dataforge-ml 0.7.0__tar.gz → 0.8.0__tar.gz

{dataforge_ml-0.7.0 → dataforge_ml-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataforge-ml
-Version: 0.7.0
+Version: 0.8.0
 Summary: A automated feature engineering and designing pipeline library
 License: MIT
 Classifier: License :: OSI Approved :: MIT License

{dataforge_ml-0.7.0 → dataforge_ml-0.8.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dataforge-ml"
-version = "0.7.0"
+version = "0.8.0"
 description = "A automated feature engineering and designing pipeline library"
 readme = "README.md"
 requires-python = ">=3.10"

{dataforge_ml-0.7.0 → dataforge_ml-0.8.0}/src/dataforge_ml/profiling/_missingness_profiler.py

@@ -208,7 +208,9 @@ class MissingnessProfiler(DatasetLevelProfiler[MissingnessProfileResult]):
 
         r = profile.effective_null_ratio
 
-        if r < _SEVERITY_MINOR and r != 0:
+        if r == 0.0:
+            profile.severity = None
+        elif r < _SEVERITY_MINOR:
             profile.severity = MissingSeverity.Minor
         elif r < _SEVERITY_MODERATE:
             profile.severity = MissingSeverity.Moderate

{dataforge_ml-0.7.0 → dataforge_ml-0.8.0}/src/dataforge_ml/profiling/_numeric_profiler.py

@@ -254,16 +254,17 @@ class NumericProfiler(ColumnBatchProfiler[NumericProfileResult]):
                 for i in range(top_rows)
             ]
         else:
-            # --- 20-Bin Histogram Distribution (Continuous) ---
+            # --- Histogram Distribution (Continuous) ---
             import numpy as np
 
             counts, bin_edges = np.histogram(clean_f64.to_numpy(), bins="auto")
+            n_clean = clean_f64.len()
             profile.histogram = [
                 HistogramBin(
                     lower_bound=float(bin_edges[i]),
                     upper_bound=float(bin_edges[i + 1]),
                     count=int(counts[i]),
-                    percentage=int(counts[i]) / n_rows if n_rows > 0 else 0.0,
+                    percentage=int(counts[i]) / n_clean if n_clean > 0 else 0.0,
                 )
                 for i in range(len(counts))
             ]

{dataforge_ml-0.7.0 → dataforge_ml-0.8.0}/src/dataforge_ml/profiling/config.py

@@ -71,6 +71,7 @@ class TypeFlag(StrEnum):
     SequentialIndex = "sequential_index"
     FloatSequentialIndex = "float_sequential_index"
     FreeTextCandidate = "free_text_candidate"
+    UserOverride = "user_override"
 
 
 # ---------------------------------------------------------------------------
@@ -240,6 +241,34 @@ class ProfileConfig:
     memory_threshold_mb: float = 500.0
     chunk_size: int = 100_000
 
+    def set_column_type(self, column: str, semantic_type: Union[str, "SemanticType"]) -> None:
+        """
+        Explicitly set the semantic type for a column, overriding auto-detection.
+
+        The override is the sole source of truth for that column's type — the
+        type detector's verdict is ignored during profiling.  Calling this method
+        multiple times on the same column is valid; the last call wins.
+
+        Parameters
+        ----------
+        column : str
+            Name of the column to override.
+        semantic_type : str | SemanticType
+            Target semantic type.  Accepts a plain string (e.g. ``"numeric"``,
+            ``"categorical"``) or a ``SemanticType`` enum value.  Invalid strings
+            raise ``ValueError``.
+        """
+        if isinstance(semantic_type, str):
+            try:
+                semantic_type = SemanticType(semantic_type)
+            except ValueError:
+                valid = [e.value for e in SemanticType]
+                raise ValueError(
+                    f"Unknown semantic type {semantic_type!r}. "
+                    f"Valid values: {valid}"
+                )
+        self.column_overrides[column] = semantic_type
+
     def to_dict(self) -> dict:
         return {
             "modality": str(self.modality),

{dataforge_ml-0.7.0 → dataforge_ml-0.8.0}/src/dataforge_ml/profiling/structural.py

@@ -40,6 +40,7 @@ from .config import (
     StructuralProfileResult,
     RowMissingnessDistribution,
     SemanticType,
+    TypeFlag,
     Modality,
 )
 
@@ -130,7 +131,10 @@ class StructuralProfiler:
         # Overrides for excluded / non-existent columns are silently ignored.
         for col_name, override_type in self.config.column_overrides.items():
             if col_name in result.columns:
-                result.columns[col_name].semantic_type = override_type
+                cp = result.columns[col_name]
+                cp.semantic_type = override_type
+                if TypeFlag.UserOverride not in cp.type_flags:
+                    cp.type_flags.append(TypeFlag.UserOverride)
 
         # ── 6. Per-column profiling routed by SemanticType ───────────────
         # Batch all columns of the same SemanticType together and call each

{dataforge_ml-0.7.0 → dataforge_ml-0.8.0}/src/dataforge_ml/utils/data_loader.py

@@ -82,8 +82,6 @@ _EXT_LOADERS: dict[str, callable] = {
 
 
 class DataLoader:
-    def __init__(self, fmt: str | None = None) -> None:
-        self._fmt_override = fmt.lower() if fmt else None
 
     def load(
         self,
@@ -92,7 +90,7 @@ class DataLoader:
     ) -> pl.DataFrame:
         raw, ext_from_path = _read_raw(source)
 
-        resolved_fmt = (fmt or self._fmt_override or ext_from_path or "").lower()
+        resolved_fmt = (ext_from_path or "").lower()
 
         if resolved_fmt not in _EXT_LOADERS:
             label = resolved_fmt if resolved_fmt else "<unknown>"

{dataforge_ml-0.7.0 → dataforge_ml-0.8.0}/src/dataforge_ml.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataforge-ml
-Version: 0.7.0
+Version: 0.8.0
 Summary: A automated feature engineering and designing pipeline library
 License: MIT
 Classifier: License :: OSI Approved :: MIT License