upgini 1.1.296a3521.dev9__tar.gz → 1.1.297__tar.gz

{upgini-1.1.296a3521.dev9 → upgini-1.1.297}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.296a3521.dev9
+Version: 1.1.297
 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-1.1.296a3521.dev9 → upgini-1.1.297}/pyproject.toml

@@ -47,8 +47,8 @@ dependencies = [
     "python-json-logger>=2.0.2",
     "requests>=2.8.0",
     "scikit-learn>=1.3.0",
-    "xhtml2pdf==0.2.11",
     "python-bidi==0.4.2",
+    "xhtml2pdf==0.2.11",
 ]
 
 [project.urls]

upgini-1.1.297/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.297"

{upgini-1.1.296a3521.dev9 → upgini-1.1.297}/src/upgini/autofe/all_operands.py

@@ -1,14 +1,7 @@
 from typing import Dict
 
 from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
-from upgini.autofe.date import (
-    DateDiff,
-    DateDiffType2,
-    DateListDiff,
-    DateListDiffBounded,
-    DatePercentile,
-    DatePercentileMethod2,
-)
+from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded, DatePercentile
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
 from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
@@ -57,7 +50,6 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
         DatePercentile(),
-        DatePercentileMethod2(),
         Norm(),
     ]
 }

{upgini-1.1.296a3521.dev9 → upgini-1.1.297}/src/upgini/autofe/date.py

@@ -1,4 +1,3 @@
-import abc
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
@@ -39,7 +38,6 @@ class DateDiffMixin(BaseModel):
 
 class DateDiff(PandasOperand, DateDiffMixin):
     name = "date_diff"
-    alias = "date_diff_type1"
     is_binary = True
     has_symmetry_importance = True
 
@@ -161,45 +159,12 @@ class DateListDiffBounded(DateListDiff):
         return super()._agg(x)
 
 
-class DatePercentileBase(PandasOperand, abc.ABC):
+class DatePercentile(PandasOperand):
+    name = "date_per"
     is_binary = True
     output_type = "float"
 
     date_unit: Optional[str] = None
-
-    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
-        # Assuming that left is a date column, right is a feature column
-        left = pd.to_datetime(left, unit=self.date_unit)
-
-        bounds = self._get_bounds(left)
-
-        return right.index.to_series().apply(lambda i: self._perc(right[i], bounds[i]))
-
-    @abc.abstractmethod
-    def _get_bounds(self, date_col: pd.Series) -> pd.Series:
-        pass
-
-    def _perc(self, f, bounds):
-        hit = np.where(f >= bounds)[0]
-        if hit.size > 0:
-            return np.max(hit) + 1
-        else:
-            return np.nan
-
-    def get_params(self) -> Dict[str, Optional[str]]:
-        res = super().get_params()
-        res.update(
-            {
-                "date_unit": self.date_unit,
-            }
-        )
-        return res
-
-
-class DatePercentile(DatePercentileBase):
-    name = "date_per"
-    alias = "date_per_method1"
-
     zero_month: Optional[int]
     zero_year: Optional[int]
     zero_bounds: Optional[List[float]]
@@ -209,6 +174,7 @@ class DatePercentile(DatePercentileBase):
         res = super().get_params()
         res.update(
             {
+                "date_unit": self.date_unit,
                 "zero_month": self.zero_month,
                 "zero_year": self.zero_year,
                 "zero_bounds": self.zero_bounds,
@@ -224,18 +190,22 @@ class DatePercentile(DatePercentileBase):
         elif isinstance(value, str):
             return value[1:-1].split(", ")
 
-    def _get_bounds(self, date_col: pd.Series) -> pd.Series:
-        months = date_col.dt.month
-        years = date_col.dt.year
+    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        # Assuming that left is a date column, right is a feature column
+        left = pd.to_datetime(left, unit=self.date_unit)
+        months = left.dt.month
+        years = left.dt.year
 
         month_diffs = 12 * (years - (self.zero_year or 0)) + (months - (self.zero_month or 0))
-        return month_diffs.apply(
+        bounds = month_diffs.apply(
             lambda d: np.array(self.zero_bounds if self.zero_bounds is not None else []) + d * self.step
         )
 
+        return right.index.to_series().apply(lambda i: self.__perc(right[i], bounds[i]))
 
-class DatePercentileMethod2(DatePercentileBase):
-    name = "date_per_method2"
-
-    def _get_bounds(self, date_col: pd.Series) -> pd.Series:
-        pass
+    def __perc(self, f, bounds):
+        hit = np.where(f >= bounds)[0]
+        if hit.size > 0:
+            return np.max(hit) + 1
+        else:
+            return np.nan

{upgini-1.1.296a3521.dev9 → upgini-1.1.297}/src/upgini/autofe/feature.py

@@ -16,9 +16,6 @@ class Column:
         self.data = data
         self.calculate_all = calculate_all
 
-    def get_name_component(self, **kwargs) -> str:
-        return self.name
-
     def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
         return self.name
 
@@ -44,7 +41,7 @@ class Column:
     def get_column_nodes(self) -> List["Column"]:
         return [self]
 
-    def get_columns(self, **kwargs) -> List[str]:
+    def get_columns(self) -> List[str]:
         return [self.name]
 
     def infer_type(self, data: pd.DataFrame) -> DtypeObj:
@@ -60,12 +57,6 @@ class Column:
     def to_pretty_formula(self) -> str:
         return self.to_formula()
 
-    def __eq__(self, value: object) -> bool:
-        if not isinstance(value, Column):
-            return False
-        else:
-            return self.name == value.name and self.calculate_all == value.calculate_all
-
 
 class Feature:
     def __init__(
@@ -134,9 +125,6 @@ class Feature:
         for child in self.children:
             child.delete_data()
 
-    def get_op_display_name(self) -> str:
-        return self.op.alias or self.op.name.lower()
-
     def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
         if self.cached_display_name is not None and cache:
             return self.cached_display_name
@@ -144,11 +132,11 @@ class Feature:
         if self.alias:
             components = ["f_autofe", self.alias]
         elif shorten and not self.op.is_unary:
-            components = ["f_autofe", self.get_op_display_name()]
+            components = ["f_autofe", self.op.alias or self.op.name.lower()]
         else:
-            components = ["f_" + "_f_".join(self.get_columns())] + [
+            components = ["f_" + "_f_".join(self.get_columns(**kwargs))] + [
                 "autofe",
-                self.get_op_display_name(),
+                self.op.alias or self.op.name.lower(),
             ]
         components.extend([str(self.display_index)] if self.display_index is not None else [])
         display_name = "_".join(components)
@@ -318,21 +306,8 @@ class FeatureGroup:
         main_column = None if self.main_column_node is None else self.main_column_node.get_columns()[0]
         if isinstance(self.op, PandasOperand):
             columns = self.get_columns()
-            lower_order_children = [
-                ch for f in self.children for ch in f.children if ch.get_display_name() != main_column
-            ]
-            lower_order_names = [ch.get_display_name() for ch in lower_order_children]
-            if any(isinstance(f, Feature) for f in lower_order_children):
-                child_data = pd.concat(
-                    [data[main_column]] + [ch.calculate(data) for ch in lower_order_children],
-                    axis=1,
-                )
-                child_data.columns = [main_column] + lower_order_names
-            else:
-                child_data = data[columns]
-
-            new_data = self.op.calculate_group(child_data, main_column=main_column)
-            new_data.rename(columns=dict(zip(lower_order_names, self.get_display_names())), inplace=True)
+            new_data = self.op.calculate_group(data[columns], main_column=main_column)
+            new_data.rename(columns=dict(zip(columns, self.get_display_names())), inplace=True)
         else:
             raise NotImplementedError(f"Unrecognized operator {self.op.name}.")
 

{upgini-1.1.296a3521.dev9 → upgini-1.1.297}/src/upgini/data_source/data_source_publisher.py

@@ -59,9 +59,35 @@ class DataSourcePublisher:
         features_for_embeddings: Optional[List[str]] = DEFAULT_GENERATE_EMBEDDINGS,
         data_table_id_to_replace: Optional[str] = None,
         keep_features: Optional[List[str]] = None,
+        date_features: Optional[List[str]] = None,
+        date_vector_features: Optional[List[str]] = None,
         _force_generation=False,
         _silent=False,
     ) -> str:
+        """Register new ADS
+
+        Parameters
+        ----------
+        data_table_uri - str - table name in format {project_id}.{datasource_name}.{table_name}
+
+        search_keys - dict with column names as keys and SearchKey as value
+
+        update_frequency - str - (Monthly, Weekly, Daily, Annually, Quarterly)
+
+        exclude_from_autofe_generation - optional list of features that should be excluded from AutoFE
+
+        secondary_search_keys - optional dict of secondary search keys
+
+        sort_column - optional str - name of unique column that could be used for sort
+
+        date_format - optional str - format of date if it is present in search keys
+
+        ...
+
+        data_table_id_to_replace - optional str - id of registered ADS that should be replaced by new table
+
+        keep_features - optional list - features that should not be removed from ADS (even if they are personal)
+        """
         trace_id = str(uuid.uuid4())
 
         with MDC(trace_id=trace_id):
@@ -124,6 +150,14 @@ class DataSourcePublisher:
                     request["excludeFromGeneration"] = exclude_from_autofe_generation
                 if keep_features is not None:
                     request["keepFeatures"] = keep_features
+                if date_features is not None:
+                    if date_format is None:
+                        raise ValidationError("date_format should be presented if you use date features")
+                    request["dateFeatures"] = date_features
+                if date_vector_features is not None:
+                    if date_format is None:
+                        raise ValidationError("date_format should be presented if you use date vector features")
+                    request["dateVectorFeatures"] = date_vector_features
                 self.logger.info(f"Start registering data table {request}")
 
                 task_id = self._rest_client.register_ads(request, trace_id)
@@ -181,6 +215,9 @@ class DataSourcePublisher:
                 msg = f"Data table successfully registered with id: {data_table_id}"
                 self.logger.info(msg)
                 print(msg)
+                if "warnings" in status_response and status_response["warnings"]:
+                    self.logger.warning(status_response["warnings"])
+                    print(status_response["warnings"])
                 return data_table_id
             except KeyboardInterrupt:
                 if task_id is not None:

{upgini-1.1.296a3521.dev9 → upgini-1.1.297}/src/upgini/features_enricher.py

@@ -2870,7 +2870,7 @@ class FeaturesEnricher(TransformerMixin):
                 self.logger.info(f"Dates interval is ({min_date}, {max_date})")
 
         except Exception:
-            self.logger.exception("Failed to log debug information")
+            self.logger.warning("Failed to log debug information", exc_info=True)
 
     def __handle_index_search_keys(self, df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> pd.DataFrame:
         index_names = df.index.names if df.index.names != [None] else [DEFAULT_INDEX]

upgini-1.1.296a3521.dev9/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.296a3521.dev9"