dataforge-ml 2.0.4__tar.gz → 2.0.6__tar.gz

{dataforge_ml-2.0.4/src/dataforge_ml.egg-info → dataforge_ml-2.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataforge-ml
-Version: 2.0.4
+Version: 2.0.6
 Summary: A automated feature engineering and designing pipeline library
 License: MIT
 Classifier: License :: OSI Approved :: MIT License

{dataforge_ml-2.0.4 → dataforge_ml-2.0.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dataforge-ml"
-version = "2.0.4"
+version = "2.0.6"
 description = "A automated feature engineering and designing pipeline library"
 readme = "README.md"
 requires-python = ">3.10"

{dataforge_ml-2.0.4 → dataforge_ml-2.0.6}/src/dataforge_ml/config.py

@@ -86,20 +86,6 @@ class PipelineConfig:
         Single seed for all stochastic pipeline operations, including GMM
         Sampling during bimodal imputation. None produces non-deterministic
         output.
-
-    Attributes
-    ----------
-    exclude_columns : tuple[str, ...]
-        Hard exclusions — columns dropped globally from every phase.
-    phase_exclusions : MappingProxyType[PipelinePhase, tuple[str, ...]]
-        Soft exclusions — columns bypassed for a specific phase but retained
-        in the dataset.
-    column_overrides : MappingProxyType[str, SemanticType]
-        Explicit semantic type assignments respected by all downstream phases.
-    numeric_kind_overrides : MappingProxyType[str, NumericKind]
-        Explicit ``NumericKind`` assignments for individual columns, applied
-        after auto-detection in Phase 1. Only valid for columns whose final
-        ``SemanticType`` is ``Numeric``; raises at orchestrator time otherwise.
     """
 
     _exclude_columns: list[str] = field(default_factory=list, init=False)
@@ -150,6 +136,9 @@ class PipelineConfig:
     def numeric_kind_overrides(self) -> "MappingProxyType[str, NumericKind]":
         """Explicit NumericKind assignments for individual columns, applied after auto-detection in Phase 1.
 
+        Only valid for columns whose final ``SemanticType`` is ``Numeric``;
+        raises at orchestrator time otherwise.
+
         Returns
         -------
         MappingProxyType[str, NumericKind]

{dataforge_ml-2.0.4 → dataforge_ml-2.0.6}/src/dataforge_ml/profiling/_config.py

@@ -628,27 +628,6 @@ class ProfileConfig:
         Default ``False``.
     nonlinearity : NonlinearityProfileConfig
         Threshold configuration for the nonlinearity sub-processor.
-
-    Attributes
-    ----------
-    numeric_sentinels : MappingProxyType[str, list[float]]
-        Per-column numeric sentinel declarations.  Keys are column names;
-        values are lists of float-compatible sentinel values that should be
-        treated as effective nulls (e.g. ``{"age": [-999.0, 9999.0]}``).
-        Applies to any column whose dtype passes ``_numeric_sentinel_eligible``
-        (all integer and float Polars dtypes).  Defaults to an empty dict —
-        columns with no declaration are completely unaffected.
-    string_sentinels : MappingProxyType[str, list[str]]
-        Per-column user-declared string sentinel declarations.  Keys are column
-        names; values are lists of string values that should be treated as
-        effective nulls for that column (e.g.
-        ``{"status": ["N/A", "missing"]}``).  Uses **replace semantics**: when
-        a declaration exists for a column, only the declared values are matched
-        (case-insensitive); the hardcoded defaults (``"NA"``, ``"NAN"``,
-        ``"NULL"``, ``"NONE"``, ``"?"``) are not applied for that column.
-        Empty/whitespace-only strings are always effective null regardless of
-        any declaration.  Defaults to an empty dict — columns with no
-        declaration continue to use the hardcoded defaults unchanged.
     """
 
     modality: Modality = Modality.Tabular
@@ -704,6 +683,13 @@ class ProfileConfig:
         """
         Get the per-column numeric sentinel declarations.
 
+        Keys are column names; values are lists of float-compatible sentinel
+        values that should be treated as effective nulls (e.g.
+        ``{"age": [-999.0, 9999.0]}``). Applies to any column whose dtype
+        passes ``_numeric_sentinel_eligible`` (all integer and float Polars
+        dtypes). Defaults to an empty dict — columns with no declaration are
+        completely unaffected.
+
         Returns
         -------
         MappingProxyType[str, list[float]]
@@ -716,6 +702,16 @@ class ProfileConfig:
         """
         Get the per-column user-declared string sentinel declarations.
 
+        Keys are column names; values are lists of string values that should
+        be treated as effective nulls for that column (e.g.
+        ``{"status": ["N/A", "missing"]}``). Uses **replace semantics**: when
+        a declaration exists for a column, only the declared values are
+        matched (case-insensitive); the hardcoded defaults (``"NA"``,
+        ``"NAN"``, ``"NULL"``, ``"NONE"``, ``"?"``) are not applied for that
+        column. Empty/whitespace-only strings are always effective null
+        regardless of any declaration. Defaults to an empty dict — columns
+        with no declaration continue to use the hardcoded defaults unchanged.
+
         Returns
         -------
         MappingProxyType[str, list[str]]

{dataforge_ml-2.0.4 → dataforge_ml-2.0.6}/src/dataforge_ml/profiling/orchestrator.py

@@ -28,7 +28,7 @@ from typing import Any
 import numpy as np
 import polars as pl
 
-from ._base import ModalityProfiler, ColumnBatchProfiler
+from ._base import ModalityProfiler, ColumnBatchProfiler, OverrideCoercionError
 from ._tabular import TabularProfiler
 from ._categorical import CategoricalProfiler
 from ._datetime_profiler import DatetimeProfiler
@@ -114,6 +114,10 @@ class StructuralProfiler:
         ------
         TypeError
             When ``data`` is not a ``polars.DataFrame``.
+        OverrideCoercionError
+            When a column carrying ``TypeFlag.UserOverride`` completely fails
+            coercion to its overridden ``SemanticType`` (zero usable values
+            remain despite the original column having non-null data).
         """
         if not isinstance(data, pl.DataFrame):
             raise TypeError(
@@ -241,6 +245,8 @@ class StructuralProfiler:
                 for col_name in batch.analysed_columns:
                     if col_name in result.columns:
                         result.columns[col_name].stats = batch.columns.get(col_name)
+            except OverrideCoercionError:
+                raise
             except Exception:
                 pass
 

{dataforge_ml-2.0.4 → dataforge_ml-2.0.6/src/dataforge_ml.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataforge-ml
-Version: 2.0.4
+Version: 2.0.6
 Summary: A automated feature engineering and designing pipeline library
 License: MIT
 Classifier: License :: OSI Approved :: MIT License