upgini 1.1.280a3418.post2__py3-none-any.whl → 1.1.280.dev0__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.280a3418-2"
+__version__ = "1.1.280.dev0"

upgini/autofe/all_operands.py

@@ -4,7 +4,7 @@ from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
 from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
-from upgini.autofe.unary import Abs, Bin, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
+from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -49,7 +49,6 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=30, upper_bound=45),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
-        Bin(),
     ]
 }
 

upgini/autofe/unary.py

@@ -111,21 +111,3 @@ class Freq(PandasOperand):
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         value_counts = data.value_counts(normalize=True)
         return self._loc(data, value_counts)
-
-
-class Bin(PandasOperand):
-    name = "bin"
-    is_unary = True
-    output_type = "int"
-    input_type = "discrete"
-
-    zero_bound_low: int
-    zero_bound_high: int
-    step: int
-
-    def calculate_unary(self, data: pd.Series) -> pd.Series:
-        res = pd.Series(np.zeros(data.shape), index=data.index, dtype="int")
-        res.update((data[data < self.zero_bound_low] - self.zero_bound_low) // self.step)
-        res.update((data[data >= self.zero_bound_high] - self.zero_bound_high) // self.step + 1)
-
-        return res

upgini/features_enricher.py

@@ -1333,6 +1333,9 @@ class FeaturesEnricher(TransformerMixin):
         excluding_search_keys = list(search_keys.keys())
         if search_keys_for_metrics is not None and len(search_keys_for_metrics) > 0:
             excluding_search_keys = [sk for sk in excluding_search_keys if sk not in search_keys_for_metrics]
+        meta = self._search_task.get_all_features_metadata_v2()
+        zero_importance_client_features = [m for m in meta if m.source == "etalon" and m.shap_value == 0.0]
+
         client_features = [
             c
             for c in X_sampled.columns.to_list()
@@ -1341,6 +1344,7 @@ class FeaturesEnricher(TransformerMixin):
                 excluding_search_keys
                 + list(self.fit_dropped_features)
                 + [DateTimeSearchKeyConverter.DATETIME_COL, SYSTEM_RECORD_ID]
+                + zero_importance_client_features
             )
         ]
 
@@ -2845,8 +2849,10 @@ class FeaturesEnricher(TransformerMixin):
             maybe_date_col = self._get_date_column(self.search_keys)
             if X is not None and maybe_date_col is not None and maybe_date_col in X.columns:
                 # TODO cast date column to single dtype
-                min_date = X[maybe_date_col].min()
-                max_date = X[maybe_date_col].max()
+                date_converter = DateTimeSearchKeyConverter(maybe_date_col, self.date_format)
+                converted_X = date_converter.convert(X)
+                min_date = converted_X[maybe_date_col].min()
+                max_date = converted_X[maybe_date_col].max()
                 self.logger.info(f"Dates interval is ({min_date}, {max_date})")
 
         except Exception:

{upgini-1.1.280a3418.post2.dist-info → upgini-1.1.280.dev0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.280a3418.post2
+Version: 1.1.280.dev0
 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-1.1.280a3418.post2.dist-info → upgini-1.1.280.dev0.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=fgIudZxw-Qs9Gp5uX0LE_GUvruwCsSuF1VAhqXKXP80,31
+upgini/__about__.py,sha256=UrHon9iXf0_L0ezeavtXrVCL8ABnaX0u5iXp6FC3PTA,29
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=uiFY-P8te7-zigib1hGWRtW5v0X7chxPM0hJFdixAN8,45623
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=NU2lpp6ZrJ3oKOOLa6u7DQ5kb64n8mDAFXadWjr219A,176290
+upgini/features_enricher.py,sha256=HQHTKpyK9MGqYTZ5FMgJLvRQ0o1JwApcQklTRKxIgMs,176683
 upgini/http.py,sha256=khrYSldpY-HbVLCcApfV1BjBFK6Uyuatb4colKybxgY,42301
 upgini/metadata.py,sha256=CFJekYGD7Ep7pRFH7wCEcsXS4bz83do33FNmtcCY9P4,9729
 upgini/metrics.py,sha256=L4LKSMOK9iKFLaJvTBTKk2tQauMgiJqtfrBclM3fBjs,29670
@@ -13,13 +13,13 @@ upgini/version_validator.py,sha256=RGg87VweujTNlibgsOuqPLIEiBgIOkuXNVTGuNCD234,1
 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=VB8-iuNanjtjo3ho2shDDfWQtXGYekeoPEBzpNy1iWo,2377
+upgini/autofe/all_operands.py,sha256=SyKVU-xGMHgoRZvHrCmba2u2Ygc73c1mXFolNSWe8Uo,2357
 upgini/autofe/binary.py,sha256=441BRuqMsxlxuw4c8rMZB6h5EpRdVMk-bVa03U7T5Hg,3973
 upgini/autofe/date.py,sha256=Vy1I92fLLYLhuYKJmtuPBMI8cPxE4Uwk40hqE2F2e1A,4224
 upgini/autofe/feature.py,sha256=ChSuuIbRPGIWnPjKAgZbeAEi7Y_PjSVRyxxx41MyFp0,11845
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
 upgini/autofe/operand.py,sha256=xgEIZuFCfckc6LpBqVu1OVK3JEabm1O-LHUsp83EHKA,2806
-upgini/autofe/unary.py,sha256=tbyptbPZubVNdvo36N7ftYIlFOUhQLZyJLizjIUOTJ4,3673
+upgini/autofe/unary.py,sha256=v-l3aiE5hj6kurvh6adCQL8W3X9u9a7RVbS_WPR2qlw,3146
 upgini/autofe/vector.py,sha256=dLxfAstJs-gw_OQ1xxoxcM6pVzORlV0HVzdzt7cLXVQ,606
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/data_source/data_source_publisher.py,sha256=taRzyGgrPrTTSGw4Y-Ca5k4bf30aiTa68rxqT9zfqeI,16478
@@ -56,7 +56,7 @@ upgini/utils/sklearn_ext.py,sha256=c23MGSUVfxLnaDWKAxavHgnOtm5dGKkF3YswdWQcFzs,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-1.1.280a3418.post2.dist-info/METADATA,sha256=lZ6l4l61_krq4P0sat3HwUocoSzaRh3NNSpq_bNa46Q,48129
-upgini-1.1.280a3418.post2.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.280a3418.post2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.280a3418.post2.dist-info/RECORD,,
+upgini-1.1.280.dev0.dist-info/METADATA,sha256=AlD_LoKBQRcf5DSTcQeTung2oC2xtzCzKnBqgMeVUH0,48123
+upgini-1.1.280.dev0.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.280.dev0.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.280.dev0.dist-info/RECORD,,