipFile
+
+import numpy as np
+import pandas as pd
+
+LOGGER = logging.getLogger(__name__)
+
+
+def _parse_numeric_value(value, dataset_name, field_name, target_type=float):
+    """Generic parser for numeric values with logging and NaN fallback."""
+    try:
+        return target_type(value)
+    except (ValueError, TypeError):
+        LOGGER.info(
+            f"Could not cast {field_name} '{value}' to {target_type.__name__} for dataset "
+            f"'{dataset_name}' defaulting to NaN."
+        )
+        return np.nan
+
+
+def _get_dataset_subset(data, metadata_dict, modality):
+    """Limit the size of a dataset for faster evaluation or testing.
+
+    This function reduces a dataset to a smaller subset by restricting the number
+    of rows and columns to 1000 rows and 10 columns. It ensures that essential
+    columns—such as sequence indices and keys in sequential datasets—are always retained.
+
+    Args:
+        data (pd.DataFrame):
+            The dataset to be reduced.
+        metadata_dict (dict):
+            A dictionary containing the dataset's metadata.
+        modality (str):
+            The dataset modality. Must be one of: ``'single_table'``, ``'sequential'``.
+
+    Returns:
+        tuple[pd.DataFrame, dict]:
+            A tuple containing:
+            - The reduced dataset as a DataFrame.
+            - The updated metadata dictionary reflecting any removed columns.
+
+    Raises:
+        ValueError:
+            If the provided modality is ``'multi_table'``.
+    """
+    if modality == 'multi_table':
+        raise ValueError('limit_dataset_size is not supported for multi-table datasets.')
+
+    max_rows, max_columns = (1000, 10)
+    tables = metadata_dict.get('tables', {})
+    mandatory_columns = []
+    table_name, table_info = next(iter(tables.items()))
+
+    columns = table_info.get('columns', {})
+    keep_columns = list(columns)
+    if modality == 'sequential':
+        seq_index = table_info.get('sequence_index')
+        seq_key = table_info.get('sequence_key')
+        mandatory_columns = [col for col in (seq_index, seq_key) if col]
+
+    optional_columns = [col for col in columns if col not in mandatory_columns]
+
+    # If we have too many columns, drop extras but never mandatory ones
+    if len(columns) > max_columns:
+        keep_count = max_columns - len(mandatory_columns)
+        keep_columns = mandatory_columns + optional_columns[:keep_count]
+        table_info['columns'] = {
+            column_name: column_definition
+            for column_name, column_definition in columns.items()
+            if column_name in keep_columns
+        }
+
+    data = data[list(keep_columns)]
+    data = data.sample(max_rows)
+    return data, metadata_dict
+
+
+def _read_zipped_data(zip_file_path, modality):
+    data = {}
+    with ZipFile(zip_file_path, 'r') as zf:
+        for file_name in zf.namelist():
+            if file_name.endswith('.csv'):
+                key = Path(file_name).stem
+                data[key] = _read_csv_from_zip(zf, csv_file_name=file_name)
+
+    if modality != 'multi_table':
+        data = next(iter(data.values()))
+
+    return data
+
+
+def _read_csv_from_zip(zip_file, csv_file_name):
+    """Read a single CSV file from an open ZipFile and return a DataFrame."""
+    with zip_file.open(csv_file_name) as csv_file:
+        return pd.read_csv(csv_file, low_memory=False)
+
+
+def _read_metadata_json(metadata_path):
+    with open(metadata_path) as metadata_file:
+        metadata_dict = json.load(metadata_file)
+
+    return metadata_dict