upgini 1.1.293__py3-none-any.whl → 1.1.296__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.293"
+__version__ = "1.1.296"

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):
@@ -95,6 +121,11 @@ class DataSourcePublisher:
                         "With MSISDN and DATE keys one of the snapshot_frequency_days or"
                         " join_date_abs_limit_days parameters is required"
                     )
+                if (
+                    set(search_keys.values()) == {SearchKey.PHONE, SearchKey.DATE}
+                    or set(search_keys.values()) == {SearchKey.HEM, SearchKey.DATE}
+                ) and not date_format:
+                    raise ValidationError("date_format argument is required for PHONE+DATE and HEM+DATE search keys")
 
                 request = {
                     "dataTableUri": data_table_uri,
@@ -119,6 +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)
@@ -176,6 +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/features_enricher.py

@@ -2557,9 +2557,6 @@ class FeaturesEnricher(TransformerMixin):
         return [c for c, v in search_keys_with_autodetection.items() if v.value.value in keys]
 
     def _validate_X(self, X, is_transform=False) -> pd.DataFrame:
-        if _num_samples(X) == 0:
-            raise ValidationError(self.bundle.get("x_is_empty"))
-
         if isinstance(X, pd.DataFrame):
             if isinstance(X.columns, pd.MultiIndex) or isinstance(X.index, pd.MultiIndex):
                 raise ValidationError(self.bundle.get("x_multiindex_unsupported"))
@@ -2573,6 +2570,9 @@ class FeaturesEnricher(TransformerMixin):
         else:
             raise ValidationError(self.bundle.get("unsupported_x_type").format(type(X)))
 
+        if _num_samples(X) == 0:
+            raise ValidationError(self.bundle.get("x_is_empty"))
+
         if len(set(validated_X.columns)) != len(validated_X.columns):
             raise ValidationError(self.bundle.get("x_contains_dup_columns"))
         if not is_transform and not validated_X.index.is_unique:
@@ -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/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-1.1.293.dist-info → upgini-1.1.296.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.293
+Version: 1.1.296
 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-1.1.293.dist-info → upgini-1.1.296.dist-info}/RECORD

@@ -1,13 +1,13 @@
-upgini/__about__.py,sha256=qZMAUJW6Js0WNRcvGFbeSyGFbiVxGPjSbHngvQV4JrY,24
+upgini/__about__.py,sha256=VYB3k4Dn9TdkyE_1qiCFNhgHJH5heaX4R3m8VNi495g,24
 upgini/__init__.py,sha256=ObEtjFkIssl83qeKNMLpIQygfwK8TzztwiI43YTsAP0,353
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=Bfqbzqj3h1Ox3s6hBA4UYXkG7hQDqGPB4JK1YXtxXxw,177530
+upgini/features_enricher.py,sha256=HQFLw3VyEsZfAt4xFnIYOnp3fzQSHAsyHzIm0gTJpOI,177543
 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
@@ -23,7 +23,7 @@ upgini/autofe/operand.py,sha256=MKEsl3zxpWzRDpTkE0sNJxTu62U20sWOvEKhPjUWS6s,2915
 upgini/autofe/unary.py,sha256=ZWjLd-CUkNt_PpM8YuWLLipW1v_RdBlsl4JxXIVo9aM,3652
 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=2BCFcglyZC1T5WYerqd_GGC6dg22o2Mh-ce53wOIOjQ,17465
+upgini/data_source/data_source_publisher.py,sha256=1cQZrK630VztwGGDp41ec9gqIeUtkefaqSSQEitVWiM,19581
 upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -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-1.1.293.dist-info/METADATA,sha256=xxqpODSdTGvAAXew_U-IjsfNzYFALrNqOS2BK81cgy8,48117
-upgini-1.1.293.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.293.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.293.dist-info/RECORD,,
+upgini-1.1.296.dist-info/METADATA,sha256=4eJQUEcmU8LjaLKmvkZ4OPJBat7dPkBI0GwnNKpBZcc,48117
+upgini-1.1.296.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.1.296.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.296.dist-info/RECORD,,

{upgini-1.1.293.dist-info → upgini-1.1.296.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.24.2
+Generator: hatchling 1.25.0
 Root-Is-Purelib: true
 Tag: py3-none-any