upgini 1.2.63__py3-none-any.whl → 1.2.65__py3-none-any.whl

upgini/autofe/vector.py

@@ -1,17 +1,11 @@
-import abc
-from typing import Dict, List, Optional
+from typing import List, Optional
 
 import pandas as pd
 
-try:
-    from pydantic import field_validator as validator  # V2
-except ImportError:
-    from pydantic import validator  # V1
+from upgini.autofe.operator import PandasOperator, VectorizableMixin
 
-from upgini.autofe.operand import PandasOperand, ParametrizedOperand, VectorizableMixin
 
-
-class Mean(PandasOperand, VectorizableMixin):
+class Mean(PandasOperator, VectorizableMixin):
     name: str = "mean"
     output_type: Optional[str] = "float"
     is_vector: bool = True
@@ -21,200 +15,10 @@ class Mean(PandasOperand, VectorizableMixin):
         return pd.DataFrame(data).T.fillna(0).mean(axis=1)
 
 
-class Sum(PandasOperand, VectorizableMixin):
+class Sum(PandasOperator, VectorizableMixin):
     name: str = "sum"
     is_vector: bool = True
     group_index: int = 0
 
     def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
         return pd.DataFrame(data).T.fillna(0).sum(axis=1)
-
-
-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
-
-    def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
-        # assuming first is date, last is value, rest is group columns
-        date = pd.to_datetime(data[0], unit=self.date_unit, errors="coerce")
-        ts = pd.concat([date] + data[1:], axis=1)
-        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]])
-            .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
-
-
-_roll_aggregations = {"norm_mean": lambda x: x[-1] / x.mean()}
-
-
-class Roll(TimeSeriesBase, ParametrizedOperand):
-    aggregation: str
-    window_size: int = 1
-    window_unit: str = "D"
-
-    @validator("window_unit")
-    @classmethod
-    def validate_window_unit(cls, v: str) -> str:
-        try:
-            pd.tseries.frequencies.to_offset(v)
-            return v
-        except ValueError:
-            raise ValueError(
-                f"Invalid window_unit: {v}. Must be a valid pandas frequency string (e.g. 'D', 'H', 'T', etc)"
-            )
-
-    def to_formula(self) -> str:
-        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)
-
-        if not match:
-            return None
-
-        window_size = int(match.group(1))
-        window_unit = match.group(2)
-        aggregation = match.group(3)
-
-        return cls(window_size=window_size, window_unit=window_unit, aggregation=aggregation)
-
-    def get_params(self) -> Dict[str, Optional[str]]:
-        res = super().get_params()
-        res.update(
-            {
-                "window_size": self.window_size,
-                "window_unit": self.window_unit,
-                "aggregation": self.aggregation,
-            }
-        )
-        return res
-
-    def _aggregate(self, ts: pd.DataFrame) -> pd.DataFrame:
-        return ts.rolling(f"{self.window_size}{self.window_unit}", min_periods=1).agg(
-            _roll_aggregations.get(self.aggregation, self.aggregation)
-        )
-
-
-class Lag(TimeSeriesBase, ParametrizedOperand):
-    lag_size: int
-    lag_unit: str = "D"
-
-    def to_formula(self) -> str:
-        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)
-
-        if not match:
-            return None
-
-        lag_size = int(match.group(1))
-        lag_unit = match.group(2)
-
-        return cls(lag_size=lag_size, lag_unit=lag_unit)
-
-    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:
-        lag_window = self.lag_size + 1
-        return ts.rolling(f"{lag_window}{self.lag_unit}", min_periods=lag_window).agg(lambda x: x[0])

upgini/features_enricher.py

@@ -31,7 +31,7 @@ from sklearn.exceptions import NotFittedError
 from sklearn.model_selection import BaseCrossValidator
 
 from upgini.autofe.feature import Feature
-from upgini.autofe.vector import TimeSeriesBase
+from upgini.autofe.timeseries import TimeSeriesBase
 from upgini.data_source.data_source_publisher import CommercialSchema
 from upgini.dataset import Dataset
 from upgini.errors import HttpError, ValidationError
@@ -3632,7 +3632,7 @@ if response.status_code == 200:
                     )
                 do_sorting = False
             else:
-                columns_to_hash = list(search_keys.keys()) + renamed_id_columns + [target_name]
+                columns_to_hash = list(set(list(search_keys.keys()) + renamed_id_columns + [target_name]))
                 columns_to_hash = sort_columns(
                     df[columns_to_hash],
                     target_name,

upgini/utils/sort.py

@@ -28,12 +28,13 @@ def sort_columns(
         logger = logging.getLogger(__name__)
         logger.setLevel(logging.FATAL)
     df = df.copy()  # avoid side effects
+    search_keys = {k: v for k, v in search_keys.items() if v != SearchKey.CUSTOM_KEY}
 
     # Check multiple search keys
     search_key_values = list(search_keys.values())
     has_duplicate_search_keys = len(search_key_values) != len(set(search_key_values))
     if has_duplicate_search_keys:
-        logging.warning(f"WARNING: Found duplicate SearchKey values in search_keys: {search_keys}")
+        logger.warning(f"WARNING: Found duplicate SearchKey values in search_keys: {search_keys}")
 
     sorted_keys = sorted(search_keys.keys(), key=lambda x: str(search_keys.get(x)))
     sorted_keys = [k for k in sorted_keys if k in df.columns and k not in exclude_columns]
@@ -68,8 +69,9 @@ def get_sort_columns_dict(
     if len(string_features) > 0:
         if len(df) > len(df.drop(columns=string_features).drop_duplicates()) or sort_all_columns:
             # factorize string features
+            df = df.copy()
             for c in string_features:
-                df.loc[:, c] = pd.Series(df[c].factorize(sort=True)[0], index=df.index, dtype="int")
+                df = df.assign(**{c: pd.factorize(df[c], sort=True)[0].astype(int)})
             columns_for_sort.extend(string_features)
 
     if len(columns_for_sort) == 0:

{upgini-1.2.63.dist-info → upgini-1.2.65.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.63
+Version: 1.2.65
 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-1.2.63.dist-info → upgini-1.2.65.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=jIcsQGjL4QjnLFsRkdEHc7S78dfQHi-auHwc_P5Xftc,23
+upgini/__about__.py,sha256=9LdiugHjYADPBPHXjA5mj8ce_XDBj0fp-oIlGtPl5HI,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=OGjpeFHbj3lWiZTOHTpWEoMMDmFY1FlNC44FKktoZvU,34956
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=2AMEXtoMrEFw3f0b0CsvkFyS1a7L4aqI2GO_fCsgWac,205336
+upgini/features_enricher.py,sha256=nXGBMC42VPAmqQKXbEqZJFIHiGj6F_G2AwhurA8LuQs,205351
 upgini/http.py,sha256=ud0Cp7h0jNeHuuZGpU_1dAAEiabGoJjGxc1X5oeBQr4,43496
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=Jh6YTaS00m_nbaOY_owvlSyn9zgkErkqu8iTr9ZjKI8,12279
@@ -14,14 +14,22 @@ upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
 upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
 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=pqwwk4_35RYXDT2fSJ9dlxGBm-R0jWBeiSb-79hZjkI,10721
-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=udkg4pP7IIeLjt0Cg6rzEKUmGaubOnqsEz3bz9R6E44,7110
+upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
+upgini/autofe/binary.py,sha256=MnQuFiERpocjCPQUjOljlsq5FE-04GPfwtNjzvfNMyU,7671
+upgini/autofe/date.py,sha256=I07psJerrxOcHao91PdSCk9X6KWu61IBVyFRLjGNgK8,10730
+upgini/autofe/feature.py,sha256=xgu6bVIlUJ5PCUgoXQRNcGkcMOhj-_BdDRmkB_qRFS4,14766
+upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
+upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
+upgini/autofe/unary.py,sha256=yVgPvtfnPSOhrii0YgezddmgWPwyOBCR0JutaIkdTTc,4658
+upgini/autofe/vector.py,sha256=l0KdKg-txlZxDSE4hPPfCtfGQofYbl7oaABPr830sPI,667
+upgini/autofe/timeseries/__init__.py,sha256=PGwwDAMwvkXl3el12tXVEmZUgDUvlmIPlXtROm6bD18,738
+upgini/autofe/timeseries/base.py,sha256=T9Ec8LKJbiwTUGGsd_xhM0U0NUJblqmKchkzUI1sK88,3755
+upgini/autofe/timeseries/cross.py,sha256=Sh5hAXZFWKaFRqf_JGODu9pWO2tmuV5VKyK9eX3i7-I,4931
+upgini/autofe/timeseries/delta.py,sha256=h0YhmI1TlPJnjwFpN_GQxLb6r59DQuucnG5tQAXSgjU,3520
+upgini/autofe/timeseries/lag.py,sha256=LfQtg484vuqM0mgY4Wft1swHX_Srq7OKKgZswCXoiXI,1882
+upgini/autofe/timeseries/roll.py,sha256=bNFMDszSYTWvB7EyhHbRY1DJqzSURvHlPAcBebt0y0Y,2878
+upgini/autofe/timeseries/trend.py,sha256=9p2Q5ByAi6cx9RH9teBTe8FyjSzqthznC2Lo5dsJ0ho,2051
+upgini/autofe/timeseries/volatility.py,sha256=9shUmIKjpWTHVYjj80YBsk0XheBJ9uBuLv5NW9Mchnk,7953
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/data_source/data_source_publisher.py,sha256=4S9qwlAklD8vg9tUU_c1pHE2_glUHAh15-wr5hMwKFw,22879
 upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
@@ -57,12 +65,12 @@ upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,1
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,44511
-upgini/utils/sort.py,sha256=w-CoT33W_53ekOROpKI_VRsRmiyWNr2b3IpE5_4MLLA,6395
+upgini/utils/sort.py,sha256=GfWfCIbfK7e7BvSPZZNJD-PEtiN19DnTCEQkeefHHxI,6491
 upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,16579
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.63.dist-info/METADATA,sha256=nH5TvEpkQ7qCwZi9uFN6qThiBIe3jLgLCIeRtZeflnA,49113
-upgini-1.2.63.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.63.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.63.dist-info/RECORD,,
+upgini-1.2.65.dist-info/METADATA,sha256=GGxmpRnHQUTsCQlWPZeNL2xk27XWuEWrvECLPVEx5vU,49113
+upgini-1.2.65.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.65.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.65.dist-info/RECORD,,

{upgini-1.2.63.dist-info → upgini-1.2.65.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