upgini 1.1.296__tar.gz → 1.1.296a3511.dev2__tar.gz

{upgini-1.1.296 → upgini-1.1.296a3511.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.296
+Version: 1.1.296a3511.dev2
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -26,6 +26,8 @@ Requires-Python: <3.11,>=3.8
 Requires-Dist: catboost>=1.0.3
 Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0
+Requires-Dist: jarowinkler>=2.0.0
+Requires-Dist: levenshtein>=0.25.1
 Requires-Dist: lightgbm>=3.3.2
 Requires-Dist: numpy>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0

{upgini-1.1.296 → upgini-1.1.296a3511.dev2}/pyproject.toml

@@ -48,6 +48,8 @@ dependencies = [
     "requests>=2.8.0",
     "scikit-learn>=1.3.0",
     "xhtml2pdf==0.2.11",
+    "jarowinkler>=2.0.0",
+    "levenshtein>=0.25.1",
 ]
 
 [project.urls]

upgini-1.1.296a3511.dev2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.296a3511.dev2"

{upgini-1.1.296 → upgini-1.1.296a3511.dev2}/src/upgini/autofe/all_operands.py

@@ -1,8 +1,22 @@
 from typing import Dict
 
-from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
+from upgini.autofe.binary import (
+    Add,
+    Combine,
+    CombineThenFreq,
+    Distance,
+    Divide,
+    JaroWinklerSim1,
+    JaroWinklerSim2,
+    LevenshteinSim,
+    Max,
+    Min,
+    Multiply,
+    Sim,
+    Subtract,
+)
 from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded, DatePercentile
-from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
+from upgini.autofe.groupby import GroupByThenAgg, GroupByThenFreq, GroupByThenNUnique, GroupByThenRank
 from upgini.autofe.operand import Operand
 from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
@@ -32,10 +46,10 @@ ALL_OPERANDS: Dict[str, Operand] = {
         GroupByThenAgg(name="GroupByThenMedian", agg="median"),
         GroupByThenAgg(name="GroupByThenStd", output_type="float", agg="std"),
         GroupByThenRank(),
-        Operand(name="Combine", has_symmetry_importance=True, output_type="object", is_categorical=True),
-        Operand(name="CombineThenFreq", has_symmetry_importance=True, output_type="float"),
-        Operand(name="GroupByThenNUnique", output_type="int", is_vectorizable=True, is_grouping=True),
-        Operand(name="GroupByThenFreq", output_type="float", is_grouping=True),
+        Combine(),
+        CombineThenFreq(),
+        GroupByThenNUnique(),
+        GroupByThenFreq(),
         Sim(),
         DateDiff(),
         DateDiffType2(),
@@ -51,6 +65,10 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
         DatePercentile(),
         Norm(),
+        JaroWinklerSim1(),
+        JaroWinklerSim2(),
+        LevenshteinSim(),
+        Distance(),
     ]
 }
 

{upgini-1.1.296 → upgini-1.1.296a3511.dev2}/src/upgini/autofe/binary.py

@@ -1,7 +1,11 @@
+import abc
+from typing import Optional
+import Levenshtein
 import numpy as np
 import pandas as pd
 from numpy import dot
 from numpy.linalg import norm
+from jarowinkler import jarowinkler_similarity
 
 from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
@@ -130,8 +134,8 @@ class CombineThenFreq(PandasOperand):
         self._loc(temp, value_counts)
 
 
-class Sim(PandasOperand):
-    name = "sim"
+class Distance(PandasOperand):
+    name = "dist"
     is_binary = True
     output_type = "float"
     is_symmetrical = True
@@ -139,3 +143,78 @@ class Sim(PandasOperand):
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return dot(left, right) / (norm(left) * norm(right))
+
+
+class Sim(Distance):
+    name = "sim"
+    is_binary = True
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
+
+
+class StringSim(PandasOperand, abc.ABC):
+    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        sims = []
+        for i in left.index:
+            left_i = self._prepare_value(left.get(i))
+            right_i = self._prepare_value(right.get(i))
+            if left_i is not None and right_i is not None:
+                sims.append(self._similarity(left_i, right_i))
+            else:
+                sims.append(None)
+
+        return pd.Series(sims, index=left.index)
+
+    @abc.abstractmethod
+    def _prepare_value(self, value: Optional[str]) -> Optional[str]:
+        pass
+
+    @abc.abstractmethod
+    def _similarity(self, left: str, right: str) -> float:
+        pass
+
+
+class JaroWinklerSim1(StringSim):
+    name = "sim_jw1"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
+
+    def _prepare_value(self, value: Optional[str]) -> Optional[str]:
+        return value
+
+    def _similarity(self, left: str, right: str) -> float:
+        return jarowinkler_similarity(left, right)
+
+
+class JaroWinklerSim2(StringSim):
+    name = "sim_jw2"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
+
+    def _prepare_value(self, value: Optional[str]) -> Optional[str]:
+        return value[::-1] if value is not None else None
+
+    def _similarity(self, left: str, right: str) -> float:
+        return jarowinkler_similarity(left, right)
+
+
+class LevenshteinSim(StringSim):
+    name = "sim_lv"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
+
+    def _prepare_value(self, value: Optional[str]) -> Optional[str]:
+        return value
+
+    def _similarity(self, left: str, right: str) -> float:
+        return 1 - Levenshtein.distance(left, right) / max(len(left), len(right))

{upgini-1.1.296 → upgini-1.1.296a3511.dev2}/src/upgini/data_source/data_source_publisher.py

@@ -59,35 +59,9 @@ 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):
@@ -150,14 +124,6 @@ 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)
@@ -215,9 +181,6 @@ 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-1.1.296 → upgini-1.1.296a3511.dev2}/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.warning("Failed to log debug information", exc_info=True)
+            self.logger.exception("Failed to log debug information")
 
     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-1.1.296/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.296"