upgini 1.1.294__py3-none-any.whl → 1.1.296a3511.dev1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.294"
+__version__ = "1.1.296a3511.dev1"

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/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/metrics.py

@@ -679,6 +679,11 @@ def validate_scoring_argument(scoring: Union[Callable, str, None]):
             raise ValidationError(
                 f"Invalid scoring function passed {scoring}. It should accept 3 input arguments: estimator, x, y"
             )
+    elif scoring is not None:
+        raise ValidationError(
+            f"Invalid scoring argument passed {scoring}. It should be string with scoring name or function"
+            " that accepts 3 input arguments: estimator, x, y"
+        )
 
 
 def _get_scorer_by_name(scoring: str) -> Tuple[Callable, str, int]:

{upgini-1.1.294.dist-info → upgini-1.1.296a3511.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.294
+Version: 1.1.296a3511.dev1
 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-1.1.294.dist-info → upgini-1.1.296a3511.dev1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=2vfGkEyxotARb9WDVVoCNdQiOrrhNqGA_vyl426_y5w,24
+upgini/__about__.py,sha256=cimRDJH6AT3BICa6gKJosTY9mQiinR-sub8yCsdaiuY,34
 upgini/__init__.py,sha256=ObEtjFkIssl83qeKNMLpIQygfwK8TzztwiI43YTsAP0,353
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
@@ -7,15 +7,15 @@ upgini/features_enricher.py,sha256=rLy6BwhL94VkRCp8W4RxJ0lBb7sZqTOsz-bUVI8nXZU,1
 upgini/http.py,sha256=bp6jWl422Icy3AhHMdCcJv5NjExE45gSMmzMTPJjPuk,42600
 upgini/lazy_import.py,sha256=EwoM0msNGbSmWBhGbrLDny1DSnOlvTxCjmMKPxYlDms,610
 upgini/metadata.py,sha256=qDAIO7NLSSQp_XiXCv3U4XJTLO0KH3YuQ8lvCLYPqzs,9781
-upgini/metrics.py,sha256=DLvA2YLV4f7lnzBCcfZ5T4NkqAv3pbstbjTepavuT7U,30688
+upgini/metrics.py,sha256=DiDgdFvYu64ArlPEgjppZShK6yybWtIEbdPAhI3yO1I,30930
 upgini/search_task.py,sha256=LtRJ9bCPjMo1gJ-sUDKERhDwGcWKImrzwVFHjkMSQHQ,17071
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=ddSKUK_-eGJB3NgrqOMoWJU-OxQ253WsNLp8aqJkaIM,1389
 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=cpwUfhZWF9QBfrUyJ0xZ72iGYyt1eXIZQ46FB-7ZDI4,2421
-upgini/autofe/binary.py,sha256=8FXPJxN7fnC5wphO0Dp1tQCa0lFMSDGQGvBMkSIVAcE,4155
+upgini/autofe/all_operands.py,sha256=ZS9A7u1gV7Bt8tHFfCiNx9u4q85I1ny4NIL-keyfWHY,2423
+upgini/autofe/binary.py,sha256=P46AVcFRiMKYucK3_N34QDqVMbvv2OuyWAREx0bUNwg,6367
 upgini/autofe/date.py,sha256=qzk0NT332Q0vR1eRwTuNiMSrGE3ulh6Ic3QLBZqSdvw,7284
 upgini/autofe/feature.py,sha256=_V9B74B3ue7eAYXSOt9JKhVC9klkAKks22MwnBRye_w,12487
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.294.dist-info/METADATA,sha256=mOES85LZo9_PlVh9tpbFPRp2QI16iINyIk5ywPby7Dc,48117
-upgini-1.1.294.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.1.294.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.294.dist-info/RECORD,,
+upgini-1.1.296a3511.dev1.dist-info/METADATA,sha256=_tPLQLuHI0_j5lGzkGhMSftXbfpLi8aCTRpjT4fd8QQ,48127
+upgini-1.1.296a3511.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.296a3511.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.296a3511.dev1.dist-info/RECORD,,

{upgini-1.1.294.dist-info → upgini-1.1.296a3511.dev1.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