upgini 1.1.274__py3-none-any.whl → 1.1.274a2__py3-none-any.whl

upgini/autofe/date.py

@@ -2,7 +2,6 @@ from typing import Any, Optional, Union
 import numpy as np
 import pandas as pd
 from pydantic import BaseModel
-from pandas.core.arrays.timedeltas import TimedeltaArray
 
 from upgini.autofe.operand import PandasOperand
 
@@ -74,13 +73,8 @@ class DateListDiff(PandasOperand, DateDiffMixin):
 
         return pd.Series(left - right.values).apply(lambda x: self._agg(self._diff(x)))
 
-    def _diff(self, x: TimedeltaArray):
-        if self.diff_unit == "Y":
-            x = (x / 365 / 24 / 60 / 60 / 10**9).astype(int)
-        elif self.diff_unit == "M":
-            raise Exception("Unsupported difference unit: Month")
-        else:
-            x = x / np.timedelta64(1, self.diff_unit)
+    def _diff(self, x):
+        x = x / np.timedelta64(1, self.diff_unit)
         return x[x > 0]
 
     def _agg(self, x):

upgini/features_enricher.py

@@ -424,9 +424,6 @@ class FeaturesEnricher(TransformerMixin):
 
             self.__validate_search_keys(self.search_keys, self.search_id)
 
-            # Validate client estimator params
-            self._get_client_cat_features(estimator, X, self.search_keys)
-
             try:
                 self.X = X
                 self.y = y
@@ -820,7 +817,6 @@ class FeaturesEnricher(TransformerMixin):
         trace_id = trace_id or str(uuid.uuid4())
         start_time = time.time()
         with MDC(trace_id=trace_id):
-            self.logger.info("Start calculate metrics")
             if len(args) > 0:
                 msg = f"WARNING: Unsupported positional arguments for calculate_metrics: {args}"
                 self.logger.warning(msg)
@@ -872,9 +868,22 @@ class FeaturesEnricher(TransformerMixin):
                     self.__display_support_link(msg)
                     return None
 
-                cat_features, search_keys_for_metrics = self._get_client_cat_features(
-                    estimator, effective_X, self.search_keys
-                )
+                cat_features = None
+                search_keys_for_metrics = []
+                if (
+                    estimator is not None
+                    and hasattr(estimator, "get_param")
+                    and estimator.get_param("cat_features") is not None
+                ):
+                    cat_features = estimator.get_param("cat_features")
+                    if len(cat_features) > 0 and isinstance(cat_features[0], int):
+                        cat_features = [effective_X.columns[i] for i in cat_features]
+                        for cat_feature in cat_features:
+                            if cat_feature in self.search_keys:
+                                if self.search_keys[cat_feature] in [SearchKey.COUNTRY, SearchKey.POSTAL_CODE]:
+                                    search_keys_for_metrics.append(cat_feature)
+                                else:
+                                    raise ValidationError(self.bundle.get("cat_feature_search_key").format(cat_feature))
 
                 prepared_data = self._prepare_data_for_metrics(
                     trace_id=trace_id,
@@ -889,7 +898,6 @@ class FeaturesEnricher(TransformerMixin):
                     search_keys_for_metrics=search_keys_for_metrics,
                     progress_bar=progress_bar,
                     progress_callback=progress_callback,
-                    cat_features=cat_features,
                 )
                 if prepared_data is None:
                     return None
@@ -1265,29 +1273,6 @@ class FeaturesEnricher(TransformerMixin):
 
         return _cv, groups
 
-    def _get_client_cat_features(
-        self, estimator: Optional[Any], X: pd.DataFrame, search_keys: Dict[str, SearchKey]
-    ) -> Optional[List[str]]:
-        cat_features = None
-        search_keys_for_metrics = []
-        if (
-            estimator is not None
-            and hasattr(estimator, "get_param")
-            and estimator.get_param("cat_features") is not None
-        ):
-            cat_features = estimator.get_param("cat_features")
-            if len(cat_features) > 0:
-                if all([isinstance(f, int) for f in cat_features]):
-                    cat_features = [X.columns[i] for i in cat_features]
-                self.logger.info(f"Collected categorical features {cat_features} from user estimator")
-                for cat_feature in cat_features:
-                    if cat_feature in search_keys:
-                        if search_keys[cat_feature] in [SearchKey.COUNTRY, SearchKey.POSTAL_CODE]:
-                            search_keys_for_metrics.append(cat_feature)
-                        else:
-                            raise ValidationError(self.bundle.get("cat_feature_search_key").format(cat_feature))
-        return cat_features, search_keys_for_metrics
-
     def _prepare_data_for_metrics(
         self,
         trace_id: str,
@@ -1302,7 +1287,6 @@ class FeaturesEnricher(TransformerMixin):
         search_keys_for_metrics: Optional[List[str]] = None,
         progress_bar: Optional[ProgressBar] = None,
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
-        cat_features: Optional[List[str]] = None,
     ):
         is_input_same_as_fit, X, y, eval_set = self._is_input_same_as_fit(X, y, eval_set)
         is_demo_dataset = hash_input(X, y, eval_set) in DEMO_DATASET_HASHES
@@ -1360,8 +1344,9 @@ class FeaturesEnricher(TransformerMixin):
 
         # Detect and drop high cardinality columns in train
         columns_with_high_cardinality = FeaturesValidator.find_high_cardinality(fitting_X)
-        non_excluding_columns = (self.generate_features or []) + (cat_features or [])
-        columns_with_high_cardinality = [c for c in columns_with_high_cardinality if c not in non_excluding_columns]
+        columns_with_high_cardinality = [
+            c for c in columns_with_high_cardinality if c not in (self.generate_features or [])
+        ]
         if len(columns_with_high_cardinality) > 0:
             self.logger.warning(
                 f"High cardinality columns {columns_with_high_cardinality} will be dropped for metrics calculation"
@@ -1824,10 +1809,12 @@ class FeaturesEnricher(TransformerMixin):
             features_section = ""
 
         search_id = self._search_task.search_task_id
-        api_example = f"""curl 'https://search.upgini.com/online/api/http_inference_trigger?search_id={search_id}' \\
+        api_example = (
+            f"""curl 'https://search.upgini.com/online/api/http_inference_trigger?search_id={search_id}' \\
     -H 'Authorization: {self.api_key}' \\
     -H 'Content-Type: application/json' \\
     -d '{{"search_keys": {keys}{features_section}}}'"""
+        )
         return api_example
 
     def _get_copy_of_runtime_parameters(self) -> RuntimeParameters:
@@ -1923,7 +1910,8 @@ class FeaturesEnricher(TransformerMixin):
             else:
                 self.logger.info("Input dataset hasn't date column")
                 if self.add_date_if_missing:
-                    df = self._add_current_date_as_key(df, search_keys, self.logger, self.bundle)
+                    df = self._add_current_date_as_key(df)
+                    search_keys[self.CURRENT_DATE] = SearchKey.DATE
             email_column = self._get_email_column(search_keys)
             hem_column = self._get_hem_column(search_keys)
             email_converted_to_hem = False
@@ -2294,7 +2282,8 @@ class FeaturesEnricher(TransformerMixin):
         else:
             self.logger.info("Input dataset hasn't date column")
             if self.add_date_if_missing:
-                df = self._add_current_date_as_key(df, self.fit_search_keys, self.logger, self.bundle)
+                df = self._add_current_date_as_key(df)
+                self.fit_search_keys[self.CURRENT_DATE] = SearchKey.DATE
         email_column = self._get_email_column(self.fit_search_keys)
         hem_column = self._get_hem_column(self.fit_search_keys)
         email_converted_to_hem = False
@@ -2876,23 +2865,8 @@ class FeaturesEnricher(TransformerMixin):
                 return col
 
     @staticmethod
-    def _add_current_date_as_key(
-        df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: logging.Logger, bundle: ResourceBundle
-    ) -> pd.DataFrame:
-        if (
-            set(search_keys.values()) == {SearchKey.PHONE}
-            or set(search_keys.values()) == {SearchKey.EMAIL}
-            or set(search_keys.values()) == {SearchKey.HEM}
-            or set(search_keys.values()) == {SearchKey.COUNTRY, SearchKey.POSTAL_CODE}
-        ):
-            msg = bundle.get("current_date_added")
-            print(msg)
-            logger.warning(msg)
-            df[FeaturesEnricher.CURRENT_DATE] = datetime.date.today()
-            search_keys[FeaturesEnricher.CURRENT_DATE] = SearchKey.DATE
-            converter = DateTimeSearchKeyConverter(FeaturesEnricher.CURRENT_DATE, None, logger, bundle)
-            df = converter.convert(df)
-        return df
+    def _add_current_date_as_key(df: pd.DataFrame) -> pd.DataFrame:
+        df[FeaturesEnricher.CURRENT_DATE] = datetime.date.today()
 
     @staticmethod
     def _get_group_columns(df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> List[str]:

upgini/metrics.py

@@ -1,4 +1,3 @@
-import inspect
 import logging
 import re
 from copy import deepcopy
@@ -382,11 +381,6 @@ class EstimatorWrapper:
             kwargs["estimator"] = estimator_copy
             if isinstance(estimator, CatBoostClassifier) or isinstance(estimator, CatBoostRegressor):
                 if cat_features is not None:
-                    for cat_feature in cat_features:
-                        if cat_feature not in X.columns:
-                            logger.error(
-                                f"Client cat_feature `{cat_feature}` not found in X columns: {X.columns.to_list()}"
-                            )
                     estimator_copy.set_params(
                         cat_features=[X.columns.get_loc(cat_feature) for cat_feature in cat_features]
                     )
@@ -651,14 +645,9 @@ class OtherEstimatorWrapper(EstimatorWrapper):
 
 
 def validate_scoring_argument(scoring: Union[Callable, str, None]):
+    # TODO validate that if it is Callable then it accepts 3 arguments
     if isinstance(scoring, str) and scoring is not None:
         _get_scorer_by_name(scoring)
-    elif isinstance(scoring, Callable):
-        spec = inspect.getfullargspec(scoring)
-        if len(spec.args) < 3:
-            raise ValidationError(
-                f"Invalid scoring function passed {scoring}. It should accept 3 input arguments: estimator, X, y"
-            )
 
 
 def _get_scorer_by_name(scoring: str) -> Tuple[Callable, str, int]:

upgini/resource_bundle/strings.properties

@@ -38,7 +38,6 @@ loss_selection_warn=\nWARNING: Loss `{0}` is not supported for feature selection
 loss_calc_metrics_warn=\nWARNING: Loss `{0}` is not supported for metrics calculation with {1}
 multivariate_timeseries_detected=\nWARNING: Multivariate TimeSeries detected. Blocked time series cross-validation split selected.\nMore details: https://github.com/upgini/upgini#-time-series-prediction-support
 group_k_fold_in_classification=\nWARNING: Using group K-fold cross-validation split for classification task.
-current_date_added=\nWARNING: No date/datetime column was detected in X to be used as a search key. The current date will be used to match the latest version of data sources
 
 # Errors
 failed_search_by_task_id=Failed to retrieve the specified search results
@@ -159,7 +158,7 @@ dataset_invalid_multiclass_target=Unexpected dtype of target for multiclass task
 dataset_invalid_regression_target=Unexpected dtype of target for regression task type: {}. Expected float
 dataset_invalid_timeseries_target=Unexpected dtype of target for timeseries task type: {}. Expected float
 dataset_to_many_multiclass_targets=The number of target classes {} exceeds the allowed threshold: {}. Please, correct your data and try again
-dataset_rarest_class_less_min=Count of rows with the rarest class `{}` is {}, minimum count must be > {} for each class\nPlease, remove rows with rarest class from your dataframe
+dataset_rarest_class_less_min=Frequency of the rarest class `{}` is {}, minimum frequency must be > {} for each class\nPlease, remove rows with rarest class from your dataframe
 dataset_rarest_class_less_threshold=\nWARNING: Target is imbalanced and will be undersampled to the rarest class. Frequency of the rarest class `{}` is {}\nMinimum number of observations for each class to avoid undersampling {} ({}%)
 dataset_date_features=\nWARNING: Columns {} is a datetime or period type but not used as a search key, removed from X
 dataset_too_many_features=Too many features. Maximum number of features is {}

upgini/utils/track_info.py

@@ -55,7 +55,7 @@ def _get_execution_ide() -> str:
 def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optional[str] = None) -> dict:
     # default values
     track = {"ide": _get_execution_ide()}
-    ident_res = "https://api64.ipify.org"
+    ident_res = "https://api.ipify.org"
 
     try:
         track["hostname"] = socket.gethostname()
@@ -74,20 +74,17 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
             display(
                 Javascript(
                     """
-                    async function getVisitorId() {
-                        return import('https://upgini.github.io/upgini/js/a.js')
+                        import('https://upgini.github.io/upgini/js/a.js')
                             .then(FingerprintJS => FingerprintJS.load())
                             .then(fp => fp.get())
-                            .then(result => result.visitorId);
-                    }
+                            .then(result => window.visitorId = result.visitorId);
                     """
                 )
             )
-            track["visitorId"] = output.eval_js("getVisitorId()", timeout_sec=30)
+            track["visitorId"] = output.eval_js("window.visitorId", timeout_sec=10)
         except Exception as e:
             track["err"] = str(e)
-            if "visitorId" not in track:
-                track["visitorId"] = "None"
+            track["visitorId"] = "None"
         if client_ip:
             track["ip"] = client_ip
         else:
@@ -98,19 +95,16 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                 display(
                     Javascript(
                         f"""
-                        async function getIP() {{
-                            return fetch("{ident_res}")
+                            fetch("{ident_res}")
                                 .then(response => response.text())
-                                .then(data => data);
-                        }}
+                                .then(data => window.clientIP = data);
                         """
                     )
                 )
-                track["ip"] = output.eval_js("getIP()", timeout_sec=10)
+                track["ip"] = output.eval_js("window.clientIP", timeout_sec=10)
             except Exception as e:
                 track["err"] = str(e)
-                if "ip" not in track:
-                    track["ip"] = "0.0.0.0"
+                track["ip"] = "0.0.0.0"
 
     elif track["ide"] == "binder":
         try:
@@ -122,10 +116,8 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                 track["visitorId"] = sha256(os.environ["CLIENT_IP"].encode()).hexdigest()
         except Exception as e:
             track["err"] = str(e)
-            if "ip" not in track:
-                track["ip"] = "0.0.0.0"
-            if "visitorId" not in track:
-                track["visitorId"] = "None"
+            track["ip"] = "0.0.0.0"
+            track["visitorId"] = "None"
 
     elif track["ide"] == "kaggle":
         try:
@@ -144,8 +136,8 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                     raise Exception(err)
         except Exception as e:
             track["err"] = str(e)
-            if "visitorId" not in track:
-                track["visitorId"] = "None"
+            track["ip"] = "0.0.0.0"
+            track["visitorId"] = "None"
     else:
         try:
             if client_ip:
@@ -158,9 +150,5 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                 track["visitorId"] = sha256(str(getnode()).encode()).hexdigest()
         except Exception as e:
             track["err"] = str(e)
-            if "visitorId" not in track:
-                track["visitorId"] = "None"
-            if "ip" not in track:
-                track["ip"] = "0.0.0.0"
 
     return track

{upgini-1.1.274.dist-info → upgini-1.1.274a2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.274
+Version: 1.1.274a2
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -28,7 +28,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: python-dateutil >=2.8.0
 Requires-Dist: requests >=2.8.0
-Requires-Dist: pandas <3.0.0,>=1.1.0
+Requires-Dist: pandas <2.1.0,>=1.1.0
 Requires-Dist: numpy >=1.19.0
 Requires-Dist: scikit-learn >=1.3.0
 Requires-Dist: pydantic <2.0.0,>=1.8.2

{upgini-1.1.274.dist-info → upgini-1.1.274a2.dist-info}/RECORD

@@ -2,11 +2,11 @@ upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
 upgini/dataset.py,sha256=xb4gIANyGbdcuM8Awyq2pJPiH_3k_LEbETApJgAoRBA,45529
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=A03SPhpJNxpZiAq6aSKiVOG6mqo3YrZ9MQRwkk8_OSg,176071
+upgini/features_enricher.py,sha256=eQqiCXs-JM8cDQiXY6VEN1--oIWY3HsqxKrjNnF7rAU,174722
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=zaO86LBBLmkieGbgYifk29eVoPCxXimZQ8YkQtKcM0I,42244
 upgini/metadata.py,sha256=fwVxtkR6Mn4iRoOqV6BfMJvJrx65I3YwZUMbZjhPyOI,9673
-upgini/metrics.py,sha256=tGzdn0jgup86OlH_GS4eoza8ZJZ9wgaJr7SaX3Upwzo,29652
+upgini/metrics.py,sha256=U3VJKbKmuWACqI4jTcszXo0WqeXFtV8bWyY9VLBL-rw,29129
 upgini/search_task.py,sha256=tmJ17WUxv3J5NWrYUJB_NKdZ792Ifz8Z8UnDXeQnpss,17077
 upgini/spinner.py,sha256=Dm1dQ5F_z_Ua2odLxZX7OypcOX9tSx_vE5MGaKtUmfw,1118
 upgini/version_validator.py,sha256=rDIncP6BEko4J2F2hUcMOtKm_vZbI4ICWcNcw8hrwM4,1400
@@ -15,7 +15,7 @@ upgini/ads_management/ads_manager.py,sha256=fP4Yqx3h2Snw5X335TbXEwFoupq1RYsE7y0P
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operands.py,sha256=H66wqVLD-H9k8A4-q2wslhV9QaNxlb49f8YiT0Xfkps,2356
 upgini/autofe/binary.py,sha256=f8LQqZi9zyaMUAv-jASMmWNA_vT05ncYCjZq0qx3USs,3972
-upgini/autofe/date.py,sha256=408p8P2OTPM2D3LsEGGtaiCepKGgM1BbOCQNRzAmI6c,4223
+upgini/autofe/date.py,sha256=_6RoEJZ5Kf-Q_aMOFucS6YSIZpCcelgpw-edV4qmRIM,3935
 upgini/autofe/feature.py,sha256=2FQRGtIumNz60hFAjfLReaY18SI7HxzYZOoC5avzSjQ,11847
 upgini/autofe/groupby.py,sha256=iXRfOmOc84ooSzRhsh9GmmG7rTafX0-ekXko8s9Qs68,3089
 upgini/autofe/operand.py,sha256=dhtToPDGWtP_0u_RjayUpezJJZAgq_TzNbPH0bI9OXI,2805
@@ -29,7 +29,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/phone_normalizer.py,sha256=_SYMX4GTgwzRXArK54Jp3vUBE5d4jZxSVyze-0tqzg0,9996
 upgini/resource_bundle/__init__.py,sha256=hdvbqL0b0xMWbY6-kiYGsW1ro2GMiWpxxsO9uCv-h9Q,8379
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=1O779a0-Ai0j7W-Z5AznvjuV69YkJvgGhJda-6VMLOQ,26287
+upgini/resource_bundle/strings.properties,sha256=TM9OykiEXNpcgFN3DpqBGbQs4N9m4mzHBn-k6aazc30,26111
 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=CC-DvPbrN7zp5--SVFuUqkVmdWM_5F7R0Do98ETV82U,6421
@@ -54,10 +54,10 @@ upgini/utils/postal_code_utils.py,sha256=_8CR9tBqsPptQsmMUvnrCAmBaMIQSWH3JfJ4ly3
 upgini/utils/progress_bar.py,sha256=iNXyqT3vKCeHpfiG5HHwr7Lk2cTtKViM93Fl8iZnjGc,1564
 upgini/utils/sklearn_ext.py,sha256=e1aMNXk1zUt7uFnl0FcUF0zOnaXSE7z5xBHmJPknUVs,44014
 upgini/utils/target_utils.py,sha256=9K67tkY7LWhQMO-vbbPqBaO-KriAmg_6fVz5RQRaLQc,7802
-upgini/utils/track_info.py,sha256=p8gmuHhLamZF5JG7K9DeK-PcytQhlFCR29lyRr-wq_U,5665
+upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.274.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.274.dist-info/METADATA,sha256=RwxLyA9AsUogY8ky3LmH6m6eWEp3CO0drCn9SXC7EHI,48156
-upgini-1.1.274.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-upgini-1.1.274.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.274.dist-info/RECORD,,
+upgini-1.1.274a2.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.274a2.dist-info/METADATA,sha256=bjcE365HG_llg9ozhC4TSFN2-bemJxgLzCQrX6O8R_M,48158
+upgini-1.1.274a2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+upgini-1.1.274a2.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.274a2.dist-info/RECORD,,