upgini 1.2.141__py3-none-any.whl → 1.2.142__py3-none-any.whl

upgini/metadata.py

@@ -96,7 +96,7 @@ class SearchKey(Enum):
         return [SearchKey.EMAIL, SearchKey.HEM, SearchKey.IP, SearchKey.PHONE]
 
     @staticmethod
-    def from_meaning_type(meaning_type: FileColumnMeaningType) -> "SearchKey":
+    def from_meaning_type(meaning_type: FileColumnMeaningType) -> Optional["SearchKey"]:
         if meaning_type == FileColumnMeaningType.EMAIL:
             return SearchKey.EMAIL
         if meaning_type == FileColumnMeaningType.HEM:
@@ -263,6 +263,7 @@ class FileMetadata(BaseModel):
     digest: Optional[str] = None
     deterministicDigest: Optional[str] = None
     droppedColumns: Optional[List[str]] = None
+    autodetectedSearchKeys: Optional[Dict[str, str]] = None
 
     def column_by_name(self, name: str) -> Optional[FileColumnMetadata]:
         for c in self.columns:

upgini/normalizer/normalize_utils.py

@@ -134,7 +134,7 @@ class Normalizer:
 
         for f in features:
             converter = DateTimeConverter(f)
-            if converter.is_datetime(df):
+            if converter.is_datetime(df) and f != DateTimeConverter.DATETIME_COL:
                 self.removed_datetime_features.append(f)
                 df.drop(columns=f, inplace=True)
 

upgini/resource_bundle/strings.properties

@@ -140,6 +140,7 @@ x_and_eval_x_diff_types=X and eval_set X has different types: {} and {}
 eval_x_has_train_samples=Eval set X has rows that are present in train set X
 oot_without_date_not_supported=Eval set {} provided as OOT but date column is missing. It will be ignored for stability check
 oot_with_online_sources_not_supported=Eval set {} provided as OOT and also provided columns for online API. It will be ignored for stability check
+autodetected_search_key_not_found=Autodetected on fit search key {} not found in X columns: {} for transform
 
 baseline_score_column_not_exists=baseline_score_column {} doesn't exist in input dataframe
 baseline_score_column_has_na=baseline_score_column contains NaN. Clear it and and retry
@@ -210,15 +211,15 @@ features_info_zero_important_features=Oops, we can't find any relevant external
 features_info_zero_hit_rate_search_keys=Oops, looks like values/formats of the search keys {} might be incorrect,\nas we won't be able to match any data source using these values\nPlease check docs https://github.com/upgini/upgini#-search-key-types-we-support-more-to-come or send us a help request in Support:
 features_not_generated=Following features didn't pass checks for automated feature generation: {}
 # Information
-datetime_detected=Datetime detected in column `{}`. It will be used as a search key\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-postal_code_detected=Postal codes detected in column `{}`. It will be used as a search key\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-country_detected=Countries detected in column `{}`. It will be used as a search key\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-country_auto_determined=Search key country_code `{}` was automatically determined by client IP. \nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-country_default_determined=Search key country_code `{}` was used as default. \nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-email_detected=Emails detected in column `{}`. It will be used as a search key\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-email_detected_not_registered=Emails detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-phone_detected=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-phone_detected_not_registered=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
+datetime_detected=Datetime detected in column `{}`. It will be used as a search key\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
+postal_code_detected=Postal codes detected in column `{}`. It will be used as a search key\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
+country_detected=Countries detected in column `{}`. It will be used as a search key\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
+country_auto_determined=Search key country_code `{}` was automatically determined by client IP. \nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
+country_default_determined=Search key country_code `{}` was used as default. \nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
+email_detected=Emails detected in column `{}`. It will be used as a search key\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
+email_detected_not_registered=Emails detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
+phone_detected=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
+phone_detected_not_registered=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
 target_type_detected=\nDetected task type: {}. Reason: {}\nYou can set task type manually with argument `model_task_type` of FeaturesEnricher constructor if task type detected incorrectly\n
 binary_target_reason=only two unique label-values observed
 non_numeric_multiclass_reason=non-numeric label values observed

upgini/utils/datetime_utils.py

@@ -282,10 +282,13 @@ class DateTimeConverter:
                     warnings.filterwarnings("ignore", message="Could not infer format")
                     return pd.to_datetime(df[self.date_column])
             except ValueError:
-                if raise_errors:
-                    raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
-                else:
-                    return None
+                try:
+                    return pd.to_datetime(df[self.date_column], format="mixed", errors="raise")
+                except ValueError:
+                    if raise_errors:
+                        raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
+                    else:
+                        return None
 
     def clean_old_dates(self, df: pd.DataFrame) -> pd.DataFrame:
         condition = df[self.date_column] <= self.MIN_SUPPORTED_DATE_TS

{upgini-1.2.141.dist-info → upgini-1.2.142.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.141
+Version: 1.2.142
 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-1.2.141.dist-info → upgini-1.2.142.dist-info}/RECORD

@@ -1,11 +1,11 @@
-upgini/__about__.py,sha256=I2bML2FqWEWGtryWcuBAZONbMQY-aJazrjRrHTVV1Cw,24
+upgini/__about__.py,sha256=J-UkV9cG8CRQHHY_zWq7GDwjkfngS30TGOqeyQgyN0Q,24
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=7qM6O2NnsdnfAVrrPIyHKyUqwlQyuiPsR12ayF0OHsc,33356
+upgini/dataset.py,sha256=bkUpUC1sdhCQcLPysB7BC8WiFDPfjiJj1SztExpv0nA,33735
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=38GmrjhWZKf-pNTdOmt8DcT19gtDWktVdRvxEjtxiro,237492
+upgini/features_enricher.py,sha256=07decijgeSDaN6A1qVf71ZETu9nXVhNRWUTPWZeNpJo,234667
 upgini/http.py,sha256=y26x4TQVYuEM3jz8JdASxSyBtvBemUkFf-FmX25sx-s,44356
-upgini/metadata.py,sha256=BwUTCY-EUHqPtO0tGazHrk3wqhh-NfjNZhlBHW8bR78,12796
+upgini/metadata.py,sha256=iYlL91g2PMHjiPIySIZb4IzIIUsPaAMIiV2It95GAjA,12866
 upgini/metrics.py,sha256=KCPE_apPN-9BIdv6GqASbJVaB_gBcy8wzNApAcyaGo4,46020
 upgini/search_task.py,sha256=5mL_qV5mVtDkIumM9xCOgfa9Lc2B8mxJ1qI21iaScnQ,18656
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
@@ -35,10 +35,10 @@ upgini/data_source/data_source_publisher.py,sha256=CQi3fEukaStV-RiadSEvEFLThOlZJ
 upgini/mdc/__init__.py,sha256=iHJlXQg6xRM1-ZOUtaPSJqw5SpQDszvxp4LyqviNLIQ,1027
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/normalizer/normalize_utils.py,sha256=oKevieBChYxtugocrbev8Uz2vqSZ_PB4Ibo55fHOylM,8452
+upgini/normalizer/normalize_utils.py,sha256=mnOFU39oOsv_UhJVArl8BSocZlNP0xzgeAbSYI14Zjs,8492
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=Dym1ymRH2uTeb0CfrO_lccoP9LWj7lxNGvsxmR7vkSw,29583
+upgini/resource_bundle/strings.properties,sha256=GvOX9GZJaWxlL9X3FqtF3LyvPGVKyJniCzb5LVNiXwo,29710
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=Fva2FEhLiNRPZ9Q6uOtJRtRzwsayjv7aphalAZO_4lc,6452
@@ -52,7 +52,7 @@ upgini/utils/config.py,sha256=zFdnjchykfp_1Tm3Qep7phLzXBpXIOzr2tIuXchRBLw,1754
 upgini/utils/country_utils.py,sha256=lY-eXWwFVegdVENFttbvLcgGDjFO17Sex8hd2PyJaRk,6937
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
-upgini/utils/datetime_utils.py,sha256=pTi5doYjjjlQgwEVDNrJuKaAEC3Jtx78fjX4W7M_UV4,17615
+upgini/utils/datetime_utils.py,sha256=rr_aUjzKxj9I-0EPyRnWCquXkb4hdh6YcEDtoxeB2XE,17783
 upgini/utils/deduplicate_utils.py,sha256=CLX0QapRxB-ZVQT7yGvv1vSd2zac5SwRjCJavujdCps,11332
 upgini/utils/display_utils.py,sha256=MoTqXZJvC6pAqgOaI3V0FG-IU_LnMfrn4TDcNvUqsdg,13316
 upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
@@ -74,7 +74,7 @@ upgini/utils/target_utils.py,sha256=CihpV6SC95HwtlMH60rGAUzVDa4Id0Bva8ySprmNHlE,
 upgini/utils/track_info.py,sha256=NDKeQTUlZaYp15UoP-xLKGoDoJQ0drbDMwB0g9R0PUg,6427
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.141.dist-info/METADATA,sha256=h3Vj1iQNywtnF9zdXkokTIWwmklXPN_090IzhjHAh_Q,51164
-upgini-1.2.141.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-upgini-1.2.141.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.141.dist-info/RECORD,,
+upgini-1.2.142.dist-info/METADATA,sha256=iWbuZsbyF4hxG9iUnlF9tYH9JKx8FOBT34J5Bhs7cPo,51164
+upgini-1.2.142.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+upgini-1.2.142.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.142.dist-info/RECORD,,