upgini 1.1.273__tar.gz → 1.1.274__tar.gz

{upgini-1.1.273/src/upgini.egg-info → upgini-1.1.274}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.273
+Version: 1.1.274
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -26,6 +26,19 @@ Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Requires-Python: >=3.8,<3.11
 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: numpy>=1.19.0
+Requires-Dist: scikit-learn>=1.3.0
+Requires-Dist: pydantic<2.0.0,>=1.8.2
+Requires-Dist: fastparquet>=0.8.1
+Requires-Dist: python-json-logger>=2.0.2
+Requires-Dist: catboost>=1.0.3
+Requires-Dist: lightgbm>=3.3.2
+Requires-Dist: pyjwt>=2.8.0
+Requires-Dist: xhtml2pdf==0.2.11
+Requires-Dist: ipywidgets>=8.1.0
 
 
 <!-- <h2 align="center"> <a href="https://upgini.com/">Upgini</a> : low-code feature search and enrichment library for machine learning </h2> -->

{upgini-1.1.273 → upgini-1.1.274}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.273"
+version = "1.1.274"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(
@@ -77,7 +77,7 @@ try:
         install_requires=[
             "python-dateutil>=2.8.0",
             "requests>=2.8.0",
-            "pandas>=1.1.0,<2.0.0",
+            "pandas>=1.1.0,<3.0.0",
             "numpy>=1.19.0",
             "scikit-learn>=1.3.0",
             "pydantic>=1.8.2,<2.0.0",

{upgini-1.1.273 → upgini-1.1.274}/src/upgini/autofe/date.py

@@ -2,6 +2,7 @@ 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
 
@@ -46,6 +47,7 @@ class DateDiffType2(PandasOperand, DateDiffMixin):
         future = right + (left.dt.year - right.dt.year).apply(
             lambda y: np.datetime64("NaT") if np.isnan(y) else pd.tseries.offsets.DateOffset(years=y)
         )
+        future = pd.to_datetime(future)
         before = future[future < left]
         future[future < left] = before + pd.tseries.offsets.DateOffset(years=1)
         diff = (future - left) / np.timedelta64(1, self.diff_unit)
@@ -72,8 +74,13 @@ class DateListDiff(PandasOperand, DateDiffMixin):
 
         return pd.Series(left - right.values).apply(lambda x: self._agg(self._diff(x)))
 
-    def _diff(self, x):
-        x = x / np.timedelta64(1, self.diff_unit)
+    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)
         return x[x > 0]
 
     def _agg(self, x):

{upgini-1.1.273 → upgini-1.1.274}/src/upgini/data_source/data_source_publisher.py

@@ -48,6 +48,7 @@ class DataSourcePublisher:
         data_table_uri: str,
         search_keys: Dict[str, SearchKey],
         update_frequency: str,
+        exclude_from_autofe_generation: Optional[List[str]],
         secondary_search_keys: Optional[Dict[str, SearchKey]] = None,
         sort_column: Optional[str] = None,
         date_format: Optional[str] = None,
@@ -57,7 +58,6 @@ class DataSourcePublisher:
         join_date_abs_limit_days: Optional[int] = None,
         features_for_embeddings: Optional[List[str]] = DEFAULT_GENERATE_EMBEDDINGS,
         data_table_id_to_replace: Optional[str] = None,
-        exclude_from_autofe_generation: Optional[List[str]] = None,
         _force_generation=False,
         _silent=False,
     ) -> str:

{upgini-1.1.273 → upgini-1.1.274}/src/upgini/features_enricher.py

@@ -1,4 +1,5 @@
 import dataclasses
+import datetime
 import gc
 import hashlib
 import itertools
@@ -146,6 +147,7 @@ class FeaturesEnricher(TransformerMixin):
     """
 
     TARGET_NAME = "target"
+    CURRENT_DATE = "current_date"
     RANDOM_STATE = 42
     CALCULATE_METRICS_THRESHOLD = 50_000_000
     CALCULATE_METRICS_MIN_THRESHOLD = 500
@@ -207,6 +209,7 @@ class FeaturesEnricher(TransformerMixin):
         client_ip: Optional[str] = None,
         client_visitorid: Optional[str] = None,
         custom_bundle_config: Optional[str] = None,
+        add_date_if_missing: bool = True,
         **kwargs,
     ):
         self.bundle = get_custom_bundle(custom_bundle_config)
@@ -317,6 +320,7 @@ class FeaturesEnricher(TransformerMixin):
         self.raise_validation_error = raise_validation_error
         self.exclude_columns = exclude_columns
         self.baseline_score_column = baseline_score_column
+        self.add_date_if_missing = add_date_if_missing
 
     def _get_api_key(self):
         return self._api_key
@@ -420,6 +424,9 @@ 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
@@ -813,6 +820,7 @@ 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)
@@ -864,22 +872,9 @@ class FeaturesEnricher(TransformerMixin):
                     self.__display_support_link(msg)
                     return None
 
-                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))
+                cat_features, search_keys_for_metrics = self._get_client_cat_features(
+                    estimator, effective_X, self.search_keys
+                )
 
                 prepared_data = self._prepare_data_for_metrics(
                     trace_id=trace_id,
@@ -894,6 +889,7 @@ 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
@@ -1269,6 +1265,29 @@ 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,
@@ -1283,6 +1302,7 @@ 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
@@ -1340,9 +1360,8 @@ class FeaturesEnricher(TransformerMixin):
 
         # Detect and drop high cardinality columns in train
         columns_with_high_cardinality = FeaturesValidator.find_high_cardinality(fitting_X)
-        columns_with_high_cardinality = [
-            c for c in columns_with_high_cardinality if c not in (self.generate_features or [])
-        ]
+        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]
         if len(columns_with_high_cardinality) > 0:
             self.logger.warning(
                 f"High cardinality columns {columns_with_high_cardinality} will be dropped for metrics calculation"
@@ -1804,10 +1823,11 @@ class FeaturesEnricher(TransformerMixin):
         else:
             features_section = ""
 
-        api_example = f"""curl 'https://inference-upgini.azurewebsites.net/api/http_inference_trigger' \\
+        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}' \\
     -H 'Authorization: {self.api_key}' \\
     -H 'Content-Type: application/json' \\
-    -d '{{"search_id": "{self._search_task.search_task_id}", "search_keys": {keys}{features_section}}}'"""
+    -d '{{"search_keys": {keys}{features_section}}}'"""
         return api_example
 
     def _get_copy_of_runtime_parameters(self) -> RuntimeParameters:
@@ -1902,6 +1922,8 @@ class FeaturesEnricher(TransformerMixin):
                 generated_features.extend(converter.generated_features)
             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)
             email_column = self._get_email_column(search_keys)
             hem_column = self._get_hem_column(search_keys)
             email_converted_to_hem = False
@@ -2220,9 +2242,7 @@ class FeaturesEnricher(TransformerMixin):
         self.fit_search_keys = self.search_keys.copy()
         self.fit_search_keys = self.__prepare_search_keys(validated_X, self.fit_search_keys, is_demo_dataset)
 
-        validate_dates_distribution(
-            validated_X, self.fit_search_keys, self.logger, self.bundle, self.warning_counter
-        )
+        validate_dates_distribution(validated_X, self.fit_search_keys, self.logger, self.bundle, self.warning_counter)
 
         maybe_date_column = self._get_date_column(self.fit_search_keys)
         has_date = maybe_date_column is not None
@@ -2273,6 +2293,8 @@ class FeaturesEnricher(TransformerMixin):
             self.fit_generated_features.extend(converter.generated_features)
         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)
         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
@@ -2853,6 +2875,25 @@ class FeaturesEnricher(TransformerMixin):
             if t in [SearchKey.DATE, SearchKey.DATETIME]:
                 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
+
     @staticmethod
     def _get_group_columns(df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> List[str]:
         return [
@@ -2903,9 +2944,7 @@ class FeaturesEnricher(TransformerMixin):
                 [
                     c
                     for c in df.columns
-                    if c not in sort_columns
-                    and c not in sort_exclude_columns
-                    and df[c].nunique() > 1
+                    if c not in sort_columns and c not in sort_exclude_columns and df[c].nunique() > 1
                 ]
                 # [
                 #     sk

{upgini-1.1.273 → upgini-1.1.274}/src/upgini/metrics.py

@@ -1,3 +1,4 @@
+import inspect
 import logging
 import re
 from copy import deepcopy
@@ -381,6 +382,11 @@ 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]
                     )
@@ -647,6 +653,12 @@ class OtherEstimatorWrapper(EstimatorWrapper):
 def validate_scoring_argument(scoring: Union[Callable, str, None]):
     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-1.1.273 → upgini-1.1.274}/src/upgini/normalizer/phone_normalizer.py

@@ -1,7 +1,7 @@
 from typing import Optional
 
 import pandas as pd
-from pandas.api.types import is_float_dtype, is_int64_dtype, is_string_dtype
+from pandas.api.types import is_float_dtype, is_int64_dtype, is_string_dtype, is_object_dtype
 
 from upgini.errors import ValidationError
 
@@ -44,7 +44,7 @@ class PhoneNormalizer:
         Method will remove all non numeric chars from string and convert it to int.
         None will be set for phone numbers that couldn"t be converted to int
         """
-        if is_string_dtype(self.df[self.phone_column_name]):
+        if is_string_dtype(self.df[self.phone_column_name]) or is_object_dtype(self.df[self.phone_column_name]):
             convert_func = self.phone_str_to_int_safe
         elif is_float_dtype(self.df[self.phone_column_name]):
             convert_func = self.phone_float_to_int_safe

{upgini-1.1.273 → upgini-1.1.274}/src/upgini/resource_bundle/strings.properties

@@ -38,6 +38,7 @@ 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
@@ -158,7 +159,7 @@ 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=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_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_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-1.1.273 → upgini-1.1.274}/src/upgini/utils/datetime_utils.py

@@ -100,6 +100,9 @@ class DateTimeSearchKeyConverter:
                 msg = self.bundle.get("unsupported_date_type").format(self.date_column)
                 self.logger.warning(msg)
                 raise ValidationError(msg)
+        else:
+            df[self.date_column] = df[self.date_column].astype("string").apply(self.clean_date)
+            df[self.date_column] = self.parse_date(df)
 
         # If column with date is datetime then extract seconds of the day and minute of the hour
         # as additional features

{upgini-1.1.273 → upgini-1.1.274}/src/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://api.ipify.org"
+    ident_res = "https://api64.ipify.org"
 
     try:
         track["hostname"] = socket.gethostname()
@@ -74,17 +74,20 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
             display(
                 Javascript(
                     """
-                        import('https://upgini.github.io/upgini/js/a.js')
+                    async function getVisitorId() {
+                        return import('https://upgini.github.io/upgini/js/a.js')
                             .then(FingerprintJS => FingerprintJS.load())
                             .then(fp => fp.get())
-                            .then(result => window.visitorId = result.visitorId);
+                            .then(result => result.visitorId);
+                    }
                     """
                 )
             )
-            track["visitorId"] = output.eval_js("window.visitorId", timeout_sec=10)
+            track["visitorId"] = output.eval_js("getVisitorId()", timeout_sec=30)
         except Exception as e:
             track["err"] = str(e)
-            track["visitorId"] = "None"
+            if "visitorId" not in track:
+                track["visitorId"] = "None"
         if client_ip:
             track["ip"] = client_ip
         else:
@@ -95,16 +98,19 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                 display(
                     Javascript(
                         f"""
-                            fetch("{ident_res}")
+                        async function getIP() {{
+                            return fetch("{ident_res}")
                                 .then(response => response.text())
-                                .then(data => window.clientIP = data);
+                                .then(data => data);
+                        }}
                         """
                     )
                 )
-                track["ip"] = output.eval_js("window.clientIP", timeout_sec=10)
+                track["ip"] = output.eval_js("getIP()", timeout_sec=10)
             except Exception as e:
                 track["err"] = str(e)
-                track["ip"] = "0.0.0.0"
+                if "ip" not in track:
+                    track["ip"] = "0.0.0.0"
 
     elif track["ide"] == "binder":
         try:
@@ -116,8 +122,10 @@ 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)
-            track["ip"] = "0.0.0.0"
-            track["visitorId"] = "None"
+            if "ip" not in track:
+                track["ip"] = "0.0.0.0"
+            if "visitorId" not in track:
+                track["visitorId"] = "None"
 
     elif track["ide"] == "kaggle":
         try:
@@ -136,8 +144,8 @@ def get_track_metrics(client_ip: Optional[str] = None, client_visitorid: Optiona
                     raise Exception(err)
         except Exception as e:
             track["err"] = str(e)
-            track["ip"] = "0.0.0.0"
-            track["visitorId"] = "None"
+            if "visitorId" not in track:
+                track["visitorId"] = "None"
     else:
         try:
             if client_ip:
@@ -150,5 +158,9 @@ 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-1.1.273 → upgini-1.1.274/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.273
+Version: 1.1.274
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -26,6 +26,19 @@ Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Requires-Python: >=3.8,<3.11
 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: numpy>=1.19.0
+Requires-Dist: scikit-learn>=1.3.0
+Requires-Dist: pydantic<2.0.0,>=1.8.2
+Requires-Dist: fastparquet>=0.8.1
+Requires-Dist: python-json-logger>=2.0.2
+Requires-Dist: catboost>=1.0.3
+Requires-Dist: lightgbm>=3.3.2
+Requires-Dist: pyjwt>=2.8.0
+Requires-Dist: xhtml2pdf==0.2.11
+Requires-Dist: ipywidgets>=8.1.0
 
 
 <!-- <h2 align="center"> <a href="https://upgini.com/">Upgini</a> : low-code feature search and enrichment library for machine learning </h2> -->

{upgini-1.1.273 → upgini-1.1.274}/src/upgini.egg-info/requires.txt

@@ -1,6 +1,6 @@
 python-dateutil>=2.8.0
 requests>=2.8.0
-pandas<2.0.0,>=1.1.0
+pandas<3.0.0,>=1.1.0
 numpy>=1.19.0
 scikit-learn>=1.3.0
 pydantic<2.0.0,>=1.8.2

{upgini-1.1.273 → upgini-1.1.274}/tests/test_autofe_operands.py

@@ -30,7 +30,8 @@ def test_date_diff_type2():
 
     operand = DateDiffType2(left_unit="s")
     expected_result = pd.Series([61.0, 182.0])
-    assert_series_equal(operand.calculate_binary(df.date1, df.date2), expected_result)
+    actual = operand.calculate_binary(df.date1, df.date2)
+    assert_series_equal(actual, expected_result)
 
 
 def test_date_diff_list():

{upgini-1.1.273 → upgini-1.1.274}/tests/test_features_enricher.py

@@ -246,7 +246,7 @@ def test_eval_set_with_diff_order_of_columns(requests_mock: Mocker):
     eval1_df = df[10000:11000].reset_index(drop=True)
     eval1_features = eval1_df.drop(columns="target")
     # shuffle columns
-    eval1_features = eval1_features[set(eval1_features.columns)]
+    eval1_features = eval1_features[list(eval1_features.columns)]
     eval1_target = eval1_df["target"].reset_index(drop=True)
 
     eval2_df = df[11000:12000]
@@ -375,7 +375,7 @@ def test_saved_features_enricher(requests_mock: Mocker):
     url = "http://fake_url2"
 
     path_to_mock_features = os.path.join(
-        os.path.dirname(os.path.realpath(__file__)), "test_data/binary/validation_features.parquet"
+        os.path.dirname(os.path.realpath(__file__)), "test_data/binary/validation_features_v3.parquet"
     )
 
     mock_default_requests(requests_mock, url)
@@ -462,7 +462,7 @@ def test_saved_features_enricher(requests_mock: Mocker):
             segment_header: [train_segment, eval_1_segment, eval_2_segment],
             rows_header: [10000, 1000, 1000],
             target_mean_header: [0.5044, 0.487, 0.486],
-            enriched_gini: [-0.000136, 0.000000, -0.003728],
+            enriched_gini: [0.021830, -0.006607, -0.018483],
         }
     )
     print("Expected metrics: ")
@@ -487,16 +487,13 @@ def test_saved_features_enricher(requests_mock: Mocker):
     train_random_indices = random.choice(train_target.index, size=9000, replace=False)
     train_target.loc[train_random_indices] = 0
 
-    metrics = enricher.calculate_metrics(
-        train_features,
-        train_target
-    )
+    metrics = enricher.calculate_metrics(train_features, train_target)
     expected_metrics = pd.DataFrame(
         {
             segment_header: [train_segment],
             rows_header: [10000],
             target_mean_header: [0.049],
-            enriched_gini: [0.000985],
+            enriched_gini: [0.054454],
         }
     )
     print("Expected metrics: ")
@@ -2230,8 +2227,9 @@ def test_email_search_key(requests_mock: Mocker):
             "hashed_email_64ff8c",
             "email_one_domain_3b0a68",
             "email_domain_10c73f",
+            "current_date_b993c4",
         }
-        assert {"hashed_email_64ff8c", "email_one_domain_3b0a68"} == {
+        assert {"hashed_email_64ff8c", "email_one_domain_3b0a68", "current_date_b993c4"} == {
             sk for sublist in self.search_keys for sk in sublist
         }
         raise TestException()
@@ -2276,10 +2274,18 @@ def test_composit_index_search_key(requests_mock: Mocker):
         **kwargs,
     ):
         self.validate()
-        assert set(self.columns.to_list()) == {"system_record_id", "country_aff64e", "postal_code_13534a", "target"}
+        assert set(self.columns.to_list()) == {
+            "system_record_id",
+            "country_aff64e",
+            "postal_code_13534a",
+            "current_date_b993c4",
+            "target",
+        }
         assert "country_aff64e" in self.columns
         assert "postal_code_13534a"
-        assert {"country_aff64e", "postal_code_13534a"} == {sk for sublist in self.search_keys for sk in sublist}
+        assert {"country_aff64e", "postal_code_13534a", "current_date_b993c4"} == {
+            sk for sublist in self.search_keys for sk in sublist
+        }
         # assert "country_fake_a" in self.columns
         # assert "postal_code_fake_a" in self.columns
         # assert {"country_fake_a", "postal_code_fake_a"} == {sk for sublist in self.search_keys for sk in sublist}
@@ -2652,5 +2658,4 @@ class DataFrameWrapper:
 
 
 class TestException(Exception):
-    def __init__(self):
-        super().__init__()
+    pass