tracepipe 0.3.3__py3-none-any.whl → 0.3.5__py3-none-any.whl

tracepipe/__init__.py

@@ -81,7 +81,7 @@ from .core import TracePipeConfig, TracePipeMode
 from .snapshot import DiffResult, Snapshot, diff, snapshot
 
 # === VERSION ===
-__version__ = "0.3.3"
+__version__ = "0.3.5"
 
 # === MINIMAL __all__ ===
 __all__ = [

tracepipe/context.py

@@ -63,6 +63,10 @@ class TracePipeContext:
         # When > 0, __getitem__[mask] skips capture (parent op will capture)
         self._filter_op_depth: int = 0
 
+        # Transform operation tracking (prevents double-counting fillna/replace)
+        # When > 0, __setitem__ skips capture (transform op will capture)
+        self._in_transform_op: int = 0
+
         # GroupBy state stack (supports nesting)
         self._groupby_stack: list[dict] = []
 

tracepipe/instrumentation/pandas_inst.py

@@ -22,6 +22,7 @@ from ..safety import (
     get_caller_info,
     wrap_pandas_method,
     wrap_pandas_method_inplace,
+    wrap_pandas_transform_method,
 )
 from ..utils.value_capture import find_changed_indices_vectorized
 from .apply_capture import instrument_apply_pipe, uninstrument_apply_pipe
@@ -554,6 +555,9 @@ def _wrap_setitem(original):
 
     Captures BEFORE state for existing columns, then executes assignment,
     then records the diff with actual old/new values.
+
+    Skips recording when inside a transform operation (fillna, replace) to
+    avoid double-counting cell changes - the transform wrapper will capture.
     """
 
     @wraps(original)
@@ -565,7 +569,9 @@ def _wrap_setitem(original):
         is_new_column = False
         should_track = False
 
-        if ctx.enabled and isinstance(key, str):
+        # Skip tracking if we're inside a transform operation (fillna, replace)
+        # Those operations will capture the change themselves
+        if ctx.enabled and isinstance(key, str) and ctx._in_transform_op == 0:
             if key in ctx.watched_columns:
                 should_track = True
                 if key in self.columns:
@@ -771,13 +777,15 @@ def instrument_pandas():
             wrapped = wrap_filter_method(method_name, original)
             setattr(pd.DataFrame, method_name, wrapped)
 
-    # === DataFrame transform methods (with inplace support) ===
+    # === DataFrame transform methods (fillna, replace) ===
+    # These use wrap_pandas_transform_method to suppress __setitem__ recording
+    # during the transform, avoiding double-counting cell changes
     transform_methods = ["fillna", "replace"]
     for method_name in transform_methods:
         if hasattr(pd.DataFrame, method_name):
             original = getattr(pd.DataFrame, method_name)
             _originals[f"DataFrame.{method_name}"] = original
-            wrapped = wrap_pandas_method_inplace(method_name, original, _capture_transform)
+            wrapped = wrap_pandas_transform_method(method_name, original, _capture_transform)
             setattr(pd.DataFrame, method_name, wrapped)
 
     # === astype (no inplace) ===

tracepipe/safety.py

@@ -103,7 +103,7 @@ def _make_wrapper(
         method_name: Name for error messages
         original_method: The original pandas method
         capture_func: func(self, args, kwargs, result, ctx, method_name)
-        mode: "standard", "filter", or "inplace"
+        mode: "standard", "filter", "inplace", or "transform"
     """
 
     @wraps(original_method)
@@ -112,10 +112,21 @@ def _make_wrapper(
 
         # === PRE-EXECUTION SETUP ===
         before_snapshot = None
+        is_inplace = kwargs.get("inplace", False)
 
         if mode == "filter" and ctx.enabled:
             ctx._filter_op_depth += 1
-        elif mode == "inplace" and ctx.enabled and kwargs.get("inplace", False):
+        elif mode == "transform" and ctx.enabled:
+            # Suppress __setitem__ recording during transform ops (fillna, replace)
+            # to avoid double-counting the same cell change
+            ctx._in_transform_op += 1
+            # Also handle inplace for transform operations
+            if is_inplace:
+                try:
+                    before_snapshot = self.copy()
+                except Exception:
+                    pass
+        elif mode == "inplace" and ctx.enabled and is_inplace:
             try:
                 before_snapshot = self.copy()
             except Exception:
@@ -127,15 +138,18 @@ def _make_wrapper(
         finally:
             if mode == "filter" and ctx.enabled:
                 ctx._filter_op_depth -= 1
+            elif mode == "transform" and ctx.enabled:
+                ctx._in_transform_op -= 1
 
         # === CAPTURE LINEAGE (SIDE EFFECT) ===
         # Skip capture if we're inside a filter operation (prevents recursion during export)
         if ctx.enabled and ctx._filter_op_depth == 0:
             try:
-                if mode == "inplace" and kwargs.get("inplace", False):
+                # Handle inplace for both "inplace" and "transform" modes
+                if (mode == "inplace" or mode == "transform") and is_inplace:
                     if before_snapshot is not None:
                         capture_func(before_snapshot, args, kwargs, self, ctx, method_name)
-                elif mode == "inplace" and result is not None:
+                elif (mode == "inplace" or mode == "transform") and result is not None:
                     capture_func(self, args, kwargs, result, ctx, method_name)
                 else:
                     capture_func(self, args, kwargs, result, ctx, method_name)
@@ -176,3 +190,14 @@ def wrap_pandas_method_inplace(
 ) -> Callable:
     """Wrap a pandas method that supports inplace=True."""
     return _make_wrapper(method_name, original_method, capture_func, mode="inplace")
+
+
+def wrap_pandas_transform_method(
+    method_name: str, original_method: Callable, capture_func: Callable
+) -> Callable:
+    """Wrap a pandas transform method (fillna, replace) that may trigger internal setitem.
+
+    These methods modify column values and pandas internally uses setitem.
+    We suppress setitem recording during these ops to avoid double-counting.
+    """
+    return _make_wrapper(method_name, original_method, capture_func, mode="transform")

tracepipe/storage/lineage_store.py

@@ -32,6 +32,22 @@ from ..core import (
 from ..utils.value_capture import capture_typed_value
 
 
+def _stable_repr(val) -> str:
+    """Create a stable string representation for deduplication.
+
+    Handles NaN, None, and other values that don't compare equal to themselves.
+    """
+    if val is None:
+        return "None"
+    # Handle NaN (which doesn't equal itself)
+    try:
+        if isinstance(val, float) and val != val:  # NaN check
+            return "NaN"
+    except (TypeError, ValueError):
+        pass
+    return repr(val)
+
+
 class InMemoryLineageStore:
     """
     Columnar storage for lineage data using Structure of Arrays (SoA).
@@ -556,12 +572,15 @@ class InMemoryLineageStore:
         Follows merge lineage recursively to build complete cell provenance.
         This is essential for tracking changes that happened before merge operations.
 
+        Deduplicates events by (col, old_val, new_val, operation) signature to prevent
+        cross-pipeline contamination when multiple DataFrames share row IDs.
+
         Args:
             row_id: Row ID to trace
             max_depth: Maximum merge depth to follow (prevents infinite loops)
 
         Returns:
-            List of events in chronological order, including parent row events.
+            List of UNIQUE events in chronological order, including parent row events.
         """
         visited: set[int] = set()
 
@@ -589,7 +608,23 @@ class InMemoryLineageStore:
         # Sort by step_id to ensure chronological order across lineage
         all_events.sort(key=lambda e: e["step_id"])
 
-        return all_events
+        # Deduplicate by (col, old_val, new_val, operation) signature
+        # This prevents cross-pipeline contamination when multiple DataFrames
+        # share the same row IDs (e.g., df.copy() followed by parallel transforms)
+        seen_signatures: set[tuple] = set()
+        unique_events = []
+        for event in all_events:
+            sig = (
+                event.get("col"),
+                _stable_repr(event.get("old_val")),
+                _stable_repr(event.get("new_val")),
+                event.get("operation"),
+            )
+            if sig not in seen_signatures:
+                seen_signatures.add(sig)
+                unique_events.append(event)
+
+        return unique_events
 
     def get_cell_history_with_lineage(
         self, row_id: int, column: str, max_depth: int = 10

{tracepipe-0.3.3.dist-info → tracepipe-0.3.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tracepipe
-Version: 0.3.3
+Version: 0.3.5
 Summary: Row-level data lineage tracking for pandas pipelines
 Project-URL: Homepage, https://github.com/tracepipe/tracepipe
 Project-URL: Documentation, https://tracepipe.github.io/tracepipe/
@@ -276,6 +276,26 @@ tp.enable(mode="debug")  # Full lineage
 
 ---
 
+## Known Limitations
+
+TracePipe tracks **cell mutations** (fillna, replace, loc assignment) and **merge provenance** reliably. However, some patterns are not yet fully supported:
+
+| Pattern | Status | Notes |
+|---------|--------|-------|
+| `df["col"] = df["col"].fillna(0)` | ✅ Tracked | Series + assignment |
+| `df = df.fillna({"col": 0})` | ✅ Tracked | DataFrame-level fillna |
+| `df.loc[mask, "col"] = val` | ✅ Tracked | Conditional assignment |
+| `df.merge(other, on="key")` | ✅ Tracked | Full provenance in debug mode |
+| `pd.concat([df1, df2])` | ⚠️ Partial | Row IDs preserved, but no "source DataFrame" tracking |
+| `df.drop_duplicates(keep='last')` | ⚠️ Partial | Which row was kept is not tracked |
+| Sort + dedup patterns | ⚠️ Partial | "Latest record wins" logic not traced |
+
+**Why?** TracePipe tracks value changes within rows, not row-selection operations. When `drop_duplicates` picks one row over another, that's a provenance decision (not a cell mutation) that isn't currently instrumented.
+
+**Planned for 0.4**: Full row-provenance tracking for concat, drop_duplicates, and sort operations.
+
+---
+
 ## Contributing
 
 ```bash

{tracepipe-0.3.3.dist-info → tracepipe-0.3.5.dist-info}/RECORD

@@ -1,11 +1,11 @@
-tracepipe/__init__.py,sha256=VhfrIqYHgzY7mDQwcsmH_Gw8_j7U_libclBKXTFMwE0,3342
+tracepipe/__init__.py,sha256=HK7i2rACJQdbyz5oMZ4z-xo9xJbS0cUqbS2AK6uMHJU,3342
 tracepipe/api.py,sha256=WdcKvvzI3voDt6fxZWa8vjyZQU8lfRshx7T78oj7oFE,13351
-tracepipe/context.py,sha256=_povLpqa5wd_ESHt5hbSmWTSMTF3nUfeutEQo4RMK2E,3856
+tracepipe/context.py,sha256=DvwAZGZbLDJ4xoqmS1VnZOBbOI8ZIIErsY9W6GEbFSM,4051
 tracepipe/contracts.py,sha256=m-rjPrgnCiAgKEkweOS7P95jrjDptt5UPdvUlqaV_rU,16226
 tracepipe/convenience.py,sha256=KuDz_ZzNivVG1SS8Srr3plu4CTwFmNhYL4rk3vV6cbE,28421
 tracepipe/core.py,sha256=kAXks694rR0Z4tD7Gyty0TyJGWx2whsSdteYYpHuazo,8010
 tracepipe/debug.py,sha256=6t2GKVZLwn7SJLhrStE9qsmTiVIHATTE3jJPQ2DYtnc,10140
-tracepipe/safety.py,sha256=jTBZv4QGDJfnZETsSZeMKbdOUtGXk-_XkmllhnGWM-M,5537
+tracepipe/safety.py,sha256=UpzhQj31Dij-DjgT9mY_jPrUpVfcA51gDI2fUos4IUA,6694
 tracepipe/snapshot.py,sha256=OLREzE1_LkWITluG_Bqeb7Y4pAKb8Lb3zJEF3cxnloU,13967
 tracepipe/value_provenance.py,sha256=ogky6aOaZ-6K2uNBQxlXpmCeuvK434Hisj30zesRTd8,9330
 tracepipe/instrumentation/__init__.py,sha256=pd0n6Z9m_V3gcBv097cXWFOZEzAP9sAq1jjQnNRrDZ8,222
@@ -13,17 +13,17 @@ tracepipe/instrumentation/apply_capture.py,sha256=cMThWzNXqWQENuMrCGTne1hO6fqaQF
 tracepipe/instrumentation/filter_capture.py,sha256=onlYLU5bBZSM3WmxM2AFHfktnlx7ReG-brEn5eZ_N10,15830
 tracepipe/instrumentation/indexer_capture.py,sha256=1ATCeJ-uNA1uGiSbgnUx0wdVsIlZGHeUBaFJPXgFQNg,28440
 tracepipe/instrumentation/merge_capture.py,sha256=Eze-PTrn7IXxZRZBYX9R13mOY3diWKAkjp4z-wa1tEk,13349
-tracepipe/instrumentation/pandas_inst.py,sha256=2YSoju9ml2PjLOYzsx8MHH1iqhjgnXHbIidnF0JDpaY,29546
+tracepipe/instrumentation/pandas_inst.py,sha256=h8RlfwYkYwuftCyBYIETdwHxVCzQM1SBBrbYP7SyjJ8,30047
 tracepipe/instrumentation/series_capture.py,sha256=i7FiA2ndEzS6duIj5y-a7SDfIMl2cCY_jGC1tmG7TGU,11271
 tracepipe/storage/__init__.py,sha256=pGFMfbIgIi2kofVPwYDqe2HTYMYJoabiGjTq77pYi-g,348
 tracepipe/storage/base.py,sha256=7DV_-rp37DjBMr9B1w85hLVYhC8OQShk2PcEhT-n4tE,4894
-tracepipe/storage/lineage_store.py,sha256=swMMf59isoCQZHaezCmquA-0R5iGNH3eGWjc9d9LGmo,27392
+tracepipe/storage/lineage_store.py,sha256=KhGri2uC_O_43fUivFGEHY6KBDHd1I0O_PPd_KD3L4M,28683
 tracepipe/storage/row_identity.py,sha256=HBU0gTTJlFtFTcAdUCKuX-c9cHa0lo3CDIodDPDgOzA,17161
 tracepipe/utils/__init__.py,sha256=CI_GXViCjdMbu1j6HuzZhoQZEW0sIB6WAve6j5pfOC0,182
 tracepipe/utils/value_capture.py,sha256=wGgegQmJnVHxHbwHSH9di7JAOBChzD3ERJrabZNiayk,4092
 tracepipe/visualization/__init__.py,sha256=M3s44ZTUNEToyghjhQW0FgbmWHKPr4Xc-7iNF6DpI_E,132
 tracepipe/visualization/html_export.py,sha256=G0hfZTJctUCfpun17zXX1NIXhvJZbca6hKmP3rcIjbg,42282
-tracepipe-0.3.3.dist-info/METADATA,sha256=OnHkiCjZ0-fUERI4PoUh3VmIWMZ_sePk8-pFBwo_8cI,9152
-tracepipe-0.3.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-tracepipe-0.3.3.dist-info/licenses/LICENSE,sha256=HMOAFHBClL79POwWL-2_aDcx42DJAq7Ce-nwJPvMB9U,1075
-tracepipe-0.3.3.dist-info/RECORD,,
+tracepipe-0.3.5.dist-info/METADATA,sha256=bWidBs8nMW6T6oah8xQum_IjdP7Y1J1inDAn-gfHUCg,10288
+tracepipe-0.3.5.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+tracepipe-0.3.5.dist-info/licenses/LICENSE,sha256=HMOAFHBClL79POwWL-2_aDcx42DJAq7Ce-nwJPvMB9U,1075
+tracepipe-0.3.5.dist-info/RECORD,,