upgini 1.2.57a2__py3-none-any.whl → 1.2.57a3675.dev5__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.57a2"
+__version__ = "1.2.57a3675.dev5"

upgini/autofe/date.py

@@ -64,6 +64,9 @@ class DateDiff(PandasOperand, DateDiffMixin):
         return res
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        if left.isna().all() or right.isna().all():
+            return pd.Series([None] * len(left))
+
         left = self._convert_to_date(left, self.left_unit)
         right = self._convert_to_date(right, self.right_unit)
         diff = self._convert_diff_to_unit(left.dt.date - right.dt.date)
@@ -142,6 +145,9 @@ class DateListDiff(PandasOperand, DateDiffMixin, ParametrizedOperand):
         return cls(aggregation=aggregation)
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        if left.isna().all() or right.isna().all():
+            return pd.Series([None] * len(left), dtype=np.float64)
+
         left = self._convert_to_date(left, self.left_unit)
         right_mask = right.apply(lambda x: len(x) > 0)
         mask = left.notna() & right.notna() & right_mask
@@ -230,6 +236,8 @@ class DatePercentileBase(PandasOperand, abc.ABC):
         pass
 
     def _perc(self, f, bounds):
+        if f is None or np.isnan(f):
+            return np.nan
         hit = np.where(f >= np.array(bounds))[0]
         if hit.size > 0:
             return np.max(hit) + 1

upgini/autofe/feature.py

@@ -26,18 +26,9 @@ class Column:
         return dict()
 
     def rename_columns(self, mapping: Dict[str, str]) -> "Column":
-        self.name = self._unhash(mapping.get(self.name) or self.name)
+        self.name = 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

@@ -2,7 +2,11 @@ import abc
 from typing import Dict, List, Optional
 
 import pandas as pd
-from pydantic import validator
+
+try:
+    from pydantic import field_validator as validator  # V2
+except ImportError:
+    from pydantic import validator  # V1
 
 from upgini.autofe.operand import PandasOperand, ParametrizedOperand, VectorizableMixin
 
@@ -29,12 +33,16 @@ class Sum(PandasOperand, VectorizableMixin):
 class TimeSeriesBase(PandasOperand, abc.ABC):
     is_vector: bool = True
     date_unit: Optional[str] = None
+    offset_size: int = 0
+    offset_unit: str = "D"
 
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
         res.update(
             {
                 "date_unit": self.date_unit,
+                "offset_size": self.offset_size,
+                "offset_unit": self.offset_unit,
             }
         )
         return res
@@ -46,13 +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()
-        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
@@ -67,6 +93,7 @@ class Roll(TimeSeriesBase, ParametrizedOperand):
     window_unit: str = "D"
 
     @validator("window_unit")
+    @classmethod
     def validate_window_unit(cls, v: str) -> str:
         try:
             pd.tseries.frequencies.to_offset(v)
@@ -77,12 +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)
 
@@ -107,7 +157,7 @@ class Roll(TimeSeriesBase, ParametrizedOperand):
         return res
 
     def _aggregate(self, ts: pd.DataFrame) -> pd.DataFrame:
-        return ts.rolling(f"{self.window_size}{self.window_unit}", min_periods=self.window_size).agg(
+        return ts.rolling(f"{self.window_size}{self.window_unit}", min_periods=1).agg(
             _roll_aggregations.get(self.aggregation, self.aggregation)
         )
 
@@ -117,12 +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)
 
@@ -136,6 +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-1.2.57a2.dist-info → upgini-1.2.57a3675.dev5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.57a2
+Version: 1.2.57a3675.dev5
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -34,7 +34,7 @@ Requires-Dist: pydantic<3.0.0,>1.0.0
 Requires-Dist: pyjwt>=2.8.0
 Requires-Dist: python-bidi==0.4.2
 Requires-Dist: python-dateutil>=2.8.0
-Requires-Dist: python-json-logger>=2.0.2
+Requires-Dist: python-json-logger>=3.3.0
 Requires-Dist: requests>=2.8.0
 Requires-Dist: scikit-learn>=1.3.0
 Requires-Dist: xhtml2pdf<0.3.0,>=0.2.11

{upgini-1.2.57a2.dist-info → upgini-1.2.57a3675.dev5.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=PD2lbh5FQufk15oyUAYIGJrdUHAs9qG5Btw3lTqrUtI,25
+upgini/__about__.py,sha256=I0ZAa2qUeGAG8w2GcOhss1hhvV9cMS2KXnSkGWg4s0A,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=NP5vHqEfZQ1HWz3TcNAa_OhXG8wiMRdydm26D6UBiRU,34166
@@ -16,12 +16,12 @@ upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo
 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=l8A8E3BH2BmYvqEC81zbcIEfH6KEEhcesJ2BH4fn0-4,15140
+upgini/autofe/date.py,sha256=oykxfmny4LOr6m79IipOUCtk2JQSUdSCWHh8K9n7nek,10726
+upgini/autofe/feature.py,sha256=zvRdlxCkaOsX0XiragNvh0tAPyOWut0MQTq5JGU5HtY,14749
 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=bvcop9b0uFFPfQ3FLTwXT2IYfxNl4dIfR8icvnBHvOA,4358
+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=0vaYz5v3KclJnA6jAWiTUiMQO5mbBTBINWV9jr2F5xM,22591
 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-1.2.57a2.dist-info/METADATA,sha256=-dEVxWnjwc3LcSqFVJGENL07YJDvWgH8mHQ0PaE93sI,49057
-upgini-1.2.57a2.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.57a2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.57a2.dist-info/RECORD,,
+upgini-1.2.57a3675.dev5.dist-info/METADATA,sha256=7bDZbjWy8pxCvyBM02xr2nvMfKLcDBh2Agf07aKc4fI,49065
+upgini-1.2.57a3675.dev5.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.57a3675.dev5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.57a3675.dev5.dist-info/RECORD,,

{upgini-1.2.57a2.dist-info → upgini-1.2.57a3675.dev5.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.25.0
+Generator: hatchling 1.24.2
 Root-Is-Purelib: true
 Tag: py3-none-any