upgini 1.2.59a3818.dev1__tar.gz → 1.2.60__tar.gz

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.59a3818.dev1
+Version: 1.2.60
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -30,6 +30,7 @@ Requires-Dist: jarowinkler>=2.0.0
 Requires-Dist: levenshtein>=0.25.1
 Requires-Dist: numpy<=1.26.4,>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0
+Requires-Dist: psutil>=6.0.0
 Requires-Dist: pydantic<3.0.0,>1.0.0
 Requires-Dist: pyjwt>=2.8.0
 Requires-Dist: python-bidi==0.4.2

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/pyproject.toml

@@ -50,6 +50,7 @@ dependencies = [
     "xhtml2pdf>=0.2.11,<0.3.0",
     "jarowinkler>=2.0.0",
     "levenshtein>=0.25.1",
+    "psutil>=6.0.0",
 ]
 
 [project.urls]

upgini-1.2.60/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.60"

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/src/upgini/autofe/date.py

@@ -1,6 +1,6 @@
 import abc
 import json
-from typing import Any, Dict, List, Optional, Union
+from typing import Dict, List, Optional, Union
 
 import numpy as np
 import pandas as pd

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/src/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-1.2.59a3818.dev1 → upgini-1.2.60}/src/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-1.2.59a3818.dev1 → upgini-1.2.60}/src/upgini/dataset.py

@@ -587,15 +587,23 @@ class Dataset:  # (pd.DataFrame):
         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 "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
 

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/src/upgini/features_enricher.py

@@ -112,6 +112,7 @@ try:
 except Exception:
     from upgini.utils.fallback_progress_bar import CustomFallbackProgressBar as ProgressBar
 
+from upgini.utils.sort import sort_columns
 from upgini.utils.target_utils import (
     balance_undersample_forced,
     calculate_psi,
@@ -222,6 +223,7 @@ 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 +347,9 @@ 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)
@@ -1257,7 +1262,7 @@ class FeaturesEnricher(TransformerMixin):
             for feature, shap in new_shaps.items()
             if feature in self.feature_names_ or renaming.get(feature, feature) in self.feature_names_
         }
-        self.__prepare_feature_importances(trace_id, x_columns, new_shaps, silent=True)
+        self.__prepare_feature_importances(trace_id, x_columns, new_shaps)
 
         if self.features_info_display_handle is not None:
             try:
@@ -1564,9 +1569,23 @@ class FeaturesEnricher(TransformerMixin):
 
         fitting_eval_set_dict = {}
         fitting_x_columns = fitting_X.columns.to_list()
-        self.logger.info(f"Final list of fitting X columns: {fitting_x_columns}")
+        # Idempotently sort columns
+        fitting_x_columns = sort_columns(
+            fitting_X, y_sorted, search_keys, self.model_task_type, sort_all_columns=True, logger=self.logger
+        )
+        fitting_X = fitting_X[fitting_x_columns]
+        self.logger.info(f"Final sorted list of fitting X columns: {fitting_x_columns}")
         fitting_enriched_x_columns = fitting_enriched_X.columns.to_list()
-        self.logger.info(f"Final list of fitting enriched X columns: {fitting_enriched_x_columns}")
+        fitting_enriched_x_columns = sort_columns(
+            fitting_enriched_X,
+            enriched_y_sorted,
+            search_keys,
+            self.model_task_type,
+            sort_all_columns=True,
+            logger=self.logger,
+        )
+        fitting_enriched_X = fitting_enriched_X[fitting_enriched_x_columns]
+        self.logger.info(f"Final sorted list of fitting enriched X columns: {fitting_enriched_x_columns}")
         for idx, eval_tuple in eval_set_sampled_dict.items():
             eval_X_sampled, enriched_eval_X, eval_y_sampled = eval_tuple
             eval_X_sorted, eval_y_sorted = self._sort_by_system_record_id(eval_X_sampled, eval_y_sampled, self.cv)
@@ -1730,11 +1749,15 @@ class FeaturesEnricher(TransformerMixin):
             if eval_set is not None
             else (Dataset.FIT_SAMPLE_THRESHOLD, Dataset.FIT_SAMPLE_ROWS)
         )
+
+        df = self.__add_fit_system_record_id(df, search_keys, SYSTEM_RECORD_ID, TARGET, columns_renaming, silent=True)
+        # Sample after sorting by system_record_id for idempotency
+        df.sort_values(by=SYSTEM_RECORD_ID, inplace=True)
+
         if num_samples > sample_threshold:
             self.logger.info(f"Downsampling from {num_samples} to {sample_rows}")
             df = df.sample(n=sample_rows, random_state=self.random_state)
 
-        df = self.__add_fit_system_record_id(df, search_keys, SYSTEM_RECORD_ID)
         if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
             df = df.drop(columns=DateTimeSearchKeyConverter.DATETIME_COL)
 
@@ -1873,15 +1896,12 @@ 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
             )
+            # TODO: check that system_record_id was added before this step
             if force_downsampling:
                 self.logger.info(f"Force downsampling from {num_samples} to {Dataset.FORCE_SAMPLE_SIZE}")
                 df = balance_undersample_forced(
@@ -1915,6 +1935,7 @@ class FeaturesEnricher(TransformerMixin):
                 progress_bar=progress_bar,
                 progress_callback=progress_callback,
                 add_fit_system_record_id=True,
+                target_name=tmp_target_name,
             )
             if enriched_df is None:
                 return None
@@ -1948,7 +1969,28 @@ 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)
 
@@ -1964,6 +2006,7 @@ class FeaturesEnricher(TransformerMixin):
                 progress_bar=progress_bar,
                 progress_callback=progress_callback,
                 add_fit_system_record_id=True,
+                target_name=tmp_target_name,
             )
             if enriched_Xy is None:
                 return None
@@ -2125,6 +2168,7 @@ if response.status_code == 200:
         progress_bar: Optional[ProgressBar] = None,
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
         add_fit_system_record_id: bool = False,
+        target_name: Optional[str] = None,
     ) -> Tuple[pd.DataFrame, Dict[str, str], List[str]]:
         if self._search_task is None:
             raise NotFittedError(self.bundle.get("transform_unfitted_enricher"))
@@ -2309,8 +2353,16 @@ if response.status_code == 200:
                 and c not in [ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]
             ]
 
-            if add_fit_system_record_id:
-                df = self.__add_fit_system_record_id(df, search_keys, SYSTEM_RECORD_ID)
+            if add_fit_system_record_id and target_name is not None:
+                reversed_columns_renaming = {v: k for k, v in columns_renaming.items()}
+                df = self.__add_fit_system_record_id(
+                    df,
+                    search_keys,
+                    SYSTEM_RECORD_ID,
+                    reversed_columns_renaming.get(target_name, target_name),
+                    columns_renaming,
+                    silent=True,
+                )
                 df = df.rename(columns={SYSTEM_RECORD_ID: SORT_ID})
                 features_not_to_pass.append(SORT_ID)
 
@@ -2620,17 +2672,18 @@ 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:
@@ -2754,7 +2807,9 @@ if response.status_code == 200:
             self.__log_warning(full_duplicates_warning)
 
         # Explode multiple search keys
-        df = self.__add_fit_system_record_id(df, self.fit_search_keys, ENTITY_SYSTEM_RECORD_ID)
+        df = self.__add_fit_system_record_id(
+            df, self.fit_search_keys, ENTITY_SYSTEM_RECORD_ID, TARGET, self.fit_columns_renaming
+        )
 
         # TODO check that this is correct for enrichment
         self.df_with_original_index = df.copy()
@@ -2836,7 +2891,9 @@ if response.status_code == 200:
         if eval_set is not None and len(eval_set) > 0:
             meaning_types[EVAL_SET_INDEX] = FileColumnMeaningType.EVAL_SET_INDEX
 
-        df = self.__add_fit_system_record_id(df, self.fit_search_keys, SYSTEM_RECORD_ID)
+        df = self.__add_fit_system_record_id(
+            df, self.fit_search_keys, SYSTEM_RECORD_ID, TARGET, self.fit_columns_renaming, silent=True
+        )
 
         if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
             df = df.drop(columns=DateTimeSearchKeyConverter.DATETIME_COL)
@@ -2852,9 +2909,7 @@ 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:
@@ -3525,56 +3580,82 @@ if response.status_code == 200:
     def __add_fit_system_record_id(
         self,
         df: pd.DataFrame,
-        # meaning_types: Dict[str, FileColumnMeaningType],
         search_keys: Dict[str, SearchKey],
         id_name: str,
+        target_name: str,
+        columns_renaming: Dict[str, str],
+        silent: bool = False,
     ) -> pd.DataFrame:
-        # save original order or rows
         original_index_name = df.index.name
         index_name = df.index.name or DEFAULT_INDEX
         original_order_name = "original_order"
+        # Save original index
         df = df.reset_index().rename(columns={index_name: ORIGINAL_INDEX})
+        # Save original order
         df = df.reset_index().rename(columns={DEFAULT_INDEX: original_order_name})
 
-        # order by date and idempotent order by other keys
-        if self.cv not in [CVType.time_series, CVType.blocked_time_series]:
-            sort_exclude_columns = [
-                original_order_name,
-                ORIGINAL_INDEX,
-                EVAL_SET_INDEX,
-                TARGET,
-                "__target",
-                ENTITY_SYSTEM_RECORD_ID,
-            ]
-            if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
-                date_column = DateTimeSearchKeyConverter.DATETIME_COL
-                sort_exclude_columns.append(self._get_date_column(search_keys))
-            else:
-                date_column = self._get_date_column(search_keys)
-            sort_columns = [date_column] if date_column is not None else []
+        # order by date and idempotent order by other keys and features
 
-            sorted_other_keys = sorted(search_keys, key=lambda x: str(search_keys.get(x)))
-            sorted_other_keys = [k for k in sorted_other_keys if k not in sort_exclude_columns]
+        sort_exclude_columns = [
+            original_order_name,
+            ORIGINAL_INDEX,
+            EVAL_SET_INDEX,
+            TARGET,
+            "__target",
+            ENTITY_SYSTEM_RECORD_ID,
+        ]
+        if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
+            date_column = DateTimeSearchKeyConverter.DATETIME_COL
+            sort_exclude_columns.append(FeaturesEnricher._get_date_column(search_keys))
+        else:
+            date_column = FeaturesEnricher._get_date_column(search_keys)
+        sort_exclude_columns.append(date_column)
+        columns_to_sort = [date_column] if date_column is not None else []
+
+        do_sorting = True
+        if self.id_columns and self.cv in [CVType.time_series, CVType.blocked_time_series]:
+            # Check duplicates by date and id_columns
+            reversed_columns_renaming = {v: k for k, v in columns_renaming.items()}
+            renamed_id_columns = [reversed_columns_renaming.get(c, c) for c in self.id_columns]
+            duplicate_check_columns = [c for c in renamed_id_columns if c in df.columns]
+            if date_column is not None:
+                duplicate_check_columns.append(date_column)
 
-            other_columns = sorted(
-                [
-                    c
-                    for c in df.columns
-                    if c not in sort_columns
-                    and c not in sorted_other_keys
-                    and c not in sort_exclude_columns
-                    and df[c].nunique() > 1
-                ]
+            duplicates = df.duplicated(subset=duplicate_check_columns, keep=False)
+            if duplicates.any():
+                if not silent:
+                    self.__log_warning(self.bundle.get("date_and_id_columns_duplicates").format(duplicates.sum()))
+                else:
+                    self.logger.warning(
+                        f"Found {duplicates.sum()} duplicate rows by date and ID columns: {duplicate_check_columns}."
+                        " Will not sort dataset"
+                    )
+                do_sorting = False
+            else:
+                columns_to_hash = list(search_keys.keys()) + renamed_id_columns + [target_name]
+                columns_to_hash = sort_columns(
+                    df[columns_to_hash],
+                    target_name,
+                    search_keys,
+                    self.model_task_type,
+                    sort_exclude_columns,
+                    logger=self.logger,
+                )
+        else:
+            columns_to_hash = sort_columns(
+                df, target_name, search_keys, self.model_task_type, sort_exclude_columns, logger=self.logger
             )
-
-            all_other_columns = sorted_other_keys + other_columns
-
+        if do_sorting:
             search_keys_hash = "search_keys_hash"
-            if len(all_other_columns) > 0:
-                sort_columns.append(search_keys_hash)
-                df[search_keys_hash] = pd.util.hash_pandas_object(df[all_other_columns], index=False)
-
-            df = df.sort_values(by=sort_columns)
+            if len(columns_to_hash) > 0:
+                factorized_df = df.copy()
+                for col in columns_to_hash:
+                    if col not in search_keys and not is_numeric_dtype(factorized_df[col]):
+                        factorized_df[col] = factorized_df[col].factorize(sort=True)[0]
+                df[search_keys_hash] = pd.util.hash_pandas_object(factorized_df[columns_to_hash], index=False)
+                columns_to_sort.append(search_keys_hash)
+
+            df = df.sort_values(by=columns_to_sort)
 
             if search_keys_hash in df.columns:
                 df.drop(columns=search_keys_hash, inplace=True)

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/src/upgini/metrics.py

@@ -30,8 +30,8 @@ except ImportError:
 from sklearn.metrics._regression import (
     _check_reg_targets,
     check_consistent_length,
-    mean_squared_error,
 )
+from sklearn.metrics import mean_squared_error
 from sklearn.model_selection import BaseCrossValidator
 
 from upgini.errors import ValidationError
@@ -289,9 +289,6 @@ class EstimatorWrapper:
         else:
             x, y = self._remove_empty_target_rows(x, y)
 
-        # Make order of columns idempotent
-        x = x[sorted(x.columns)]
-
         self.logger.info(f"After preparing data columns: {x.columns.to_list()}")
         return x, y, groups
 
@@ -569,7 +566,7 @@ class CatBoostWrapper(EstimatorWrapper):
             if all([isinstance(c, int) for c in estimator_cat_features]):
                 cat_features_idx = {x.columns.get_loc(c) for c in self.cat_features}
                 cat_features_idx.update(estimator_cat_features)
-                self.cat_features = [x.columns[idx] for idx in sorted(cat_features_idx)]
+                self.cat_features = [x.columns[idx] for idx in cat_features_idx]
             elif all([isinstance(c, str) for c in estimator_cat_features]):
                 self.cat_features = list(set(self.cat_features + estimator_cat_features))
             else:
@@ -940,13 +937,13 @@ def _ext_mean_squared_log_error(y_true, y_pred, *, sample_weight=None, multioutp
     if (y_true < 0).any():
         raise ValidationError(bundle.get("metrics_msle_negative_target"))
 
-    return mean_squared_error(
+    mse = mean_squared_error(
         log1p(y_true),
         log1p(y_pred.clip(0)),
         sample_weight=sample_weight,
         multioutput=multioutput,
-        squared=squared,
     )
+    return mse if squared else np.sqrt(mse)
 
 
 def fill_na_cat_features(df: pd.DataFrame, cat_features: List[str]) -> pd.DataFrame:

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/src/upgini/resource_bundle/strings.properties

@@ -35,6 +35,7 @@ trial_quota_limit_riched=You have reached the quota limit of trial data usage. P
 loss_selection_warn=Loss `{0}` is not supported for feature selection with {1}
 loss_calc_metrics_warn=Loss `{0}` is not supported for metrics calculation with {1}
 multivariate_timeseries_detected=Multivariate TimeSeries detected. Blocked time series cross-validation split selected.\nMore details: https://github.com/upgini/upgini#-time-series-prediction-support
+date_and_id_columns_duplicates=Found {} duplicate rows by date and id_columns
 group_k_fold_in_classification=Using group K-fold cross-validation split for classification task.
 current_date_added=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
@@ -111,6 +112,7 @@ 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-1.2.59a3818.dev1 → upgini-1.2.60}/src/upgini/utils/datetime_utils.py

@@ -166,6 +166,8 @@ class DateTimeSearchKeyConverter:
 
             # Drop intermediate columns if not needed
             df.drop(columns=["second", "minute", "hour"], inplace=True)
+        else:
+            keep_time = False
 
         for generated_feature in self.generated_features[:]:
             if df[generated_feature].dropna().nunique() <= 1:

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/src/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-1.2.60/src/upgini/utils/mstats.py

@@ -0,0 +1,177 @@
+import warnings
+from collections import namedtuple
+
+import numpy as np
+import numpy.ma as ma
+import scipy
+from joblib import Parallel, delayed
+from numpy import ndarray
+from psutil import cpu_count
+
+np.seterr(divide="ignore")
+
+
+warnings.simplefilter(action="ignore", category=RuntimeWarning)
+
+
+def _find_repeats(arr):
+    # This function assumes it may clobber its input.
+    if len(arr) == 0:
+        return np.array(0, np.float64), np.array(0, np.intp)
+
+    # XXX This cast was previously needed for the Fortran implementation,
+    # should we ditch it?
+    arr = np.asarray(arr, np.float64).ravel()
+    arr.sort()
+
+    # Taken from NumPy 1.9's np.unique.
+    change = np.concatenate(([True], arr[1:] != arr[:-1]))
+    unique = arr[change]
+    change_idx = np.concatenate(np.nonzero(change) + ([arr.size],))
+    freq = np.diff(change_idx)
+    atleast2 = freq > 1
+    return unique[atleast2], freq[atleast2]
+
+
+def find_repeats(arr):
+    # Make sure we get a copy. ma.compressed promises a "new array", but can
+    # actually return a reference.
+    compr = np.asarray(ma.compressed(arr), dtype=np.float64)
+    try:
+        need_copy = np.may_share_memory(compr, arr)
+    except AttributeError:
+        # numpy < 1.8.2 bug: np.may_share_memory([], []) raises,
+        # while in numpy 1.8.2 and above it just (correctly) returns False.
+        need_copy = False
+    if need_copy:
+        compr = compr.copy()
+    return _find_repeats(compr)
+
+
+def rankdata(data, axis=None, use_missing=False):
+    def _rank1d(data, use_missing=False):
+        n = data.count()
+        rk = np.empty(data.size, dtype=float)
+        idx = data.argsort()
+        rk[idx[:n]] = np.arange(1, n + 1)
+
+        if use_missing:
+            rk[idx[n:]] = (n + 1) / 2.0
+        else:
+            rk[idx[n:]] = 0
+
+        repeats = find_repeats(data.copy())
+        for r in repeats[0]:
+            condition = (data == r).filled(False)
+            rk[condition] = rk[condition].mean()
+        return rk
+
+    data = ma.array(data, copy=False)
+    if axis is None:
+        if data.ndim > 1:
+            return _rank1d(data.ravel(), use_missing).reshape(data.shape)
+        else:
+            return _rank1d(data, use_missing)
+    else:
+        return ma.apply_along_axis(_rank1d, axis, data, use_missing).view(ndarray)
+
+
+def _chk_asarray(a, axis):
+    # Always returns a masked array, raveled for axis=None
+    a = ma.asanyarray(a)
+    if axis is None:
+        a = ma.ravel(a)
+        outaxis = 0
+    else:
+        outaxis = axis
+    return a, outaxis
+
+
+SpearmanrResult = namedtuple("SpearmanrResult", ("correlation", "pvalue"))
+
+
+# Taken from scipy.mstats with following tweaks:
+# 1. parallel pairwise computation
+# 2. custom masking
+def spearmanr(
+    x, y=None, use_ties=True, axis=None, nan_policy="propagate", alternative="two-sided", mask_fn=ma.masked_invalid
+):
+    if not use_ties:
+        raise ValueError("`use_ties=False` is not supported in SciPy >= 1.2.0")
+
+    # Always returns a masked array, raveled if axis=None
+    x, axisout = _chk_asarray(x, axis)
+    if y is not None:
+        # Deal only with 2-D `x` case.
+        y, _ = _chk_asarray(y, axis)
+        if axisout == 0:
+            x = ma.column_stack((x, y))
+        else:
+            x = ma.row_stack((x, y))
+
+    if axisout == 1:
+        # To simplify the code that follow (always use `n_obs, n_vars` shape)
+        x = x.T
+
+    if nan_policy == "omit":
+        x = mask_fn(x)
+
+    def _spearmanr_2cols(x):
+        # Mask the same observations for all variables, and then drop those
+        # observations (can't leave them masked, rankdata is weird).
+        x = ma.mask_rowcols(x, axis=0)
+        x = x[~x.mask.any(axis=1), :]
+
+        # If either column is entirely NaN or Inf
+        if not np.any(x.data):
+            return SpearmanrResult(np.nan, np.nan)
+
+        m = ma.getmask(x)
+        n_obs = x.shape[0]
+        dof = n_obs - 2 - int(m.sum(axis=0)[0])
+        if dof < 0:
+            return SpearmanrResult(np.nan, np.nan)
+
+        # Gets the ranks and rank differences
+        x_ranked = rankdata(x, axis=0)
+        rs = ma.corrcoef(x_ranked, rowvar=False).data
+
+        # rs can have elements equal to 1, so avoid zero division warnings
+        with np.errstate(divide="ignore"):
+            # clip the small negative values possibly caused by rounding
+            # errors before taking the square root
+            t = rs * np.sqrt((dof / ((rs + 1.0) * (1.0 - rs))).clip(0))
+
+        t, prob = scipy.stats._mstats_basic._ttest_finish(dof, t, alternative)
+
+        # For backwards compatibility, return scalars when comparing 2 columns
+        if rs.shape == (2, 2):
+            return SpearmanrResult(rs[1, 0], prob[1, 0])
+        else:
+            return SpearmanrResult(rs, prob)
+
+    # Need to do this per pair of variables, otherwise the dropped observations
+    # in a third column mess up the result for a pair.
+    n_vars = x.shape[1]
+    if n_vars == 2:
+        return _spearmanr_2cols(x)
+    else:
+        max_cpu_cores = cpu_count(logical=False)
+        with np.errstate(divide="ignore"):
+            results = Parallel(n_jobs=max_cpu_cores)(
+                delayed(_spearmanr_2cols)(x[:, [var1, var2]])
+                for var1 in range(n_vars - 1)
+                for var2 in range(var1 + 1, n_vars)
+            )
+
+        rs = np.ones((n_vars, n_vars), dtype=float)
+        prob = np.zeros((n_vars, n_vars), dtype=float)
+        for var1 in range(n_vars - 1):
+            for var2 in range(var1 + 1, n_vars):
+                result = results.pop(0)
+                rs[var1, var2] = result.correlation
+                rs[var2, var1] = result.correlation
+                prob[var1, var2] = result.pvalue
+                prob[var2, var1] = result.pvalue
+
+        return SpearmanrResult(rs, prob)

upgini-1.2.60/src/upgini/utils/sort.py

@@ -0,0 +1,172 @@
+import hashlib
+import logging
+from typing import Any, Dict, List, Optional, Union
+
+import numpy as np
+import pandas as pd
+from joblib import Parallel, delayed
+from pandas.api.types import is_datetime64_any_dtype, is_numeric_dtype
+from psutil import cpu_count
+from scipy.stats import skew, spearmanr
+
+from upgini.metadata import ModelTaskType, SearchKey
+from upgini.utils import mstats
+
+
+def sort_columns(
+    df: pd.DataFrame,
+    target_column: Union[str, pd.Series],
+    search_keys: Dict[str, SearchKey],
+    model_task_type: ModelTaskType,
+    exclude_columns: Optional[List[str]] = None,
+    sort_all_columns: bool = False,
+    logger: Optional[logging.Logger] = None,
+) -> List[str]:
+    if exclude_columns is None:
+        exclude_columns = []
+    if logger is None:
+        logger = logging.getLogger(__name__)
+        logger.setLevel(logging.FATAL)
+    df = df.copy()  # avoid side effects
+
+    # Check multiple search keys
+    search_key_values = list(search_keys.values())
+    has_duplicate_search_keys = len(search_key_values) != len(set(search_key_values))
+    if has_duplicate_search_keys:
+        logging.warning(f"WARNING: Found duplicate SearchKey values in search_keys: {search_keys}")
+
+    sorted_keys = sorted(search_keys.keys(), key=lambda x: str(search_keys.get(x)))
+    sorted_keys = [k for k in sorted_keys if k in df.columns and k not in exclude_columns]
+
+    other_columns = sorted(
+        [
+            c
+            for c in df.columns
+            if c not in sorted_keys and c not in exclude_columns and (df[c].nunique() > 1 or sort_all_columns)
+        ]
+    )
+    target = target_column if isinstance(target_column, pd.Series) else df[target_column]
+    target = prepare_target(target, model_task_type)
+    sort_dict = get_sort_columns_dict(
+        df[sorted_keys + other_columns], target, sorted_keys, omit_nan=True, sort_all_columns=sort_all_columns
+    )
+    other_columns = [c for c in other_columns if c in sort_dict]
+    columns_for_sort = sorted_keys + sorted(other_columns, key=lambda e: sort_dict[e], reverse=True)
+    return columns_for_sort
+
+
+def get_sort_columns_dict(
+    df: pd.DataFrame,
+    target: pd.Series,
+    sorted_keys: List[str],
+    omit_nan: bool,
+    n_jobs: Optional[int] = None,
+    sort_all_columns: bool = False,
+) -> Dict[str, Any]:
+    string_features = [c for c in df.select_dtypes(exclude=[np.number]).columns if c not in sorted_keys]
+    columns_for_sort = [c for c in df.columns if c not in sorted_keys + string_features]
+    if len(string_features) > 0:
+        if len(df) > len(df.drop(columns=string_features).drop_duplicates()) or sort_all_columns:
+            # factorize string features
+            for c in string_features:
+                df.loc[:, c] = pd.Series(df[c].factorize(sort=True)[0], index=df.index, dtype="int")
+            columns_for_sort.extend(string_features)
+
+    if len(columns_for_sort) == 0:
+        return {}
+
+    df = df[columns_for_sort]
+    hashes = [hash_series(df[col]) for col in columns_for_sort]
+    df = np.asarray(df, dtype=np.float32)
+    correlations = get_sort_columns_correlations(df, target, omit_nan, n_jobs)
+
+    sort_dict = {col: (corr, h) for col, corr, h in zip(columns_for_sort, correlations, hashes)}
+    return sort_dict
+
+
+def get_sort_columns_correlations(df: np.ndarray, target: pd.Series, omit_nan: bool, n_jobs: Optional[int] = None):
+    target_correlations = get_target_correlations(df, target, omit_nan, n_jobs, precision=7)
+
+    return np.max(target_correlations, axis=0)
+
+
+def get_target_correlations(
+    df: np.ndarray, target: pd.Series, omit_nan: bool, n_jobs: Optional[int] = None, precision: int = 15
+):
+    df = np.asarray(df, dtype=np.float32)
+    target_correlations = np.zeros((2, df.shape[1]))
+    target_correlations[0, :] = np.nan_to_num(
+        calculate_spearman_corr_with_target(df, target, omit_nan, n_jobs), copy=False
+    )
+    target_correlations[1, :] = np.nan_to_num(np.abs(np.corrcoef(df.T, target.T, rowvar=True)[-1, :-1]))
+
+    target_correlations = np.trunc(target_correlations * 10**precision) / (10**precision)
+
+    return target_correlations
+
+
+def calculate_spearman_corr_with_target(
+    X: Union[pd.DataFrame, np.ndarray], y: pd.Series, omit_nan: bool = False, n_jobs: Optional[int] = None
+) -> np.ndarray:
+    if isinstance(X, pd.DataFrame):
+        X = np.asarray(X, dtype=np.float32)
+
+    if X.size == 0:
+        return np.ndarray(shape=(0,))
+
+    all_correlations = np.zeros(X.shape[1])
+    all_correlations.fill(np.nan)
+    cols2calc = np.where([c.size > 0 and not (c == c[0]).all() for c in X.T])[0]
+
+    if omit_nan:
+        results = Parallel(n_jobs=n_jobs or cpu_count(logical=False))(
+            delayed(mstats.spearmanr)(
+                X[:, i],
+                y,
+                nan_policy="omit",
+                axis=0,
+            )
+            for i in cols2calc
+        )
+        target_correlations = np.array([abs(res.correlation) for res in results])
+    else:
+        cols2calc = cols2calc[np.where(~np.isnan(X[:, cols2calc]).any(axis=0))[0]]
+        target_correlations = calculate_spearman(X[:, cols2calc], y, nan_policy="raise")
+        if isinstance(target_correlations, float):
+            target_correlations = np.abs([target_correlations])
+        else:
+            target_correlations = np.abs(target_correlations)[-1, :-1]
+
+    all_correlations[cols2calc] = target_correlations
+
+    return all_correlations
+
+
+def calculate_spearman(X: np.ndarray, y: Optional[pd.Series], nan_policy: str):
+    features_num = X.shape[1]
+    if y is not None:
+        features_num += 1
+
+    if features_num < 2:
+        return 1.0
+    else:
+        return spearmanr(X, y, nan_policy=nan_policy).correlation
+
+
+def hash_series(series: pd.Series) -> int:
+    return int(hashlib.sha256(pd.util.hash_pandas_object(series, index=True).values).hexdigest(), 16)
+
+
+def prepare_target(target: pd.Series, model_task_type: ModelTaskType) -> pd.Series:
+    target_name = target.name
+    if model_task_type != ModelTaskType.REGRESSION or (
+        not is_numeric_dtype(target) and not is_datetime64_any_dtype(target)
+    ):
+        target = target.astype(str).astype("category").cat.codes
+
+    elif model_task_type == ModelTaskType.REGRESSION:
+        skewness = round(abs(skew(target)), 2)
+        if (target.min() >= 0) and (skewness >= 0.9):
+            target = np.log1p(target)
+
+    return pd.Series(target, name=target_name)

{upgini-1.2.59a3818.dev1 → upgini-1.2.60}/src/upgini/utils/target_utils.py

@@ -1,4 +1,3 @@
-import itertools
 import logging
 from typing import Callable, List, Optional, Union
 
@@ -207,7 +206,7 @@ def balance_undersample_forced(
     id_columns: List[str],
     date_column: str,
     task_type: ModelTaskType,
-    cv_type: CVType | None,
+    cv_type: Optional[CVType],
     random_state: int,
     sample_size: int = 7000,
     logger: Optional[logging.Logger] = None,
@@ -319,7 +318,8 @@ def balance_undersample_time_series(
     if len(id_counts) < min_different_ids:
         if logger is not None:
             logger.info(
-                f"Different ids count {len(id_counts)} for sample size {sample_size} is less than min different ids {min_different_ids}, sampling time window"
+                f"Different ids count {len(id_counts)} for sample size {sample_size}"
+                f" is less than min different ids {min_different_ids}, sampling time window"
             )
         date_counts = df.groupby(id_columns)[date_column].nunique().sort_values(ascending=False)
         ids_to_sample = date_counts.index[:min_different_ids] if len(id_counts) > 0 else date_counts.index

upgini-1.2.59a3818.dev1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.59a3818.dev1"