upgini 1.2.86.dev1__py3-none-any.whl → 1.2.87a3857.dev1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.86.dev1"
+__version__ = "1.2.87a3857.dev1"

upgini/features_enricher.py

@@ -1664,6 +1664,10 @@ class FeaturesEnricher(TransformerMixin):
                 enriched_eval_y_sorted,
             )
 
+        fitting_X, fitting_enriched_X, fitting_eval_set_dict = self._convert_id_columns_to_int(
+            fitting_X, fitting_enriched_X, fitting_eval_set_dict, columns_renaming
+        )
+
         return (
             validated_X,
             fitting_X,
@@ -1677,6 +1681,38 @@ class FeaturesEnricher(TransformerMixin):
             columns_renaming,
         )
 
+    def _convert_id_columns_to_int(
+        self,
+        fitting_X: pd.DataFrame,
+        fitting_enriched_X: pd.DataFrame,
+        fitting_eval_set_dict: Dict[int, Tuple[pd.DataFrame, pd.Series]],
+        columns_renaming: Dict[str, str] = {},
+    ) -> pd.DataFrame:
+        def _set_encoded(col_name: str, df: pd.DataFrame, slice: Tuple[int, int], combined_col: pd.Series):
+            df[col_name] = combined_col.iloc[slice[0] : slice[1]]
+            return slice[1]
+
+        inverse_columns_renaming = {v: k for k, v in columns_renaming.items()}
+
+        if self.id_columns:
+            self.logger.info(f"Convert id columns to int: {self.id_columns}")
+            for col in self.id_columns:
+                col = inverse_columns_renaming.get(col, col)
+                combined_col = pd.concat(
+                    [fitting_X[col], fitting_enriched_X[col]]
+                    + [eval_set_pair[0][col] for eval_set_pair in fitting_eval_set_dict.values()]
+                )
+                combined_col = combined_col.astype("category").cat.codes
+                slice_end = _set_encoded(col, fitting_X, (0, len(fitting_X)), combined_col)
+                slice_end = _set_encoded(
+                    col, fitting_enriched_X, (slice_end, slice_end + len(fitting_enriched_X)), combined_col
+                )
+                for eval_set_pair in fitting_eval_set_dict.values():
+                    slice_end = _set_encoded(
+                        col, eval_set_pair[0], (slice_end, slice_end + len(eval_set_pair[0])), combined_col
+                    )
+        return fitting_X, fitting_enriched_X, fitting_eval_set_dict
+
     @dataclass
     class _SampledDataForMetrics:
         X_sampled: pd.DataFrame
@@ -2204,10 +2240,12 @@ class FeaturesEnricher(TransformerMixin):
                         {"name": name, "value": key_example(sk_type)} for name in sk_meta.unnestKeyNames
                     ]
                 else:
-                    search_keys_with_values[sk_type.name] = [{
-                        "name": sk_meta.originalName,
-                        "value": key_example(sk_type),
-                    }]
+                    search_keys_with_values[sk_type.name] = [
+                        {
+                            "name": sk_meta.originalName,
+                            "value": key_example(sk_type),
+                        }
+                    ]
 
         keys_section = json.dumps(search_keys_with_values)
         features_for_transform = self._search_task.get_features_for_transform()
@@ -3927,7 +3965,7 @@ if response.status_code == 200:
         if features_meta is None:
             raise Exception(self.bundle.get("missing_features_meta"))
 
-        return [f.name for f in features_meta if f.type == "categorical"]
+        return [f.name for f in features_meta if f.type == "categorical" and f.name not in self.id_columns]
 
     def __prepare_feature_importances(
         self, trace_id: str, df: pd.DataFrame, updated_shaps: Optional[Dict[str, float]] = None, silent=False

upgini/metrics.py

@@ -314,7 +314,7 @@ class EstimatorWrapper:
         self.groups = groups
         self.text_features = text_features
         self.logger = logger or logging.getLogger()
-        self.droped_features = []
+        self.dropped_features = []
         self.converted_to_int = []
         self.converted_to_str = []
         self.converted_to_numeric = []
@@ -363,10 +363,11 @@ class EstimatorWrapper:
         x, y, groups = self._prepare_data(x, y, groups=self.groups)
 
         self.logger.info(f"Before preparing data columns: {x.columns.to_list()}")
-        self.droped_features = []
+        self.dropped_features = []
         self.converted_to_int = []
         self.converted_to_str = []
         self.converted_to_numeric = []
+
         for c in x.columns:
 
             if _get_unique_count(x[c]) < 2:
@@ -374,7 +375,7 @@ class EstimatorWrapper:
                 if c in self.cat_features:
                     self.cat_features.remove(c)
                 x.drop(columns=[c], inplace=True)
-                self.droped_features.append(c)
+                self.dropped_features.append(c)
             elif self.text_features is not None and c in self.text_features:
                 x[c] = x[c].astype(str)
                 self.converted_to_str.append(c)
@@ -391,9 +392,7 @@ class EstimatorWrapper:
                     self.converted_to_int.append(c)
                     self.cat_features.remove(c)
                 elif is_float_dtype(x[c]) or (x[c].dtype == "category" and is_float_dtype(x[c].cat.categories)):
-                    self.logger.info(
-                        f"Convert float cat feature {c} to string"
-                    )
+                    self.logger.info(f"Convert float cat feature {c} to string")
                     x[c] = x[c].astype(str)
                     self.converted_to_str.append(c)
                 elif x[c].dtype not in ["category", "int64"]:
@@ -411,16 +410,16 @@ class EstimatorWrapper:
                     except (ValueError, TypeError):
                         self.logger.warning(f"Remove feature {c} because it is not numeric and not in cat_features")
                         x.drop(columns=[c], inplace=True)
-                        self.droped_features.append(c)
+                        self.dropped_features.append(c)
 
         return x, y, groups, {}
 
     def _prepare_to_calculate(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
         x, y, _ = self._prepare_data(x, y)
 
-        if self.droped_features:
-            self.logger.info(f"Drop features on calculate metrics: {self.droped_features}")
-            x = x.drop(columns=self.droped_features)
+        if self.dropped_features:
+            self.logger.info(f"Drop features on calculate metrics: {self.dropped_features}")
+            x = x.drop(columns=self.dropped_features)
 
         if self.converted_to_int:
             self.logger.info(f"Convert to int features on calculate metrics: {self.converted_to_int}")
@@ -763,7 +762,7 @@ class CatBoostWrapper(EstimatorWrapper):
                     )
                 for f in high_cardinality_features:
                     self.text_features.remove(f)
-                    self.droped_features.append(f)
+                    self.dropped_features.append(f)
                     x = x.drop(columns=f, errors="ignore")
                 return super().cross_val_predict(x, y, baseline_score_column)
             else:
@@ -853,7 +852,7 @@ class LightGBMWrapper(EstimatorWrapper):
         for c in x.columns:
             if x[c].dtype not in ["category", "int64", "float64", "bool"]:
                 self.logger.warning(f"Feature {c} is not numeric and will be dropped")
-                self.droped_features.append(c)
+                self.dropped_features.append(c)
                 x = x.drop(columns=c, errors="ignore")
         return x, y_numpy, groups, params
 
@@ -933,7 +932,7 @@ class OtherEstimatorWrapper(EstimatorWrapper):
         for c in x.columns:
             if x[c].dtype not in ["category", "int64", "float64", "bool"]:
                 self.logger.warning(f"Feature {c} is not numeric and will be dropped")
-                self.droped_features.append(c)
+                self.dropped_features.append(c)
                 x = x.drop(columns=c, errors="ignore")
         return x, y_numpy, groups, params
 

upgini/utils/datetime_utils.py

@@ -121,31 +121,31 @@ class DateTimeSearchKeyConverter:
                 df[cos_feature] = np.cos(2 * np.pi * df[column] / period)
                 self.generated_features.append(cos_feature)
 
-        # df["quarter"] = df[self.date_column].dt.quarter
+        df["quarter"] = df[self.date_column].dt.quarter
 
-        # # Calculate the start date of the quarter for each timestamp
-        # df["quarter_start"] = df[self.date_column].dt.to_period("Q").dt.start_time
+        # Calculate the start date of the quarter for each timestamp
+        df["quarter_start"] = df[self.date_column].dt.to_period("Q").dt.start_time
 
-        # # Calculate the day in the quarter
-        # df["day_in_quarter"] = (df[self.date_column] - df["quarter_start"]).dt.days + 1
+        # Calculate the day in the quarter
+        df["day_in_quarter"] = (df[self.date_column] - df["quarter_start"]).dt.days + 1
 
-        # # Vectorized calculation of days_in_quarter
-        # quarter = df["quarter"]
-        # start = df["quarter_start"]
-        # year = start.dt.year
-        # month = start.dt.month
+        # Vectorized calculation of days_in_quarter
+        quarter = df["quarter"]
+        start = df["quarter_start"]
+        year = start.dt.year
+        month = start.dt.month
 
-        # quarter_end_year = np.where(quarter == 4, year + 1, year)
-        # quarter_end_month = np.where(quarter == 4, 1, month + 3)
+        quarter_end_year = np.where(quarter == 4, year + 1, year)
+        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
+        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
+        df["days_in_quarter"] = (end - start).dt.days
 
-        # add_cyclical_features(df, "day_in_quarter", df["days_in_quarter"])  # Days in the quarter
+        add_cyclical_features(df, "day_in_quarter", df["days_in_quarter"])  # Days in the quarter
 
-        # df.drop(columns=["quarter", "quarter_start", "day_in_quarter", "days_in_quarter"], inplace=True)
+        df.drop(columns=["quarter", "quarter_start", "day_in_quarter", "days_in_quarter"], inplace=True)
 
         df[seconds] = (df[self.date_column] - df[self.date_column].dt.floor("D")).dt.seconds
 

upgini/utils/email_utils.py

@@ -36,11 +36,11 @@ class EmailDomainGenerator:
         self.generated_features = []
 
     def generate(self, df: pd.DataFrame) -> pd.DataFrame:
-        # for email_col in self.email_columns:
-        #     domain_feature = email_col + self.DOMAIN_SUFFIX
-        #     if domain_feature not in df.columns:
-        #         df[domain_feature] = df[email_col].apply(self._email_to_domain).astype("string")
-        #         self.generated_features.append(domain_feature)
+        for email_col in self.email_columns:
+            domain_feature = email_col + self.DOMAIN_SUFFIX
+            if domain_feature not in df.columns:
+                df[domain_feature] = df[email_col].apply(self._email_to_domain).astype("string")
+                self.generated_features.append(domain_feature)
         return df
 
     @staticmethod

{upgini-1.2.86.dev1.dist-info → upgini-1.2.87a3857.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.86.dev1
+Version: 1.2.87a3857.dev1
 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-1.2.86.dev1.dist-info → upgini-1.2.87a3857.dev1.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=x1iyqkRuCxNu5kTIKv8yNfzxxa0JD4GnBFMpKHM2wRM,28
+upgini/__about__.py,sha256=3sSsl0Y82MTrFi1HkJZNIy6czqNHsAzjhFjDu3_mdew,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=fRtqSkXNONLnPe6cCL967GMt349FTIpXzy_u8LUKncw,35354
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=G0qbRPdlWe9p6cwYF3khP99-0kgAO8N0A2sfQxSLgmM,213446
+upgini/features_enricher.py,sha256=G69F0tRPjKWMhNwvXK0dgHzyTSMHShGN0ycrtYge6kA,215354
 upgini/http.py,sha256=6Qcepv0tDC72mBBJxYHnA2xqw6QwFaKrXN8o4vju8Es,44372
 upgini/metadata.py,sha256=zt_9k0iQbWXuiRZcel4ORNPdQKt6Ou69ucZD_E1Q46o,12341
-upgini/metrics.py,sha256=3cip0_L6-OFew74KsRwzxJDU6UFq05h2v7IsyHLcMRc,43164
+upgini/metrics.py,sha256=HJ5DpnrWAwrlw3_JlAWEhs1SXfI-_R4TGp2ajavOE14,43129
 upgini/search_task.py,sha256=Q5HjBpLIB3OCxAD1zNv5yQ3ZNJx696WCK_-H35_y7Rs,17912
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -51,10 +51,10 @@ 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=FKeCc5PQnhMSyLiw8nuiMccmMkrUCj4zCIgpZnffpbU,13569
+upgini/utils/datetime_utils.py,sha256=_jq-kn_dGNFfs-DGXcWCGzy9bkplfAjrZ8SsmN28zXc,13535
 upgini/utils/deduplicate_utils.py,sha256=AcMLoObMjhOTQ_fMS1LWy0GKp6WXnZ-FNux_8V3nbZU,8914
 upgini/utils/display_utils.py,sha256=hAeWEcJtPDg8fAVcMNrNB-azFD2WJp1nvbPAhR7SeP4,12071
-upgini/utils/email_utils.py,sha256=TZ_2UL0T7rzXG5WNu3dLUReY15qt6PozEGY_4cyuhdM,5287
+upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
 upgini/utils/feature_info.py,sha256=Q9HN6A-fvfVD-irFWrmOqqZG9RsUSvh5MTY_k0xu-tE,7287
 upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=LRN840dzx78-wg7ftdxAkp2c1eu8-JDvkACiRThm4HE,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.86.dev1.dist-info/METADATA,sha256=WbxVPEQbJJMxYSDRTiJAdevnfltYEQ8WjxyGgVv7vaE,49167
-upgini-1.2.86.dev1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.86.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.86.dev1.dist-info/RECORD,,
+upgini-1.2.87a3857.dev1.dist-info/METADATA,sha256=CAuubJghDMbrQnw0lkf8Go-cHO0uvsYaQYVel40FlLM,49172
+upgini-1.2.87a3857.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.87a3857.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.87a3857.dev1.dist-info/RECORD,,

{upgini-1.2.86.dev1.dist-info → upgini-1.2.87a3857.dev1.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