upgini 1.2.70a3832.dev3__tar.gz → 1.2.71a3832.dev3__tar.gz

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.70a3832.dev3
+Version: 1.2.71a3832.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/
@@ -17,12 +17,11 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Telecommunications Industry
 Classifier: License :: OSI Approved :: BSD License
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: <3.12,>=3.8
+Requires-Python: <3.12,>=3.10
 Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0
 Requires-Dist: jarowinkler>=2.0.0

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/pyproject.toml

@@ -7,7 +7,7 @@ name = "upgini"
 dynamic = ["version"]
 description = "Intelligent data search & enrichment for Machine Learning"
 readme = "README.md"
-requires-python = ">=3.8,<3.12"
+requires-python = ">=3.10,<3.12"
 authors = [
     { name = "Upgini Developers", email = "madewithlove@upgini.com" },
 ]
@@ -28,9 +28,8 @@ classifiers = [
     "Intended Audience :: Telecommunications Industry",
     "License :: OSI Approved :: BSD License",
     "Operating System :: OS Independent",
-    "Programming Language :: Python :: 3.8",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Topic :: Scientific/Engineering :: Information Analysis",
 ]
@@ -89,15 +88,11 @@ lint = "ruff check {args}"
 test_all = 'pytest -s -vv tests'
 
 [[tool.hatch.envs.test.matrix]]
-python = ["3.8"]
-pandas = ["1.1.0"]
-
-[[tool.hatch.envs.test.matrix]]
-python = ["3.8", "3.9", "3.10", "3.11"]
+python = ["3.10", "3.11"]
 pandas = ["1.2.0", "1.3.0", "1.4.0", "1.5.0", "2.0.0"]
 
 [[tool.hatch.envs.test.matrix]]
-python = ["3.9", "3.10", "3.11"]
+python = ["3.10", "3.11"]
 pandas = ["2.1.0", "2.2.0"]
 
 # from versions: 0.1, 0.2, 0.3.0, 0.4.0, 0.4.1, 0.4.2, 0.4.3, 0.5.0, 0.6.0, 0.6.1, 0.7.0, 0.7.1, 0.7.2, 0.7.3, 0.8.0, 0.8.1, 0.9.0, 0.9.1, 0.10.0, 0.10.1, 0.11.0, 0.12.0, 0.13.0, 0.13.1, 0.14.0, 0.14.1, 0.15.0, 0.15.1, 0.15.2, 0.16.0, 0.16.1, 0.16.2, 0.17.0, 0.17.1, 0.18.0, 0.18.1, 0.19.0, 0.19.1, 0.19.2, 0.20.0, 0.20.1, 0.20.2, 0.20.3, 0.21.0, 0.21.1, 0.22.0, 0.23.0, 0.23.1, 0.23.2, 0.23.3, 0.23.4, 0.24.0, 0.24.1, 0.24.2, 0.25.0, 0.25.1, 0.25.2, 0.25.3, 1.0.0, 1.0.1, 1.0.2, 1.0.3, 1.0.4, 1.0.5, 1.1.0, 1.1.1, 1.1.2, 1.1.3, 1.1.4, 1.1.5, 1.2.0, 1.2.1, 1.2.2, 1.2.3, 1.2.4, 1.2.5, 1.3.0, 1.3.1, 1.3.2, 1.3.3, 1.3.4, 1.3.5, 1.4.0rc0, 1.4.0, 1.4.1, 1.4.2, 1.4.3, 1.4.4, 1.5.0rc0, 1.5.0, 1.5.1, 1.5.2, 1.5.3, 2.0.0rc0, 2.0.0rc1, 2.0.0, 2.0.1, 2.0.2, 2.0.3

upgini-1.2.71a3832.dev3/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.71a3832.dev3"

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/src/upgini/autofe/date.py

@@ -8,6 +8,7 @@ from pandas.core.arrays.timedeltas import TimedeltaArray
 from pydantic import BaseModel, __version__ as pydantic_version
 
 from upgini.autofe.operator import PandasOperator, ParametrizedOperator
+from upgini.autofe.utils import pydantic_validator
 
 
 def get_pydantic_version():
@@ -209,6 +210,14 @@ class DateListDiffBounded(DateListDiff, ParametrizedOperator):
 
         return cls(diff_unit=diff_unit, lower_bound=lower_bound, upper_bound=upper_bound, aggregation=aggregation)
 
+    def get_params(self) -> Dict[str, Optional[str]]:
+        res = super().get_params()
+        if self.lower_bound is not None:
+            res["lower_bound"] = str(self.lower_bound)
+        if self.upper_bound is not None:
+            res["upper_bound"] = str(self.upper_bound)
+        return res
+
     def _agg(self, x):
         x = x[
             (x >= (self.lower_bound if self.lower_bound is not None else -np.inf))
@@ -269,32 +278,17 @@ class DatePercentile(DatePercentileBase):
             {
                 "zero_month": self.zero_month,
                 "zero_year": self.zero_year,
-                "zero_bounds": self.zero_bounds,
+                "zero_bounds": json.dumps(self.zero_bounds),
                 "step": self.step,
             }
         )
         return res
 
-    # Check Pydantic version
-    if get_pydantic_version() >= 2:
-        # Use @field_validator for Pydantic 2.x
-        from pydantic import field_validator
-
-        @field_validator("zero_bounds", mode="before")
-        def parse_zero_bounds(cls, value):
-            if isinstance(value, str):
-                return json.loads(value)
-            return value
-
-    else:
-        # Use @validator for Pydantic 1.x
-        from pydantic import validator
-
-        @validator("zero_bounds", pre=True)
-        def parse_zero_bounds(cls, value):
-            if isinstance(value, str):
-                return json.loads(value)
-            return value
+    @pydantic_validator("zero_bounds", mode="before")
+    def parse_zero_bounds(cls, value):
+        if isinstance(value, str):
+            return json.loads(value)
+        return value
 
     def _get_bounds(self, date_col: pd.Series) -> pd.Series:
         months = date_col.dt.month

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/src/upgini/autofe/feature.py

@@ -112,7 +112,11 @@ class Feature:
 
     def get_hash(self) -> str:
         return hashlib.sha256(
-            "_".join([self.op.get_hash_component()] + [ch.get_display_name() for ch in self.children]).encode("utf-8")
+            "_".join(
+                [self.op.get_hash_component()]
+                + [ch.op.get_hash_component() for ch in self.children if isinstance(ch, Feature)]
+                + [ch.get_display_name() for ch in self.children]
+            ).encode("utf-8")
         ).hexdigest()[:8]
 
     def set_alias(self, alias: str) -> "Feature":

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/src/upgini/autofe/timeseries/base.py

@@ -1,15 +1,9 @@
 import abc
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Tuple
 
 import pandas as pd
 from upgini.autofe.operator import PandasOperator
 
-# Used in derived classes
-try:
-    from pydantic import field_validator as validator  # V2
-except ImportError:
-    from pydantic import validator  # V1
-
 
 class TimeSeriesBase(PandasOperator, abc.ABC):
     is_vector: bool = True
@@ -70,7 +64,7 @@ class TimeSeriesBase(PandasOperator, abc.ABC):
         return base_formula
 
     @classmethod
-    def _parse_offset_from_formula(cls, formula: str, base_regex: str) -> tuple[Optional[dict], Optional[str]]:
+    def _parse_offset_from_formula(cls, formula: str, base_regex: str) -> Tuple[Optional[Dict], Optional[str]]:
         """
         Parse the offset component from a formula.
 
@@ -85,7 +79,7 @@ class TimeSeriesBase(PandasOperator, abc.ABC):
         """
         import re
 
-        offset_regex = f"{base_regex}_offset_(\\d+)([a-zA-Z])"
+        offset_regex = f"{base_regex}_offset_(\\d+)([a-zA-Z])$"
         match = re.match(offset_regex, formula)
 
         if match:

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/src/upgini/autofe/timeseries/cross.py

@@ -1,16 +1,13 @@
+import json
 from typing import Dict, List, Optional
 
 import numpy as np
 import pandas as pd
 
-try:
-    from pydantic import field_validator as validator  # V2
-except ImportError:
-    from pydantic import validator  # V1
-
 from upgini.autofe.all_operators import find_op
 from upgini.autofe.operator import PandasOperator, ParametrizedOperator
 from upgini.autofe.timeseries.base import TimeSeriesBase
+from upgini.autofe.utils import pydantic_validator
 
 
 class CrossSeriesInteraction(TimeSeriesBase, ParametrizedOperator):
@@ -20,11 +17,24 @@ class CrossSeriesInteraction(TimeSeriesBase, ParametrizedOperator):
     left_descriptor: List[str] = []
     right_descriptor: List[str] = []
 
-    @validator("descriptor_indices")
-    @classmethod
+    @pydantic_validator("descriptor_indices", mode="before")
     def validate_descriptor_indices(cls, v):
+        if isinstance(v, str):
+            v = json.loads(v)
         if not v:
-            raise ValueError("descriptor_indices cannot be empty for CrossSeriesInteraction")
+            raise ValueError("descriptor_indices cannot be empty")
+        return v
+
+    @pydantic_validator("left_descriptor", "right_descriptor", mode="before")
+    def parse_descriptors(cls, v):
+        if isinstance(v, str):
+            return json.loads(v)
+        return v
+
+    @pydantic_validator("interaction_op", mode="before")
+    def validate_interaction_op(cls, v):
+        if isinstance(v, str):
+            return find_op(v)
         return v
 
     def __init__(self, **data):
@@ -83,14 +93,14 @@ class CrossSeriesInteraction(TimeSeriesBase, ParametrizedOperator):
 
         return cls(**params)
 
-    def get_params(self) -> Dict[str, str | None]:
+    def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
         res.update(
             {
                 "interaction_op": self._get_interaction_op_name(),
-                "descriptor_indices": self.descriptor_indices,
-                "left_descriptor": self.left_descriptor,
-                "right_descriptor": self.right_descriptor,
+                "descriptor_indices": json.dumps(self.descriptor_indices),
+                "left_descriptor": json.dumps(self.left_descriptor),
+                "right_descriptor": json.dumps(self.right_descriptor),
             }
         )
         return res

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/src/upgini/autofe/timeseries/roll.py

@@ -3,6 +3,7 @@ from typing import Dict, Optional
 
 from upgini.autofe.operator import ParametrizedOperator
 from upgini.autofe.timeseries.base import TimeSeriesBase
+from upgini.autofe.utils import pydantic_validator
 
 # Roll aggregation functions
 roll_aggregations = {
@@ -12,19 +13,13 @@ roll_aggregations = {
     "iqr": lambda x: x.quantile(0.75) - x.quantile(0.25),
 }
 
-try:
-    from pydantic import field_validator as validator  # V2
-except ImportError:
-    from pydantic import validator  # V1
-
 
 class Roll(TimeSeriesBase, ParametrizedOperator):
     aggregation: str
     window_size: int = 1
     window_unit: str = "D"
 
-    @validator("window_unit")
-    @classmethod
+    @pydantic_validator("window_unit")
     def validate_window_unit(cls, v: str) -> str:
         try:
             pd.tseries.frequencies.to_offset(v)

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/src/upgini/autofe/timeseries/trend.py

@@ -2,10 +2,11 @@ from typing import Dict, Optional, Union
 import numpy as np
 import pandas as pd
 
+from upgini.autofe.operator import ParametrizedOperator
 from upgini.autofe.timeseries.base import TimeSeriesBase
 
 
-class TrendCoefficient(TimeSeriesBase):
+class TrendCoefficient(TimeSeriesBase, ParametrizedOperator):
     name: str = "trend_coef"
     step_size: int = 1
     step_unit: str = "D"

upgini-1.2.71a3832.dev3/src/upgini/autofe/utils.py

@@ -0,0 +1,83 @@
+"""
+Utility functions for autofe module.
+"""
+
+import functools
+from typing import Callable
+
+
+def get_pydantic_version():
+    """
+    Get the major version of pydantic.
+
+    Returns:
+        int: Major version number (1 or 2)
+    """
+    try:
+        from pydantic import __version__ as pydantic_version
+
+        major_version = int(pydantic_version.split(".")[0])
+        return major_version
+    except (ImportError, ValueError):
+        # Default to version 1 if unable to determine
+        return 1
+
+
+def pydantic_validator(field_name: str, *fields, mode: str = "before", **kwargs):
+    """
+    A decorator that applies the appropriate Pydantic validator based on the installed version.
+
+    This decorator handles the differences between Pydantic v1 and v2 validator syntax,
+    making it easier to write code that works with both versions.
+
+    Args:
+        field_name (str): The name of the field to validate
+        mode (str): The validation mode, either "before" or "after" (for Pydantic v2)
+        **kwargs: Additional arguments to pass to the validator
+
+    Returns:
+        Callable: A decorator that can be applied to validator methods
+
+    Example:
+        ```python
+        class MyModel(BaseModel):
+            items: List[int]
+
+            @pydantic_validator("items")
+            def parse_items(cls, value):
+                if isinstance(value, str):
+                    return [int(x) for x in value.split(",")]
+                return value
+        ```
+    """
+    pydantic_version = get_pydantic_version()
+
+    if pydantic_version >= 2:
+        # Use field_validator for Pydantic 2.x
+        from pydantic import field_validator
+
+        def decorator(func: Callable) -> Callable:
+            @field_validator(field_name, *fields, mode=mode, **kwargs)
+            @functools.wraps(func)
+            def wrapper(cls, value, **kw):
+                return func(cls, value)
+
+            return wrapper
+
+        return decorator
+    else:
+        # Use validator for Pydantic 1.x
+        from pydantic import validator
+
+        # Map mode to Pydantic v1 parameters
+        pre = True if mode == "before" else False
+
+        def decorator(func: Callable) -> Callable:
+            @validator(field_name, *fields, pre=pre, **kwargs)
+            @functools.wraps(func)
+            def wrapper(cls, value, **kw):
+                return func(cls, value)
+
+            return wrapper
+
+        return decorator

{upgini-1.2.70a3832.dev3 → upgini-1.2.71a3832.dev3}/src/upgini/dataset.py

@@ -22,6 +22,7 @@ from upgini.metadata import (
     EVAL_SET_INDEX,
     SYSTEM_RECORD_ID,
     TARGET,
+    AutoFEParameters,
     CVType,
     DataType,
     FeaturesFilter,
@@ -558,6 +559,7 @@ class Dataset:  # (pd.DataFrame):
         filter_features: Optional[dict] = None,
         runtime_parameters: Optional[RuntimeParameters] = None,
         metrics_calculation: Optional[bool] = False,
+        auto_fe_parameters: Optional[AutoFEParameters] = None,
     ) -> SearchCustomization:
         # self.logger.info("Constructing search customization")
         search_customization = SearchCustomization(
@@ -585,7 +587,10 @@ class Dataset:  # (pd.DataFrame):
             search_customization.featuresFilter = feature_filter
 
         search_customization.runtimeParameters.properties["etalon_imbalanced"] = self.imbalanced
-
+        if auto_fe_parameters is not None:
+            search_customization.runtimeParameters.properties["feature_generation_params.ts.gap_days"] = (
+                auto_fe_parameters.ts_gap_days
+            )
         return search_customization
 
     def _rename_generate_features(self, runtime_parameters: Optional[RuntimeParameters]) -> Optional[RuntimeParameters]:
@@ -640,6 +645,7 @@ class Dataset:  # (pd.DataFrame):
         max_features: Optional[int] = None,  # deprecated
         filter_features: Optional[dict] = None,  # deprecated
         runtime_parameters: Optional[RuntimeParameters] = None,
+        auto_fe_parameters: Optional[AutoFEParameters] = None,
         force_downsampling: bool = False,
     ) -> SearchTask:
         if self.etalon_def is None:
@@ -658,6 +664,7 @@ class Dataset:  # (pd.DataFrame):
             max_features=max_features,
             filter_features=filter_features,
             runtime_parameters=runtime_parameters,
+            auto_fe_parameters=auto_fe_parameters,
         )
 
         if self.file_upload_id is not None and self.rest_client.check_uploaded_file_v2(