upgini 1.1.262a3250.post4__py3-none-any.whl → 1.1.274a4__py3-none-any.whl

upgini/autofe/all_operands.py

@@ -1,5 +1,5 @@
 from typing import Dict
-from upgini.autofe.date import DateDiff, DateDiffFuture
+from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
 from upgini.autofe.unary import Abs, Log, Residual, Sqrt, Square, Sigmoid, Floor, Freq
@@ -37,7 +37,17 @@ ALL_OPERANDS: Dict[str, Operand] = {
         Operand(name="GroupByThenFreq", output_type="float", is_grouping=True),
         Sim(),
         DateDiff(),
-        DateDiffFuture(),
+        DateDiffType2(),
+        DateListDiff(aggregation="min"),
+        DateListDiff(aggregation="max"),
+        DateListDiff(aggregation="mean"),
+        DateListDiff(aggregation="nunique"),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=0, upper_bound=18),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=18, upper_bound=23),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=23, upper_bound=30),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=30, upper_bound=45),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
     ]
 }
 

upgini/autofe/date.py

@@ -1,11 +1,12 @@
-from typing import Optional, Union
+from typing import Any, Optional, Union
 import numpy as np
 import pandas as pd
+from pydantic import BaseModel
 
 from upgini.autofe.operand import PandasOperand
 
 
-class DateDiffMixin:
+class DateDiffMixin(BaseModel):
     diff_unit: str = "D"
     left_unit: Optional[str] = None
     right_unit: Optional[str] = None
@@ -34,18 +35,77 @@ class DateDiff(PandasOperand, DateDiffMixin):
         return x
 
 
-class DateDiffFuture(PandasOperand, DateDiffMixin):
-    name = "date_diff_future"
+class DateDiffType2(PandasOperand, DateDiffMixin):
+    name = "date_diff_type2"
     is_binary = True
     has_symmetry_importance = True
-    is_vectorizable = False
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         left = self._convert_to_date(left, self.left_unit)
         right = self._convert_to_date(right, self.right_unit)
-        future = pd.to_datetime(dict(day=right.dt.day, month=right.dt.month, year=left.dt.year))
+        future = right + (left.dt.year - right.dt.year).apply(
+            lambda y: np.datetime64("NaT") if np.isnan(y) else pd.tseries.offsets.DateOffset(years=y)
+        )
+        future = pd.to_datetime(future)
         before = future[future < left]
-        future[future < left] = pd.to_datetime(dict(day=before.dt.day, month=before.dt.month, year=before.dt.year + 1))
+        future[future < left] = before + pd.tseries.offsets.DateOffset(years=1)
         diff = (future - left) / np.timedelta64(1, self.diff_unit)
 
         return diff
+
+
+_ext_aggregations = {"nunique": (lambda x: len(np.unique(x)), 0), "count": (len, 0)}
+
+
+class DateListDiff(PandasOperand, DateDiffMixin):
+    is_binary = True
+    has_symmetry_importance = True
+    aggregation: str
+
+    def __init__(self, **data: Any) -> None:
+        if "name" not in data:
+            data["name"] = f"date_diff_{data.get('aggregation')}"
+        super().__init__(**data)
+
+    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        left = self._convert_to_date(left, self.left_unit)
+        right = right.apply(lambda x: pd.arrays.DatetimeArray(self._convert_to_date(x, self.right_unit)))
+
+        return pd.Series(left - right.values).apply(lambda x: self._agg(self._diff(x)))
+
+    def _diff(self, x):
+        x = x / np.timedelta64(1, self.diff_unit)
+        return x[x > 0]
+
+    def _agg(self, x):
+        method = getattr(np, self.aggregation, None)
+        default = np.nan
+        if method is None and self.aggregation in _ext_aggregations:
+            method, default = _ext_aggregations[self.aggregation]
+        elif not callable(method):
+            raise ValueError(f"Unsupported aggregation: {self.aggregation}")
+
+        return method(x) if len(x) > 0 else default
+
+
+class DateListDiffBounded(DateListDiff):
+    lower_bound: Optional[int]
+    upper_bound: Optional[int]
+
+    def __init__(self, **data: Any) -> None:
+        if "name" not in data:
+            lower_bound = data.get("lower_bound")
+            upper_bound = data.get("upper_bound")
+            components = [
+                "date_diff",
+                data.get("diff_unit"),
+                str(lower_bound if lower_bound is not None else "minusinf"),
+                str(upper_bound if upper_bound is not None else "plusinf"),
+            ]
+            components.append(data.get("aggregation"))
+            data["name"] = "_".join(components)
+        super().__init__(**data)
+
+    def _agg(self, x):
+        x = x[(x >= (self.lower_bound or -np.inf)) & (x < (self.upper_bound or np.inf))]
+        return super()._agg(x)

upgini/data_source/data_source_publisher.py

@@ -48,6 +48,7 @@ class DataSourcePublisher:
         data_table_uri: str,
         search_keys: Dict[str, SearchKey],
         update_frequency: str,
+        exclude_from_autofe_generation: Optional[List[str]],
         secondary_search_keys: Optional[Dict[str, SearchKey]] = None,
         sort_column: Optional[str] = None,
         date_format: Optional[str] = None,
@@ -57,7 +58,6 @@ class DataSourcePublisher:
         join_date_abs_limit_days: Optional[int] = None,
         features_for_embeddings: Optional[List[str]] = DEFAULT_GENERATE_EMBEDDINGS,
         data_table_id_to_replace: Optional[str] = None,
-        exclude_from_autofe_generation: Optional[List[str]] = None,
         _force_generation=False,
         _silent=False,
     ) -> str:
@@ -72,8 +72,8 @@ class DataSourcePublisher:
                     )
                 if search_keys is None or len(search_keys) == 0:
                     raise ValidationError("Empty search keys")
-                if SearchKey.DATE in search_keys.values() and date_format is None:
-                    raise ValidationError("date_format is required for DATE search key")
+                # if SearchKey.DATE in search_keys.values() and date_format is None:
+                #     raise ValidationError("date_format is required for DATE search key")
                 if update_frequency not in self.ACCEPTABLE_UPDATE_FREQUENCIES:
                     raise ValidationError(
                         f"Invalid update frequency: {update_frequency}. "
@@ -85,11 +85,19 @@ class DataSourcePublisher:
                     or set(search_keys.values()) == {SearchKey.MSISDN_RANGE_FROM, SearchKey.MSISDN_RANGE_TO}
                 ) and sort_column is None:
                     raise ValidationError("Sort column is required for passed search keys")
+                if (
+                    set(search_keys.values()) == {SearchKey.PHONE, SearchKey.DATE}
+                    and snapshot_frequency_days is None
+                    and join_date_abs_limit_days is None
+                ):
+                    raise ValidationError(
+                        "With MSISDN and DATE keys one of the snapshot_frequency_days or"
+                        " join_date_abs_limit_days parameters is required"
+                    )
 
                 request = {
                     "dataTableUri": data_table_uri,
                     "searchKeys": {k: v.value.value for k, v in search_keys.items()},
-                    "dateFormat": date_format,
                     "excludeColumns": exclude_columns,
                     "hashFeatureNames": str(hash_feature_names).lower(),
                     "snapshotFrequencyDays": snapshot_frequency_days,
@@ -98,6 +106,8 @@ class DataSourcePublisher:
                     "featuresForEmbeddings": features_for_embeddings,
                     "forceGeneration": str(_force_generation).lower(),
                 }
+                if date_format is not None:
+                    request["dateFormat"] = date_format
                 if secondary_search_keys is not None:
                     request["secondarySearchKeys"] = {k: v.value.value for k, v in secondary_search_keys.items()}
                 if sort_column is not None:

upgini/dataset.py

@@ -60,7 +60,7 @@ class Dataset:  # (pd.DataFrame):
     FIT_SAMPLE_WITH_EVAL_SET_ROWS = 200_000
     FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD = 200_000
     MIN_SAMPLE_THRESHOLD = 5_000
-    IMBALANCE_THESHOLD = 0.4
+    IMBALANCE_THESHOLD = 0.6
     BINARY_BOOTSTRAP_LOOPS = 5
     MULTICLASS_BOOTSTRAP_LOOPS = 2
     MIN_TARGET_CLASS_ROWS = 100

upgini/features_enricher.py

@@ -1,4 +1,5 @@
 import dataclasses
+import datetime
 import gc
 import hashlib
 import itertools
@@ -70,6 +71,7 @@ from upgini.utils.datetime_utils import (
     DateTimeSearchKeyConverter,
     is_blocked_time_series,
     is_time_series,
+    validate_dates_distribution,
 )
 from upgini.utils.deduplicate_utils import (
     clean_full_duplicates,
@@ -93,7 +95,7 @@ try:
 except Exception:
     from upgini.utils.fallback_progress_bar import CustomFallbackProgressBar as ProgressBar
 
-from upgini.utils.target_utils import define_task
+from upgini.utils.target_utils import calculate_psi, define_task
 from upgini.utils.warning_counter import WarningCounter
 from upgini.version_validator import validate_version
 
@@ -145,6 +147,7 @@ class FeaturesEnricher(TransformerMixin):
     """
 
     TARGET_NAME = "target"
+    CURRENT_DATE = "current_date"
     RANDOM_STATE = 42
     CALCULATE_METRICS_THRESHOLD = 50_000_000
     CALCULATE_METRICS_MIN_THRESHOLD = 500
@@ -206,6 +209,7 @@ class FeaturesEnricher(TransformerMixin):
         client_ip: Optional[str] = None,
         client_visitorid: Optional[str] = None,
         custom_bundle_config: Optional[str] = None,
+        add_date_if_missing: bool = True,
         **kwargs,
     ):
         self.bundle = get_custom_bundle(custom_bundle_config)
@@ -316,6 +320,7 @@ class FeaturesEnricher(TransformerMixin):
         self.raise_validation_error = raise_validation_error
         self.exclude_columns = exclude_columns
         self.baseline_score_column = baseline_score_column
+        self.add_date_if_missing = add_date_if_missing
 
     def _get_api_key(self):
         return self._api_key
@@ -423,7 +428,7 @@ class FeaturesEnricher(TransformerMixin):
                 self.X = X
                 self.y = y
                 self.eval_set = self._check_eval_set(eval_set, X, self.bundle)
-                self.dump_input(trace_id, X, y, eval_set)
+                self.dump_input(trace_id, X, y, self.eval_set)
                 self.__inner_fit(
                     trace_id,
                     X,
@@ -562,7 +567,7 @@ class FeaturesEnricher(TransformerMixin):
                 self.X = X
                 self.y = y
                 self.eval_set = self._check_eval_set(eval_set, X, self.bundle)
-                self.dump_input(trace_id, X, y, eval_set)
+                self.dump_input(trace_id, X, y, self.eval_set)
 
                 if _num_samples(drop_duplicates(X)) > Dataset.MAX_ROWS:
                     raise ValidationError(self.bundle.get("dataset_too_many_rows_registered").format(Dataset.MAX_ROWS))
@@ -822,12 +827,16 @@ class FeaturesEnricher(TransformerMixin):
                 print(msg)
 
             self.__validate_search_keys(self.search_keys, self.search_id)
+            effective_X = X if X is not None else self.X
+            effective_y = y if y is not None else self.y
+            effective_eval_set = eval_set if eval_set is not None else self.eval_set
+            effective_eval_set = self._check_eval_set(effective_eval_set, effective_X, self.bundle)
 
             try:
                 self.__log_debug_information(
-                    X if X is not None else self.X,
-                    y if y is not None else self.y,
-                    eval_set if eval_set is not None else self.eval_set,
+                    effective_X,
+                    effective_y,
+                    effective_eval_set,
                     exclude_features_sources=exclude_features_sources,
                     cv=cv if cv is not None else self.cv,
                     importance_threshold=importance_threshold,
@@ -841,17 +850,14 @@ class FeaturesEnricher(TransformerMixin):
                     self._search_task is None
                     or self._search_task.provider_metadata_v2 is None
                     or len(self._search_task.provider_metadata_v2) == 0
-                    or (self.X is None and X is None)
-                    or (self.y is None and y is None)
+                    or effective_X is None
+                    or effective_y is None
                 ):
                     raise ValidationError(self.bundle.get("metrics_unfitted_enricher"))
 
                 if X is not None and y is None:
                     raise ValidationError("X passed without y")
 
-                effective_X = X if X is not None else self.X
-                effective_eval_set = eval_set if eval_set is not None else self.eval_set
-
                 validate_scoring_argument(scoring)
 
                 self._validate_baseline_score(effective_X, effective_eval_set)
@@ -871,8 +877,7 @@ class FeaturesEnricher(TransformerMixin):
                 ):
                     cat_features = estimator.get_param("cat_features")
                     if len(cat_features) > 0 and isinstance(cat_features[0], int):
-                        effectiveX = X or self.X
-                        cat_features = [effectiveX.columns[i] for i in cat_features]
+                        cat_features = [effective_X.columns[i] for i in cat_features]
                         for cat_feature in cat_features:
                             if cat_feature in self.search_keys:
                                 if self.search_keys[cat_feature] in [SearchKey.COUNTRY, SearchKey.POSTAL_CODE]:
@@ -882,9 +887,9 @@ class FeaturesEnricher(TransformerMixin):
 
                 prepared_data = self._prepare_data_for_metrics(
                     trace_id=trace_id,
-                    X=X,
-                    y=y,
-                    eval_set=eval_set,
+                    X=effective_X,
+                    y=effective_y,
+                    eval_set=effective_eval_set,
                     exclude_features_sources=exclude_features_sources,
                     importance_threshold=importance_threshold,
                     max_features=max_features,
@@ -994,8 +999,6 @@ class FeaturesEnricher(TransformerMixin):
                         enriched_metric = None
                         uplift = None
 
-                    effective_X = X if X is not None else self.X
-                    effective_y = y if y is not None else self.y
                     train_metrics = {
                         self.bundle.get("quality_metrics_segment_header"): self.bundle.get(
                             "quality_metrics_train_segment"
@@ -1256,6 +1259,7 @@ class FeaturesEnricher(TransformerMixin):
             ).get_cv_and_groups(X)
         else:
             from sklearn import __version__ as sklearn_version
+
             try:
                 from sklearn.model_selection._split import GroupsConsumerMixin
 
@@ -1684,6 +1688,9 @@ class FeaturesEnricher(TransformerMixin):
             df = validated_X.copy()
 
             df[TARGET] = validated_y
+
+            df = clean_full_duplicates(df, logger=self.logger, silent=True, bundle=self.bundle)
+
             num_samples = _num_samples(df)
             if num_samples > Dataset.FIT_SAMPLE_THRESHOLD:
                 self.logger.info(f"Downsampling from {num_samples} to {Dataset.FIT_SAMPLE_ROWS}")
@@ -1801,10 +1808,11 @@ class FeaturesEnricher(TransformerMixin):
         else:
             features_section = ""
 
-        api_example = f"""curl 'https://inference-upgini.azurewebsites.net/api/http_inference_trigger' \\
+        search_id = self._search_task.search_task_id
+        api_example = f"""curl 'https://search.upgini.com/online/api/http_inference_trigger?search_id={search_id}' \\
     -H 'Authorization: {self.api_key}' \\
     -H 'Content-Type: application/json' \\
-    -d '{{"search_id": "{self._search_task.search_task_id}", "search_keys": {keys}{features_section}}}'"""
+    -d '{{"search_keys": {keys}{features_section}}}'"""
         return api_example
 
     def _get_copy_of_runtime_parameters(self) -> RuntimeParameters:
@@ -1899,6 +1907,8 @@ class FeaturesEnricher(TransformerMixin):
                 generated_features.extend(converter.generated_features)
             else:
                 self.logger.info("Input dataset hasn't date column")
+                if self.add_date_if_missing:
+                    df = self._add_current_date_as_key(df, search_keys, self.logger, self.bundle)
             email_column = self._get_email_column(search_keys)
             hem_column = self._get_hem_column(search_keys)
             email_converted_to_hem = False
@@ -1918,6 +1928,7 @@ class FeaturesEnricher(TransformerMixin):
 
             meaning_types = {col: key.value for col, key in search_keys.items()}
             non_keys_columns = [column for column in df.columns if column not in search_keys.keys()]
+
             if email_converted_to_hem:
                 non_keys_columns.append(email_column)
 
@@ -1939,6 +1950,7 @@ class FeaturesEnricher(TransformerMixin):
             if add_fit_system_record_id:
                 df = self.__add_fit_system_record_id(df, dict(), search_keys)
                 df = df.rename(columns={SYSTEM_RECORD_ID: SORT_ID})
+                non_keys_columns.append(SORT_ID)
 
             columns_for_system_record_id = sorted(list(search_keys.keys()) + (original_features_for_transform or []))
 
@@ -2215,14 +2227,13 @@ class FeaturesEnricher(TransformerMixin):
         self.fit_search_keys = self.search_keys.copy()
         self.fit_search_keys = self.__prepare_search_keys(validated_X, self.fit_search_keys, is_demo_dataset)
 
-        has_date = self._get_date_column(self.fit_search_keys) is not None
+        validate_dates_distribution(validated_X, self.fit_search_keys, self.logger, self.bundle, self.warning_counter)
+
+        maybe_date_column = self._get_date_column(self.fit_search_keys)
+        has_date = maybe_date_column is not None
         model_task_type = self.model_task_type or define_task(validated_y, has_date, self.logger)
         self._validate_binary_observations(validated_y, model_task_type)
 
-        df = self.__handle_index_search_keys(df, self.fit_search_keys)
-
-        df = self.__correct_target(df)
-
         self.runtime_parameters = get_runtime_params_custom_loss(
             self.loss, model_task_type, self.runtime_parameters, self.logger
         )
@@ -2234,6 +2245,13 @@ class FeaturesEnricher(TransformerMixin):
                 eval_df[EVAL_SET_INDEX] = idx + 1
                 df = pd.concat([df, eval_df])
 
+        df = self.__correct_target(df)
+
+        df = self.__handle_index_search_keys(df, self.fit_search_keys)
+
+        if is_numeric_dtype(df[self.TARGET_NAME]) and has_date:
+            self._validate_PSI(df.sort_values(by=maybe_date_column))
+
         if DEFAULT_INDEX in df.columns:
             msg = self.bundle.get("unsupported_index_column")
             self.logger.info(msg)
@@ -2260,6 +2278,8 @@ class FeaturesEnricher(TransformerMixin):
             self.fit_generated_features.extend(converter.generated_features)
         else:
             self.logger.info("Input dataset hasn't date column")
+            if self.add_date_if_missing:
+                df = self._add_current_date_as_key(df, self.fit_search_keys, self.logger, self.bundle)
         email_column = self._get_email_column(self.fit_search_keys)
         hem_column = self._get_hem_column(self.fit_search_keys)
         email_converted_to_hem = False
@@ -2808,6 +2828,7 @@ class FeaturesEnricher(TransformerMixin):
 
             maybe_date_col = self._get_date_column(self.search_keys)
             if X is not None and maybe_date_col is not None and maybe_date_col in X.columns:
+                # TODO cast date column to single dtype
                 min_date = X[maybe_date_col].min()
                 max_date = X[maybe_date_col].max()
                 self.logger.info(f"Dates interval is ({min_date}, {max_date})")
@@ -2839,6 +2860,25 @@ class FeaturesEnricher(TransformerMixin):
             if t in [SearchKey.DATE, SearchKey.DATETIME]:
                 return col
 
+    @staticmethod
+    def _add_current_date_as_key(
+        df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: logging.Logger, bundle: ResourceBundle
+    ) -> pd.DataFrame:
+        if (
+            set(search_keys.values()) == {SearchKey.PHONE}
+            or set(search_keys.values()) == {SearchKey.EMAIL}
+            or set(search_keys.values()) == {SearchKey.HEM}
+            or set(search_keys.values()) == {SearchKey.COUNTRY, SearchKey.POSTAL_CODE}
+        ):
+            msg = bundle.get("current_date_added")
+            print(msg)
+            logger.warning(msg)
+            df[FeaturesEnricher.CURRENT_DATE] = datetime.date.today()
+            search_keys[FeaturesEnricher.CURRENT_DATE] = SearchKey.DATE
+            converter = DateTimeSearchKeyConverter(FeaturesEnricher.CURRENT_DATE, None, logger, bundle)
+            df = converter.convert(df)
+        return df
+
     @staticmethod
     def _get_group_columns(df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> List[str]:
         return [
@@ -2877,26 +2917,33 @@ class FeaturesEnricher(TransformerMixin):
 
         # 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"]
             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 []
 
-            other_search_keys = sorted(
+            other_columns = sorted(
                 [
-                    sk
-                    for sk, key_type in search_keys.items()
-                    if key_type not in [SearchKey.DATE, SearchKey.DATETIME]
-                    and sk in df.columns
-                    and df[sk].nunique() > 1  # don't use constant keys for hash
+                    c
+                    for c in df.columns
+                    if c not in sort_columns and c not in sort_exclude_columns and df[c].nunique() > 1
                 ]
+                # [
+                #     sk
+                #     for sk, key_type in search_keys.items()
+                #     if key_type not in [SearchKey.DATE, SearchKey.DATETIME]
+                #     and sk in df.columns
+                #     and df[sk].nunique() > 1  # don't use constant keys for hash
+                # ]
             )
 
             search_keys_hash = "search_keys_hash"
-            if len(other_search_keys) > 0:
+            if len(other_columns) > 0:
                 sort_columns.append(search_keys_hash)
-                df[search_keys_hash] = pd.util.hash_pandas_object(df[sorted(other_search_keys)], index=False)
+                df[search_keys_hash] = pd.util.hash_pandas_object(df[other_columns], index=False)
 
             df = df.sort_values(by=sort_columns)
 
@@ -3185,22 +3232,21 @@ class FeaturesEnricher(TransformerMixin):
                 return None
             features_meta = self._search_task.get_all_features_metadata_v2()
 
-            def get_feature_by_display_index(idx, op):
+            def get_feature_by_name(name: str):
                 for m in features_meta:
-                    if m.name.endswith(f"_{op}_{idx}"):
+                    if m.name == name:
                         return m
 
             descriptions = []
             for m in autofe_meta:
                 autofe_feature = Feature.from_formula(m.formula)
+                autofe_feature.set_display_index(m.display_index)
                 if autofe_feature.op.is_vector:
                     continue
 
                 description = dict()
 
-                feature_meta = get_feature_by_display_index(
-                    m.display_index, autofe_feature.op.alias or autofe_feature.op.name
-                )
+                feature_meta = get_feature_by_name(autofe_feature.get_display_name(shorten=True))
                 if feature_meta is None:
                     self.logger.warning(f"Feature meta for display index {m.display_index} not found")
                     continue
@@ -3547,6 +3593,34 @@ class FeaturesEnricher(TransformerMixin):
             self.logger.warning(msg)
             print(msg)
 
+    def _validate_PSI(self, df: pd.DataFrame):
+        if EVAL_SET_INDEX in df.columns:
+            train = df.query(f"{EVAL_SET_INDEX} == 0")
+            eval1 = df.query(f"{EVAL_SET_INDEX} == 1")
+        else:
+            train = df
+            eval1 = None
+
+        # 1. Check train PSI
+        half_train = round(len(train) / 2)
+        part1 = train[:half_train]
+        part2 = train[half_train:]
+        train_psi = calculate_psi(part1[self.TARGET_NAME], part2[self.TARGET_NAME])
+        if train_psi > 0.2:
+            self.warning_counter.increment()
+            msg = self.bundle.get("train_unstable_target").format(train_psi)
+            print(msg)
+            self.logger.warning(msg)
+
+        # 2. Check train-test PSI
+        if eval1 is not None:
+            train_test_psi = calculate_psi(train[self.TARGET_NAME], eval1[self.TARGET_NAME])
+            if train_test_psi > 0.2:
+                self.warning_counter.increment()
+                msg = self.bundle.get("eval_unstable_target").format(train_test_psi)
+                print(msg)
+                self.logger.warning(msg)
+
     def _dump_python_libs(self):
         try:
             from pip._internal.operations.freeze import freeze
@@ -3613,7 +3687,7 @@ class FeaturesEnricher(TransformerMixin):
                     if y is not None:
                         with open(f"{tmp_dir}/y.pickle", "wb") as y_file:
                             pickle.dump(sample(y, xy_sample_index), y_file)
-                        if eval_set is not None:
+                        if eval_set:
                             eval_xy_sample_index = rnd.randint(0, _num_samples(eval_set[0][0]), size=1000)
                             with open(f"{tmp_dir}/eval_x.pickle", "wb") as eval_x_file:
                                 pickle.dump(sample(eval_set[0][0], eval_xy_sample_index), eval_x_file)

upgini/fingerprint.js

@@ -0,0 +1,8 @@
+/**
+ * FingerprintJS v3.4.2 - Copyright (c) FingerprintJS, Inc, 2023 (https://fingerprint.com)
+ * Licensed under the MIT (http://www.opensource.org/licenses/mit-license.php) license.
+ *
+ * This software contains code from open-source projects:
+ * MurmurHash3 by Karan Lyons (https://github.com/karanlyons/murmurHash3.js)
+ */
+var e=function(){return e=Object.assign||function(e){for(var n,t=1,r=arguments.length;t<r;t++)for(var o in n=arguments[t])Object.prototype.hasOwnProperty.call(n,o)&&(e[o]=n[o]);return e},e.apply(this,arguments)};function n(e,n,t,r){return new(t||(t=Promise))((function(o,a){function i(e){try{u(r.next(e))}catch(n){a(n)}}function c(e){try{u(r.throw(e))}catch(n){a(n)}}function u(e){var n;e.done?o(e.value):(n=e.value,n instanceof t?n:new t((function(e){e(n)}))).then(i,c)}u((r=r.apply(e,n||[])).next())}))}function t(e,n){var t,r,o,a,i={label:0,sent:function(){if(1&o[0])throw o[1];return o[1]},trys:[],ops:[]};return a={next:c(0),throw:c(1),return:c(2)},"function"==typeof Symbol&&(a[Symbol.iterator]=function(){return this}),a;function c(c){return function(u){return function(c){if(t)throw new TypeError("Generator is already executing.");for(;a&&(a=0,c[0]&&(i=0)),i;)try{if(t=1,r&&(o=2&c[0]?r.return:c[0]?r.throw||((o=r.return)&&o.call(r),0):r.next)&&!(o=o.call(r,c[1])).done)return o;switch(r=0,o&&(c=[2&c[0],o.value]),c[0]){case 0:case 1:o=c;break;case 4:return i.label++,{value:c[1],done:!1};case 5:i.label++,r=c[1],c=[0];continue;case 7:c=i.ops.pop(),i.trys.pop();continue;default:if(!(o=i.trys,(o=o.length>0&&o[o.length-1])||6!==c[0]&&2!==c[0])){i=0;continue}if(3===c[0]&&(!o||c[1]>o[0]&&c[1]<o[3])){i.label=c[1];break}if(6===c[0]&&i.label<o[1]){i.label=o[1],o=c;break}if(o&&i.label<o[2]){i.label=o[2],i.ops.push(c);break}o[2]&&i.ops.pop(),i.trys.pop();continue}c=n.call(e,i)}catch(u){c=[6,u],r=0}finally{t=o=0}if(5&c[0])throw c[1];return{value:c[0]?c[1]:void 0,done:!0}}([c,u])}}}function r(e,n,t){if(t||2===arguments.length)for(var r,o=0,a=n.length;o<a;o++)!r&&o in n||(r||(r=Array.prototype.slice.call(n,0,o)),r[o]=n[o]);return e.concat(r||Array.prototype.slice.call(n))}function o(e,n){return new Promise((function(t){return setTimeout(t,e,n)}))}function a(e){return!!e&&"function"==typeof e.then}function i(e,n){try{var t=e();a(t)?t.then((function(e){return n(!0,e)}),(function(e){return n(!1,e)})):n(!0,t)}catch(r){n(!1,r)}}function c(e,r,a){return void 0===a&&(a=16),n(this,void 0,void 0,(function(){var n,i,c,u;return t(this,(function(t){switch(t.label){case 0:n=Array(e.length),i=Date.now(),c=0,t.label=1;case 1:return c<e.length?(n[c]=r(e[c],c),(u=Date.now())>=i+a?(i=u,[4,o(0)]):[3,3]):[3,4];case 2:t.sent(),t.label=3;case 3:return++c,[3,1];case 4:return[2,n]}}))}))}function u(e){e.then(void 0,(function(){}))}function l(e,n){e=[e[0]>>>16,65535&e[0],e[1]>>>16,65535&e[1]],n=[n[0]>>>16,65535&n[0],n[1]>>>16,65535&n[1]];var t=[0,0,0,0];return t[3]+=e[3]+n[3],t[2]+=t[3]>>>16,t[3]&=65535,t[2]+=e[2]+n[2],t[1]+=t[2]>>>16,t[2]&=65535,t[1]+=e[1]+n[1],t[0]+=t[1]>>>16,t[1]&=65535,t[0]+=e[0]+n[0],t[0]&=65535,[t[0]<<16|t[1],t[2]<<16|t[3]]}function s(e,n){e=[e[0]>>>16,65535&e[0],e[1]>>>16,65535&e[1]],n=[n[0]>>>16,65535&n[0],n[1]>>>16,65535&n[1]];var t=[0,0,0,0];return t[3]+=e[3]*n[3],t[2]+=t[3]>>>16,t[3]&=65535,t[2]+=e[2]*n[3],t[1]+=t[2]>>>16,t[2]&=65535,t[2]+=e[3]*n[2],t[1]+=t[2]>>>16,t[2]&=65535,t[1]+=e[1]*n[3],t[0]+=t[1]>>>16,t[1]&=65535,t[1]+=e[2]*n[2],t[0]+=t[1]>>>16,t[1]&=65535,t[1]+=e[3]*n[1],t[0]+=t[1]>>>16,t[1]&=65535,t[0]+=e[0]*n[3]+e[1]*n[2]+e[2]*n[1]+e[3]*n[0],t[0]&=65535,[t[0]<<16|t[1],t[2]<<16|t[3]]}function d(e,n){return 32===(n%=64)?[e[1],e[0]]:n<32?[e[0]<<n|e[1]>>>32-n,e[1]<<n|e[0]>>>32-n]:(n-=32,[e[1]<<n|e[0]>>>32-n,e[0]<<n|e[1]>>>32-n])}function m(e,n){return 0===(n%=64)?e:n<32?[e[0]<<n|e[1]>>>32-n,e[1]<<n]:[e[1]<<n-32,0]}function f(e,n){return[e[0]^n[0],e[1]^n[1]]}function v(e){return e=f(e,[0,e[0]>>>1]),e=f(e=s(e,[4283543511,3981806797]),[0,e[0]>>>1]),e=f(e=s(e,[3301882366,444984403]),[0,e[0]>>>1])}function h(e,n){n=n||0;var t,r=(e=e||"").length%16,o=e.length-r,a=[0,n],i=[0,n],c=[0,0],u=[0,0],h=[2277735313,289559509],p=[1291169091,658871167];for(t=0;t<o;t+=16)c=[255&e.charCodeAt(t+4)|(255&e.charCodeAt(t+5))<<8|(255&e.charCodeAt(t+6))<<16|(255&e.charCodeAt(t+7))<<24,255&e.charCodeAt(t)|(255&e.charCodeAt(t+1))<<8|(255&e.charCodeAt(t+2))<<16|(255&e.charCodeAt(t+3))<<24],u=[255&e.charCodeAt(t+12)|(255&e.charCodeAt(t+13))<<8|(255&e.charCodeAt(t+14))<<16|(255&e.charCodeAt(t+15))<<24,255&e.charCodeAt(t+8)|(255&e.charCodeAt(t+9))<<8|(255&e.charCodeAt(t+10))<<16|(255&e.charCodeAt(t+11))<<24],c=d(c=s(c,h),31),a=l(a=d(a=f(a,c=s(c,p)),27),i),a=l(s(a,[0,5]),[0,1390208809]),u=d(u=s(u,p),33),i=l(i=d(i=f(i,u=s(u,h)),31),a),i=l(s(i,[0,5]),[0,944331445]);switch(c=[0,0],u=[0,0],r){case 15:u=f(u,m([0,e.charCodeAt(t+14)],48));case 14:u=f(u,m([0,e.charCodeAt(t+13)],40));case 13:u=f(u,m([0,e.charCodeAt(t+12)],32));case 12:u=f(u,m([0,e.charCodeAt(t+11)],24));case 11:u=f(u,m([0,e.charCodeAt(t+10)],16));case 10:u=f(u,m([0,e.charCodeAt(t+9)],8));case 9:u=s(u=f(u,[0,e.charCodeAt(t+8)]),p),i=f(i,u=s(u=d(u,33),h));case 8:c=f(c,m([0,e.charCodeAt(t+7)],56));case 7:c=f(c,m([0,e.charCodeAt(t+6)],48));case 6:c=f(c,m([0,e.charCodeAt(t+5)],40));case 5:c=f(c,m([0,e.charCodeAt(t+4)],32));case 4:c=f(c,m([0,e.charCodeAt(t+3)],24));case 3:c=f(c,m([0,e.charCodeAt(t+2)],16));case 2:c=f(c,m([0,e.charCodeAt(t+1)],8));case 1:c=s(c=f(c,[0,e.charCodeAt(t)]),h),a=f(a,c=s(c=d(c,31),p))}return a=l(a=f(a,[0,e.length]),i=f(i,[0,e.length])),i=l(i,a),a=l(a=v(a),i=v(i)),i=l(i,a),("00000000"+(a[0]>>>0).toString(16)).slice(-8)+("00000000"+(a[1]>>>0).toString(16)).slice(-8)+("00000000"+(i[0]>>>0).toString(16)).slice(-8)+("00000000"+(i[1]>>>0).toString(16)).slice(-8)}function p(e){return parseInt(e)}function b(e){return parseFloat(e)}function y(e,n){return"number"==typeof e&&isNaN(e)?n:e}function g(e){return e.reduce((function(e,n){return e+(n?1:0)}),0)}function w(e,n){if(void 0===n&&(n=1),Math.abs(n)>=1)return Math.round(e/n)*n;var t=1/n;return Math.round(e*t)/t}function L(e){return e&&"object"==typeof e&&"message"in e?e:{message:e}}function k(e){return"function"!=typeof e}function V(e,r,o){var a=Object.keys(e).filter((function(e){return!function(e,n){for(var t=0,r=e.length;t<r;++t)if(e[t]===n)return!0;return!1}(o,e)})),l=c(a,(function(n){return function(e,n){var t=new Promise((function(t){var r=Date.now();i(e.bind(null,n),(function(){for(var e=[],n=0;n<arguments.length;n++)e[n]=arguments[n];var o=Date.now()-r;if(!e[0])return t((function(){return{error:L(e[1]),duration:o}}));var a=e[1];if(k(a))return t((function(){return{value:a,duration:o}}));t((function(){return new Promise((function(e){var n=Date.now();i(a,(function(){for(var t=[],r=0;r<arguments.length;r++)t[r]=arguments[r];var a=o+Date.now()-n;if(!t[0])return e({error:L(t[1]),duration:a});e({value:t[1],duration:a})}))}))}))}))}));return u(t),function(){return t.then((function(e){return e()}))}}(e[n],r)}));return u(l),function(){return n(this,void 0,void 0,(function(){var e,n,r,o;return t(this,(function(t){switch(t.label){case 0:return[4,l];case 1:return[4,c(t.sent(),(function(e){var n=e();return u(n),n}))];case 2:return e=t.sent(),[4,Promise.all(e)];case 3:for(n=t.sent(),r={},o=0;o<a.length;++o)r[a[o]]=n[o];return[2,r]}}))}))}}function Z(e,n){var t=function(e){return k(e)?n(e):function(){var t=e();return a(t)?t.then(n):n(t)}};return function(n){var r=e(n);return a(r)?r.then(t):t(r)}}function W(){var e=window,n=navigator;return g(["MSCSSMatrix"in e,"msSetImmediate"in e,"msIndexedDB"in e,"msMaxTouchPoints"in n,"msPointerEnabled"in n])>=4}function C(){var e=window,n=navigator;return g(["msWriteProfilerMark"in e,"MSStream"in e,"msLaunchUri"in n,"msSaveBlob"in n])>=3&&!W()}function S(){var e=window,n=navigator;return g(["webkitPersistentStorage"in n,"webkitTemporaryStorage"in n,0===n.vendor.indexOf("Google"),"webkitResolveLocalFileSystemURL"in e,"BatteryManager"in e,"webkitMediaStream"in e,"webkitSpeechGrammar"in e])>=5}function x(){var e=window,n=navigator;return g(["ApplePayError"in e,"CSSPrimitiveValue"in e,"Counter"in e,0===n.vendor.indexOf("Apple"),"getStorageUpdates"in n,"WebKitMediaKeys"in e])>=4}function F(){var e=window;return g(["safari"in e,!("DeviceMotionEvent"in e),!("ongestureend"in e),!("standalone"in navigator)])>=3}function Y(){var e,n,t=window;return g(["buildID"in navigator,"MozAppearance"in(null!==(n=null===(e=document.documentElement)||void 0===e?void 0:e.style)&&void 0!==n?n:{}),"onmozfullscreenchange"in t,"mozInnerScreenX"in t,"CSSMozDocumentRule"in t,"CanvasCaptureMediaStream"in t])>=4}function M(){var e=document;return e.fullscreenElement||e.msFullscreenElement||e.mozFullScreenElement||e.webkitFullscreenElement||null}function G(){var e=S(),n=Y();if(!e&&!n)return!1;var t=window;return g(["onorientationchange"in t,"orientation"in t,e&&!("SharedWorker"in t),n&&/android/i.test(navigator.appVersion)])>=2}function R(e){var n=new Error(e);return n.name=e,n}function X(e,r,a){var i,c,u;return void 0===a&&(a=50),n(this,void 0,void 0,(function(){var n,l;return t(this,(function(t){switch(t.label){case 0:n=document,t.label=1;case 1:return n.body?[3,3]:[4,o(a)];case 2:return t.sent(),[3,1];case 3:l=n.createElement("iframe"),t.label=4;case 4:return t.trys.push([4,,10,11]),[4,new Promise((function(e,t){var o=!1,a=function(){o=!0,e()};l.onload=a,l.onerror=function(e){o=!0,t(e)};var i=l.style;i.setProperty("display","block","important"),i.position="absolute",i.top="0",i.left="0",i.visibility="hidden",r&&"srcdoc"in l?l.srcdoc=r:l.src="about:blank",n.body.appendChild(l);var c=function(){var e,n;o||("complete"===(null===(n=null===(e=l.contentWindow)||void 0===e?void 0:e.document)||void 0===n?void 0:n.readyState)?a():setTimeout(c,10))};c()}))];case 5:t.sent(),t.label=6;case 6:return(null===(c=null===(i=l.contentWindow)||void 0===i?void 0:i.document)||void 0===c?void 0:c.body)?[3,8]:[4,o(a)];case 7:return t.sent(),[3,6];case 8:return[4,e(l,l.contentWindow)];case 9:return[2,t.sent()];case 10:return null===(u=l.parentNode)||void 0===u||u.removeChild(l),[7];case 11:return[2]}}))}))}function A(e){for(var n=function(e){for(var n,t,r="Unexpected syntax '".concat(e,"'"),o=/^\s*([a-z-]*)(.*)$/i.exec(e),a=o[1]||void 0,i={},c=/([.:#][\w-]+|\[.+?\])/gi,u=function(e,n){i[e]=i[e]||[],i[e].push(n)};;){var l=c.exec(o[2]);if(!l)break;var s=l[0];switch(s[0]){case".":u("class",s.slice(1));break;case"#":u("id",s.slice(1));break;case"[":var d=/^\[([\w-]+)([~|^$*]?=("(.*?)"|([\w-]+)))?(\s+[is])?\]$/.exec(s);if(!d)throw new Error(r);u(d[1],null!==(t=null!==(n=d[4])&&void 0!==n?n:d[5])&&void 0!==t?t:"");break;default:throw new Error(r)}}return[a,i]}(e),t=n[0],r=n[1],o=document.createElement(null!=t?t:"div"),a=0,i=Object.keys(r);a<i.length;a++){var c=i[a],u=r[c].join(" ");"style"===c?j(o.style,u):o.setAttribute(c,u)}return o}function j(e,n){for(var t=0,r=n.split(";");t<r.length;t++){var o=r[t],a=/^\s*([\w-]+)\s*:\s*(.+?)(\s*!([\w-]+))?\s*$/.exec(o);if(a){var i=a[1],c=a[2],u=a[4];e.setProperty(i,c,u||"")}}}var I=["monospace","sans-serif","serif"],J=["sans-serif-thin","ARNO PRO","Agency FB","Arabic Typesetting","Arial Unicode MS","AvantGarde Bk BT","BankGothic Md BT","Batang","Bitstream Vera Sans Mono","Calibri","Century","Century Gothic","Clarendon","EUROSTILE","Franklin Gothic","Futura Bk BT","Futura Md BT","GOTHAM","Gill Sans","HELV","Haettenschweiler","Helvetica Neue","Humanst521 BT","Leelawadee","Letter Gothic","Levenim MT","Lucida Bright","Lucida Sans","Menlo","MS Mincho","MS Outlook","MS Reference Specialty","MS UI Gothic","MT Extra","MYRIAD PRO","Marlett","Meiryo UI","Microsoft Uighur","Minion Pro","Monotype Corsiva","PMingLiU","Pristina","SCRIPTINA","Segoe UI Light","Serifa","SimHei","Small Fonts","Staccato222 BT","TRAJAN PRO","Univers CE 55 Medium","Vrinda","ZWAdobeF"];function H(e){return e.toDataURL()}var P,N;function z(){var e=this;return function(){if(void 0===N){var e=function(){var n=D();E(n)?N=setTimeout(e,2500):(P=n,N=void 0)};e()}}(),function(){return n(e,void 0,void 0,(function(){var e;return t(this,(function(n){switch(n.label){case 0:return E(e=D())?P?[2,r([],P,!0)]:M()?[4,(t=document,(t.exitFullscreen||t.msExitFullscreen||t.mozCancelFullScreen||t.webkitExitFullscreen).call(t))]:[3,2]:[3,2];case 1:n.sent(),e=D(),n.label=2;case 2:return E(e)||(P=e),[2,e]}var t}))}))}}function D(){var e=screen;return[y(b(e.availTop),null),y(b(e.width)-b(e.availWidth)-y(b(e.availLeft),0),null),y(b(e.height)-b(e.availHeight)-y(b(e.availTop),0),null),y(b(e.availLeft),null)]}function E(e){for(var n=0;n<4;++n)if(e[n])return!1;return!0}function T(e){var r;return n(this,void 0,void 0,(function(){var n,a,i,c,u,l,s;return t(this,(function(t){switch(t.label){case 0:for(n=document,a=n.createElement("div"),i=new Array(e.length),c={},B(a),s=0;s<e.length;++s)"DIALOG"===(u=A(e[s])).tagName&&u.show(),B(l=n.createElement("div")),l.appendChild(u),a.appendChild(l),i[s]=u;t.label=1;case 1:return n.body?[3,3]:[4,o(50)];case 2:return t.sent(),[3,1];case 3:n.body.appendChild(a);try{for(s=0;s<e.length;++s)i[s].offsetParent||(c[e[s]]=!0)}finally{null===(r=a.parentNode)||void 0===r||r.removeChild(a)}return[2,c]}}))}))}function B(e){e.style.setProperty("display","block","important")}function _(e){return matchMedia("(inverted-colors: ".concat(e,")")).matches}function O(e){return matchMedia("(forced-colors: ".concat(e,")")).matches}function U(e){return matchMedia("(prefers-contrast: ".concat(e,")")).matches}function Q(e){return matchMedia("(prefers-reduced-motion: ".concat(e,")")).matches}function K(e){return matchMedia("(dynamic-range: ".concat(e,")")).matches}var q=Math,$=function(){return 0};var ee={default:[],apple:[{font:"-apple-system-body"}],serif:[{fontFamily:"serif"}],sans:[{fontFamily:"sans-serif"}],mono:[{fontFamily:"monospace"}],min:[{fontSize:"1px"}],system:[{fontFamily:"system-ui"}]};var ne={fonts:function(){return X((function(e,n){var t=n.document,r=t.body;r.style.fontSize="48px";var o=t.createElement("div"),a={},i={},c=function(e){var n=t.createElement("span"),r=n.style;return r.position="absolute",r.top="0",r.left="0",r.fontFamily=e,n.textContent="mmMwWLliI0O&1",o.appendChild(n),n},u=I.map(c),l=function(){for(var e={},n=function(n){e[n]=I.map((function(e){return function(e,n){return c("'".concat(e,"',").concat(n))}(n,e)}))},t=0,r=J;t<r.length;t++){n(r[t])}return e}();r.appendChild(o);for(var s=0;s<I.length;s++)a[I[s]]=u[s].offsetWidth,i[I[s]]=u[s].offsetHeight;return J.filter((function(e){return n=l[e],I.some((function(e,t){return n[t].offsetWidth!==a[e]||n[t].offsetHeight!==i[e]}));var n}))}))},domBlockers:function(e){var r=(void 0===e?{}:e).debug;return n(this,void 0,void 0,(function(){var e,n,o,a,i;return t(this,(function(t){switch(t.label){case 0:return x()||G()?(c=atob,e={abpIndo:["#Iklan-Melayang","#Kolom-Iklan-728","#SidebarIklan-wrapper",'[title="ALIENBOLA" i]',c("I0JveC1CYW5uZXItYWRz")],abpvn:[".quangcao","#mobileCatfish",c("LmNsb3NlLWFkcw=="),'[id^="bn_bottom_fixed_"]',"#pmadv"],adBlockFinland:[".mainostila",c("LnNwb25zb3JpdA=="),".ylamainos",c("YVtocmVmKj0iL2NsaWNrdGhyZ2guYXNwPyJd"),c("YVtocmVmXj0iaHR0cHM6Ly9hcHAucmVhZHBlYWsuY29tL2FkcyJd")],adBlockPersian:["#navbar_notice_50",".kadr",'TABLE[width="140px"]',"#divAgahi",c("YVtocmVmXj0iaHR0cDovL2cxLnYuZndtcm0ubmV0L2FkLyJd")],adBlockWarningRemoval:["#adblock-honeypot",".adblocker-root",".wp_adblock_detect",c("LmhlYWRlci1ibG9ja2VkLWFk"),c("I2FkX2Jsb2NrZXI=")],adGuardAnnoyances:[".hs-sosyal","#cookieconsentdiv",'div[class^="app_gdpr"]',".as-oil",'[data-cypress="soft-push-notification-modal"]'],adGuardBase:[".BetterJsPopOverlay",c("I2FkXzMwMFgyNTA="),c("I2Jhbm5lcmZsb2F0MjI="),c("I2NhbXBhaWduLWJhbm5lcg=="),c("I0FkLUNvbnRlbnQ=")],adGuardChinese:[c("LlppX2FkX2FfSA=="),c("YVtocmVmKj0iLmh0aGJldDM0LmNvbSJd"),"#widget-quan",c("YVtocmVmKj0iLzg0OTkyMDIwLnh5eiJd"),c("YVtocmVmKj0iLjE5NTZobC5jb20vIl0=")],adGuardFrench:["#pavePub",c("LmFkLWRlc2t0b3AtcmVjdGFuZ2xl"),".mobile_adhesion",".widgetadv",c("LmFkc19iYW4=")],adGuardGerman:['aside[data-portal-id="leaderboard"]'],adGuardJapanese:["#kauli_yad_1",c("YVtocmVmXj0iaHR0cDovL2FkMi50cmFmZmljZ2F0ZS5uZXQvIl0="),c("Ll9wb3BJbl9pbmZpbml0ZV9hZA=="),c("LmFkZ29vZ2xl"),c("Ll9faXNib29zdFJldHVybkFk")],adGuardMobile:[c("YW1wLWF1dG8tYWRz"),c("LmFtcF9hZA=="),'amp-embed[type="24smi"]',"#mgid_iframe1",c("I2FkX2ludmlld19hcmVh")],adGuardRussian:[c("YVtocmVmXj0iaHR0cHM6Ly9hZC5sZXRtZWFkcy5jb20vIl0="),c("LnJlY2xhbWE="),'div[id^="smi2adblock"]',c("ZGl2W2lkXj0iQWRGb3hfYmFubmVyXyJd"),"#psyduckpockeball"],adGuardSocial:[c("YVtocmVmXj0iLy93d3cuc3R1bWJsZXVwb24uY29tL3N1Ym1pdD91cmw9Il0="),c("YVtocmVmXj0iLy90ZWxlZ3JhbS5tZS9zaGFyZS91cmw/Il0="),".etsy-tweet","#inlineShare",".popup-social"],adGuardSpanishPortuguese:["#barraPublicidade","#Publicidade","#publiEspecial","#queTooltip",".cnt-publi"],adGuardTrackingProtection:["#qoo-counter",c("YVtocmVmXj0iaHR0cDovL2NsaWNrLmhvdGxvZy5ydS8iXQ=="),c("YVtocmVmXj0iaHR0cDovL2hpdGNvdW50ZXIucnUvdG9wL3N0YXQucGhwIl0="),c("YVtocmVmXj0iaHR0cDovL3RvcC5tYWlsLnJ1L2p1bXAiXQ=="),"#top100counter"],adGuardTurkish:["#backkapat",c("I3Jla2xhbWk="),c("YVtocmVmXj0iaHR0cDovL2Fkc2Vydi5vbnRlay5jb20udHIvIl0="),c("YVtocmVmXj0iaHR0cDovL2l6bGVuemkuY29tL2NhbXBhaWduLyJd"),c("YVtocmVmXj0iaHR0cDovL3d3dy5pbnN0YWxsYWRzLm5ldC8iXQ==")],bulgarian:[c("dGQjZnJlZW5ldF90YWJsZV9hZHM="),"#ea_intext_div",".lapni-pop-over","#xenium_hot_offers"],easyList:[".yb-floorad",c("LndpZGdldF9wb19hZHNfd2lkZ2V0"),c("LnRyYWZmaWNqdW5reS1hZA=="),".textad_headline",c("LnNwb25zb3JlZC10ZXh0LWxpbmtz")],easyListChina:[c("LmFwcGd1aWRlLXdyYXBbb25jbGljayo9ImJjZWJvcy5jb20iXQ=="),c("LmZyb250cGFnZUFkdk0="),"#taotaole","#aafoot.top_box",".cfa_popup"],easyListCookie:[".ezmob-footer",".cc-CookieWarning","[data-cookie-number]",c("LmF3LWNvb2tpZS1iYW5uZXI="),".sygnal24-gdpr-modal-wrap"],easyListCzechSlovak:["#onlajny-stickers",c("I3Jla2xhbW5pLWJveA=="),c("LnJla2xhbWEtbWVnYWJvYXJk"),".sklik",c("W2lkXj0ic2tsaWtSZWtsYW1hIl0=")],easyListDutch:[c("I2FkdmVydGVudGll"),c("I3ZpcEFkbWFya3RCYW5uZXJCbG9jaw=="),".adstekst",c("YVtocmVmXj0iaHR0cHM6Ly94bHR1YmUubmwvY2xpY2svIl0="),"#semilo-lrectangle"],easyListGermany:["#SSpotIMPopSlider",c("LnNwb25zb3JsaW5rZ3J1ZW4="),c("I3dlcmJ1bmdza3k="),c("I3Jla2xhbWUtcmVjaHRzLW1pdHRl"),c("YVtocmVmXj0iaHR0cHM6Ly9iZDc0Mi5jb20vIl0=")],easyListItaly:[c("LmJveF9hZHZfYW5udW5jaQ=="),".sb-box-pubbliredazionale",c("YVtocmVmXj0iaHR0cDovL2FmZmlsaWF6aW9uaWFkcy5zbmFpLml0LyJd"),c("YVtocmVmXj0iaHR0cHM6Ly9hZHNlcnZlci5odG1sLml0LyJd"),c("YVtocmVmXj0iaHR0cHM6Ly9hZmZpbGlhemlvbmlhZHMuc25haS5pdC8iXQ==")],easyListLithuania:[c("LnJla2xhbW9zX3RhcnBhcw=="),c("LnJla2xhbW9zX251b3JvZG9z"),c("aW1nW2FsdD0iUmVrbGFtaW5pcyBza3lkZWxpcyJd"),c("aW1nW2FsdD0iRGVkaWt1b3RpLmx0IHNlcnZlcmlhaSJd"),c("aW1nW2FsdD0iSG9zdGluZ2FzIFNlcnZlcmlhaS5sdCJd")],estonian:[c("QVtocmVmKj0iaHR0cDovL3BheTRyZXN1bHRzMjQuZXUiXQ==")],fanboyAnnoyances:["#ac-lre-player",".navigate-to-top","#subscribe_popup",".newsletter_holder","#back-top"],fanboyAntiFacebook:[".util-bar-module-firefly-visible"],fanboyEnhancedTrackers:[".open.pushModal","#issuem-leaky-paywall-articles-zero-remaining-nag","#sovrn_container",'div[class$="-hide"][zoompage-fontsize][style="display: block;"]',".BlockNag__Card"],fanboySocial:["#FollowUs","#meteored_share","#social_follow",".article-sharer",".community__social-desc"],frellwitSwedish:[c("YVtocmVmKj0iY2FzaW5vcHJvLnNlIl1bdGFyZ2V0PSJfYmxhbmsiXQ=="),c("YVtocmVmKj0iZG9rdG9yLXNlLm9uZWxpbmsubWUiXQ=="),"article.category-samarbete",c("ZGl2LmhvbGlkQWRz"),"ul.adsmodern"],greekAdBlock:[c("QVtocmVmKj0iYWRtYW4ub3RlbmV0LmdyL2NsaWNrPyJd"),c("QVtocmVmKj0iaHR0cDovL2F4aWFiYW5uZXJzLmV4b2R1cy5nci8iXQ=="),c("QVtocmVmKj0iaHR0cDovL2ludGVyYWN0aXZlLmZvcnRobmV0LmdyL2NsaWNrPyJd"),"DIV.agores300","TABLE.advright"],hungarian:["#cemp_doboz",".optimonk-iframe-container",c("LmFkX19tYWlu"),c("W2NsYXNzKj0iR29vZ2xlQWRzIl0="),"#hirdetesek_box"],iDontCareAboutCookies:['.alert-info[data-block-track*="CookieNotice"]',".ModuleTemplateCookieIndicator",".o--cookies--container","#cookies-policy-sticky","#stickyCookieBar"],icelandicAbp:[c("QVtocmVmXj0iL2ZyYW1ld29yay9yZXNvdXJjZXMvZm9ybXMvYWRzLmFzcHgiXQ==")],latvian:[c("YVtocmVmPSJodHRwOi8vd3d3LnNhbGlkemluaS5sdi8iXVtzdHlsZT0iZGlzcGxheTogYmxvY2s7IHdpZHRoOiAxMjBweDsgaGVpZ2h0OiA0MHB4OyBvdmVyZmxvdzogaGlkZGVuOyBwb3NpdGlvbjogcmVsYXRpdmU7Il0="),c("YVtocmVmPSJodHRwOi8vd3d3LnNhbGlkemluaS5sdi8iXVtzdHlsZT0iZGlzcGxheTogYmxvY2s7IHdpZHRoOiA4OHB4OyBoZWlnaHQ6IDMxcHg7IG92ZXJmbG93OiBoaWRkZW47IHBvc2l0aW9uOiByZWxhdGl2ZTsiXQ==")],listKr:[c("YVtocmVmKj0iLy9hZC5wbGFuYnBsdXMuY28ua3IvIl0="),c("I2xpdmVyZUFkV3JhcHBlcg=="),c("YVtocmVmKj0iLy9hZHYuaW1hZHJlcC5jby5rci8iXQ=="),c("aW5zLmZhc3R2aWV3LWFk"),".revenue_unit_item.dable"],listeAr:[c("LmdlbWluaUxCMUFk"),".right-and-left-sponsers",c("YVtocmVmKj0iLmFmbGFtLmluZm8iXQ=="),c("YVtocmVmKj0iYm9vcmFxLm9yZyJd"),c("YVtocmVmKj0iZHViaXp6bGUuY29tL2FyLz91dG1fc291cmNlPSJd")],listeFr:[c("YVtocmVmXj0iaHR0cDovL3Byb21vLnZhZG9yLmNvbS8iXQ=="),c("I2FkY29udGFpbmVyX3JlY2hlcmNoZQ=="),c("YVtocmVmKj0id2Vib3JhbWEuZnIvZmNnaS1iaW4vIl0="),".site-pub-interstitiel",'div[id^="crt-"][data-criteo-id]'],officialPolish:["#ceneo-placeholder-ceneo-12",c("W2hyZWZePSJodHRwczovL2FmZi5zZW5kaHViLnBsLyJd"),c("YVtocmVmXj0iaHR0cDovL2Fkdm1hbmFnZXIudGVjaGZ1bi5wbC9yZWRpcmVjdC8iXQ=="),c("YVtocmVmXj0iaHR0cDovL3d3dy50cml6ZXIucGwvP3V0bV9zb3VyY2UiXQ=="),c("ZGl2I3NrYXBpZWNfYWQ=")],ro:[c("YVtocmVmXj0iLy9hZmZ0cmsuYWx0ZXgucm8vQ291bnRlci9DbGljayJd"),c("YVtocmVmXj0iaHR0cHM6Ly9ibGFja2ZyaWRheXNhbGVzLnJvL3Ryay9zaG9wLyJd"),c("YVtocmVmXj0iaHR0cHM6Ly9ldmVudC4ycGVyZm9ybWFudC5jb20vZXZlbnRzL2NsaWNrIl0="),c("YVtocmVmXj0iaHR0cHM6Ly9sLnByb2ZpdHNoYXJlLnJvLyJd"),'a[href^="/url/"]'],ruAd:[c("YVtocmVmKj0iLy9mZWJyYXJlLnJ1LyJd"),c("YVtocmVmKj0iLy91dGltZy5ydS8iXQ=="),c("YVtocmVmKj0iOi8vY2hpa2lkaWtpLnJ1Il0="),"#pgeldiz",".yandex-rtb-block"],thaiAds:["a[href*=macau-uta-popup]",c("I2Fkcy1nb29nbGUtbWlkZGxlX3JlY3RhbmdsZS1ncm91cA=="),c("LmFkczMwMHM="),".bumq",".img-kosana"],webAnnoyancesUltralist:["#mod-social-share-2","#social-tools",c("LmN0cGwtZnVsbGJhbm5lcg=="),".zergnet-recommend",".yt.btn-link.btn-md.btn"]},n=Object.keys(e),[4,T((i=[]).concat.apply(i,n.map((function(n){return e[n]}))))]):[2,void 0];case 1:return o=t.sent(),r&&function(e,n){for(var t="DOM blockers debug:\n```",r=0,o=Object.keys(e);r<o.length;r++){var a=o[r];t+="\n".concat(a,":");for(var i=0,c=e[a];i<c.length;i++){var u=c[i];t+="\n  ".concat(n[u]?"🚫":"➡️"," ").concat(u)}}console.log("".concat(t,"\n```"))}(e,o),(a=n.filter((function(n){var t=e[n];return g(t.map((function(e){return o[e]})))>.6*t.length}))).sort(),[2,a]}var c}))}))},fontPreferences:function(){return function(e,n){void 0===n&&(n=4e3);return X((function(t,o){var a=o.document,i=a.body,c=i.style;c.width="".concat(n,"px"),c.webkitTextSizeAdjust=c.textSizeAdjust="none",S()?i.style.zoom="".concat(1/o.devicePixelRatio):x()&&(i.style.zoom="reset");var u=a.createElement("div");return u.textContent=r([],Array(n/20<<0),!0).map((function(){return"word"})).join(" "),i.appendChild(u),e(a,i)}),'<!doctype html><html><head><meta name="viewport" content="width=device-width, initial-scale=1">')}((function(e,n){for(var t={},r={},o=0,a=Object.keys(ee);o<a.length;o++){var i=a[o],c=ee[i],u=c[0],l=void 0===u?{}:u,s=c[1],d=void 0===s?"mmMwWLliI0fiflO&1":s,m=e.createElement("span");m.textContent=d,m.style.whiteSpace="nowrap";for(var f=0,v=Object.keys(l);f<v.length;f++){var h=v[f],p=l[h];void 0!==p&&(m.style[h]=p)}t[i]=m,n.appendChild(e.createElement("br")),n.appendChild(m)}for(var b=0,y=Object.keys(ee);b<y.length;b++){r[i=y[b]]=t[i].getBoundingClientRect().width}return r}))},audio:function(){var e=window,n=e.OfflineAudioContext||e.webkitOfflineAudioContext;if(!n)return-2;if(x()&&!F()&&!function(){var e=window;return g(["DOMRectList"in e,"RTCPeerConnectionIceEvent"in e,"SVGGeometryElement"in e,"ontransitioncancel"in e])>=3}())return-1;var t=new n(1,5e3,44100),r=t.createOscillator();r.type="triangle",r.frequency.value=1e4;var o=t.createDynamicsCompressor();o.threshold.value=-50,o.knee.value=40,o.ratio.value=12,o.attack.value=0,o.release.value=.25,r.connect(o),o.connect(t.destination),r.start(0);var i=function(e){var n=3,t=500,r=500,o=5e3,i=function(){};return[new Promise((function(c,l){var s=!1,d=0,m=0;e.oncomplete=function(e){return c(e.renderedBuffer)};var f=function(){setTimeout((function(){return l(R("timeout"))}),Math.min(r,m+o-Date.now()))},v=function(){try{var r=e.startRendering();switch(a(r)&&u(r),e.state){case"running":m=Date.now(),s&&f();break;case"suspended":document.hidden||d++,s&&d>=n?l(R("suspended")):setTimeout(v,t)}}catch(o){l(o)}};v(),i=function(){s||(s=!0,m>0&&f())}})),i]}(t),c=i[0],l=i[1],s=c.then((function(e){return function(e){for(var n=0,t=0;t<e.length;++t)n+=Math.abs(e[t]);return n}(e.getChannelData(0).subarray(4500))}),(function(e){if("timeout"===e.name||"suspended"===e.name)return-3;throw e}));return u(s),function(){return l(),s}},screenFrame:function(){var e=this,r=z();return function(){return n(e,void 0,void 0,(function(){var e,n;return t(this,(function(t){switch(t.label){case 0:return[4,r()];case 1:return e=t.sent(),[2,[(n=function(e){return null===e?null:w(e,10)})(e[0]),n(e[1]),n(e[2]),n(e[3])]]}}))}))}},osCpu:function(){return navigator.oscpu},languages:function(){var e,n=navigator,t=[],r=n.language||n.userLanguage||n.browserLanguage||n.systemLanguage;if(void 0!==r&&t.push([r]),Array.isArray(n.languages))S()&&g([!("MediaSettingsRange"in(e=window)),"RTCEncodedAudioFrame"in e,""+e.Intl=="[object Intl]",""+e.Reflect=="[object Reflect]"])>=3||t.push(n.languages);else if("string"==typeof n.languages){var o=n.languages;o&&t.push(o.split(","))}return t},colorDepth:function(){return window.screen.colorDepth},deviceMemory:function(){return y(b(navigator.deviceMemory),void 0)},screenResolution:function(){var e=screen,n=function(e){return y(p(e),null)},t=[n(e.width),n(e.height)];return t.sort().reverse(),t},hardwareConcurrency:function(){return y(p(navigator.hardwareConcurrency),void 0)},timezone:function(){var e,n=null===(e=window.Intl)||void 0===e?void 0:e.DateTimeFormat;if(n){var t=(new n).resolvedOptions().timeZone;if(t)return t}var r,o=(r=(new Date).getFullYear(),-Math.max(b(new Date(r,0,1).getTimezoneOffset()),b(new Date(r,6,1).getTimezoneOffset())));return"UTC".concat(o>=0?"+":"").concat(Math.abs(o))},sessionStorage:function(){try{return!!window.sessionStorage}catch(e){return!0}},localStorage:function(){try{return!!window.localStorage}catch(e){return!0}},indexedDB:function(){if(!W()&&!C())try{return!!window.indexedDB}catch(e){return!0}},openDatabase:function(){return!!window.openDatabase},cpuClass:function(){return navigator.cpuClass},platform:function(){var e=navigator.platform;return"MacIntel"===e&&x()&&!F()?function(){if("iPad"===navigator.platform)return!0;var e=screen,n=e.width/e.height;return g(["MediaSource"in window,!!Element.prototype.webkitRequestFullscreen,n>.65&&n<1.53])>=2}()?"iPad":"iPhone":e},plugins:function(){var e=navigator.plugins;if(e){for(var n=[],t=0;t<e.length;++t){var r=e[t];if(r){for(var o=[],a=0;a<r.length;++a){var i=r[a];o.push({type:i.type,suffixes:i.suffixes})}n.push({name:r.name,description:r.description,mimeTypes:o})}}return n}},canvas:function(){var e,n,t=!1,r=function(){var e=document.createElement("canvas");return e.width=1,e.height=1,[e,e.getContext("2d")]}(),o=r[0],a=r[1];if(function(e,n){return!(!n||!e.toDataURL)}(o,a)){t=function(e){return e.rect(0,0,10,10),e.rect(2,2,6,6),!e.isPointInPath(5,5,"evenodd")}(a),function(e,n){e.width=240,e.height=60,n.textBaseline="alphabetic",n.fillStyle="#f60",n.fillRect(100,1,62,20),n.fillStyle="#069",n.font='11pt "Times New Roman"';var t="Cwm fjordbank gly ".concat(String.fromCharCode(55357,56835));n.fillText(t,2,15),n.fillStyle="rgba(102, 204, 0, 0.2)",n.font="18pt Arial",n.fillText(t,4,45)}(o,a);var i=H(o);i!==H(o)?e=n="unstable":(n=i,function(e,n){e.width=122,e.height=110,n.globalCompositeOperation="multiply";for(var t=0,r=[["#f2f",40,40],["#2ff",80,40],["#ff2",60,80]];t<r.length;t++){var o=r[t],a=o[0],i=o[1],c=o[2];n.fillStyle=a,n.beginPath(),n.arc(i,c,40,0,2*Math.PI,!0),n.closePath(),n.fill()}n.fillStyle="#f9c",n.arc(60,60,60,0,2*Math.PI,!0),n.arc(60,60,20,0,2*Math.PI,!0),n.fill("evenodd")}(o,a),e=H(o))}else e=n="";return{winding:t,geometry:e,text:n}},touchSupport:function(){var e,n=navigator,t=0;void 0!==n.maxTouchPoints?t=p(n.maxTouchPoints):void 0!==n.msMaxTouchPoints&&(t=n.msMaxTouchPoints);try{document.createEvent("TouchEvent"),e=!0}catch(r){e=!1}return{maxTouchPoints:t,touchEvent:e,touchStart:"ontouchstart"in window}},vendor:function(){return navigator.vendor||""},vendorFlavors:function(){for(var e=[],n=0,t=["chrome","safari","__crWeb","__gCrWeb","yandex","__yb","__ybro","__firefox__","__edgeTrackingPreventionStatistics","webkit","oprt","samsungAr","ucweb","UCShellJava","puffinDevice"];n<t.length;n++){var r=t[n],o=window[r];o&&"object"==typeof o&&e.push(r)}return e.sort()},cookiesEnabled:function(){var e=document;try{e.cookie="cookietest=1; SameSite=Strict;";var n=-1!==e.cookie.indexOf("cookietest=");return e.cookie="cookietest=1; SameSite=Strict; expires=Thu, 01-Jan-1970 00:00:01 GMT",n}catch(t){return!1}},colorGamut:function(){for(var e=0,n=["rec2020","p3","srgb"];e<n.length;e++){var t=n[e];if(matchMedia("(color-gamut: ".concat(t,")")).matches)return t}},invertedColors:function(){return!!_("inverted")||!_("none")&&void 0},forcedColors:function(){return!!O("active")||!O("none")&&void 0},monochrome:function(){if(matchMedia("(min-monochrome: 0)").matches){for(var e=0;e<=100;++e)if(matchMedia("(max-monochrome: ".concat(e,")")).matches)return e;throw new Error("Too high value")}},contrast:function(){return U("no-preference")?0:U("high")||U("more")?1:U("low")||U("less")?-1:U("forced")?10:void 0},reducedMotion:function(){return!!Q("reduce")||!Q("no-preference")&&void 0},hdr:function(){return!!K("high")||!K("standard")&&void 0},math:function(){var e,n=q.acos||$,t=q.acosh||$,r=q.asin||$,o=q.asinh||$,a=q.atanh||$,i=q.atan||$,c=q.sin||$,u=q.sinh||$,l=q.cos||$,s=q.cosh||$,d=q.tan||$,m=q.tanh||$,f=q.exp||$,v=q.expm1||$,h=q.log1p||$;return{acos:n(.12312423423423424),acosh:t(1e308),acoshPf:(e=1e154,q.log(e+q.sqrt(e*e-1))),asin:r(.12312423423423424),asinh:o(1),asinhPf:function(e){return q.log(e+q.sqrt(e*e+1))}(1),atanh:a(.5),atanhPf:function(e){return q.log((1+e)/(1-e))/2}(.5),atan:i(.5),sin:c(-1e300),sinh:u(1),sinhPf:function(e){return q.exp(e)-1/q.exp(e)/2}(1),cos:l(10.000000000123),cosh:s(1),coshPf:function(e){return(q.exp(e)+1/q.exp(e))/2}(1),tan:d(-1e300),tanh:m(1),tanhPf:function(e){return(q.exp(2*e)-1)/(q.exp(2*e)+1)}(1),exp:f(1),expm1:v(1),expm1Pf:function(e){return q.exp(e)-1}(1),log1p:h(10),log1pPf:function(e){return q.log(1+e)}(10),powPI:function(e){return q.pow(q.PI,e)}(-100)}},videoCard:function(){var e,n=document.createElement("canvas"),t=null!==(e=n.getContext("webgl"))&&void 0!==e?e:n.getContext("experimental-webgl");if(t&&"getExtension"in t){var r=t.getExtension("WEBGL_debug_renderer_info");if(r)return{vendor:(t.getParameter(r.UNMASKED_VENDOR_WEBGL)||"").toString(),renderer:(t.getParameter(r.UNMASKED_RENDERER_WEBGL)||"").toString()}}},pdfViewerEnabled:function(){return navigator.pdfViewerEnabled},architecture:function(){var e=new Float32Array(1),n=new Uint8Array(e.buffer);return e[0]=1/0,e[0]=e[0]-e[0],n[3]}};function te(e){var n=function(e){if(G())return.4;if(x())return F()?.5:.3;var n=e.platform.value||"";if(/^Win/.test(n))return.6;if(/^Mac/.test(n))return.5;return.7}(e),t=function(e){return w(.99+.01*e,1e-4)}(n);return{score:n,comment:"$ if upgrade to Pro: https://fpjs.dev/pro".replace(/\$/g,"".concat(t))}}function re(n){return JSON.stringify(n,(function(n,t){return t instanceof Error?e({name:(r=t).name,message:r.message,stack:null===(o=r.stack)||void 0===o?void 0:o.split("\n")},r):t;var r,o}),2)}function oe(e){return h(function(e){for(var n="",t=0,r=Object.keys(e).sort();t<r.length;t++){var o=r[t],a=e[o],i=a.error?"error":JSON.stringify(a.value);n+="".concat(n?"|":"").concat(o.replace(/([:|\\])/g,"\\$1"),":").concat(i)}return n}(e))}function ae(e){return void 0===e&&(e=50),function(e,n){void 0===n&&(n=1/0);var t=window.requestIdleCallback;return t?new Promise((function(e){return t.call(window,(function(){return e()}),{timeout:n})})):o(Math.min(e,n))}(e,2*e)}function ie(e,r){var o=Date.now();return{get:function(a){return n(this,void 0,void 0,(function(){var n,i,c;return t(this,(function(t){switch(t.label){case 0:return n=Date.now(),[4,e()];case 1:return i=t.sent(),c=function(e){var n;return{get visitorId(){return void 0===n&&(n=oe(this.components)),n},set visitorId(e){n=e},confidence:te(e),components:e,version:"3.4.2"}}(i),(r||(null==a?void 0:a.debug))&&console.log("Copy the text below to get the debug data:\n\n```\nversion: ".concat(c.version,"\nuserAgent: ").concat(navigator.userAgent,"\ntimeBetweenLoadAndGet: ").concat(n-o,"\nvisitorId: ").concat(c.visitorId,"\ncomponents: ").concat(re(i),"\n```")),[2,c]}}))}))}}}function ce(e){var r=void 0===e?{}:e,o=r.delayFallback,a=r.debug;return r.monitoring,n(this,void 0,void 0,(function(){return t(this,(function(e){switch(e.label){case 0:return[4,ae(o)];case 1:return e.sent(),[2,ie(V(ne,{debug:a},[]),a)]}}))}))}var ue={load:ce,hashComponents:oe,componentsToDebugString:re},le=h;export{re as componentsToDebugString,ue as default,M as getFullscreenElement,z as getScreenFrame,oe as hashComponents,G as isAndroid,S as isChromium,F as isDesktopSafari,C as isEdgeHTML,Y as isGecko,W as isTrident,x as isWebKit,ce as load,V as loadSources,le as murmurX64Hash128,ae as prepareForSources,ne as sources,Z as transformSource,X as withIframe};

upgini/metrics.py

@@ -3,15 +3,16 @@ import re
 from copy import deepcopy
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
+import catboost
 import numpy as np
 import pandas as pd
 from catboost import CatBoostClassifier, CatBoostRegressor
-import catboost
 from lightgbm import LGBMClassifier, LGBMRegressor
 from numpy import log1p
 from pandas.api.types import is_numeric_dtype
 from sklearn.metrics import check_scoring, get_scorer, make_scorer, roc_auc_score
 
+from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.sklearn_ext import cross_validate
 
 try:
@@ -352,6 +353,7 @@ class EstimatorWrapper:
             "target_type": target_type,
             "groups": groups,
             "text_features": text_features,
+            "logger": logger,
         }
         if estimator is None:
             params = dict()
@@ -414,12 +416,22 @@ class CatBoostWrapper(EstimatorWrapper):
         target_type: ModelTaskType,
         groups: Optional[List[str]] = None,
         text_features: Optional[List[str]] = None,
+        logger: Optional[logging.Logger] = None,
     ):
         super(CatBoostWrapper, self).__init__(
-            estimator, scorer, metric_name, multiplier, cv, target_type, groups=groups, text_features=text_features
+            estimator,
+            scorer,
+            metric_name,
+            multiplier,
+            cv,
+            target_type,
+            groups=groups,
+            text_features=text_features,
+            logger=logger,
         )
         self.cat_features = None
         self.emb_features = None
+        self.exclude_features = []
 
     def _prepare_to_fit(self, X: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, np.ndarray, dict]:
         X, y, groups, params = super()._prepare_to_fit(X, y)
@@ -437,9 +449,7 @@ class CatBoostWrapper(EstimatorWrapper):
                 X, embedding_features = self.group_embeddings(X)
                 params["embedding_features"] = embedding_features
             else:
-                self.logger.info(
-                    f"Embedding features count less than 3, so use them separately: {self.emb_features}"
-                )
+                self.logger.info(f"Embedding features count less than 3, so use them separately: {self.emb_features}")
                 self.emb_features = []
         else:
             self.logger.warning(f"Embedding features are not supported by Catboost version {catboost.__version__}")
@@ -498,6 +508,8 @@ class CatBoostWrapper(EstimatorWrapper):
         return df, [emb_name]
 
     def _prepare_to_calculate(self, X: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
+        if self.exclude_features:
+            X = X.drop(columns=self.exclude_features)
         X, y, params = super()._prepare_to_calculate(X, y)
         if self.text_features:
             params["text_features"] = self.text_features
@@ -510,6 +522,26 @@ class CatBoostWrapper(EstimatorWrapper):
 
         return X, y, params
 
+    def cross_val_predict(
+        self, X: pd.DataFrame, y: np.ndarray, baseline_score_column: Optional[Any] = None
+    ) -> Optional[float]:
+        try:
+            return super().cross_val_predict(X, y, baseline_score_column)
+        except Exception as e:
+            if "Dictionary size is 0" in e.args[0] and self.text_features:
+                high_cardinality_features = FeaturesValidator.find_high_cardinality(X[self.text_features])
+                self.logger.warning(
+                    "Failed to calculate metrics. Try to remove high cardinality"
+                    f" text features {high_cardinality_features} and retry"
+                )
+                for f in high_cardinality_features:
+                    self.text_features.remove(f)
+                    self.exclude_features.append(f)
+                    X = X.drop(columns=f)
+                return super().cross_val_predict(X, y, baseline_score_column)
+            else:
+                raise e
+
 
 class LightGBMWrapper(EstimatorWrapper):
     def __init__(
@@ -522,9 +554,18 @@ class LightGBMWrapper(EstimatorWrapper):
         target_type: ModelTaskType,
         groups: Optional[List[str]] = None,
         text_features: Optional[List[str]] = None,
+        logger: Optional[logging.Logger] = None,
     ):
         super(LightGBMWrapper, self).__init__(
-            estimator, scorer, metric_name, multiplier, cv, target_type, groups=groups, text_features=text_features
+            estimator,
+            scorer,
+            metric_name,
+            multiplier,
+            cv,
+            target_type,
+            groups=groups,
+            text_features=text_features,
+            logger=logger,
         )
         self.cat_features = None
 
@@ -561,9 +602,18 @@ class OtherEstimatorWrapper(EstimatorWrapper):
         target_type: ModelTaskType,
         groups: Optional[List[str]] = None,
         text_features: Optional[List[str]] = None,
+        logger: Optional[logging.Logger] = None,
     ):
         super(OtherEstimatorWrapper, self).__init__(
-            estimator, scorer, metric_name, multiplier, cv, target_type, groups=groups, text_features=text_features
+            estimator,
+            scorer,
+            metric_name,
+            multiplier,
+            cv,
+            target_type,
+            groups=groups,
+            text_features=text_features,
+            logger=logger,
         )
         self.cat_features = None
 
@@ -595,6 +645,7 @@ class OtherEstimatorWrapper(EstimatorWrapper):
 
 
 def validate_scoring_argument(scoring: Union[Callable, str, None]):
+    # TODO validate that if it is Callable then it accepts 3 arguments
     if isinstance(scoring, str) and scoring is not None:
         _get_scorer_by_name(scoring)
 

upgini/normalizer/phone_normalizer.py

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

upgini/resource_bundle/strings.properties

@@ -38,6 +38,7 @@ loss_selection_warn=\nWARNING: Loss `{0}` is not supported for feature selection
 loss_calc_metrics_warn=\nWARNING: Loss `{0}` is not supported for metrics calculation with {1}
 multivariate_timeseries_detected=\nWARNING: Multivariate TimeSeries detected. Blocked time series cross-validation split selected.\nMore details: https://github.com/upgini/upgini#-time-series-prediction-support
 group_k_fold_in_classification=\nWARNING: Using group K-fold cross-validation split for classification task.
+current_date_added=\nWARNING: No date/datetime column was detected in X to be used as a search key. The current date will be used to match the latest version of data sources
 
 # Errors
 failed_search_by_task_id=Failed to retrieve the specified search results
@@ -111,6 +112,9 @@ 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=\nWARNING: Feature {} specified in `generate_features` is not present in input columns: {}
+x_unstable_by_date=\nWARNING: Your training sample is unstable in number of rows per date. It is recommended to redesign the training sample
+train_unstable_target=\nWARNING: 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=\nWARNING: 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
     # eval set validation
 unsupported_type_eval_set=Unsupported type of eval_set: {}. It should be list of tuples with two elements: X and y
 eval_set_invalid_tuple_size=eval_set contains a tuple of size {}. It should contain only pairs of X and y
@@ -145,7 +149,8 @@ dataset_too_many_rows_registered=X rows limit for transform is {}. Please sample
 dataset_empty_column_names=Some column names are empty. Add names please
 dataset_full_duplicates=\nWARNING: {:.5f}% of the rows are fully duplicated
 dataset_diff_target_duplicates=\nWARNING: {:.4f}% of rows ({}) in X and eval_set are duplicates with different y values. These rows will be deleted as incorrect\nIncorrect row indexes: {}
-dataset_diff_target_duplicates_fintech=\nWARNING: {:.4f}% of rows ({}) in X and eval_set are duplicates, not taking into consideration dates, IP addresses and features from the training set, but have different y values. These rows have been removed to optimize search results.\nRemoved row indexes: {}
+dataset_train_diff_target_duplicates_fintech=\nWARNING: {:.4f}% of rows ({}) in X are duplicates, not taking into consideration dates, IP addresses and features from the training set, but have different y values. These rows have been removed to optimize search results.\nRemoved row indexes: {}
+dataset_eval_diff_target_duplicates_fintech=\nWARNING: {:.4f}% of rows ({}) in eval{} X are duplicates, not taking into consideration dates, IP addresses and features from the training set, but have different y values. These rows have been removed to optimize search results.\nRemoved row indexes: {}
 dataset_drop_old_dates=\nWARNING: We don't have data before '2000-01-01' and removed all earlier records from the search dataset
 dataset_all_dates_old=There is empty train dataset after removing data before '2000-01-01'
 dataset_invalid_target_type=Unexpected dtype of target for binary task type: {}. Expected int or bool
@@ -196,10 +201,10 @@ email_detected=Emails detected in column `{}`. It will be used as a search key\n
 email_detected_not_registered=Emails detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
 phone_detected=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
 phone_detected_not_registered=\nWARNING: Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns
-target_type_detected=Detected task type: {}\n
+target_type_detected=\nDetected task type: {}\n
 # all_ok_community_invite=Chat with us in Slack community:
 all_ok_community_invite=❓ Support request 
-too_small_for_metrics=Your train dataset contains less than 500 rows. For such dataset Upgini will not calculate accuracy metrics. Please increase the number of rows in the training dataset to calculate accuracy metrics
+too_small_for_metrics=Your train dataset or one of eval datasets contains less than 500 rows. For such dataset Upgini will not calculate accuracy metrics. Please increase the number of rows in the training dataset to calculate accuracy metrics
 imbalance_multiclass=Class {0} is on 25% quantile of classes distribution ({1} records in train dataset). \nDownsample classes with records more than {1}.
 loss_selection_info=Using loss `{}` for feature selection
 loss_calc_metrics_info=Using loss `{}` for metrics calculation with default estimator

upgini/utils/datetime_utils.py

@@ -1,7 +1,7 @@
 import datetime
 import logging
 import re
-from typing import List, Optional
+from typing import Dict, List, Optional
 
 import numpy as np
 import pandas as pd
@@ -9,7 +9,9 @@ from dateutil.relativedelta import relativedelta
 from pandas.api.types import is_numeric_dtype, is_period_dtype, is_string_dtype
 
 from upgini.errors import ValidationError
+from upgini.metadata import SearchKey
 from upgini.resource_bundle import ResourceBundle, get_custom_bundle
+from upgini.utils.warning_counter import WarningCounter
 
 DATE_FORMATS = [
     "%Y-%m-%d",
@@ -98,6 +100,9 @@ class DateTimeSearchKeyConverter:
                 msg = self.bundle.get("unsupported_date_type").format(self.date_column)
                 self.logger.warning(msg)
                 raise ValidationError(msg)
+        else:
+            df[self.date_column] = df[self.date_column].astype("string").apply(self.clean_date)
+            df[self.date_column] = self.parse_date(df)
 
         # If column with date is datetime then extract seconds of the day and minute of the hour
         # as additional features
@@ -225,3 +230,49 @@ def is_blocked_time_series(df: pd.DataFrame, date_col: str, search_keys: List[st
 
     is_diff_less_than_two_columns = grouped.apply(check_differences)
     return is_diff_less_than_two_columns.all()
+
+
+def validate_dates_distribution(
+    X: pd.DataFrame,
+    search_keys: Dict[str, SearchKey],
+    logger: Optional[logging.Logger] = None,
+    bundle: Optional[ResourceBundle] = None,
+    warning_counter: Optional[WarningCounter] = None,
+):
+    maybe_date_col = None
+    for key, key_type in search_keys.items():
+        if key_type in [SearchKey.DATE, SearchKey.DATETIME]:
+            maybe_date_col = key
+
+    if maybe_date_col is None:
+        for col in X.columns:
+            if col in search_keys:
+                continue
+            try:
+                pd.to_datetime(X[col])
+                maybe_date_col = col
+                break
+            except Exception:
+                pass
+
+    if maybe_date_col is None:
+        return
+
+    dates = pd.to_datetime(X[maybe_date_col]).dt.date
+
+    date_counts = dates.value_counts().sort_index()
+
+    date_counts_1 = date_counts[: round(len(date_counts) / 2)]
+    date_counts_2 = date_counts[round(len(date_counts) / 2) :]
+    ratio = date_counts_2.mean() / date_counts_1.mean()
+
+    if ratio > 1.2 or ratio < 0.8:
+        if warning_counter is not None:
+            warning_counter.increment()
+        if logger is None:
+            logger = logging.getLogger("muted_logger")
+            logger.setLevel("FATAL")
+        bundle = bundle or get_custom_bundle()
+        msg = bundle.get("x_unstable_by_date")
+        print(msg)
+        logger.warning(msg)

upgini/utils/deduplicate_utils.py

@@ -3,7 +3,7 @@ from typing import Dict, List, Optional, Union
 
 import pandas as pd
 
-from upgini.metadata import SORT_ID, SYSTEM_RECORD_ID, TARGET, ModelTaskType, SearchKey
+from upgini.metadata import EVAL_SET_INDEX, SORT_ID, SYSTEM_RECORD_ID, TARGET, ModelTaskType, SearchKey
 from upgini.resource_bundle import ResourceBundle
 from upgini.utils.datetime_utils import DateTimeSearchKeyConverter
 from upgini.utils.target_utils import define_task
@@ -78,20 +78,58 @@ def remove_fintech_duplicates(
     rows_with_diff_target = grouped_by_personal_cols.filter(has_diff_target_within_60_days)
     if len(rows_with_diff_target) > 0:
         unique_keys_to_delete = rows_with_diff_target[personal_cols].drop_duplicates()
-        rows_to_remove = pd.merge(df.reset_index(), unique_keys_to_delete, on=personal_cols)
-        rows_to_remove = rows_to_remove.set_index(df.index.name or "index")
-        perc = len(rows_to_remove) * 100 / len(df)
-        msg = bundle.get("dataset_diff_target_duplicates_fintech").format(
-            perc, len(rows_to_remove), rows_to_remove.index.to_list()
-        )
-        if not silent:
-            print(msg)
-        if logger:
-            logger.warning(msg)
-        logger.info(f"Dataset shape before clean fintech duplicates: {df.shape}")
-        df = df[~df.index.isin(rows_to_remove.index)]
-        logger.info(f"Dataset shape after clean fintech duplicates: {df.shape}")
-
+        if EVAL_SET_INDEX not in df.columns:
+            rows_to_remove = pd.merge(df.reset_index(), unique_keys_to_delete, on=personal_cols)
+            rows_to_remove = rows_to_remove.set_index(df.index.name or "index")
+            perc = len(rows_to_remove) * 100 / len(df)
+            msg = bundle.get("dataset_train_diff_target_duplicates_fintech").format(
+                perc, len(rows_to_remove), rows_to_remove.index.to_list()
+            )
+            if not silent:
+                print(msg)
+            if logger:
+                logger.warning(msg)
+            logger.info(f"Dataset shape before clean fintech duplicates: {df.shape}")
+            df = df[~df.index.isin(rows_to_remove.index)]
+            logger.info(f"Dataset shape after clean fintech duplicates: {df.shape}")
+        else:
+            # Indices in train and eval_set can be the same so we remove rows from them separately
+            train = df.query(f"{EVAL_SET_INDEX} == 0")
+            train_rows_to_remove = pd.merge(train.reset_index(), unique_keys_to_delete, on=personal_cols)
+            train_rows_to_remove = train_rows_to_remove.set_index(train.index.name or "index")
+            train_perc = len(train_rows_to_remove) * 100 / len(train)
+            msg = bundle.get("dataset_train_diff_target_duplicates_fintech").format(
+                train_perc, len(train_rows_to_remove), train_rows_to_remove.index.to_list()
+            )
+            if not silent:
+                print(msg)
+            if logger:
+                logger.warning(msg)
+            logger.info(f"Train dataset shape before clean fintech duplicates: {train.shape}")
+            train = train[~train.index.isin(train_rows_to_remove.index)]
+            logger.info(f"Train dataset shape after clean fintech duplicates: {train.shape}")
+
+            evals = [df.query(f"{EVAL_SET_INDEX} == {i}") for i in df[EVAL_SET_INDEX].unique() if i != 0]
+            new_evals = []
+            for i, eval in enumerate(evals):
+                eval_rows_to_remove = pd.merge(eval.reset_index(), unique_keys_to_delete, on=personal_cols)
+                eval_rows_to_remove = eval_rows_to_remove.set_index(eval.index.name or "index")
+                eval_perc = len(eval_rows_to_remove) * 100 / len(eval)
+                msg = bundle.get("dataset_eval_diff_target_duplicates_fintech").format(
+                    eval_perc, len(eval_rows_to_remove), i + 1, eval_rows_to_remove.index.to_list()
+                )
+                if not silent:
+                    print(msg)
+                if logger:
+                    logger.warning(msg)
+                logger.info(f"Eval {i + 1} dataset shape before clean fintech duplicates: {eval.shape}")
+                eval = eval[~eval.index.isin(eval_rows_to_remove.index)]
+                logger.info(f"Eval {i + 1} dataset shape after clean fintech duplicates: {eval.shape}")
+                new_evals.append(eval)
+
+            logger.info(f"Dataset shape before clean fintech duplicates: {df.shape}")
+            df = pd.concat([train] + new_evals)
+            logger.info(f"Dataset shape after clean fintech duplicates: {df.shape}")
     return df
 
 
@@ -101,14 +139,18 @@ def clean_full_duplicates(
     nrows = len(df)
     if nrows == 0:
         return df
-    # Remove absolute duplicates (exclude system_record_id)
+    # Remove full duplicates (exclude system_record_id, sort_id and eval_set_index)
     unique_columns = df.columns.tolist()
     if SYSTEM_RECORD_ID in unique_columns:
         unique_columns.remove(SYSTEM_RECORD_ID)
     if SORT_ID in unique_columns:
         unique_columns.remove(SORT_ID)
+    if EVAL_SET_INDEX in unique_columns:
+        unique_columns.remove(EVAL_SET_INDEX)
     logger.info(f"Dataset shape before clean duplicates: {df.shape}")
-    df = df.drop_duplicates(subset=unique_columns)
+    # Train segment goes first so if duplicates are found in train and eval set
+    # then we keep unique rows in train segment
+    df = df.drop_duplicates(subset=unique_columns, keep="first")
     logger.info(f"Dataset shape after clean duplicates: {df.shape}")
     nrows_after_full_dedup = len(df)
     share_full_dedup = 100 * (1 - nrows_after_full_dedup / nrows)
@@ -123,7 +165,7 @@ def clean_full_duplicates(
         marked_duplicates = df.duplicated(subset=unique_columns, keep=False)
         if marked_duplicates.sum() > 0:
             dups_indices = df[marked_duplicates].index.to_list()
-            nrows_after_tgt_dedup = len(df.drop_duplicates(subset=unique_columns))
+            nrows_after_tgt_dedup = len(df.drop_duplicates(subset=unique_columns, keep=False))
             num_dup_rows = nrows_after_full_dedup - nrows_after_tgt_dedup
             share_tgt_dedup = 100 * num_dup_rows / nrows_after_full_dedup
 
@@ -133,6 +175,7 @@ def clean_full_duplicates(
                 print(msg)
             df = df.drop_duplicates(subset=unique_columns, keep=False)
             logger.info(f"Dataset shape after clean invalid target duplicates: {df.shape}")
+
     return df
 
 

upgini/utils/sklearn_ext.py

@@ -1,5 +1,4 @@
 import functools
-import logging
 import numbers
 import time
 import warnings
@@ -313,7 +312,7 @@ def cross_validate(
 
         return ret
     except Exception:
-        logging.exception("Failed to execute overriden cross_validate. Fallback to original")
+        # logging.exception("Failed to execute overriden cross_validate. Fallback to original")
         raise
         # fit_params["use_best_model"] = False
         # return original_cross_validate(

upgini/utils/target_utils.py

@@ -132,9 +132,7 @@ def balance_undersample(
                 class_value = classes[class_idx]
                 class_count = vc[class_value]
                 sample_strategy[class_value] = min(class_count, quantile25_class_cnt * multiclass_bootstrap_loops)
-            sampler = RandomUnderSampler(
-                sampling_strategy=sample_strategy, random_state=random_state
-            )
+            sampler = RandomUnderSampler(sampling_strategy=sample_strategy, random_state=random_state)
             X = df[SYSTEM_RECORD_ID]
             X = X.to_frame(SYSTEM_RECORD_ID)
             new_x, _ = sampler.fit_resample(X, target)  # type: ignore
@@ -153,9 +151,7 @@ def balance_undersample(
         minority_class = df[df[target_column] == min_class_value]
         majority_class = df[df[target_column] != min_class_value]
         sample_size = min(len(majority_class), min_sample_threshold - min_class_count)
-        sampled_majority_class = majority_class.sample(
-            n=sample_size, random_state=random_state
-        )
+        sampled_majority_class = majority_class.sample(n=sample_size, random_state=random_state)
         resampled_data = df[
             (df[SYSTEM_RECORD_ID].isin(minority_class[SYSTEM_RECORD_ID]))
             | (df[SYSTEM_RECORD_ID].isin(sampled_majority_class[SYSTEM_RECORD_ID]))
@@ -181,3 +177,21 @@ def balance_undersample(
 
     logger.info(f"Shape after rebalance resampling: {resampled_data}")
     return resampled_data
+
+
+def calculate_psi(expected: pd.Series, actual: pd.Series) -> float:
+    df = pd.concat([expected, actual])
+
+    # Define the bins for the target variable
+    df_min = df.min()
+    df_max = df.max()
+    bins = [df_min, (df_min + df_max) / 2, df_max]
+
+    # Calculate the base distribution
+    train_distribution = expected.value_counts(bins=bins, normalize=True).sort_index().values
+
+    # Calculate the target distribution
+    test_distribution = actual.value_counts(bins=bins, normalize=True).sort_index().values
+
+    # Calculate the PSI
+    return np.sum((train_distribution - test_distribution) * np.log(train_distribution / test_distribution))

{upgini-1.1.262a3250.post4.dist-info → upgini-1.1.274a4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.262a3250.post4
+Version: 1.1.274a4
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -28,7 +28,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: python-dateutil >=2.8.0
 Requires-Dist: requests >=2.8.0
-Requires-Dist: pandas <2.0.0,>=1.1.0
+Requires-Dist: pandas <2.1.0,>=1.1.0
 Requires-Dist: numpy >=1.19.0
 Requires-Dist: scikit-learn >=1.3.0
 Requires-Dist: pydantic <2.0.0,>=1.8.2

{upgini-1.1.262a3250.post4.dist-info → upgini-1.1.274a4.dist-info}/RECORD

@@ -1,34 +1,35 @@
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
-upgini/dataset.py,sha256=4LfrUwxhd__ZVqZkjPVxbC4SW3YLsk1sMMqnYPUaVpw,45529
+upgini/dataset.py,sha256=xb4gIANyGbdcuM8Awyq2pJPiH_3k_LEbETApJgAoRBA,45529
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=WbwnLvPVqn4m995b6jSamWkXyRVy18fnG7faBeuJbWI,172132
+upgini/features_enricher.py,sha256=WDj4DO5lqANBdihEcRmwox4w1kqWVOorlIKY4dbsqrU,175376
+upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=zaO86LBBLmkieGbgYifk29eVoPCxXimZQ8YkQtKcM0I,42244
 upgini/metadata.py,sha256=fwVxtkR6Mn4iRoOqV6BfMJvJrx65I3YwZUMbZjhPyOI,9673
-upgini/metrics.py,sha256=3VvSZW1cCOIPHImXuqcnWzD3fWcpPzVa9k8eulLbUmY,27426
+upgini/metrics.py,sha256=U3VJKbKmuWACqI4jTcszXo0WqeXFtV8bWyY9VLBL-rw,29129
 upgini/search_task.py,sha256=tmJ17WUxv3J5NWrYUJB_NKdZ792Ifz8Z8UnDXeQnpss,17077
 upgini/spinner.py,sha256=Dm1dQ5F_z_Ua2odLxZX7OypcOX9tSx_vE5MGaKtUmfw,1118
 upgini/version_validator.py,sha256=rDIncP6BEko4J2F2hUcMOtKm_vZbI4ICWcNcw8hrwM4,1400
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
 upgini/ads_management/ads_manager.py,sha256=fP4Yqx3h2Snw5X335TbXEwFoupq1RYsE7y0PAduvetU,2646
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/autofe/all_operands.py,sha256=KWAdcYv6cToc6NZPcCmz6P3N8Nwjp8UqojKuz-f2BZY,1589
+upgini/autofe/all_operands.py,sha256=H66wqVLD-H9k8A4-q2wslhV9QaNxlb49f8YiT0Xfkps,2356
 upgini/autofe/binary.py,sha256=f8LQqZi9zyaMUAv-jASMmWNA_vT05ncYCjZq0qx3USs,3972
-upgini/autofe/date.py,sha256=AC7Gabc7x2n4-_EmO1Q-7ncfCI_5-kPMQ3r3vFgQ1g4,1788
+upgini/autofe/date.py,sha256=_6RoEJZ5Kf-Q_aMOFucS6YSIZpCcelgpw-edV4qmRIM,3935
 upgini/autofe/feature.py,sha256=2FQRGtIumNz60hFAjfLReaY18SI7HxzYZOoC5avzSjQ,11847
 upgini/autofe/groupby.py,sha256=iXRfOmOc84ooSzRhsh9GmmG7rTafX0-ekXko8s9Qs68,3089
 upgini/autofe/operand.py,sha256=dhtToPDGWtP_0u_RjayUpezJJZAgq_TzNbPH0bI9OXI,2805
 upgini/autofe/unary.py,sha256=YRTzQLttbDdOnkogWBPnBexpu7uHWSLSFAxSCu3iFdY,3145
 upgini/autofe/vector.py,sha256=5qhI_bdwaWM1l7fgCkx1tMt9R9gxWzoYCl-7WO4KiOs,604
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/data_source/data_source_publisher.py,sha256=QASEDhJ9SxJKcWxoN2vUPxrM_HTlwKQOPa92L7EQneA,15962
+upgini/data_source/data_source_publisher.py,sha256=taRzyGgrPrTTSGw4Y-Ca5k4bf30aiTa68rxqT9zfqeI,16478
 upgini/mdc/__init__.py,sha256=ETDh3JKbrDdPMOECiYLAa8lvKYe68mv4IY6fZa9FimA,1126
 upgini/mdc/context.py,sha256=Sl1S_InKlzzRxYqwJ2k24lawJdCKWgGJ-RIRfvzWJrk,1468
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/normalizer/phone_normalizer.py,sha256=lhwsPEnfyjeIsndW2EcQGZksXYsfxaQ1ghAzVYoDRKM,9927
+upgini/normalizer/phone_normalizer.py,sha256=_SYMX4GTgwzRXArK54Jp3vUBE5d4jZxSVyze-0tqzg0,9996
 upgini/resource_bundle/__init__.py,sha256=hdvbqL0b0xMWbY6-kiYGsW1ro2GMiWpxxsO9uCv-h9Q,8379
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=MGU_oBc15VAmbPZdThCpm3B4xERAKwbCIUTIG66dvUo,25228
+upgini/resource_bundle/strings.properties,sha256=x-2fXtGc5Z2n7eUg9b6I4yhok56TTXDvzwU1JUaKcj4,26285
 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=CC-DvPbrN7zp5--SVFuUqkVmdWM_5F7R0Do98ETV82U,6421
@@ -40,8 +41,8 @@ upgini/utils/blocked_time_series.py,sha256=dMz5ewk3PsoeOrc3lDzInCVPS9u_2XQkV0W6P
 upgini/utils/country_utils.py,sha256=1KXhLSNqkNYVL3on8-zK0Arc_SspUH7AMZvGZICysOU,6462
 upgini/utils/custom_loss_utils.py,sha256=DBslpjWGPt7xTeypt78baR59012SYphbPsO_YLKdilo,3972
 upgini/utils/cv_utils.py,sha256=Tn01RJvpZGZh0PUQUimlBkV-AXwe7s6yjCNFtw352Uc,3525
-upgini/utils/datetime_utils.py,sha256=ol5Bgh98wU6KBY9z4QskNO0ja-L7HJL70HmTAjl7iRU,8836
-upgini/utils/deduplicate_utils.py,sha256=ckJrpU8Ruc_vcwIPTopbUjyJuNiseLHNAbQlLfhUCxo,5888
+upgini/utils/datetime_utils.py,sha256=XciFOIYI4Zi7PqQS8dHxuPDEtdtwXbOrWsiAa04v2J4,10511
+upgini/utils/deduplicate_utils.py,sha256=6AbARehUCghJZ4PppFtrej2s3gFRruh41MEm6mzakHs,8607
 upgini/utils/display_utils.py,sha256=LKoSwjrE0xgS5_cqVhc2og2CQ1UCZ1nTI2VKboIhoQA,10858
 upgini/utils/email_utils.py,sha256=3CvHXTSzlgLyGsQOXfRYVfFhfPy6OXG4uXOBWRaLfHg,3479
 upgini/utils/fallback_progress_bar.py,sha256=cdbd1XGcWm4Ed4eAqV2_St3z7uC_kkH22gEyrN5ub6M,1090
@@ -51,12 +52,12 @@ upgini/utils/ip_utils.py,sha256=Zf3F2cnQmOCH09QLQHetpjMFu1PnD0cTmDymn0SnSy8,1672
 upgini/utils/phone_utils.py,sha256=JNSkF8G6mgsN8Czy11pamaJdsY6rBINEMpi7jbVt_RA,408
 upgini/utils/postal_code_utils.py,sha256=_8CR9tBqsPptQsmMUvnrCAmBaMIQSWH3JfJ4ly3x_zs,409
 upgini/utils/progress_bar.py,sha256=iNXyqT3vKCeHpfiG5HHwr7Lk2cTtKViM93Fl8iZnjGc,1564
-upgini/utils/sklearn_ext.py,sha256=fvuTWJ5AnT3ED9KSaQu_yIgW2JR19hFlaGDoVP3k60g,44027
-upgini/utils/target_utils.py,sha256=WVhhxpQVvnhsDV7ctlds51VFg7hz59S_MFUSoRZFszw,7204
+upgini/utils/sklearn_ext.py,sha256=e1aMNXk1zUt7uFnl0FcUF0zOnaXSE7z5xBHmJPknUVs,44014
+upgini/utils/target_utils.py,sha256=9K67tkY7LWhQMO-vbbPqBaO-KriAmg_6fVz5RQRaLQc,7802
 upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.262a3250.post4.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.262a3250.post4.dist-info/METADATA,sha256=XfUGTmbya5IYq0uJYXwhUGxBy9DAnrQyWvNsyiZl6gM,48167
-upgini-1.1.262a3250.post4.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-upgini-1.1.262a3250.post4.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.262a3250.post4.dist-info/RECORD,,
+upgini-1.1.274a4.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.274a4.dist-info/METADATA,sha256=xng0cJvEGeFT2zSBqLDy-qf9I6ONKxdKtXsFWokPpPs,48158
+upgini-1.1.274a4.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+upgini-1.1.274a4.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.274a4.dist-info/RECORD,,