mostlyai-engine 1.5.7__tar.gz → 1.5.8__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (51) hide show
  1. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/PKG-INFO +1 -1
  2. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/__init__.py +1 -1
  3. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/tabular/numeric.py +2 -2
  4. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/pyproject.toml +1 -1
  5. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/.gitignore +0 -0
  6. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/LICENSE +0 -0
  7. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/README.md +0 -0
  8. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_common.py +0 -0
  9. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_dtypes.py +0 -0
  10. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/__init__.py +0 -0
  11. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/language/__init__.py +0 -0
  12. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/language/categorical.py +0 -0
  13. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/language/datetime.py +0 -0
  14. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/language/numeric.py +0 -0
  15. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/language/text.py +0 -0
  16. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/tabular/__init__.py +0 -0
  17. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/tabular/categorical.py +0 -0
  18. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/tabular/character.py +0 -0
  19. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/tabular/datetime.py +0 -0
  20. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/tabular/itt.py +0 -0
  21. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_encoding_types/tabular/lat_long.py +0 -0
  22. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/__init__.py +0 -0
  23. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/common.py +0 -0
  24. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/encoding.py +0 -0
  25. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/engine/__init__.py +0 -0
  26. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/engine/base.py +0 -0
  27. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/engine/hf_engine.py +0 -0
  28. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/engine/vllm_engine.py +0 -0
  29. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/generation.py +0 -0
  30. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/lstm.py +0 -0
  31. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/tokenizer_utils.py +0 -0
  32. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/training.py +0 -0
  33. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_language/xgrammar_utils.py +0 -0
  34. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_memory.py +0 -0
  35. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_tabular/__init__.py +0 -0
  36. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_tabular/argn.py +0 -0
  37. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_tabular/common.py +0 -0
  38. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_tabular/encoding.py +0 -0
  39. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_tabular/fairness.py +0 -0
  40. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_tabular/generation.py +0 -0
  41. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_tabular/training.py +0 -0
  42. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_training_utils.py +0 -0
  43. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/_workspace.py +0 -0
  44. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/analysis.py +0 -0
  45. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/domain.py +0 -0
  46. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/encoding.py +0 -0
  47. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/generation.py +0 -0
  48. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/logging.py +0 -0
  49. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/random_state.py +0 -0
  50. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/splitting.py +0 -0
  51. {mostlyai_engine-1.5.7 → mostlyai_engine-1.5.8}/mostlyai/engine/training.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: mostlyai-engine
3
- Version: 1.5.7
3
+ Version: 1.5.8
4
4
  Summary: Synthetic Data Engine
5
5
  Project-URL: homepage, https://github.com/mostly-ai/mostlyai-engine
6
6
  Project-URL: repository, https://github.com/mostly-ai/mostlyai-engine
@@ -22,7 +22,7 @@ from mostlyai.engine.splitting import split
22
22
  from mostlyai.engine.training import train
23
23
 
24
24
  __all__ = ["split", "analyze", "encode", "train", "generate", "init_logging", "set_random_state"]
25
- __version__ = "1.5.7"
25
+ __version__ = "1.5.8"
26
26
 
27
27
  # suppress specific warning related to os.fork() in multi-threaded processes
28
28
  warnings.filterwarnings("ignore", category=DeprecationWarning, message=".*multi-threaded.*fork.*")
@@ -401,10 +401,10 @@ def _encode_numeric_digit(values: pd.Series, stats: dict, _: pd.Series | None =
401
401
  # replace extreme values with min/max
402
402
  if stats["min"] is not None:
403
403
  reduced_min = _type_safe_numeric_series([stats["min"]], dtype).iloc[0]
404
- values.loc[values < reduced_min] = reduced_min
404
+ values = values.where((values.isna()) | (values >= reduced_min), reduced_min)
405
405
  if stats["max"] is not None:
406
406
  reduced_max = _type_safe_numeric_series([stats["max"]], dtype).iloc[0]
407
- values.loc[values > reduced_max] = reduced_max
407
+ values = values.where((values.isna()) | (values <= reduced_max), reduced_max)
408
408
  # split to sub_columns
409
409
  df = split_sub_columns_digit(values, stats["max_decimal"], stats["min_decimal"])
410
410
  is_not_nan = df["nan"] == 0
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "mostlyai-engine"
3
- version = "1.5.7"
3
+ version = "1.5.8"
4
4
  description = "Synthetic Data Engine"
5
5
  authors = [{ name = "MOSTLY AI", email = "dev@mostly.ai" }]
6
6
  requires-python = ">=3.10"
File without changes