upgini 1.2.56a3818.dev1__py3-none-any.whl → 1.2.56a3818.dev3__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.56a3818.dev1"
+__version__ = "1.2.56a3818.dev3"

upgini/autofe/feature.py

@@ -29,6 +29,15 @@ class Column:
         self.name = self._unhash(mapping.get(self.name) or self.name)
         return self
 
+    def _unhash(self, feature_name: str) -> str:
+        last_component_idx = feature_name.rfind("_")
+        if not feature_name.startswith("f_"):
+            return feature_name  # etalon feature
+        elif last_component_idx == 1:
+            return feature_name[2:]  # fully hashed name, cannot unhash
+        else:
+            return feature_name[2:last_component_idx]
+
     def delete_data(self):
         self.data = None
 

upgini/autofe/vector.py

@@ -54,20 +54,31 @@ class TimeSeriesBase(PandasOperand, abc.ABC):
         ts.drop_duplicates(subset=ts.columns[:-1], keep="first", inplace=True)
         ts.set_index(date.name, inplace=True)
         ts = ts[ts.index.notna()].sort_index()
-        if self.offset_size > 0:
-            ts = ts.iloc[:, :-1].merge(
-                ts.iloc[:, -1].shift(freq=f"{self.offset_size}{self.offset_unit}"),
-                left_index=True,
-                right_index=True,
-                how="left",
-            )
-        ts = ts.groupby([c.name for c in data[1:-1]]) if len(data) > 2 else ts
+        ts = (
+            ts.groupby([c.name for c in data[1:-1]])
+            .apply(self._shift)[data[-1].name]
+            .to_frame()
+            .reset_index()
+            .set_index(date.name)
+            .groupby([c.name for c in data[1:-1]])
+            if len(data) > 2
+            else self._shift(ts)
+        )
         ts = self._aggregate(ts)
         ts = ts.reindex(data[1:-1] + [date] if len(data) > 2 else date).reset_index()
         ts.index = date.index
 
         return ts.iloc[:, -1]
 
+    def _shift(self, ts: pd.DataFrame) -> pd.DataFrame:
+        if self.offset_size > 0:
+            return ts.iloc[:, :-1].merge(
+                ts.iloc[:, -1].shift(freq=f"{self.offset_size}{self.offset_unit}"),
+                left_index=True,
+                right_index=True,
+            )
+        return ts
+
     @abc.abstractmethod
     def _aggregate(self, ts: pd.DataFrame) -> pd.DataFrame:
         pass
@@ -93,12 +104,35 @@ class Roll(TimeSeriesBase, ParametrizedOperand):
             )
 
     def to_formula(self) -> str:
-        return f"roll_{self.window_size}{self.window_unit}_{self.aggregation}"
+        roll_component = f"roll_{self.window_size}{self.window_unit}"
+        if self.offset_size > 0:
+            roll_component += f"_offset_{self.offset_size}{self.offset_unit}"
+        return f"{roll_component}_{self.aggregation}"
 
     @classmethod
     def from_formula(cls, formula: str) -> Optional["Roll"]:
         import re
 
+        # Try matching pattern with offset first
+        pattern_with_offset = r"^roll_(\d+)([a-zA-Z])_offset_(\d+)([a-zA-Z])_(\w+)$"
+        match_with_offset = re.match(pattern_with_offset, formula)
+
+        if match_with_offset:
+            window_size = int(match_with_offset.group(1))
+            window_unit = match_with_offset.group(2)
+            offset_size = int(match_with_offset.group(3))
+            offset_unit = match_with_offset.group(4)
+            aggregation = match_with_offset.group(5)
+
+            return cls(
+                window_size=window_size,
+                window_unit=window_unit,
+                offset_size=offset_size,
+                offset_unit=offset_unit,
+                aggregation=aggregation,
+            )
+
+        # If no offset pattern found, try basic pattern
         pattern = r"^roll_(\d+)([a-zA-Z])_(\w+)$"
         match = re.match(pattern, formula)
 
@@ -133,12 +167,33 @@ class Lag(TimeSeriesBase, ParametrizedOperand):
     lag_unit: str = "D"
 
     def to_formula(self) -> str:
-        return f"lag_{self.lag_size}{self.lag_unit}"
+        lag_component = f"lag_{self.lag_size}{self.lag_unit}"
+        if self.offset_size > 0:
+            lag_component += f"_offset_{self.offset_size}{self.offset_unit}"
+        return lag_component
 
     @classmethod
     def from_formula(cls, formula: str) -> Optional["Lag"]:
         import re
 
+        # Try matching pattern with offset first
+        pattern_with_offset = r"^lag_(\d+)([a-zA-Z])_offset_(\d+)([a-zA-Z])$"
+        match_with_offset = re.match(pattern_with_offset, formula)
+
+        if match_with_offset:
+            lag_size = int(match_with_offset.group(1))
+            lag_unit = match_with_offset.group(2)
+            offset_size = int(match_with_offset.group(3))
+            offset_unit = match_with_offset.group(4)
+
+            return cls(
+                lag_size=lag_size,
+                lag_unit=lag_unit,
+                offset_size=offset_size,
+                offset_unit=offset_unit,
+            )
+
+        # If no offset pattern found, try basic pattern
         pattern = r"^lag_(\d+)([a-zA-Z])$"
         match = re.match(pattern, formula)
 
@@ -152,6 +207,12 @@ class Lag(TimeSeriesBase, ParametrizedOperand):
 
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
+        res.update(
+            {
+                "lag_size": self.lag_size,
+                "lag_unit": self.lag_unit,
+            }
+        )
         return res
 
     def _aggregate(self, ts: pd.DataFrame) -> pd.DataFrame:

{upgini-1.2.56a3818.dev1.dist-info → upgini-1.2.56a3818.dev3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.56a3818.dev1
+Version: 1.2.56a3818.dev3
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.2.56a3818.dev1.dist-info → upgini-1.2.56a3818.dev3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=9Q-YAgHCpn_n0_PUmuZMMX9GDhEwIxeK81U6HvLvWLA,33
+upgini/__about__.py,sha256=XfQddTt7Eukn9oKzHOurK-q9Fsg4ob2XoIvu2NhKfS0,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=vT4JyHmafLNbj54SySXr93f5hNS6-t94aFslbBy-7No,33535
@@ -17,11 +17,11 @@ upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operands.py,sha256=v0_NozalvvzeojSAA0d7UJ5INS654ZVaLn4S8djK6Ac,329
 upgini/autofe/binary.py,sha256=zMhtHVuGUAFLUqem-XiXqJj-GRXxS88tdz8tFuDfSNM,7659
 upgini/autofe/date.py,sha256=d-sijAD7dETfqIOCaZh1vhuVjsS_nqa-6dhjwkCdny4,10441
-upgini/autofe/feature.py,sha256=WFob1r-E5s1ano_ogzUZ9xnMjTBN26wGv9lcOX8XghI,14763
+upgini/autofe/feature.py,sha256=l8A8E3BH2BmYvqEC81zbcIEfH6KEEhcesJ2BH4fn0-4,15140
 upgini/autofe/groupby.py,sha256=G48_sQZw016eGx3cOy8YQrEIOp95puWqYUpFWd-gdeM,3595
 upgini/autofe/operand.py,sha256=8Ttrfxv_H91dMbS7J55zxluzAJHfGXU_Y2xCh4OHwb8,4774
 upgini/autofe/unary.py,sha256=T3E7F3dA_7o_rkdCFq7JV6nHLzcoHLHQTcxO7y5Opa4,4646
-upgini/autofe/vector.py,sha256=lndD4YOY0pO2va6X-2akITS2VD3pZ1dFpwiAEDMtBOc,4872
+upgini/autofe/vector.py,sha256=udkg4pP7IIeLjt0Cg6rzEKUmGaubOnqsEz3bz9R6E44,7110
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/data_source/data_source_publisher.py,sha256=X-8aGtVgzGmxyXkMVBoBLIGDMb4lYQaGZbxDnOd4A3Q,22516
 upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
@@ -59,7 +59,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=RlpKGss9kMibVSlA8iZuO_qxmyeplqzn7X8g6hiGGGs,14341
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.56a3818.dev1.dist-info/METADATA,sha256=R_ooFZF6RCW80rkva4Divg2KGhYXmSo1J6kKrNVzUWg,49065
-upgini-1.2.56a3818.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.56a3818.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.56a3818.dev1.dist-info/RECORD,,
+upgini-1.2.56a3818.dev3.dist-info/METADATA,sha256=wNOPrGCBYPZvYeVT6RQql1c7MDIE6ls83ZOtHoSFsIc,49065
+upgini-1.2.56a3818.dev3.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.56a3818.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.56a3818.dev3.dist-info/RECORD,,