dataforge-ml 2.0.7__tar.gz → 2.0.8__tar.gz

{dataforge_ml-2.0.7/src/dataforge_ml.egg-info → dataforge_ml-2.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataforge-ml
-Version: 2.0.7
+Version: 2.0.8
 Summary: A automated feature engineering and designing pipeline library
 License: MIT
 Classifier: License :: OSI Approved :: MIT License

{dataforge_ml-2.0.7 → dataforge_ml-2.0.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dataforge-ml"
-version = "2.0.7"
+version = "2.0.8"
 description = "A automated feature engineering and designing pipeline library"
 readme = "README.md"
 requires-python = ">3.10"

{dataforge_ml-2.0.7 → dataforge_ml-2.0.8}/src/dataforge_ml/profiling/_datetime_config.py

@@ -31,77 +31,12 @@ class DatetimeFlag(StrEnum):
     FormatMismatch = "format_mismatch"
 
 
-@dataclass
-class TemporalSignals:
-    """Which time-component features are present in a Datetime column.
-
-    Each boolean field indicates that the corresponding granularity was
-    detected as non-constant, making it a candidate for feature extraction
-    in Phase 5 Encoding.
-    """
-
-    has_year: bool = False
-    has_month: bool = False
-    has_day: bool = False
-    has_day_of_week: bool = False
-    has_hour: bool = False
-    has_is_weekend: bool = False
-    has_is_month_end: bool = False
-
-    def extractable_features(self) -> list[str]:
-        """Return the names of all time-component features that can be extracted.
-
-        Returns
-        -------
-        list[str]
-            Feature names corresponding to every ``has_*`` field that is
-            ``True``.  An empty list means no temporal variation was detected.
-        """
-        features = []
-        if self.has_year:
-            features.append("year")
-        if self.has_month:
-            features.append("month")
-        if self.has_day:
-            features.append("day_of_month")
-        if self.has_day_of_week:
-            features.append("day_of_week")
-        if self.has_hour:
-            features.append("hour")
-        if self.has_is_weekend:
-            features.append("is_weekend")
-        if self.has_is_month_end:
-            features.append("is_month_end")
-        return features
-
-    def to_dict(self) -> dict:
-        """Serialise the temporal signals to a plain dictionary.
-
-        Returns
-        -------
-        dict
-            All ``has_*`` flags plus an ``extractable_features`` key
-            containing the result of :meth:`extractable_features`.
-        """
-        return {
-            "has_year": self.has_year,
-            "has_month": self.has_month,
-            "has_day": self.has_day,
-            "has_day_of_week": self.has_day_of_week,
-            "has_hour": self.has_hour,
-            "has_is_weekend": self.has_is_weekend,
-            "has_is_month_end": self.has_is_month_end,
-            "extractable_features": self.extractable_features(),
-        }
-
-
 @dataclass
 class DatetimeStats:
     """Statistical summary of a single Datetime column.
 
     Produced by ``DatetimeProfiler`` for each opted-in column.  Stores
-    range, gap regularity, inferred granularity, and ``TemporalSignals``
-    indicating which time components are available for feature extraction.
+    range, gap regularity, and inferred granularity.
     """
 
     min_date: Optional[str] = None
@@ -111,7 +46,6 @@ class DatetimeStats:
     inferred_granularity: Optional[InferredGranularity] = None
     median_gap_seconds: Optional[float] = None
     gap_cv: Optional[float] = None
-    signals: TemporalSignals = field(default_factory=TemporalSignals)
     flags: list[DatetimeFlag] = field(default_factory=list)
 
     def has_flag(self, flag: DatetimeFlag) -> bool:
@@ -137,8 +71,7 @@ class DatetimeStats:
         -------
         dict
             All fields keyed by field name.  ``inferred_granularity`` is
-            serialised as its string value; ``signals`` is expanded via
-            :meth:`TemporalSignals.to_dict`; ``flags`` are serialised as
+            serialised as its string value; ``flags`` are serialised as
             their string values.
         """
         return {
@@ -149,7 +82,6 @@ class DatetimeStats:
             "inferred_granularity": str(self.inferred_granularity) if self.inferred_granularity else None,
             "median_gap_seconds": self.median_gap_seconds,
             "gap_cv": self.gap_cv,
-            "signals": self.signals.to_dict(),
             "flags": [str(f) for f in self.flags],
         }
 

{dataforge_ml-2.0.7 → dataforge_ml-2.0.8}/src/dataforge_ml/profiling/_datetime_profiler.py

@@ -7,9 +7,10 @@ Per-column metrics (opt-in via ProfileConfig.datetime_columns):
   3. Future dates       – count of values > now, with context note
   4. Granularity        – inferred periodicity from median consecutive gap;
                           high gap-CV flagged as irregular
-  5. Temporal signals   – audit which of {year, month, day, day-of-week,
-                          hour, is-weekend, is-month-end} vary in the data,
-                          to guide downstream feature engineering
+
+Temporal-component variance (whether year, month, day-of-week, etc. vary) is
+intentionally not profiled here; Phase 5 Encoding derives it on demand from
+the column.
 
 Granularity inference bands (median gap in seconds):
   < 90 s        → secondly
@@ -34,7 +35,6 @@ from ._datetime_config import (
     DatetimeStats,
     InferredGranularity,
     DatetimeFlag,
-    TemporalSignals,
 )
 
 # Granularity bands — upper bound (exclusive) in seconds for each label.
@@ -226,9 +226,6 @@ class DatetimeProfiler(ColumnBatchProfiler[DatetimeProfileResult]):
         # 6. Granularity
         self._infer_granularity(clean, profile)
 
-        # 7. Temporal signals
-        self._audit_temporal_signals(clean, profile)
-
         return profile
 
     # ------------------------------------------------------------------
@@ -377,51 +374,3 @@ class DatetimeProfiler(ColumnBatchProfiler[DatetimeProfileResult]):
                 break
 
         profile.inferred_granularity = granularity
-
-    # ------------------------------------------------------------------
-    # Step 7: Temporal signal audit
-    # ------------------------------------------------------------------
-
-    @staticmethod
-    def _audit_temporal_signals(
-        clean: pl.Series,
-        profile: DatetimeStats,
-    ) -> None:
-        """
-        Check which temporal features vary across rows.
-
-        All checks are done via Polars expressions on the full clean series,
-        so no Python-level loops are required.
-        """
-        signals = TemporalSignals()
-
-        years = clean.dt.year()
-        months = clean.dt.month()
-        days = clean.dt.day()
-        dow = clean.dt.weekday()  # 0=Monday … 6=Sunday
-        hours = clean.dt.hour()
-
-        signals.has_year = years.n_unique() > 1
-        signals.has_month = months.n_unique() > 1
-        signals.has_day = days.n_unique() > 1
-        signals.has_day_of_week = dow.n_unique() > 1
-        signals.has_hour = int(hours.max()) > 0  # type: ignore[arg-type]
-
-        # Weekend signal is only meaningful when day-of-week varies
-        if signals.has_day_of_week:
-            weekend_mask = dow >= 5  # Saturday=5, Sunday=6
-            signals.has_is_weekend = bool(weekend_mask.any())
-
-        # Month-end: day == last day of the respective month
-        try:
-            month_end_ts = clean.dt.month_end()
-            is_month_end_mask = (
-                (clean.dt.year() == month_end_ts.dt.year())
-                & (clean.dt.month() == month_end_ts.dt.month())
-                & (clean.dt.day() == month_end_ts.dt.day())
-            )
-            signals.has_is_month_end = bool(is_month_end_mask.any())
-        except Exception:
-            signals.has_is_month_end = False
-
-        profile.signals = signals

{dataforge_ml-2.0.7 → dataforge_ml-2.0.8/src/dataforge_ml.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataforge-ml
-Version: 2.0.7
+Version: 2.0.8
 Summary: A automated feature engineering and designing pipeline library
 License: MIT
 Classifier: License :: OSI Approved :: MIT License