upgini 1.2.91a3884.dev5__py3-none-any.whl → 1.2.91a3906.dev1__py3-none-any.whl

upgini/metadata.py

@@ -159,9 +159,6 @@ class ModelTaskType(Enum):
     REGRESSION = "REGRESSION"
     TIMESERIES = "TIMESERIES"
 
-    def is_classification(self) -> bool:
-        return self in [ModelTaskType.BINARY, ModelTaskType.MULTICLASS]
-
 
 class ModelLabelType(Enum):
     GINI = "gini"

upgini/metrics.py

@@ -332,7 +332,7 @@ class EstimatorWrapper:
         self.groups = groups
         self.text_features = text_features
         self.logger = logger or logging.getLogger()
-        self.dropped_features = []
+        self.droped_features = []
         self.converted_to_int = []
         self.converted_to_str = []
         self.converted_to_numeric = []
@@ -381,11 +381,10 @@ class EstimatorWrapper:
         x, y, groups = self._prepare_data(x, y, groups=self.groups)
 
         self.logger.info(f"Before preparing data columns: {x.columns.to_list()}")
-        self.dropped_features = []
+        self.droped_features = []
         self.converted_to_int = []
         self.converted_to_str = []
         self.converted_to_numeric = []
-
         for c in x.columns:
 
             if _get_unique_count(x[c]) < 2:
@@ -393,7 +392,7 @@ class EstimatorWrapper:
                 if c in self.cat_features:
                     self.cat_features.remove(c)
                 x.drop(columns=[c], inplace=True)
-                self.dropped_features.append(c)
+                self.droped_features.append(c)
             elif self.text_features is not None and c in self.text_features:
                 x[c] = x[c].astype(str)
                 self.converted_to_str.append(c)
@@ -428,16 +427,16 @@ class EstimatorWrapper:
                     except (ValueError, TypeError):
                         self.logger.warning(f"Remove feature {c} because it is not numeric and not in cat_features")
                         x.drop(columns=[c], inplace=True)
-                        self.dropped_features.append(c)
+                        self.droped_features.append(c)
 
         return x, y, groups, {}
 
     def _prepare_to_calculate(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
         x, y, _ = self._prepare_data(x, y)
 
-        if self.dropped_features:
-            self.logger.info(f"Drop features on calculate metrics: {self.dropped_features}")
-            x = x.drop(columns=self.dropped_features)
+        if self.droped_features:
+            self.logger.info(f"Drop features on calculate metrics: {self.droped_features}")
+            x = x.drop(columns=self.droped_features)
 
         if self.converted_to_int:
             self.logger.info(f"Convert to int features on calculate metrics: {self.converted_to_int}")
@@ -798,7 +797,7 @@ class CatBoostWrapper(EstimatorWrapper):
                     )
                 for f in high_cardinality_features:
                     self.text_features.remove(f)
-                    self.dropped_features.append(f)
+                    self.droped_features.append(f)
                     x = x.drop(columns=f, errors="ignore")
                 return super().cross_val_predict(x, y, baseline_score_column)
             else:
@@ -815,7 +814,7 @@ class CatBoostWrapper(EstimatorWrapper):
                 else:
                     encoded = cat_encoder.transform(x[self.cat_features])
                     cat_features = encoded.columns.to_list()
-                x.loc[:, self.cat_features] = encoded
+                x[self.cat_features] = encoded
             else:
                 cat_features = self.cat_features
 
@@ -898,7 +897,7 @@ class LightGBMWrapper(EstimatorWrapper):
         for c in x.columns:
             if x[c].dtype not in ["category", "int64", "float64", "bool"]:
                 self.logger.warning(f"Feature {c} is not numeric and will be dropped")
-                self.dropped_features.append(c)
+                self.droped_features.append(c)
                 x = x.drop(columns=c, errors="ignore")
         return x, y_numpy, groups, params
 
@@ -989,7 +988,7 @@ class OtherEstimatorWrapper(EstimatorWrapper):
         for c in x.columns:
             if x[c].dtype not in ["category", "int64", "float64", "bool"]:
                 self.logger.warning(f"Feature {c} is not numeric and will be dropped")
-                self.dropped_features.append(c)
+                self.droped_features.append(c)
                 x = x.drop(columns=c, errors="ignore")
         return x, y_numpy, groups, params
 

upgini/resource_bundle/strings.properties

@@ -144,7 +144,6 @@ baseline_score_column_has_na=baseline_score_column contains NaN. Clear it and an
 missing_features_for_transform=Missing some features for transform that were presented on fit: {}
 missing_target_for_transform=Search contains features on target. Please add y to the call and try again
 missing_id_column=Id column {} not found in X: {}
-unknown_id_column_value_in_eval_set=Unknown values in id columns: {}
     # target validation
 empty_target=Target is empty in all rows
 # non_numeric_target=Binary target should be numerical type
@@ -196,7 +195,6 @@ timeseries_invalid_test_size_type=test_size={} should be a float in the (0, 1) r
 timeseries_splits_more_than_samples=Number of splits={} can't be more than number of samples={}
 timeseries_invalid_test_size=Wrong number of samples in a test fold: (test_size * n_samples / n_splits) <= 1
 date_and_id_columns_duplicates=Found {} duplicate rows by date and id_columns. Please remove them and try again
-missing_ids_in_eval_set=Following ids are present in eval set but not in sampled train set: {}. They will be removed from eval set.
     # Upload ads validation
 ads_upload_too_few_rows=At least 1000 records per sample are needed. Increase the sample size for evaluation and resubmit the data
 ads_upload_search_key_not_found=Search key {} wasn't found in dataframe columns

upgini/utils/target_utils.py

@@ -1,14 +1,17 @@
 import logging
-from typing import Callable, Optional, Union
+from typing import Callable, List, Optional, Union
 
 import numpy as np
 import pandas as pd
 from pandas.api.types import is_bool_dtype, is_datetime64_any_dtype, is_numeric_dtype
 
 from upgini.errors import ValidationError
-from upgini.metadata import SYSTEM_RECORD_ID, ModelTaskType
-from upgini.resource_bundle import ResourceBundle, get_custom_bundle, bundle
+from upgini.metadata import SYSTEM_RECORD_ID, CVType, ModelTaskType
+from upgini.resource_bundle import ResourceBundle, bundle, get_custom_bundle
 from upgini.sampler.random_under_sampler import RandomUnderSampler
+from upgini.utils.ts_utils import get_most_frequent_time_unit, trunc_datetime
+
+TS_MIN_DIFFERENT_IDS_RATIO = 0.2
 
 
 def prepare_target(y: Union[pd.Series, np.ndarray], target_type: ModelTaskType) -> Union[pd.Series, np.ndarray]:
@@ -201,6 +204,199 @@ def balance_undersample(
     return resampled_data
 
 
+def balance_undersample_forced(
+    df: pd.DataFrame,
+    target_column: str,
+    id_columns: Optional[List[str]],
+    date_column: str,
+    task_type: ModelTaskType,
+    cv_type: Optional[CVType],
+    random_state: int,
+    sample_size: int = 7000,
+    logger: Optional[logging.Logger] = None,
+    bundle: Optional[ResourceBundle] = None,
+    warning_callback: Optional[Callable] = None,
+):
+    if len(df) <= sample_size:
+        return df
+
+    if logger is None:
+        logger = logging.getLogger("muted_logger")
+        logger.setLevel("FATAL")
+    bundle = bundle or get_custom_bundle()
+    if SYSTEM_RECORD_ID not in df.columns:
+        raise Exception("System record id must be presented for undersampling")
+
+    msg = bundle.get("forced_balance_undersample")
+    logger.info(msg)
+    if warning_callback is not None:
+        warning_callback(msg)
+
+    target = df[target_column].copy()
+
+    vc = target.value_counts()
+    max_class_value = vc.index[0]
+    min_class_value = vc.index[len(vc) - 1]
+    max_class_count = vc[max_class_value]
+    min_class_count = vc[min_class_value]
+
+    resampled_data = df
+    df = df.copy().sort_values(by=SYSTEM_RECORD_ID)
+    if cv_type is not None and cv_type.is_time_series():
+        logger.warning(f"Sampling time series dataset from {len(df)} to {sample_size}")
+        resampled_data = balance_undersample_time_series_trunc(
+            df,
+            id_columns=id_columns,
+            date_column=date_column,
+            sample_size=sample_size,
+            random_state=random_state,
+            logger=logger,
+        )
+    elif task_type in [ModelTaskType.MULTICLASS, ModelTaskType.REGRESSION]:
+        logger.warning(f"Sampling dataset from {len(df)} to {sample_size}")
+        resampled_data = df.sample(n=sample_size, random_state=random_state)
+    else:
+        msg = bundle.get("imbalanced_target").format(min_class_value, min_class_count)
+        logger.warning(msg)
+
+        # fill up to min_sample_threshold by majority class
+        minority_class = df[df[target_column] == min_class_value]
+        majority_class = df[df[target_column] != min_class_value]
+        logger.info(
+            f"Min class count: {min_class_count}. Max class count: {max_class_count}."
+            f" Rebalance sample size: {sample_size}"
+        )
+        if len(minority_class) > (sample_size / 2):
+            sampled_minority_class = minority_class.sample(n=int(sample_size / 2), random_state=random_state)
+        else:
+            sampled_minority_class = minority_class
+
+        if len(majority_class) > (sample_size) / 2:
+            sampled_majority_class = majority_class.sample(n=int(sample_size / 2), random_state=random_state)
+
+        resampled_data = df[
+            (df[SYSTEM_RECORD_ID].isin(sampled_minority_class[SYSTEM_RECORD_ID]))
+            | (df[SYSTEM_RECORD_ID].isin(sampled_majority_class[SYSTEM_RECORD_ID]))
+        ]
+
+    logger.info(f"Shape after forced rebalance resampling: {resampled_data}")
+    return resampled_data
+
+
+DEFAULT_HIGH_FREQ_TRUNC_LENGTHS = [pd.DateOffset(years=2, months=6), pd.DateOffset(years=2, days=7)]
+DEFAULT_LOW_FREQ_TRUNC_LENGTHS = [pd.DateOffset(years=7), pd.DateOffset(years=5)]
+DEFAULT_TIME_UNIT_THRESHOLD = pd.Timedelta(weeks=4)
+
+
+def balance_undersample_time_series_trunc(
+    df: pd.DataFrame,
+    id_columns: Optional[List[str]],
+    date_column: str,
+    sample_size: int,
+    random_state: int = 42,
+    logger: Optional[logging.Logger] = None,
+    highfreq_trunc_lengths: List[pd.DateOffset] = DEFAULT_HIGH_FREQ_TRUNC_LENGTHS,
+    lowfreq_trunc_lengths: List[pd.DateOffset] = DEFAULT_LOW_FREQ_TRUNC_LENGTHS,
+    time_unit_threshold: pd.Timedelta = DEFAULT_TIME_UNIT_THRESHOLD,
+    **kwargs,
+):
+    if id_columns is None:
+        id_columns = []
+    # Convert date column to datetime
+    dates_df = df[id_columns + [date_column]].copy()
+    dates_df[date_column] = pd.to_datetime(dates_df[date_column], unit="ms")
+
+    time_unit = get_most_frequent_time_unit(dates_df, id_columns, date_column)
+    if logger is not None:
+        logger.info(f"Time unit: {time_unit}")
+
+    if time_unit is None:
+        if logger is not None:
+            logger.info("Cannot detect time unit, returning original dataset")
+        return df
+
+    if time_unit < time_unit_threshold:
+        for trunc_length in highfreq_trunc_lengths:
+            sampled_df = trunc_datetime(dates_df, id_columns, date_column, trunc_length, logger=logger)
+            if len(sampled_df) <= sample_size:
+                break
+        if len(sampled_df) > sample_size:
+            sampled_df = balance_undersample_time_series(
+                sampled_df, id_columns, date_column, sample_size, random_state, logger=logger, **kwargs
+            )
+    else:
+        for trunc_length in lowfreq_trunc_lengths:
+            sampled_df = trunc_datetime(dates_df, id_columns, date_column, trunc_length, logger=logger)
+            if len(sampled_df) <= sample_size:
+                break
+        if len(sampled_df) > sample_size:
+            sampled_df = balance_undersample_time_series(
+                sampled_df, id_columns, date_column, sample_size, random_state, logger=logger, **kwargs
+            )
+
+    return df.loc[sampled_df.index]
+
+
+def balance_undersample_time_series(
+    df: pd.DataFrame,
+    id_columns: List[str],
+    date_column: str,
+    sample_size: int,
+    random_state: int = 42,
+    min_different_ids_ratio: float = TS_MIN_DIFFERENT_IDS_RATIO,
+    prefer_recent_dates: bool = True,
+    logger: Optional[logging.Logger] = None,
+):
+    def ensure_tuple(x):
+        return tuple([x]) if not isinstance(x, tuple) else x
+
+    random_state = np.random.RandomState(random_state)
+
+    if not id_columns:
+        id_columns = [date_column]
+    ids_sort = df.groupby(id_columns)[date_column].aggregate(["max", "count"]).T.to_dict()
+    ids_sort = {
+        ensure_tuple(k): (
+            (v["max"], v["count"], random_state.rand()) if prefer_recent_dates else (v["count"], random_state.rand())
+        )
+        for k, v in ids_sort.items()
+    }
+    id_counts = df[id_columns].value_counts()
+    id_counts.index = [ensure_tuple(i) for i in id_counts.index]
+    id_counts = id_counts.sort_index(key=lambda x: [ids_sort[y] for y in x], ascending=False).cumsum()
+    id_counts = id_counts[id_counts <= sample_size]
+    min_different_ids = max(int(len(df[id_columns].drop_duplicates()) * min_different_ids_ratio), 1)
+
+    def id_mask(sample_index: pd.Index) -> pd.Index:
+        if isinstance(sample_index, pd.MultiIndex):
+            return pd.MultiIndex.from_frame(df[id_columns]).isin(sample_index)
+        else:
+            return df[id_columns[0]].isin(sample_index)
+
+    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}"
+                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
+        mask = id_mask(ids_to_sample)
+        df = df[mask]
+        sample_date_counts = df[date_column].value_counts().sort_index(ascending=False).cumsum()
+        sample_date_counts = sample_date_counts[sample_date_counts <= sample_size]
+        df = df[df[date_column].isin(sample_date_counts.index)]
+    else:
+        if len(id_columns) > 1:
+            id_counts.index = pd.MultiIndex.from_tuples(id_counts.index)
+        else:
+            id_counts.index = [i[0] for i in id_counts.index]
+        mask = id_mask(id_counts.index)
+        df = df[mask]
+
+    return df
+
+
 def calculate_psi(expected: pd.Series, actual: pd.Series) -> Union[float, Exception]:
     try:
         df = pd.concat([expected, actual])

{upgini-1.2.91a3884.dev5.dist-info → upgini-1.2.91a3906.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.91a3884.dev5
+Version: 1.2.91a3906.dev1
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.2.91a3884.dev5.dist-info → upgini-1.2.91a3906.dev1.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=tqdF5EG5u2XotiGWCSnsQ61GODo019Lr-s097ItdAHs,33
+upgini/__about__.py,sha256=Lvq_aBqVHaMSRjnG_m_EJn-gwVd5w5KGUuuS1LiJ_dY,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=MituLJZTDdIwSk-Ia5G1pS52PERNHQ2P99FgCH2kTjQ,32790
+upgini/dataset.py,sha256=fRtqSkXNONLnPe6cCL967GMt349FTIpXzy_u8LUKncw,35354
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=udQdXpqVO4YAwEHjUzS195k2jxe5_CtZ-KTpWRicjfs,218225
+upgini/features_enricher.py,sha256=rieH8wjC1c_q2LYZoju8KZyshokNzFpwVtrCtG88w3s,215940
 upgini/http.py,sha256=4i7fQwrwU3WzDUOWzrgR-4C8eJwj_5dBwRAR-UjUtlc,44345
-upgini/metadata.py,sha256=vsbbHyPCP3Rs8WkeDgQg99uAA_zmsbDStAT-NwDYhO4,12455
-upgini/metrics.py,sha256=Bc1L9DUmEL8OWwNvIEjPjw5EyHSZbiu3v2hWyBmedis,45313
+upgini/metadata.py,sha256=zt_9k0iQbWXuiRZcel4ORNPdQKt6Ou69ucZD_E1Q46o,12341
+upgini/metrics.py,sha256=zIOaiyfQLedU9Fk4877drnlWh-KiImSkZpPeiq6Xr1E,45295
 upgini/search_task.py,sha256=Q5HjBpLIB3OCxAD1zNv5yQ3ZNJx696WCK_-H35_y7Rs,17912
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -19,7 +19,7 @@ upgini/autofe/date.py,sha256=MM1S-6imNSzCDOhbNnmsc_bwSqUWBcS8vWAdHF8j1kY,11134
 upgini/autofe/feature.py,sha256=cu4xXjzVVF13ZV4RxuTrysK2qCfezlRCMOzCKRo1rNs,15558
 upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
 upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
-upgini/autofe/unary.py,sha256=Sx11IoHRh5nwyALzjgG9GQOrVNIs8NZ1JzunAJuN66A,5731
+upgini/autofe/unary.py,sha256=N76Pehn-hO8FWlSdqJ2Wm-yoU1MSR7m6yb2GWYBcumU,5933
 upgini/autofe/utils.py,sha256=dYrtyAM8Vcc_R8u4dNo54IsGrHKagTHDJTKhGho0bRg,2967
 upgini/autofe/vector.py,sha256=jHs0nNTOaHspYUlxW7fjQepk4cvr_JDQ65L1OCiVsds,1360
 upgini/autofe/timeseries/__init__.py,sha256=PGwwDAMwvkXl3el12tXVEmZUgDUvlmIPlXtROm6bD18,738
@@ -38,7 +38,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=g2TcDXZeJp9kAFO2sTqZ4CAsN4J1qHNgoJHZ8gtzUWo,7376
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=Hfpr2-I5Ws6ugIN1QSz549OHayZeLYglRsbrGDT6g9g,28491
+upgini/resource_bundle/strings.properties,sha256=SxO1uWFAc1s7BOFi01OyEI3ajklUKBhs8LkKrstImIg,28290
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -64,14 +64,13 @@ upgini/utils/mstats.py,sha256=u3gQVUtDRbyrOQK6V1UJ2Rx1QbkSNYGjXa6m3Z_dPVs,6286
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
-upgini/utils/sample_utils.py,sha256=jQ1em2FRnMFLul9ujuBgs5XZ9jAZ4eM4FHT3aDSjOy8,15351
 upgini/utils/sklearn_ext.py,sha256=jLJWAKkqQinV15Z4y1ZnsN3c-fKFwXTsprs00COnyVU,49315
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
-upgini/utils/target_utils.py,sha256=i3Xt5l9ybB2_nF_ma5cfPuL3OeFTs2dY2xDI0p4Azpg,9049
+upgini/utils/target_utils.py,sha256=mVZ8wrkBb-tzEnVZwZw0m-Y0Sojb5t-wIsACRH05nIw,16890
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.91a3884.dev5.dist-info/METADATA,sha256=A9MDv_VCFrWDDw2Xyo7Wsx3ps6ECwTul36gmw-wujgI,49546
-upgini-1.2.91a3884.dev5.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.91a3884.dev5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.91a3884.dev5.dist-info/RECORD,,
+upgini-1.2.91a3906.dev1.dist-info/METADATA,sha256=YhyG3QmIoZnjZm_YW29eCRBdyfETpzOk7yPhlNb-lcE,49546
+upgini-1.2.91a3906.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.91a3906.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.91a3906.dev1.dist-info/RECORD,,