upgini 1.2.29a3__py3-none-any.whl → 1.2.29a5__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.29a3"
+__version__ = "1.2.29a5"

upgini/features_enricher.py

@@ -2,7 +2,6 @@ import dataclasses
 import datetime
 import gc
 import hashlib
-import itertools
 import logging
 import numbers
 import os
@@ -54,6 +53,7 @@ from upgini.metadata import (
     SYSTEM_RECORD_ID,
     TARGET,
     CVType,
+    FeaturesMetadataV2,
     FileColumnMeaningType,
     ModelTaskType,
     RuntimeParameters,
@@ -95,6 +95,7 @@ from upgini.utils.email_utils import (
     EmailSearchKeyConverter,
     EmailSearchKeyDetector,
 )
+from upgini.utils.feature_info import FeatureInfo, _round_shap_value
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.format import Format
 from upgini.utils.ip_utils import IpSearchKeyConverter
@@ -224,6 +225,7 @@ class FeaturesEnricher(TransformerMixin):
         client_visitorid: Optional[str] = None,
         custom_bundle_config: Optional[str] = None,
         add_date_if_missing: bool = True,
+        select_features: bool = False,
         **kwargs,
     ):
         self.bundle = get_custom_bundle(custom_bundle_config)
@@ -277,8 +279,11 @@ class FeaturesEnricher(TransformerMixin):
         self._relevant_data_sources_wo_links: pd.DataFrame = self.EMPTY_DATA_SOURCES
         self.metrics: Optional[pd.DataFrame] = None
         self.feature_names_ = []
+        self.client_feature_names_ = []
         self.feature_importances_ = []
         self.search_id = search_id
+        self.select_features = select_features
+
         if search_id:
             search_task = SearchTask(search_id, rest_client=self.rest_client, logger=self.logger)
 
@@ -999,9 +1004,10 @@ class FeaturesEnricher(TransformerMixin):
                             text_features=self.generate_features,
                             has_date=has_date,
                         )
-                        etalon_metric, _ = baseline_estimator.cross_val_predict(
+                        etalon_cv_result = baseline_estimator.cross_val_predict(
                             fitting_X, y_sorted, self.baseline_score_column
                         )
+                        etalon_metric = etalon_cv_result.get_display_metric()
                         if etalon_metric is None:
                             self.logger.info(
                                 f"Baseline {metric} on train client features is None (maybe all features was removed)"
@@ -1033,9 +1039,9 @@ class FeaturesEnricher(TransformerMixin):
                             text_features=self.generate_features,
                             has_date=has_date,
                         )
-                        enriched_metric, enriched_shaps = enriched_estimator.cross_val_predict(
-                            fitting_enriched_X, enriched_y_sorted
-                        )
+                        enriched_cv_result = enriched_estimator.cross_val_predict(fitting_enriched_X, enriched_y_sorted)
+                        enriched_metric = enriched_cv_result.get_display_metric()
+                        enriched_shaps = enriched_cv_result.shap_values
 
                         if enriched_shaps is not None:
                             self._update_shap_values(enriched_shaps)
@@ -1048,7 +1054,7 @@ class FeaturesEnricher(TransformerMixin):
                         else:
                             self.logger.info(f"Enriched {metric} on train combined features: {enriched_metric}")
                         if etalon_metric is not None and enriched_metric is not None:
-                            uplift = (enriched_metric - etalon_metric) * multiplier
+                            uplift = (enriched_cv_result.metric - etalon_cv_result.metric) * multiplier
 
                     train_metrics = {
                         self.bundle.get("quality_metrics_segment_header"): self.bundle.get(
@@ -1091,9 +1097,10 @@ class FeaturesEnricher(TransformerMixin):
                                     f"Calculate baseline {metric} on eval set {idx + 1} "
                                     f"on client features: {eval_X_sorted.columns.to_list()}"
                                 )
-                                etalon_eval_metric = baseline_estimator.calculate_metric(
+                                etalon_eval_results = baseline_estimator.calculate_metric(
                                     eval_X_sorted, eval_y_sorted, self.baseline_score_column
                                 )
+                                etalon_eval_metric = etalon_eval_results.get_display_metric()
                                 self.logger.info(
                                     f"Baseline {metric} on eval set {idx + 1} client features: {etalon_eval_metric}"
                                 )
@@ -1105,9 +1112,10 @@ class FeaturesEnricher(TransformerMixin):
                                     f"Calculate enriched {metric} on eval set {idx + 1} "
                                     f"on combined features: {enriched_eval_X_sorted.columns.to_list()}"
                                 )
-                                enriched_eval_metric = enriched_estimator.calculate_metric(
+                                enriched_eval_results = enriched_estimator.calculate_metric(
                                     enriched_eval_X_sorted, enriched_eval_y_sorted
                                 )
+                                enriched_eval_metric = enriched_eval_results.get_display_metric()
                                 self.logger.info(
                                     f"Enriched {metric} on eval set {idx + 1} combined features: {enriched_eval_metric}"
                                 )
@@ -1115,7 +1123,7 @@ class FeaturesEnricher(TransformerMixin):
                                 enriched_eval_metric = None
 
                             if etalon_eval_metric is not None and enriched_eval_metric is not None:
-                                eval_uplift = (enriched_eval_metric - etalon_eval_metric) * multiplier
+                                eval_uplift = (enriched_eval_results.metric - etalon_eval_results.metric) * multiplier
                             else:
                                 eval_uplift = None
 
@@ -1198,9 +1206,7 @@ class FeaturesEnricher(TransformerMixin):
 
     def _update_shap_values(self, new_shaps: Dict[str, float]):
         new_shaps = {
-            feature: self._round_shap_value(shap)
-            for feature, shap in new_shaps.items()
-            if feature in self.feature_names_
+            feature: _round_shap_value(shap) for feature, shap in new_shaps.items() if feature in self.feature_names_
         }
         features_importances = list(new_shaps.items())
         features_importances.sort(key=lambda m: (-m[1], m[0]))
@@ -1437,7 +1443,8 @@ class FeaturesEnricher(TransformerMixin):
         client_features = [
             c
             for c in X_sampled.columns.to_list()
-            if c
+            if (not self.select_features or c in self.feature_names_)
+            and c
             not in (
                 excluding_search_keys
                 + list(self.fit_dropped_features)
@@ -2063,7 +2070,9 @@ class FeaturesEnricher(TransformerMixin):
 
             is_demo_dataset = hash_input(validated_X) in DEMO_DATASET_HASHES
 
-            columns_to_drop = [c for c in validated_X.columns if c in self.feature_names_]
+            columns_to_drop = [
+                c for c in validated_X.columns if c in self.feature_names_ and c not in self.client_feature_names_
+            ]
             if len(columns_to_drop) > 0:
                 msg = self.bundle.get("x_contains_enriching_columns").format(columns_to_drop)
                 self.logger.warning(msg)
@@ -3490,15 +3499,7 @@ class FeaturesEnricher(TransformerMixin):
 
         return result_train, result_eval_sets
 
-    @staticmethod
-    def _round_shap_value(shap: float) -> float:
-        if shap > 0.0 and shap < 0.0001:
-            return 0.0001
-        else:
-            return round(shap, 4)
-
     def __prepare_feature_importances(self, trace_id: str, x_columns: List[str], silent=False):
-        llm_source = "LLM with external data augmentation"
         if self._search_task is None:
             raise NotFittedError(self.bundle.get("transform_unfitted_enricher"))
         features_meta = self._search_task.get_all_features_metadata_v2()
@@ -3509,116 +3510,36 @@ class FeaturesEnricher(TransformerMixin):
         features_df = self._search_task.get_all_initial_raw_features(trace_id, metrics_calculation=True)
 
         self.feature_names_ = []
+        self.client_feature_names_ = []
         self.feature_importances_ = []
         features_info = []
         features_info_without_links = []
         internal_features_info = []
 
-        def list_or_single(lst: List[str], single: str):
-            return lst or ([single] if single else [])
-
-        def to_anchor(link: str, value: str) -> str:
-            if not value:
-                return ""
-            elif not link:
-                return value
-            elif value == llm_source:
-                return value
-            else:
-                return f"<a href='{link}' target='_blank' rel='noopener noreferrer'>{value}</a>"
-
-        def make_links(names: List[str], links: List[str]):
-            all_links = [to_anchor(link, name) for name, link in itertools.zip_longest(names, links)]
-            return ",".join(all_links)
-
         features_meta.sort(key=lambda m: (-m.shap_value, m.name))
         for feature_meta in features_meta:
             if feature_meta.name in original_names_dict.keys():
                 feature_meta.name = original_names_dict[feature_meta.name]
-            # Use only enriched features
+            # Use only important features
             if (
-                feature_meta.name in x_columns
-                or feature_meta.name == COUNTRY
-                or feature_meta.shap_value == 0.0
-                or feature_meta.name in self.fit_generated_features
+                (feature_meta.shap_value == 0.0)
+                or (feature_meta.name in self.fit_generated_features)
+                or (feature_meta.name == COUNTRY)
             ):
                 continue
 
-            feature_sample = []
-            self.feature_names_.append(feature_meta.name)
-            self.feature_importances_.append(self._round_shap_value(feature_meta.shap_value))
-            if feature_meta.name in features_df.columns:
-                feature_sample = np.random.choice(features_df[feature_meta.name].dropna().unique(), 3).tolist()
-                if len(feature_sample) > 0 and isinstance(feature_sample[0], float):
-                    feature_sample = [round(f, 4) for f in feature_sample]
-                feature_sample = [str(f) for f in feature_sample]
-                feature_sample = ", ".join(feature_sample)
-                if len(feature_sample) > 30:
-                    feature_sample = feature_sample[:30] + "..."
-
-            internal_provider = feature_meta.data_provider or "Upgini"
-            providers = list_or_single(feature_meta.data_providers, feature_meta.data_provider)
-            provider_links = list_or_single(feature_meta.data_provider_links, feature_meta.data_provider_link)
-            if providers:
-                provider = make_links(providers, provider_links)
-            else:
-                provider = to_anchor("https://upgini.com", "Upgini")
+            is_client_feature = feature_meta.name in x_columns
+            # In select_features mode we select also from etalon features and need to show them
+            if not self.select_features and is_client_feature:
+                continue
 
-            internal_source = feature_meta.data_source or (
-                llm_source
-                if not feature_meta.name.endswith("_country") and not feature_meta.name.endswith("_postal_code")
-                else ""
-            )
-            sources = list_or_single(feature_meta.data_sources, feature_meta.data_source)
-            source_links = list_or_single(feature_meta.data_source_links, feature_meta.data_source_link)
-            if sources:
-                source = make_links(sources, source_links)
-            else:
-                source = internal_source
+            self.feature_names_.append(feature_meta.name)
+            self.feature_importances_.append(_round_shap_value(feature_meta.shap_value))
 
-            internal_feature_name = feature_meta.name
-            if feature_meta.doc_link:
-                feature_name = to_anchor(feature_meta.doc_link, feature_meta.name)
-            else:
-                feature_name = internal_feature_name
-
-            features_info.append(
-                {
-                    self.bundle.get("features_info_name"): feature_name,
-                    self.bundle.get("features_info_shap"): self._round_shap_value(feature_meta.shap_value),
-                    self.bundle.get("features_info_hitrate"): feature_meta.hit_rate,
-                    self.bundle.get("features_info_value_preview"): feature_sample,
-                    self.bundle.get("features_info_provider"): provider,
-                    self.bundle.get("features_info_source"): source,
-                    self.bundle.get("features_info_update_frequency"): feature_meta.update_frequency,
-                }
-            )
-            features_info_without_links.append(
-                {
-                    self.bundle.get("features_info_name"): internal_feature_name,
-                    self.bundle.get("features_info_shap"): self._round_shap_value(feature_meta.shap_value),
-                    self.bundle.get("features_info_hitrate"): feature_meta.hit_rate,
-                    self.bundle.get("features_info_value_preview"): feature_sample,
-                    self.bundle.get("features_info_provider"): internal_provider,
-                    self.bundle.get("features_info_source"): internal_source,
-                    self.bundle.get("features_info_update_frequency"): feature_meta.update_frequency,
-                }
-            )
-            internal_features_info.append(
-                {
-                    self.bundle.get("features_info_name"): internal_feature_name,
-                    "feature_link": feature_meta.doc_link,
-                    self.bundle.get("features_info_shap"): self._round_shap_value(feature_meta.shap_value),
-                    self.bundle.get("features_info_hitrate"): feature_meta.hit_rate,
-                    self.bundle.get("features_info_value_preview"): feature_sample,
-                    self.bundle.get("features_info_provider"): internal_provider,
-                    "provider_link": feature_meta.data_provider_link,
-                    self.bundle.get("features_info_source"): internal_source,
-                    "source_link": feature_meta.data_source_link,
-                    self.bundle.get("features_info_commercial_schema"): feature_meta.commercial_schema or "",
-                    self.bundle.get("features_info_update_frequency"): feature_meta.update_frequency,
-                }
-            )
+            feature_info = FeatureInfo.from_metadata(feature_meta, features_df, is_client_feature)
+            features_info.append(feature_info.to_row(self.bundle))
+            features_info_without_links.append(feature_info.to_row_without_links(self.bundle))
+            internal_features_info.append(feature_info.to_internal_row(self.bundle))
 
         if len(features_info) > 0:
             self.features_info = pd.DataFrame(features_info)

upgini/metrics.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from dataclasses import dataclass
 import inspect
 import logging
 import re
@@ -210,6 +211,21 @@ SUPPORTED_CATBOOST_METRICS = {
 }
 
 
+@dataclass
+class _CrossValResults:
+    metric: Optional[float]
+    metric_std: Optional[float]
+    shap_values: Optional[Dict[str, float]]
+
+    def get_display_metric(self) -> Optional[str]:
+        if self.metric is None:
+            return None
+        elif self.metric_std is None:
+            return f"{self.metric:.3f}"
+        else:
+            return f"{self.metric:.3f} ± {self.metric_std:.3f}"
+
+
 class EstimatorWrapper:
     def __init__(
         self,
@@ -297,11 +313,11 @@ class EstimatorWrapper:
 
     def cross_val_predict(
         self, x: pd.DataFrame, y: np.ndarray, baseline_score_column: Optional[Any] = None
-    ) -> Tuple[Optional[float], Optional[Dict[str, float]]]:
+    ) -> _CrossValResults:
         x, y, groups, fit_params = self._prepare_to_fit(x, y)
 
         if x.shape[1] == 0:
-            return None
+            return _CrossValResults(metric=None, metric_std=None, shap_values=None)
 
         scorer = check_scoring(self.estimator, scoring=self.scorer)
 
@@ -326,7 +342,7 @@ class EstimatorWrapper:
 
             self.check_fold_metrics(metrics_by_fold)
 
-            metric = np.mean(metrics_by_fold) * self.multiplier
+            metric, metric_std = self._calculate_metric_from_folds(metrics_by_fold)
 
             splits = self.cv.split(x, y, groups)
 
@@ -351,7 +367,7 @@ class EstimatorWrapper:
         else:
             average_shap_values = None
 
-        return self.post_process_metric(metric), average_shap_values
+        return _CrossValResults(metric=metric, metric_std=metric_std, shap_values=average_shap_values)
 
     def process_shap_values(self, shap_values: Dict[str, float]) -> Dict[str, float]:
         return shap_values
@@ -367,17 +383,25 @@ class EstimatorWrapper:
             metric = 2 * metric - 1
         return metric
 
-    def calculate_metric(self, x: pd.DataFrame, y: np.ndarray, baseline_score_column: Optional[Any] = None) -> float:
+    def calculate_metric(
+        self, x: pd.DataFrame, y: np.ndarray, baseline_score_column: Optional[Any] = None
+    ) -> _CrossValResults:
         x, y, _ = self._prepare_to_calculate(x, y)
         if baseline_score_column is not None and self.metric_name == "GINI":
-            metric = roc_auc_score(y, x[baseline_score_column])
+            metric, metric_std = roc_auc_score(y, x[baseline_score_column]), None
         else:
             metrics = []
             for est in self.cv_estimators:
                 metrics.append(self.scorer(est, x, y))
 
-            metric = np.mean(metrics) * self.multiplier
-        return self.post_process_metric(metric)
+            metric, metric_std = self._calculate_metric_from_folds(metrics)
+        return _CrossValResults(metric=metric, metric_std=metric_std, shap_values=None)
+
+    def _calculate_metric_from_folds(self, metrics_by_fold: List[float]) -> Tuple[float, float]:
+        metrics_by_fold = [self.post_process_metric(m) for m in metrics_by_fold]
+        metric = np.mean(metrics_by_fold) * self.multiplier
+        metric_std = np.std(metrics_by_fold) * np.abs(self.multiplier)
+        return metric, metric_std
 
     @staticmethod
     def create(
@@ -591,7 +615,7 @@ class CatBoostWrapper(EstimatorWrapper):
 
     def cross_val_predict(
         self, x: pd.DataFrame, y: np.ndarray, baseline_score_column: Optional[Any] = None
-    ) -> Tuple[Optional[float], Optional[Dict[str, float]]]:
+    ) -> _CrossValResults:
         try:
             return super().cross_val_predict(x, y, baseline_score_column)
         except Exception as e:

upgini/utils/datetime_utils.py

@@ -111,7 +111,7 @@ class DateTimeSearchKeyConverter:
 
         # Define function to apply sine and cosine transformations
         def add_cyclical_features(df, column, period):
-            period_suffix = f"_{period}" if column != 'day_in_quarter' else ""
+            period_suffix = f"_{period}" if column != "day_in_quarter" else ""
             sin_feature = f"datetime_{column}_sin{period_suffix}"
             cos_feature = f"datetime_{column}_cos{period_suffix}"
             df[sin_feature] = np.sin(2 * np.pi * df[column] / period)
@@ -137,6 +137,7 @@ class DateTimeSearchKeyConverter:
         quarter_end_month = np.where(quarter == 4, 1, month + 3)
 
         end = pd.to_datetime({"year": quarter_end_year, "month": quarter_end_month, "day": 1})
+        end.index = df.index
 
         df["days_in_quarter"] = (end - start).dt.days
 

upgini/utils/feature_info.py

@@ -0,0 +1,172 @@
+from dataclasses import dataclass
+import itertools
+from typing import Dict, List
+
+import numpy as np
+import pandas as pd
+
+from upgini.metadata import FeaturesMetadataV2
+from upgini.resource_bundle import ResourceBundle
+
+
+LLM_SOURCE = "LLM with external data augmentation"
+
+
+@dataclass
+class FeatureInfo:
+    name: str
+    internal_name: str
+    rounded_shap: float
+    hitrate: float
+    value_preview: str
+    provider: str
+    internal_provider: str
+    source: str
+    internal_source: str
+    update_frequency: str
+    commercial_schema: str
+    doc_link: str
+    data_provider_link: str
+    data_source_link: str
+
+    @staticmethod
+    def from_metadata(feature_meta: FeaturesMetadataV2, data: pd.DataFrame, is_client_feature: bool) -> "FeatureInfo":
+        return FeatureInfo(
+            name=_get_name(feature_meta),
+            internal_name=_get_internal_name(feature_meta),
+            rounded_shap=_round_shap_value(feature_meta.shap_value),
+            hitrate=feature_meta.hit_rate,
+            value_preview=_get_feature_sample(feature_meta, data),
+            provider=_get_provider(feature_meta, is_client_feature),
+            internal_provider=_get_internal_provider(feature_meta, is_client_feature),
+            source=_get_source(feature_meta, is_client_feature),
+            internal_source=_get_internal_source(feature_meta, is_client_feature),
+            update_frequency=feature_meta.update_frequency,
+            commercial_schema=feature_meta.commercial_schema,
+            doc_link=feature_meta.doc_link,
+            data_provider_link=feature_meta.data_provider_link,
+            data_source_link=feature_meta.data_source_link,
+        )
+
+    def to_row(self, bundle: ResourceBundle) -> Dict[str, str]:
+        return {
+            bundle.get("features_info_name"): self.name,
+            bundle.get("features_info_shap"): self.rounded_shap,
+            bundle.get("features_info_hitrate"): self.hitrate,
+            bundle.get("features_info_value_preview"): self.value_preview,
+            bundle.get("features_info_provider"): self.provider,
+            bundle.get("features_info_source"): self.source,
+            bundle.get("features_info_update_frequency"): self.update_frequency,
+        }
+
+    def to_row_without_links(self, bundle: ResourceBundle) -> Dict[str, str]:
+        return {
+            bundle.get("features_info_name"): self.internal_name,
+            bundle.get("features_info_shap"): self.rounded_shap,
+            bundle.get("features_info_hitrate"): self.hitrate,
+            bundle.get("features_info_value_preview"): self.value_preview,
+            bundle.get("features_info_provider"): self.internal_provider,
+            bundle.get("features_info_source"): self.internal_source,
+            bundle.get("features_info_update_frequency"): self.update_frequency,
+        }
+
+    def to_internal_row(self, bundle: ResourceBundle) -> Dict[str, str]:
+        return {
+            bundle.get("features_info_name"): self.internal_name,
+            "feature_link": self.doc_link,
+            bundle.get("features_info_shap"): self.rounded_shap,
+            bundle.get("features_info_hitrate"): self.hitrate,
+            bundle.get("features_info_value_preview"): self.value_preview,
+            bundle.get("features_info_provider"): self.internal_provider,
+            "provider_link": self.data_provider_link,
+            bundle.get("features_info_source"): self.internal_source,
+            "source_link": self.data_source_link,
+            bundle.get("features_info_commercial_schema"): self.commercial_schema or "",
+            bundle.get("features_info_update_frequency"): self.update_frequency,
+        }
+
+
+def _get_feature_sample(feature_meta: FeaturesMetadataV2, data: pd.DataFrame) -> str:
+    if feature_meta.name in data.columns:
+        feature_sample = np.random.choice(data[feature_meta.name].dropna().unique(), 3).tolist()
+        if len(feature_sample) > 0 and isinstance(feature_sample[0], float):
+            feature_sample = [round(f, 4) for f in feature_sample]
+        feature_sample = [str(f) for f in feature_sample]
+        feature_sample = ", ".join(feature_sample)
+        if len(feature_sample) > 30:
+            feature_sample = feature_sample[:30] + "..."
+    else:
+        feature_sample = ""
+    return feature_sample
+
+
+def _get_name(feature_meta: FeaturesMetadataV2) -> str:
+    if feature_meta.doc_link:
+        return _to_anchor(feature_meta.doc_link, feature_meta.name)
+    else:
+        return feature_meta.name
+
+
+def _get_internal_name(feature_meta: FeaturesMetadataV2) -> str:
+    return feature_meta.name
+
+
+def _get_provider(feature_meta: FeaturesMetadataV2, is_client_feature: bool) -> str:
+    providers = _list_or_single(feature_meta.data_providers, feature_meta.data_provider)
+    provider_links = _list_or_single(feature_meta.data_provider_links, feature_meta.data_provider_link)
+    if providers:
+        provider = _make_links(providers, provider_links)
+    else:
+        provider = "" if is_client_feature else _to_anchor("https://upgini.com", "Upgini")
+    return provider
+
+
+def _get_internal_provider(feature_meta: FeaturesMetadataV2, is_client_feature: bool) -> str:
+    return "" if is_client_feature else (feature_meta.data_provider or "Upgini")
+
+
+def _get_source(feature_meta: FeaturesMetadataV2, is_client_feature: bool) -> str:
+    sources = _list_or_single(feature_meta.data_sources, feature_meta.data_source)
+    source_links = _list_or_single(feature_meta.data_source_links, feature_meta.data_source_link)
+    if sources:
+        source = _make_links(sources, source_links)
+    else:
+        source = _get_internal_source(feature_meta, is_client_feature)
+    return source
+
+
+def _get_internal_source(feature_meta: FeaturesMetadataV2, is_client_feature: bool) -> str:
+    return feature_meta.data_source or (
+        LLM_SOURCE
+        if not feature_meta.name.endswith("_country")
+        and not feature_meta.name.endswith("_postal_code")
+        and not is_client_feature
+        else ""
+    )
+
+
+def _list_or_single(lst: List[str], single: str):
+    return lst or ([single] if single else [])
+
+
+def _to_anchor(link: str, value: str) -> str:
+    if not value:
+        return ""
+    elif not link:
+        return value
+    elif value == LLM_SOURCE:
+        return value
+    else:
+        return f"<a href='{link}' target='_blank' rel='noopener noreferrer'>{value}</a>"
+
+
+def _make_links(names: List[str], links: List[str]):
+    all_links = [_to_anchor(link, name) for name, link in itertools.zip_longest(names, links)]
+    return ",".join(all_links)
+
+
+def _round_shap_value(shap: float) -> float:
+    if shap > 0.0 and shap < 0.0001:
+        return 0.0001
+    else:
+        return round(shap, 4)

{upgini-1.2.29a3.dist-info → upgini-1.2.29a5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.29a3
+Version: 1.2.29a5
 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-1.2.29a3.dist-info → upgini-1.2.29a5.dist-info}/RECORD

@@ -1,13 +1,13 @@
-upgini/__about__.py,sha256=g5pIOn0QIK7AYvLSK8cOcem2I_ZfKqz9pqOf071XTPQ,25
+upgini/__about__.py,sha256=kPhSfYAPCirj2ias-m_3Zttb3tZcyZpwrnKTzNizAdQ,25
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=iPFiMJtk4HF1ytw9wCQr8H9RfoOKj_TIo8XYZKWgcMc,31331
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=YYboYw--vCH9VerkTnCF3njztU3fVLrhlhU3NfBVJYQ,194302
+upgini/features_enricher.py,sha256=mEb1I_qnheDHNL2LEm-q9Yg3ZR_UPnavxe8H4JkVdvk,190405
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
-upgini/metrics.py,sha256=PoY1fq6XYAHNzn-rmnwRQZjCoVYP5bJNmKhR0ST2Txk,34588
+upgini/metrics.py,sha256=hr7UwLphbZ_FEglLuO2lzr_pFgxOJ4c3WBeg7H-fNqY,35521
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=h1GViOWzULy5vf6M4dpTJuIk-4V38UCrTY1sb9yLa5I,1594
@@ -43,11 +43,12 @@ upgini/utils/blocked_time_series.py,sha256=Uqr3vp4YqNclj2-PzEYqVy763GSXHn86sbpIl
 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=GiJhOXE4taDtC0PEBYloSN7jeLwN26AchOQnMSTUDpc,12996
+upgini/utils/datetime_utils.py,sha256=_uINXZUZ2MXvpGFBcxk_kZKMa1Umd8nhs8Iam-Gbwo0,13025
 upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
 upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
 upgini/utils/email_utils.py,sha256=j0Ug1R_0AnCg1Y92zIZ4XMwvKo3G5_pcOlBN1OH_gZs,5191
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
+upgini/utils/feature_info.py,sha256=Tp_2g5-rCjY4NpzKhzxwNxuqH5FFL8vG94OU5kH6wzk,6702
 upgini/utils/features_validator.py,sha256=1Xj2ir5LzzYiX3NH8o88c2J6RTTetaTwu0MhjLTyuvM,3378
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/ip_utils.py,sha256=Q6vb7Sr5Khx3Sq3eENjW2qCXKej_S5jZbneH6zEOkzQ,5171
@@ -58,7 +59,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=PU77nIhTz7IHbC4rpTpxrVxib6cdpRL9F1dhkjIffLY,10225
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.29a3.dist-info/METADATA,sha256=Ek9umOS0JA_zCCYMq7PWIcokbDM59DB0lbwQappDk1g,48580
-upgini-1.2.29a3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.29a3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.29a3.dist-info/RECORD,,
+upgini-1.2.29a5.dist-info/METADATA,sha256=ccMETf-MYrRSaOwmMEW0Smo9IjLU_b-LS6MTOvyilpc,48580
+upgini-1.2.29a5.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.29a5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.29a5.dist-info/RECORD,,

{upgini-1.2.29a3.dist-info → upgini-1.2.29a5.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