upgini 1.2.81a3832.dev16__py3-none-any.whl → 1.2.81a3853.dev1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.81a3832.dev16"
+__version__ = "1.2.81a3853.dev1"

upgini/autofe/feature.py

@@ -161,7 +161,7 @@ class Feature:
         if self.cached_display_name is not None and cache:
             return self.cached_display_name
 
-        should_stack_op = not isinstance(self.children[0], Column) if self.op.is_unary else False
+        should_stack_op = not isinstance(self.children[0], Column) if self.op.is_unary or self.op.is_vector else False
         components = []
 
         if self.alias:

upgini/autofe/timeseries/volatility.py

@@ -60,12 +60,14 @@ class EWMAVolatility(VolatilityBase, ParametrizedOperator):
         return res
 
     def _aggregate(self, ts: pd.DataFrame) -> pd.DataFrame:
-        return ts.apply(self._ewma_vol)
+        return ts.apply(self._ewma_vol).iloc[:, [-1]]
 
     def _ewma_vol(self, x):
-        x = pd.DataFrame(x).iloc[:, -1]
-        returns = self._get_returns(x, f"{self.step_size}{self.step_unit}")
-        return returns.ewm(span=self.window_size).std()
+        return_series = isinstance(x, pd.Series)
+        x = pd.DataFrame(x)
+        returns = self._get_returns(x.iloc[:, -1], f"{self.step_size}{self.step_unit}")
+        x.iloc[:, -1] = returns.ewm(span=self.window_size).std()
+        return x.iloc[:, -1] if return_series else x
 
 
 class RollingVolBase(VolatilityBase):

upgini/features_enricher.py

@@ -453,6 +453,7 @@ class FeaturesEnricher(TransformerMixin):
         """
         trace_id = str(uuid.uuid4())
         start_time = time.time()
+        auto_fe_parameters = AutoFEParameters() if auto_fe_parameters is None else auto_fe_parameters
         search_progress = SearchProgress(0.0, ProgressStage.START_FIT)
         if progress_callback is not None:
             progress_callback(search_progress)
@@ -607,6 +608,7 @@ class FeaturesEnricher(TransformerMixin):
         """
 
         self.warning_counter.reset()
+        auto_fe_parameters = AutoFEParameters() if auto_fe_parameters is None else auto_fe_parameters
         trace_id = str(uuid.uuid4())
         start_time = time.time()
         with MDC(trace_id=trace_id):
@@ -2379,6 +2381,25 @@ if response.status_code == 200:
                 df[columns_for_system_record_id], index=False
             ).astype("float64")
 
+            features_not_to_pass = []
+            if add_fit_system_record_id:
+                df = self.__add_fit_system_record_id(
+                    df,
+                    search_keys,
+                    SYSTEM_RECORD_ID,
+                    TARGET,
+                    columns_renaming,
+                    silent=True,
+                )
+                df = df.rename(columns={SYSTEM_RECORD_ID: SORT_ID})
+                features_not_to_pass.append(SORT_ID)
+
+            system_columns_with_original_index = [ENTITY_SYSTEM_RECORD_ID] + generated_features
+            if add_fit_system_record_id:
+                system_columns_with_original_index.append(SORT_ID)
+
+            df_before_explode = df[system_columns_with_original_index].copy()
+
             # Explode multiple search keys
             df, unnest_search_keys = self._explode_multiple_search_keys(df, search_keys, columns_renaming)
 
@@ -2426,25 +2447,13 @@ if response.status_code == 200:
             meaning_types.update({col: FileColumnMeaningType.FEATURE for col in features_for_transform})
             meaning_types.update({col: key.value for col, key in search_keys.items()})
 
-            features_not_to_pass = [
+            features_not_to_pass.extend([
                 c
                 for c in df.columns
                 if c not in search_keys.keys()
                 and c not in features_for_transform
                 and c not in [ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]
-            ]
-
-            if add_fit_system_record_id:
-                df = self.__add_fit_system_record_id(
-                    df,
-                    search_keys,
-                    SYSTEM_RECORD_ID,
-                    TARGET,
-                    columns_renaming,
-                    silent=True,
-                )
-                df = df.rename(columns={SYSTEM_RECORD_ID: SORT_ID})
-                features_not_to_pass.append(SORT_ID)
+            ])
 
             if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
                 df = df.drop(columns=DateTimeSearchKeyConverter.DATETIME_COL)
@@ -2460,10 +2469,6 @@ if response.status_code == 200:
                 meaning_types[SEARCH_KEY_UNNEST] = FileColumnMeaningType.UNNEST_KEY
 
             df = df.reset_index(drop=True)
-            system_columns_with_original_index = [SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID] + generated_features
-            if add_fit_system_record_id:
-                system_columns_with_original_index.append(SORT_ID)
-            df_with_original_index = df[system_columns_with_original_index].copy()
 
             combined_search_keys = combine_search_keys(search_keys.keys())
 
@@ -2571,7 +2576,7 @@ if response.status_code == 200:
             combined_df = pd.concat(
                 [
                     validated_Xy.reset_index(drop=True),
-                    df_with_original_index.reset_index(drop=True),
+                    df_before_explode.reset_index(drop=True),
                 ],
                 axis=1,
             ).set_index(validated_Xy.index)
@@ -2728,7 +2733,7 @@ if response.status_code == 200:
         importance_threshold: Optional[float],
         max_features: Optional[int],
         remove_outliers_calc_metrics: Optional[bool],
-        auto_fe_parameters: Optional[AutoFEParameters] = None,
+        auto_fe_parameters: AutoFEParameters,
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
         search_id_callback: Optional[Callable[[str], Any]] = None,
     ):

upgini/metrics.py

@@ -368,6 +368,7 @@ class EstimatorWrapper:
         self.converted_to_str = []
         self.converted_to_numeric = []
         for c in x.columns:
+
             if _get_unique_count(x[c]) < 2:
                 self.logger.warning(f"Remove feature {c} because it has less than 2 unique values")
                 if c in self.cat_features:

{upgini-1.2.81a3832.dev16.dist-info → upgini-1.2.81a3853.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.81a3832.dev16
+Version: 1.2.81a3853.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-1.2.81a3832.dev16.dist-info → upgini-1.2.81a3853.dev1.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=Wtqf6woIkVhwgW_fiUm7UjHlXkCw_59KumFHUwoY2rU,34
+upgini/__about__.py,sha256=lTpfELfQnKZizte-HRZ9wE8F3tEopfpe9cTE8ZbJymk,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=AGF2u2mbFL4KIdqZECiSkGuMhfluamJOveqhYnkKfQM,212614
+upgini/features_enricher.py,sha256=cWbEA2lOt51x62NrLkyxu1G8I4KQo_2aOgqt3Ypyr1M,212819
 upgini/http.py,sha256=AfaJ3c8z_tK2hZFEehNybDKE0mp1tYcyAP_l0_p8bLQ,43933
 upgini/metadata.py,sha256=zt_9k0iQbWXuiRZcel4ORNPdQKt6Ou69ucZD_E1Q46o,12341
-upgini/metrics.py,sha256=nVt4zJKt7y1xD1ga9698QKlJQfXv93lARjUMC1E1_U4,43163
+upgini/metrics.py,sha256=3cip0_L6-OFew74KsRwzxJDU6UFq05h2v7IsyHLcMRc,43164
 upgini/search_task.py,sha256=Q5HjBpLIB3OCxAD1zNv5yQ3ZNJx696WCK_-H35_y7Rs,17912
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -16,7 +16,7 @@ upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
 upgini/autofe/binary.py,sha256=oOEECc4nRzZN2tYaiqx8F2XHnfWpk1bVvb7ZkZJ0lO8,7709
 upgini/autofe/date.py,sha256=MM1S-6imNSzCDOhbNnmsc_bwSqUWBcS8vWAdHF8j1kY,11134
-upgini/autofe/feature.py,sha256=G_YgnsauIoaMgByx9JXDPiKc4nqs0pwWZUfvoIGMKxY,15305
+upgini/autofe/feature.py,sha256=HYg6ngZXp9t-mzQN5KFCXJ8_EGGTg8TwTuw1W_uhzqI,15326
 upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
 upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
 upgini/autofe/unary.py,sha256=Sx11IoHRh5nwyALzjgG9GQOrVNIs8NZ1JzunAJuN66A,5731
@@ -29,7 +29,7 @@ upgini/autofe/timeseries/delta.py,sha256=h0YhmI1TlPJnjwFpN_GQxLb6r59DQuucnG5tQAX
 upgini/autofe/timeseries/lag.py,sha256=LfQtg484vuqM0mgY4Wft1swHX_Srq7OKKgZswCXoiXI,1882
 upgini/autofe/timeseries/roll.py,sha256=zADKXU-eYWQnQ5R3am1yEal8uU6Tm0jLAixwPb_aCHg,2794
 upgini/autofe/timeseries/trend.py,sha256=K1_iw2ko_LIUU8YCUgrvN3n0MkHtsi7-63-8x9er1k4,2129
-upgini/autofe/timeseries/volatility.py,sha256=9shUmIKjpWTHVYjj80YBsk0XheBJ9uBuLv5NW9Mchnk,7953
+upgini/autofe/timeseries/volatility.py,sha256=SvZfhM_ZAWCNpTf87WjSnZsnlblARgruDlu4By4Zvhc,8078
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/data_source/data_source_publisher.py,sha256=4S9qwlAklD8vg9tUU_c1pHE2_glUHAh15-wr5hMwKFw,22879
 upgini/mdc/__init__.py,sha256=iHJlXQg6xRM1-ZOUtaPSJqw5SpQDszvxp4LyqviNLIQ,1027
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=LRN840dzx78-wg7ftdxAkp2c1eu8-JDvkACiRThm4HE,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.81a3832.dev16.dist-info/METADATA,sha256=jE8_Lb2S-QjU7tcbGPQcoxiCCu-AcuMyHpoxW3KEvv0,49173
-upgini-1.2.81a3832.dev16.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.81a3832.dev16.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.81a3832.dev16.dist-info/RECORD,,
+upgini-1.2.81a3853.dev1.dist-info/METADATA,sha256=0X9NO-JymZWgNv0-YsNoj_cVfSxsIZjI_IurJLrKR20,49172
+upgini-1.2.81a3853.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.81a3853.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.81a3853.dev1.dist-info/RECORD,,

{upgini-1.2.81a3832.dev16.dist-info → upgini-1.2.81a3853.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