upgini 1.2.59a3818.dev1__py3-none-any.whl → 1.2.60a3792.dev1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.59a3818.dev1"
+__version__ = "1.2.60a3792.dev1"

upgini/autofe/vector.py

@@ -55,7 +55,7 @@ class TimeSeriesBase(PandasOperand, abc.ABC):
         ts.set_index(date.name, inplace=True)
         ts = ts[ts.index.notna()].sort_index()
         ts = (
-            ts.groupby([c.name for c in data[1:-1]], group_keys=True)
+            ts.groupby([c.name for c in data[1:-1]])
             .apply(self._shift)[data[-1].name]
             .to_frame()
             .reset_index()

upgini/data_source/data_source_publisher.py

@@ -386,6 +386,7 @@ class DataSourcePublisher:
                 search_keys = [k.value.value for k in search_keys] if search_keys else None
                 request = {"bqTableId": bq_table_id, "searchKeys": search_keys}
                 task_id = self._rest_client.upload_online(request, trace_id)
+                print(f"Uploading online task created. task_id={task_id}")
                 with Spinner():
                     status_response = self._rest_client.poll_ads_management_task_status(task_id, trace_id)
                     while status_response["status"] not in self.FINAL_STATUSES:

upgini/dataset.py

@@ -41,6 +41,7 @@ from upgini.utils.target_utils import (
     balance_undersample,
     balance_undersample_forced,
     balance_undersample_time_series,
+    balance_undersample_time_series_trunc,
 )
 
 try:
@@ -58,6 +59,8 @@ class Dataset:  # (pd.DataFrame):
     FIT_SAMPLE_THRESHOLD = 200_000
     FIT_SAMPLE_WITH_EVAL_SET_ROWS = 200_000
     FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD = 200_000
+    FIT_SAMPLE_THRESHOLD_TS = 54_000
+    FIT_SAMPLE_ROWS_TS = 54_000
     BINARY_MIN_SAMPLE_THRESHOLD = 5_000
     MULTICLASS_MIN_SAMPLE_THRESHOLD = 25_000
     IMBALANCE_THESHOLD = 0.6
@@ -304,6 +307,9 @@ class Dataset:  # (pd.DataFrame):
         if not self.imbalanced and EVAL_SET_INDEX in self.data.columns:
             sample_threshold = self.FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD
             sample_rows = self.FIT_SAMPLE_WITH_EVAL_SET_ROWS
+        elif self.cv_type is not None and self.cv_type.is_time_series():
+            sample_threshold = self.FIT_SAMPLE_THRESHOLD_TS
+            sample_rows = self.FIT_SAMPLE_ROWS_TS
         else:
             sample_threshold = self.FIT_SAMPLE_THRESHOLD
             sample_rows = self.FIT_SAMPLE_ROWS
@@ -314,7 +320,7 @@ class Dataset:  # (pd.DataFrame):
                 f"and will be downsampled to {sample_rows}"
             )
             if self.cv_type is not None and self.cv_type.is_time_series():
-                resampled_data = balance_undersample_time_series(
+                resampled_data = balance_undersample_time_series_trunc(
                     df=self.data,
                     id_columns=self.id_columns,
                     date_column=next(
@@ -584,19 +590,31 @@ class Dataset:  # (pd.DataFrame):
         return search_customization
 
     def _rename_generate_features(self, runtime_parameters: Optional[RuntimeParameters]) -> Optional[RuntimeParameters]:
-        if (
-            runtime_parameters is not None
-            and runtime_parameters.properties is not None
-            and "generate_features" in runtime_parameters.properties
-        ):
-            generate_features = runtime_parameters.properties["generate_features"].split(",")
-            renamed_generate_features = []
-            for f in generate_features:
-                for new_column, orig_column in self.columns_renaming.items():
-                    if f == orig_column:
-                        renamed_generate_features.append(new_column)
-            runtime_parameters.properties["generate_features"] = ",".join(renamed_generate_features)
+        if runtime_parameters is not None and runtime_parameters.properties is not None:
+            if "generate_features" in runtime_parameters.properties:
+                generate_features = runtime_parameters.properties["generate_features"].split(",")
+                renamed_generate_features = []
+                for f in generate_features:
+                    for new_column, orig_column in self.columns_renaming.items():
+                        if f == orig_column:
+                            renamed_generate_features.append(new_column)
+                runtime_parameters.properties["generate_features"] = ",".join(renamed_generate_features)
+            if "columns_for_online_api" in runtime_parameters.properties:
+                columns_for_online_api = runtime_parameters.properties["columns_for_online_api"].split(",")
+                renamed_columns_for_online_api = []
+                for f in columns_for_online_api:
+                    for new_column, orig_column in self.columns_renaming.items():
+                        if f == orig_column:
+                            renamed_columns_for_online_api.append(new_column)
+                runtime_parameters.properties["columns_for_online_api"] = ",".join(renamed_columns_for_online_api)
+
+        return runtime_parameters
 
+    def _set_sample_size(self, runtime_parameters: Optional[RuntimeParameters]) -> Optional[RuntimeParameters]:
+        if runtime_parameters is not None and runtime_parameters.properties is not None:
+            if self.cv_type is not None and self.cv_type.is_time_series():
+                runtime_parameters.properties["sample_size"] = self.FIT_SAMPLE_ROWS_TS
+                runtime_parameters.properties["iter0_sample_size"] = self.FIT_SAMPLE_ROWS_TS
         return runtime_parameters
 
     def _clean_generate_features(self, runtime_parameters: Optional[RuntimeParameters]) -> Optional[RuntimeParameters]:
@@ -630,6 +648,7 @@ class Dataset:  # (pd.DataFrame):
         file_metrics = FileMetrics()
 
         runtime_parameters = self._rename_generate_features(runtime_parameters)
+        runtime_parameters = self._set_sample_size(runtime_parameters)
 
         file_metadata = self.__construct_metadata(exclude_features_sources)
         search_customization = self.__construct_search_customization(

upgini/features_enricher.py

@@ -222,6 +222,7 @@ class FeaturesEnricher(TransformerMixin):
         loss: Optional[str] = None,
         detect_missing_search_keys: bool = True,
         generate_features: Optional[List[str]] = None,
+        columns_for_online_api: Optional[List[str]] = None,
         round_embeddings: Optional[int] = None,
         logs_enabled: bool = True,
         raise_validation_error: bool = True,
@@ -345,6 +346,9 @@ class FeaturesEnricher(TransformerMixin):
                     self.logger.error(msg)
                     raise ValidationError(msg)
                 self.runtime_parameters.properties["round_embeddings"] = round_embeddings
+        self.columns_for_online_api = columns_for_online_api
+        if columns_for_online_api is not None:
+            self.runtime_parameters.properties["columns_for_online_api"] = ",".join(columns_for_online_api)
         maybe_downsampling_limit = self.runtime_parameters.properties.get("downsampling_limit")
         if maybe_downsampling_limit is not None:
             Dataset.FIT_SAMPLE_THRESHOLD = int(maybe_downsampling_limit)
@@ -1873,13 +1877,9 @@ class FeaturesEnricher(TransformerMixin):
 
             # downsample if need to eval_set threshold
             num_samples = _num_samples(df)
-            phone_column = self._get_phone_column(self.search_keys)
             force_downsampling = (
                 not self.disable_force_downsampling
-                and self.generate_features is not None
-                and phone_column is not None
-                and self.fit_columns_renaming is not None
-                and self.fit_columns_renaming.get(phone_column) in self.generate_features
+                and self.columns_for_online_api is not None
                 and num_samples > Dataset.FORCE_SAMPLE_SIZE
             )
             if force_downsampling:
@@ -1948,7 +1948,27 @@ class FeaturesEnricher(TransformerMixin):
             df, _ = clean_full_duplicates(df, logger=self.logger, bundle=self.bundle)
 
             num_samples = _num_samples(df)
-            if num_samples > Dataset.FIT_SAMPLE_THRESHOLD:
+            force_downsampling = (
+                not self.disable_force_downsampling
+                and self.columns_for_online_api is not None
+                and num_samples > Dataset.FORCE_SAMPLE_SIZE
+            )
+            if force_downsampling:
+                self.logger.info(f"Force downsampling from {num_samples} to {Dataset.FORCE_SAMPLE_SIZE}")
+                df = balance_undersample_forced(
+                    df=df,
+                    target_column=TARGET,
+                    id_columns=self.id_columns,
+                    date_column=self._get_date_column(self.search_keys),
+                    task_type=self.model_task_type,
+                    cv_type=self.cv,
+                    random_state=self.random_state,
+                    sample_size=Dataset.FORCE_SAMPLE_SIZE,
+                    logger=self.logger,
+                    bundle=self.bundle,
+                    warning_callback=self.__log_warning,
+                )
+            elif num_samples > Dataset.FIT_SAMPLE_THRESHOLD:
                 self.logger.info(f"Downsampling from {num_samples} to {Dataset.FIT_SAMPLE_ROWS}")
                 df = df.sample(n=Dataset.FIT_SAMPLE_ROWS, random_state=self.random_state)
 
@@ -2620,17 +2640,18 @@ if response.status_code == 200:
             checked_generate_features = []
             for gen_feature in self.generate_features:
                 if gen_feature not in x_columns:
-                    if gen_feature == self._get_phone_column(self.search_keys):
-                        raise ValidationError(
-                            self.bundle.get("missing_generate_feature").format(gen_feature, x_columns)
-                        )
-                    else:
-                        self.__log_warning(self.bundle.get("missing_generate_feature").format(gen_feature, x_columns))
+                    msg = self.bundle.get("missing_generate_feature").format(gen_feature, x_columns)
+                    self.__log_warning(msg)
                 else:
                     checked_generate_features.append(gen_feature)
             self.generate_features = checked_generate_features
             self.runtime_parameters.properties["generate_features"] = ",".join(self.generate_features)
 
+        if self.columns_for_online_api is not None and len(self.columns_for_online_api) > 0:
+            for column in self.columns_for_online_api:
+                if column not in validated_X.columns:
+                    raise ValidationError(self.bundle.get("missing_column_for_online_api").format(column))
+
         if self.id_columns is not None:
             for id_column in self.id_columns:
                 if id_column not in validated_X.columns:
@@ -2852,9 +2873,7 @@ if response.status_code == 200:
         # Force downsampling to 7000 for API features generation
         force_downsampling = (
             not self.disable_force_downsampling
-            and self.generate_features is not None
-            and phone_column is not None
-            and self.fit_columns_renaming[phone_column] in self.generate_features
+            and self.columns_for_online_api is not None
             and len(df) > Dataset.FORCE_SAMPLE_SIZE
         )
         if force_downsampling:

upgini/resource_bundle/strings.properties

@@ -111,6 +111,7 @@ x_is_empty=X is empty
 y_is_empty=y is empty
 x_contains_reserved_column_name=Column name {} is reserved. Please rename column and try again
 missing_generate_feature=Feature {} specified in `generate_features` is not present in input columns: {}
+missing_column_for_online_api=Column {} specified in `columns_for_online_api` is not present in input columns: {}
 x_unstable_by_date=Your training sample is unstable in number of rows per date. It is recommended to redesign the training sample
 train_unstable_target=Your training sample contains an unstable target event, PSI = {}. This will lead to unstable scoring on deferred samples. It is recommended to redesign the training sample
 eval_unstable_target=Your training and evaluation samples have a difference in target distribution. PSI = {}. The results will be unstable. It is recommended to redesign the training and evaluation samples

upgini/utils/email_utils.py

@@ -116,17 +116,17 @@ class EmailSearchKeyConverter:
         else:
             df[self.hem_column] = df[self.hem_column].astype("string").str.lower()
 
-        del self.search_keys[self.email_column]
-        if self.email_column in self.unnest_search_keys:
-            self.unnest_search_keys.remove(self.email_column)
+        # del self.search_keys[self.email_column]
+        # if self.email_column in self.unnest_search_keys:
+        #     self.unnest_search_keys.remove(self.email_column)
 
         one_domain_name = self.email_column + self.ONE_DOMAIN_SUFFIX
         df[one_domain_name] = df[self.email_column].apply(self._email_to_one_domain)
         self.columns_renaming[one_domain_name] = original_email_column
         self.search_keys[one_domain_name] = SearchKey.EMAIL_ONE_DOMAIN
 
-        if self.email_converted_to_hem:
-            df = df.drop(columns=self.email_column)
-            del self.columns_renaming[self.email_column]
+        # if self.email_converted_to_hem:
+        #     df = df.drop(columns=self.email_column)
+        #     del self.columns_renaming[self.email_column]
 
         return df

upgini/utils/target_utils.py

@@ -10,6 +10,7 @@ from upgini.errors import ValidationError
 from upgini.metadata import SYSTEM_RECORD_ID, CVType, ModelTaskType
 from upgini.resource_bundle import ResourceBundle, bundle, get_custom_bundle
 from upgini.sampler.random_under_sampler import RandomUnderSampler
+from upgini.utils.ts_utils import get_most_frequent_time_unit, trunc_datetime
 
 TS_MIN_DIFFERENT_IDS_RATIO = 0.2
 
@@ -241,7 +242,7 @@ def balance_undersample_forced(
     df = df.copy().sort_values(by=SYSTEM_RECORD_ID)
     if cv_type is not None and cv_type.is_time_series():
         logger.warning(f"Sampling time series dataset from {len(df)} to {sample_size}")
-        resampled_data = balance_undersample_time_series(
+        resampled_data = balance_undersample_time_series_trunc(
             df,
             id_columns=id_columns,
             date_column=date_column,
@@ -280,6 +281,58 @@ def balance_undersample_forced(
     return resampled_data
 
 
+DEFAULT_HIGH_FREQ_TRUNC_LENGTHS = [pd.DateOffset(years=2, months=6), pd.DateOffset(years=2, days=7)]
+DEFAULT_LOW_FREQ_TRUNC_LENGTHS = [pd.DateOffset(years=7), pd.DateOffset(years=5)]
+DEFAULT_TIME_UNIT_THRESHOLD = pd.Timedelta(weeks=4)
+
+
+def balance_undersample_time_series_trunc(
+    df: pd.DataFrame,
+    id_columns: List[str],
+    date_column: str,
+    sample_size: int,
+    random_state: int = 42,
+    logger: Optional[logging.Logger] = None,
+    highfreq_trunc_lengths: List[pd.DateOffset] = DEFAULT_HIGH_FREQ_TRUNC_LENGTHS,
+    lowfreq_trunc_lengths: List[pd.DateOffset] = DEFAULT_LOW_FREQ_TRUNC_LENGTHS,
+    time_unit_threshold: pd.Timedelta = DEFAULT_TIME_UNIT_THRESHOLD,
+    **kwargs,
+):
+    # Convert date column to datetime
+    dates_df = df[id_columns + [date_column]].copy()
+    dates_df[date_column] = pd.to_datetime(dates_df[date_column], unit="ms")
+
+    time_unit = get_most_frequent_time_unit(dates_df, id_columns, date_column)
+    if logger is not None:
+        logger.info(f"Time unit: {time_unit}")
+
+    if time_unit is None:
+        if logger is not None:
+            logger.info("Cannot detect time unit, returning original dataset")
+        return df
+
+    if time_unit < time_unit_threshold:
+        for trunc_length in highfreq_trunc_lengths:
+            sampled_df = trunc_datetime(dates_df, id_columns, date_column, trunc_length)
+            if len(sampled_df) <= sample_size:
+                break
+        if len(sampled_df) > sample_size:
+            sampled_df = balance_undersample_time_series(
+                sampled_df, id_columns, date_column, sample_size, random_state, logger=logger, **kwargs
+            )
+    else:
+        for trunc_length in lowfreq_trunc_lengths:
+            sampled_df = trunc_datetime(dates_df, id_columns, date_column, trunc_length)
+            if len(sampled_df) <= sample_size:
+                break
+        if len(sampled_df) > sample_size:
+            sampled_df = balance_undersample_time_series(
+                sampled_df, id_columns, date_column, sample_size, random_state, logger=logger, **kwargs
+            )
+
+    return df.loc[sampled_df.index]
+
+
 def balance_undersample_time_series(
     df: pd.DataFrame,
     id_columns: List[str],

upgini/utils/ts_utils.py

@@ -0,0 +1,47 @@
+import logging
+from typing import List, Optional
+import pandas as pd
+
+
+def get_most_frequent_time_unit(df: pd.DataFrame, id_columns: List[str], date_column: str) -> Optional[pd.DateOffset]:
+
+    def closest_unit(diff):
+        return pd.tseries.frequencies.to_offset(pd.Timedelta(diff, unit="s"))
+
+    # Calculate differences for each ID group
+    all_diffs = []
+    groups = df.groupby(id_columns) if id_columns else [(None, df)]
+    for _, group in groups:
+        # Get sorted dates for this group
+        group_dates = group[date_column].sort_values().unique()
+        if len(group_dates) > 1:
+            # Calculate time differences between consecutive dates
+            diff_series = pd.Series(group_dates[1:] - group_dates[:-1])
+            # Convert to nanoseconds
+            diff_ns = diff_series.dt.total_seconds()
+            all_diffs.extend(diff_ns)
+
+    # Convert to series for easier processing
+    all_diffs = pd.Series(all_diffs)
+
+    # Get most common time unit across all groups
+    most_frequent_unit = all_diffs.apply(closest_unit).mode().min()
+
+    return most_frequent_unit if isinstance(most_frequent_unit, pd.DateOffset) else None
+
+
+def trunc_datetime(
+    df: pd.DataFrame,
+    id_columns: List[str],
+    date_column: str,
+    length: pd.DateOffset,
+    logger: Optional[logging.Logger] = None,
+) -> pd.DataFrame:
+    if logger is not None:
+        logger.info(f"Truncating time series dataset to {length}")
+
+    if id_columns:
+        min_datetime = df.groupby(id_columns)[date_column].transform(lambda group: group.max() - length)
+    else:
+        min_datetime = df[date_column].max() - length
+    return df[df[date_column] > min_datetime]

{upgini-1.2.59a3818.dev1.dist-info → upgini-1.2.60a3792.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.59a3818.dev1
+Version: 1.2.60a3792.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-1.2.59a3818.dev1.dist-info → upgini-1.2.60a3792.dev1.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=z4el4nWucz8yDnQ3Kw0cOsmIM0He3P64K0v3ZqFnhaI,33
+upgini/__about__.py,sha256=yYjoHiqKj96yFzYqXlsnJPzF_FcgZvyGwKBQjTVsNi4,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=vT4JyHmafLNbj54SySXr93f5hNS6-t94aFslbBy-7No,33535
+upgini/dataset.py,sha256=iSZX4KiDJlJFukNnAzBgkuT3UqbS-pyOyJlVXwTyaU0,34993
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=FkAKQV_XOXTobwOXpdy9BPfRkL4fkgoNa2B6NniiCrs,201554
+upgini/features_enricher.py,sha256=IXU6ahvQqMGLdZsrHCjOGEia1pBAgixfld3pNVPcGEM,202468
 upgini/http.py,sha256=ud0Cp7h0jNeHuuZGpU_1dAAEiabGoJjGxc1X5oeBQr4,43496
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=Jh6YTaS00m_nbaOY_owvlSyn9zgkErkqu8iTr9ZjKI8,12279
@@ -21,16 +21,16 @@ upgini/autofe/feature.py,sha256=zvRdlxCkaOsX0XiragNvh0tAPyOWut0MQTq5JGU5HtY,1474
 upgini/autofe/groupby.py,sha256=G48_sQZw016eGx3cOy8YQrEIOp95puWqYUpFWd-gdeM,3595
 upgini/autofe/operand.py,sha256=8Ttrfxv_H91dMbS7J55zxluzAJHfGXU_Y2xCh4OHwb8,4774
 upgini/autofe/unary.py,sha256=T3E7F3dA_7o_rkdCFq7JV6nHLzcoHLHQTcxO7y5Opa4,4646
-upgini/autofe/vector.py,sha256=_ZHgAnVG0O86HBGBoJxTPbn5VoFMdsim-eaFImXjXCM,7127
+upgini/autofe/vector.py,sha256=udkg4pP7IIeLjt0Cg6rzEKUmGaubOnqsEz3bz9R6E44,7110
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/data_source/data_source_publisher.py,sha256=X-8aGtVgzGmxyXkMVBoBLIGDMb4lYQaGZbxDnOd4A3Q,22516
+upgini/data_source/data_source_publisher.py,sha256=0vaYz5v3KclJnA6jAWiTUiMQO5mbBTBINWV9jr2F5xM,22591
 upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=0_KAExIi1u48N1CQ13LKJS3bgDlRs-MPOyU3VxcE-qY,27350
+upgini/resource_bundle/strings.properties,sha256=UXMiaFP3p-WdiXyZJN3O_OZstb-F33BWVDxDiofyxd4,27464
 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=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -46,7 +46,7 @@ upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=RVAk4_rakK8X9zjybK3-rj0to0e3elye8tnBuA4wTWU,13491
 upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
 upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
-upgini/utils/email_utils.py,sha256=GbnhHJn1nhUBytmK6PophYqaoq4t7Lp6i0-O0Gd3RV8,5265
+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=0rOXSyCj-sw-8migWP0ge8qrOzGU50dQvH0JUJUrDfQ,6766
 upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
@@ -56,10 +56,11 @@ upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,1
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,44511
-upgini/utils/target_utils.py,sha256=RlpKGss9kMibVSlA8iZuO_qxmyeplqzn7X8g6hiGGGs,14341
+upgini/utils/target_utils.py,sha256=a7Ck7WgQeUhDrnluOdFXvOdX6zDL-4Wiqt_f4jZxHag,16543
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
+upgini/utils/ts_utils.py,sha256=_YbNVE144vtEPlvLpvPGguDNzrnUM9IIjdX2VQz4T7E,1671
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.59a3818.dev1.dist-info/METADATA,sha256=mMXI6ZakQLfL9anKmHIvuX8X3ud-XD83uRLOaEQV9PA,49065
-upgini-1.2.59a3818.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.59a3818.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.59a3818.dev1.dist-info/RECORD,,
+upgini-1.2.60a3792.dev1.dist-info/METADATA,sha256=4k4LdGfGvuhNHhpT83pomgnfvZr8x2fKQDQbFCEAyPA,49065
+upgini-1.2.60a3792.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.60a3792.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.60a3792.dev1.dist-info/RECORD,,