upgini 1.1.253a5__tar.gz → 1.1.253a3261__tar.gz

{upgini-1.1.253a5/src/upgini.egg-info → upgini-1.1.253a3261}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.253a5
+Version: 1.1.253a3261
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -18,12 +18,13 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Telecommunications Industry
 Classifier: License :: OSI Approved :: BSD License
 Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: >=3.8,<3.11
+Requires-Python: >=3.7,<3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: python-dateutil>=2.8.0

{upgini-1.1.253a5 → upgini-1.1.253a3261}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.253a5"
+version = "1.1.253a3261"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(
@@ -62,6 +62,7 @@ try:
             "Intended Audience :: Telecommunications Industry",
             "License :: OSI Approved :: BSD License",
             "Operating System :: OS Independent",
+            "Programming Language :: Python :: 3.7",
             "Programming Language :: Python :: 3.8",
             "Programming Language :: Python :: 3.9",
             "Programming Language :: Python :: 3.10",
@@ -73,7 +74,7 @@ try:
         package_dir={"": "src"},
         packages=find_packages(where="src"),
         package_data={"": ["strings.properties", "strings_widget.properties", "fingerprint.js"]},
-        python_requires=">=3.8,<3.11",
+        python_requires=">=3.7,<3.11",
         install_requires=[
             "python-dateutil>=2.8.0",
             "requests>=2.8.0",

{upgini-1.1.253a5 → upgini-1.1.253a3261}/src/upgini/data_source/data_source_publisher.py

@@ -40,7 +40,7 @@ class DataSourcePublisher:
         if logs_enabled:
             self.logger = LoggerFactory().get_logger(endpoint, api_key)
         else:
-            self.logger = logging.getLogger("muted_logger")
+            self.logger = logging.getLogger()
             self.logger.setLevel("FATAL")
 
     def place(

{upgini-1.1.253a5 → upgini-1.1.253a3261}/src/upgini/dataset.py

@@ -39,10 +39,10 @@ from upgini.metadata import (
 )
 from upgini.normalizer.phone_normalizer import PhoneNormalizer
 from upgini.resource_bundle import ResourceBundle, get_custom_bundle
+from upgini.sampler.random_under_sampler import RandomUnderSampler
 from upgini.search_task import SearchTask
 from upgini.utils import combine_search_keys, find_numbers_with_decimal_comma
 from upgini.utils.email_utils import EmailSearchKeyConverter
-from upgini.utils.target_utils import balance_undersample
 
 try:
     from upgini.utils.progress_bar import CustomProgressBar as ProgressBar
@@ -61,8 +61,6 @@ class Dataset:  # (pd.DataFrame):
     FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD = 200_000
     MIN_SAMPLE_THRESHOLD = 5_000
     IMBALANCE_THESHOLD = 0.4
-    BINARY_BOOTSTRAP_LOOPS = 5
-    MULTICLASS_BOOTSTRAP_LOOPS = 2
     MIN_TARGET_CLASS_ROWS = 100
     MAX_MULTICLASS_CLASS_COUNT = 100
     MIN_SUPPORTED_DATE_TS = 946684800000  # 2000-01-01
@@ -463,8 +461,10 @@ class Dataset:  # (pd.DataFrame):
             self.task_type == ModelTaskType.BINARY and len(train_segment) > self.MIN_SAMPLE_THRESHOLD
         ):
             count = len(train_segment)
-            target_column = self.etalon_def_checked.get(FileColumnMeaningType.TARGET.value, TARGET)
-            target = train_segment[target_column]
+            min_class_count = count
+            min_class_value = None
+            target_column = self.etalon_def_checked.get(FileColumnMeaningType.TARGET.value, "")
+            target = train_segment[target_column].copy()
             target_classes_count = target.nunique()
 
             if target_classes_count > self.MAX_MULTICLASS_CLASS_COUNT:
@@ -474,9 +474,12 @@ class Dataset:  # (pd.DataFrame):
                 self.logger.warning(msg)
                 raise ValidationError(msg)
 
-            vc = target.value_counts()
-            min_class_value = vc.index[len(vc) - 1]
-            min_class_count = vc[min_class_value]
+            unique_target = target.unique()
+            for v in list(unique_target):  # type: ignore
+                current_class_count = len(train_segment.loc[target == v])
+                if current_class_count < min_class_count:
+                    min_class_count = current_class_count
+                    min_class_value = v
 
             if min_class_count < self.MIN_TARGET_CLASS_ROWS:
                 msg = self.bundle.get("dataset_rarest_class_less_min").format(
@@ -489,19 +492,53 @@ class Dataset:  # (pd.DataFrame):
             min_class_threshold = min_class_percent * count
 
             if min_class_count < min_class_threshold:
-                self.imbalanced = True
-                self.data = balance_undersample(
-                    df=train_segment,
-                    target_column=target_column,
-                    task_type=self.task_type,
-                    random_state=self.random_state,
-                    imbalance_threshold=self.IMBALANCE_THESHOLD,
-                    binary_bootstrap_loops=self.BINARY_BOOTSTRAP_LOOPS,
-                    multiclass_bootstrap_loops=self.MULTICLASS_BOOTSTRAP_LOOPS,
-                    logger=self.logger,
-                    bundle=self.bundle,
-                    warning_counter=self.warning_counter,
+                msg = self.bundle.get("dataset_rarest_class_less_threshold").format(
+                    min_class_value, min_class_count, min_class_threshold, min_class_percent * 100
                 )
+                self.logger.warning(msg)
+                print(msg)
+                self.warning_counter.increment()
+
+                train_segment = train_segment.copy().sort_values(by=SYSTEM_RECORD_ID)
+                if self.task_type == ModelTaskType.MULTICLASS:
+                    # Sort classes by rows count and find 25% quantile class
+                    classes = target.value_counts().index
+                    quantile25_idx = int(0.75 * len(classes))
+                    quantile25_class = classes[quantile25_idx]
+                    count_of_quantile25_class = len(target[target == quantile25_class])
+                    msg = self.bundle.get("imbalance_multiclass").format(quantile25_class, count_of_quantile25_class)
+                    self.logger.warning(msg)
+                    print(msg)
+                    # 25% and lower classes will stay as is. Higher classes will be downsampled
+                    parts = []
+                    for class_idx in range(quantile25_idx):
+                        sampled = train_segment[train_segment[target_column] == classes[class_idx]].sample(
+                            n=count_of_quantile25_class, random_state=self.random_state
+                        )
+                        parts.append(sampled)
+                    for class_idx in range(quantile25_idx, len(classes)):
+                        parts.append(train_segment[train_segment[target_column] == classes[class_idx]])
+                    resampled_data = pd.concat(parts)
+                elif self.task_type == ModelTaskType.BINARY and min_class_count < self.MIN_SAMPLE_THRESHOLD / 2:
+                    minority_class = train_segment[train_segment[target_column] == min_class_value]
+                    majority_class = train_segment[train_segment[target_column] != min_class_value]
+                    sampled_majority_class = majority_class.sample(
+                        n=self.MIN_SAMPLE_THRESHOLD - min_class_count, random_state=self.random_state
+                    )
+                    resampled_data = train_segment[
+                        (train_segment[SYSTEM_RECORD_ID].isin(minority_class[SYSTEM_RECORD_ID]))
+                        | (train_segment[SYSTEM_RECORD_ID].isin(sampled_majority_class[SYSTEM_RECORD_ID]))
+                    ]
+                else:
+                    sampler = RandomUnderSampler(random_state=self.random_state)
+                    X = train_segment[SYSTEM_RECORD_ID]
+                    X = X.to_frame(SYSTEM_RECORD_ID)
+                    new_x, _ = sampler.fit_resample(X, target)  # type: ignore
+                    resampled_data = train_segment[train_segment[SYSTEM_RECORD_ID].isin(new_x[SYSTEM_RECORD_ID])]
+
+                self.data = resampled_data
+                self.logger.info(f"Shape after rebalance resampling: {self.data.shape}")
+                self.imbalanced = True
 
         # Resample over fit threshold
         if not self.imbalanced and EVAL_SET_INDEX in self.data.columns:

{upgini-1.1.253a5 → upgini-1.1.253a3261}/src/upgini/features_enricher.py

@@ -221,7 +221,7 @@ class FeaturesEnricher(TransformerMixin):
         if logs_enabled:
             self.logger = LoggerFactory().get_logger(endpoint, self._api_key, client_ip, client_visitorid)
         else:
-            self.logger = logging.getLogger("muted_logger")
+            self.logger = logging.getLogger()
             self.logger.setLevel("FATAL")
 
         if len(kwargs) > 0:
@@ -3047,6 +3047,20 @@ class FeaturesEnricher(TransformerMixin):
         def list_or_single(lst: List[str], single: str):
             return lst or ([single] if single else [])
 
+        def to_anchor(link: str, value: str) -> str:
+            if not value:
+                return ""
+            elif not link:
+                return value
+            elif value == llm_source:
+                return value
+            else:
+                return f"<a href='{link}' target='_blank' rel='noopener noreferrer'>{value}</a>"
+
+        def make_links(names: List[str], links: List[str]):
+            all_links = [to_anchor(link, name) for name, link in itertools.zip_longest(names, links)]
+            return ",".join(all_links)
+
         features_meta.sort(key=lambda m: (-m.shap_value, m.name))
         for feature_meta in features_meta:
             if feature_meta.name in original_names_dict.keys():
@@ -3072,20 +3086,6 @@ class FeaturesEnricher(TransformerMixin):
                 if len(feature_sample) > 30:
                     feature_sample = feature_sample[:30] + "..."
 
-            def to_anchor(link: str, value: str) -> str:
-                if not value:
-                    return ""
-                elif not link:
-                    return value
-                elif value == llm_source:
-                    return value
-                else:
-                    return f"<a href='{link}' target='_blank' rel='noopener noreferrer'>{value}</a>"
-
-            def make_links(names: List[str], links: List[str]):
-                all_links = [to_anchor(link, name) for name, link in itertools.zip_longest(names, links)]
-                return ",".join(all_links)
-
             internal_provider = feature_meta.data_provider or "Upgini"
             providers = list_or_single(feature_meta.data_providers, feature_meta.data_provider)
             provider_links = list_or_single(feature_meta.data_provider_links, feature_meta.data_provider_link)

{upgini-1.1.253a5 → upgini-1.1.253a3261}/src/upgini/search_task.py

@@ -57,7 +57,7 @@ class SearchTask:
         if logger is not None:
             self.logger = logger
         else:
-            self.logger = logging.getLogger("muted_logger")
+            self.logger = logging.getLogger()
             self.logger.setLevel("FATAL")
         self.provider_metadata_v2: Optional[List[ProviderTaskMetadataV2]] = None
         self.unused_features_for_generation: Optional[List[str]] = None

{upgini-1.1.253a5 → upgini-1.1.253a3261}/src/upgini/utils/datetime_utils.py

@@ -31,7 +31,7 @@ class DateTimeSearchKeyConverter:
         if logger is not None:
             self.logger = logger
         else:
-            self.logger = logging.getLogger("muted_logger")
+            self.logger = logging.getLogger()
             self.logger.setLevel("FATAL")
         self.generated_features: List[str] = []
         self.bundle = bundle or get_custom_bundle()

upgini-1.1.253a3261/src/upgini/utils/target_utils.py

@@ -0,0 +1,74 @@
+import logging
+from typing import Optional, Union
+
+import numpy as np
+import pandas as pd
+from pandas.api.types import is_numeric_dtype
+
+from upgini.errors import ValidationError
+from upgini.metadata import ModelTaskType
+from upgini.resource_bundle import bundle
+
+
+def correct_string_target(y: Union[pd.Series, np.ndarray]) -> Union[pd.Series, np.ndarray]:
+    if isinstance(y, pd.Series):
+        return y.astype(str).astype("category").cat.codes
+    elif isinstance(y, np.ndarray):
+        return pd.Series(y).astype(str).astype("category").cat.codes.values
+
+
+def define_task(
+    y: pd.Series, has_date: bool = False, logger: Optional[logging.Logger] = None, silent: bool = False
+) -> ModelTaskType:
+    if logger is None:
+        logger = logging.getLogger()
+    target = y.dropna()
+    if is_numeric_dtype(target):
+        target = target.loc[np.isfinite(target)]
+    else:
+        target = target.loc[target != ""]
+    if len(target) == 0:
+        raise ValidationError(bundle.get("empty_target"))
+    target_items = target.nunique()
+    if target_items == 1:
+        raise ValidationError(bundle.get("dataset_constant_target"))
+    if target_items == 2:
+        task = ModelTaskType.BINARY
+    else:
+        try:
+            target = pd.to_numeric(target)
+            is_numeric = True
+        except Exception:
+            is_numeric = False
+
+        # If any value is non numeric - multiclass
+        if not is_numeric:
+            task = ModelTaskType.MULTICLASS
+        else:
+            if target.nunique() <= 50 and is_int_encoding(target.unique()):
+                task = ModelTaskType.MULTICLASS
+            elif has_date:
+                task = ModelTaskType.REGRESSION
+            else:
+                non_zero_target = target[target != 0]
+                target_items = non_zero_target.nunique()
+                target_ratio = target_items / len(non_zero_target)
+                if (
+                    (target.dtype.kind == "f" and np.any(target != target.astype(int)))  # any non integer
+                    or target_items > 50
+                    or target_ratio > 0.2
+                ):
+                    task = ModelTaskType.REGRESSION
+                else:
+                    task = ModelTaskType.MULTICLASS
+
+    logger.info(f"Detected task type: {task}")
+    if not silent:
+        print(bundle.get("target_type_detected").format(task))
+    return task
+
+
+def is_int_encoding(unique_values):
+    return set(unique_values) == set(range(len(unique_values))) or set(unique_values) == set(
+        range(1, len(unique_values) + 1)
+    )

{upgini-1.1.253a5 → upgini-1.1.253a3261/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.253a5
+Version: 1.1.253a3261
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -18,12 +18,13 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Telecommunications Industry
 Classifier: License :: OSI Approved :: BSD License
 Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: >=3.8,<3.11
+Requires-Python: >=3.7,<3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: python-dateutil>=2.8.0

{upgini-1.1.253a5 → upgini-1.1.253a3261}/tests/test_etalon_validation.py

@@ -244,13 +244,11 @@ def test_imbalanced_target():
     }
     dataset.task_type = ModelTaskType.MULTICLASS
     dataset._Dataset__resample()
-    assert len(dataset) == 1800
+    assert len(dataset) == 400
     value_counts = dataset.data["target"].value_counts()
     assert len(value_counts) == 4
-    assert value_counts["a"] == 100
-    assert value_counts["b"] == 400
-    assert value_counts["c"] == 500
-    assert value_counts["d"] == 800
+    for label in dataset.data["target"].unique():
+        assert value_counts[label] == 100
 
 
 def test_fail_on_small_class_observations():

{upgini-1.1.253a5 → upgini-1.1.253a3261}/tests/test_features_enricher.py

@@ -2136,6 +2136,8 @@ def test_idempotent_order_with_imbalanced_dataset(requests_mock: Mocker):
         expected_result_df = (
             pd.read_parquet(expected_result_path).sort_values(by="system_record_id").reset_index(drop=True)
         )
+        expected_result_df["phone_num_a54a33"] = expected_result_df["phone_num_a54a33"].astype("Int64")
+        expected_result_df["rep_date_f5d6bb"] = expected_result_df["rep_date_f5d6bb"].astype("Int64")
 
         def test(n_shuffles: int):
             train_df = initial_train_df.copy()
@@ -2161,7 +2163,6 @@ def test_idempotent_order_with_imbalanced_dataset(requests_mock: Mocker):
                 pass
 
             actual_result_df = result_wrapper.df.sort_values(by="system_record_id").reset_index(drop=True)
-            # actual_result_df.to_parquet(expected_result_path)
             assert_frame_equal(actual_result_df, expected_result_df)
 
         for i in range(5):
@@ -2603,7 +2604,9 @@ def test_unsupported_arguments(requests_mock: Mocker):
 
         enricher.transform(df.drop(columns="target"), "unsupported_positional_argument", unsupported_key_argument=False)
 
-        with pytest.raises(ValueError, match="Only one class present in y_true. ROC AUC score is not defined in that case."):
+        with pytest.raises(
+            ValueError, match="Only one class present in y_true. ROC AUC score is not defined in that case."
+        ):
             enricher.calculate_metrics(
                 df.drop(columns="target"),
                 df["target"],

upgini-1.1.253a3261/tests/test_target_utils.py

@@ -0,0 +1,74 @@
+import numpy as np
+import pandas as pd
+import pytest
+
+from upgini.errors import ValidationError
+from upgini.metadata import ModelTaskType
+from upgini.resource_bundle import bundle
+from upgini.utils.target_utils import define_task
+
+
+def test_invalid_target():
+    y = pd.Series(["", "", ""])
+    with pytest.raises(ValidationError, match=bundle.get("empty_target")):
+        define_task(y)
+
+    y = pd.Series([np.nan, np.inf, -np.inf])
+    with pytest.raises(ValidationError, match=bundle.get("empty_target")):
+        define_task(y)
+
+    y = pd.Series([1, 1, 1, 1, 1])
+    with pytest.raises(ValidationError, match=bundle.get("dataset_constant_target")):
+        define_task(y)
+
+
+def test_define_binary_task_type():
+    y = pd.Series([0, 1, 0, 1, 0, 1])
+    assert define_task(y, False) == ModelTaskType.BINARY
+    assert define_task(y, True) == ModelTaskType.BINARY
+
+    y = pd.Series(["a", "b", "a", "b", "a"])
+    assert define_task(y, False) == ModelTaskType.BINARY
+    assert define_task(y, True) == ModelTaskType.BINARY
+
+
+def test_define_multiclass_task_type():
+    y = pd.Series(range(1, 51))
+    assert define_task(y, False) == ModelTaskType.MULTICLASS
+    assert define_task(y, True) == ModelTaskType.MULTICLASS
+
+    y = pd.Series([float(x) for x in range(1, 51)])
+    assert define_task(y, False) == ModelTaskType.MULTICLASS
+    assert define_task(y, True) == ModelTaskType.MULTICLASS
+
+    y = pd.Series(range(0, 50))
+    assert define_task(y, False) == ModelTaskType.MULTICLASS
+    assert define_task(y, True) == ModelTaskType.MULTICLASS
+
+    y = pd.Series(["a", "b", "c", "b", "a"])
+    assert define_task(y, False) == ModelTaskType.MULTICLASS
+    assert define_task(y, True) == ModelTaskType.MULTICLASS
+
+    y = pd.Series(["0", "1", "2", "3", "a"])
+    assert define_task(y, False) == ModelTaskType.MULTICLASS
+    assert define_task(y, True) == ModelTaskType.MULTICLASS
+
+    y = pd.Series([0.0, 3.0, 5.0, 0.0, 5.0, 0.0, 3.0, 0.0, 5.0, 0.0, 5.0, 0.0, 3.0, 0.0, 3.0, 5.0, 3.0])
+    assert define_task(y, False) == ModelTaskType.MULTICLASS
+
+
+def test_define_regression_task_type():
+    y = pd.Series([0.0, 3.0, 5.0, 0.0, 5.0, 0.0, 3.0, 0.0, 5.0, 0.0, 5.0, 0.0, 3.0, 0.0, 3.0, 5.0, 3.0])
+    assert define_task(y, True) == ModelTaskType.REGRESSION
+
+    y = pd.Series([0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.5])
+    assert define_task(y, False) == ModelTaskType.REGRESSION
+    assert define_task(y, True) == ModelTaskType.REGRESSION
+
+    y = pd.Series([0, 1, 2, 3, 4, 5, 6, 8])
+    assert define_task(y, False) == ModelTaskType.REGRESSION
+    assert define_task(y, True) == ModelTaskType.REGRESSION
+
+    y = pd.Series([0.0, 3.0, 5.0, 0.0, 5.0, 0.0, 3.0])
+    assert define_task(y, False) == ModelTaskType.REGRESSION
+    assert define_task(y, True) == ModelTaskType.REGRESSION

upgini-1.1.253a5/src/upgini/utils/target_utils.py

@@ -1,183 +0,0 @@
-import logging
-from typing import Optional, Union
-
-import numpy as np
-import pandas as pd
-from pandas.api.types import is_numeric_dtype
-
-from upgini.errors import ValidationError
-from upgini.metadata import SYSTEM_RECORD_ID, ModelTaskType
-from upgini.resource_bundle import ResourceBundle, bundle, get_custom_bundle
-from upgini.sampler.random_under_sampler import RandomUnderSampler
-from upgini.utils.warning_counter import WarningCounter
-
-
-def correct_string_target(y: Union[pd.Series, np.ndarray]) -> Union[pd.Series, np.ndarray]:
-    if isinstance(y, pd.Series):
-        return y.astype(str).astype("category").cat.codes
-    elif isinstance(y, np.ndarray):
-        return pd.Series(y).astype(str).astype("category").cat.codes.values
-
-
-def define_task(
-    y: pd.Series, has_date: bool = False, logger: Optional[logging.Logger] = None, silent: bool = False
-) -> ModelTaskType:
-    if logger is None:
-        logger = logging.getLogger()
-    target = y.dropna()
-    if is_numeric_dtype(target):
-        target = target.loc[np.isfinite(target)]
-    else:
-        target = target.loc[target != ""]
-    if len(target) == 0:
-        raise ValidationError(bundle.get("empty_target"))
-    target_items = target.nunique()
-    if target_items == 1:
-        raise ValidationError(bundle.get("dataset_constant_target"))
-    if target_items == 2:
-        task = ModelTaskType.BINARY
-    else:
-        try:
-            target = pd.to_numeric(target)
-            is_numeric = True
-        except Exception:
-            is_numeric = False
-
-        # If any value is non numeric - multiclass
-        if not is_numeric:
-            task = ModelTaskType.MULTICLASS
-        else:
-            if target.nunique() <= 50 and is_int_encoding(target.unique()):
-                task = ModelTaskType.MULTICLASS
-            elif has_date:
-                task = ModelTaskType.REGRESSION
-            else:
-                non_zero_target = target[target != 0]
-                target_items = non_zero_target.nunique()
-                target_ratio = target_items / len(non_zero_target)
-                if (
-                    (target.dtype.kind == "f" and np.any(target != target.astype(int)))  # any non integer
-                    or target_items > 50
-                    or target_ratio > 0.2
-                ):
-                    task = ModelTaskType.REGRESSION
-                else:
-                    task = ModelTaskType.MULTICLASS
-
-    logger.info(f"Detected task type: {task}")
-    if not silent:
-        print(bundle.get("target_type_detected").format(task))
-    return task
-
-
-def is_int_encoding(unique_values):
-    return set(unique_values) == set(range(len(unique_values))) or set(unique_values) == set(
-        range(1, len(unique_values) + 1)
-    )
-
-
-def balance_undersample(
-    df: pd.DataFrame,
-    target_column: str,
-    task_type: ModelTaskType,
-    random_state: int,
-    imbalance_threshold: int = 0.2,
-    min_sample_threshold: int = 5000,
-    binary_bootstrap_loops: int = 5,
-    multiclass_bootstrap_loops: int = 2,
-    logger: Optional[logging.Logger] = None,
-    bundle: Optional[ResourceBundle] = None,
-    warning_counter: Optional[WarningCounter] = None,
-) -> pd.DataFrame:
-    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")
-
-    count = len(df)
-    target = df[target_column].copy()
-    target_classes_count = target.nunique()
-
-    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]
-
-    min_class_percent = imbalance_threshold / target_classes_count
-    min_class_threshold = min_class_percent * count
-
-    resampled_data = df
-    df = df.copy().sort_values(by=SYSTEM_RECORD_ID)
-    if task_type == ModelTaskType.MULTICLASS:
-        # Sort classes by rows count and find 25% quantile class
-        classes = vc.index
-        quantile25_idx = int(0.75 * len(classes)) - 1
-        quantile25_class = classes[quantile25_idx]
-        quantile25_class_cnt = vc[quantile25_class]
-
-        if max_class_count > (quantile25_class_cnt * multiclass_bootstrap_loops):
-            msg = bundle.get("imbalance_multiclass").format(quantile25_class, quantile25_class_cnt)
-            logger.warning(msg)
-            print(msg)
-            if warning_counter:
-                warning_counter.increment()
-
-            # 25% and lower classes will stay as is. Higher classes will be downsampled
-            sample_strategy = dict()
-            for class_idx in range(quantile25_idx):
-                # compare class count with count_of_quantile25_class * 2
-                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
-            )
-            X = df[SYSTEM_RECORD_ID]
-            X = X.to_frame(SYSTEM_RECORD_ID)
-            new_x, _ = sampler.fit_resample(X, target)  # type: ignore
-
-            resampled_data = df[df[SYSTEM_RECORD_ID].isin(new_x[SYSTEM_RECORD_ID])]
-    elif len(df) > min_sample_threshold and min_class_count < min_sample_threshold / 2:
-        msg = bundle.get("dataset_rarest_class_less_threshold").format(
-            min_class_value, min_class_count, min_class_threshold, min_class_percent * 100
-        )
-        logger.warning(msg)
-        print(msg)
-        if warning_counter:
-            warning_counter.increment()
-
-        # 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]
-        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
-        )
-        resampled_data = df[
-            (df[SYSTEM_RECORD_ID].isin(minority_class[SYSTEM_RECORD_ID]))
-            | (df[SYSTEM_RECORD_ID].isin(sampled_majority_class[SYSTEM_RECORD_ID]))
-        ]
-
-    elif max_class_count > min_class_count * binary_bootstrap_loops:
-        msg = bundle.get("dataset_rarest_class_less_threshold").format(
-            min_class_value, min_class_count, min_class_threshold, min_class_percent * 100
-        )
-        logger.warning(msg)
-        print(msg)
-        if warning_counter:
-            warning_counter.increment()
-
-        sampler = RandomUnderSampler(
-            sampling_strategy={max_class_value: binary_bootstrap_loops * min_class_count}, 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
-
-        resampled_data = df[df[SYSTEM_RECORD_ID].isin(new_x[SYSTEM_RECORD_ID])]
-
-    logger.info(f"Shape after rebalance resampling: {resampled_data}")
-    return resampled_data

upgini-1.1.253a5/tests/test_target_utils.py

@@ -1,134 +0,0 @@
-import numpy as np
-import pandas as pd
-import pytest
-from pandas.testing import assert_frame_equal
-
-from upgini.errors import ValidationError
-from upgini.metadata import SYSTEM_RECORD_ID, TARGET, ModelTaskType
-from upgini.resource_bundle import bundle
-from upgini.utils.target_utils import balance_undersample, define_task
-
-
-def test_invalid_target():
-    y = pd.Series(["", "", ""])
-    with pytest.raises(ValidationError, match=bundle.get("empty_target")):
-        define_task(y)
-
-    y = pd.Series([np.nan, np.inf, -np.inf])
-    with pytest.raises(ValidationError, match=bundle.get("empty_target")):
-        define_task(y)
-
-    y = pd.Series([1, 1, 1, 1, 1])
-    with pytest.raises(ValidationError, match=bundle.get("dataset_constant_target")):
-        define_task(y)
-
-
-def test_define_binary_task_type():
-    y = pd.Series([0, 1, 0, 1, 0, 1])
-    assert define_task(y, False) == ModelTaskType.BINARY
-    assert define_task(y, True) == ModelTaskType.BINARY
-
-    y = pd.Series(["a", "b", "a", "b", "a"])
-    assert define_task(y, False) == ModelTaskType.BINARY
-    assert define_task(y, True) == ModelTaskType.BINARY
-
-
-def test_define_multiclass_task_type():
-    y = pd.Series(range(1, 51))
-    assert define_task(y, False) == ModelTaskType.MULTICLASS
-    assert define_task(y, True) == ModelTaskType.MULTICLASS
-
-    y = pd.Series([float(x) for x in range(1, 51)])
-    assert define_task(y, False) == ModelTaskType.MULTICLASS
-    assert define_task(y, True) == ModelTaskType.MULTICLASS
-
-    y = pd.Series(range(0, 50))
-    assert define_task(y, False) == ModelTaskType.MULTICLASS
-    assert define_task(y, True) == ModelTaskType.MULTICLASS
-
-    y = pd.Series(["a", "b", "c", "b", "a"])
-    assert define_task(y, False) == ModelTaskType.MULTICLASS
-    assert define_task(y, True) == ModelTaskType.MULTICLASS
-
-    y = pd.Series(["0", "1", "2", "3", "a"])
-    assert define_task(y, False) == ModelTaskType.MULTICLASS
-    assert define_task(y, True) == ModelTaskType.MULTICLASS
-
-    y = pd.Series([0.0, 3.0, 5.0, 0.0, 5.0, 0.0, 3.0, 0.0, 5.0, 0.0, 5.0, 0.0, 3.0, 0.0, 3.0, 5.0, 3.0])
-    assert define_task(y, False) == ModelTaskType.MULTICLASS
-
-
-def test_define_regression_task_type():
-    y = pd.Series([0.0, 3.0, 5.0, 0.0, 5.0, 0.0, 3.0, 0.0, 5.0, 0.0, 5.0, 0.0, 3.0, 0.0, 3.0, 5.0, 3.0])
-    assert define_task(y, True) == ModelTaskType.REGRESSION
-
-    y = pd.Series([0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.5])
-    assert define_task(y, False) == ModelTaskType.REGRESSION
-    assert define_task(y, True) == ModelTaskType.REGRESSION
-
-    y = pd.Series([0, 1, 2, 3, 4, 5, 6, 8])
-    assert define_task(y, False) == ModelTaskType.REGRESSION
-    assert define_task(y, True) == ModelTaskType.REGRESSION
-
-    y = pd.Series([0.0, 3.0, 5.0, 0.0, 5.0, 0.0, 3.0])
-    assert define_task(y, False) == ModelTaskType.REGRESSION
-    assert define_task(y, True) == ModelTaskType.REGRESSION
-
-
-def test_balance_undersampling_binary():
-    df = pd.DataFrame({SYSTEM_RECORD_ID: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10], TARGET: [0, 1, 0, 0, 0, 0, 0, 0, 0, 0]})
-    balanced_df = balance_undersample(
-        df, TARGET, ModelTaskType.BINARY, 42, imbalance_threshold=0.1, min_sample_threshold=2
-    )
-    # Get all minority class and 5x of majority class if minority class count (1)
-    # more or equal to min_sample_threshold/2 (1)
-    expected_df = pd.DataFrame({
-        SYSTEM_RECORD_ID: [1, 2, 3, 7, 9, 10],
-        TARGET: [0, 1, 0, 0, 0, 0]
-    })
-    assert_frame_equal(balanced_df.sort_values(by=SYSTEM_RECORD_ID).reset_index(drop=True), expected_df)
-
-    balanced_df = balance_undersample(
-        df, TARGET, ModelTaskType.BINARY, 42, imbalance_threshold=0.1, min_sample_threshold=8
-    )
-    # Get all minority class and fill up to min_sample_threshold (8) by majority class
-    expected_df = pd.DataFrame({
-        SYSTEM_RECORD_ID: [1, 2, 3, 4, 6, 7, 9, 10],
-        TARGET: [0, 1, 0, 0, 0, 0, 0, 0]
-    })
-    assert_frame_equal(balanced_df.sort_values(by=SYSTEM_RECORD_ID).reset_index(drop=True), expected_df)
-
-    df = pd.DataFrame({"system_record_id": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10], TARGET: [0, 1, 0, 0, 0, 0, 0, 0, 1, 0]})
-    balanced_df = balance_undersample(
-        df, "target", ModelTaskType.BINARY, 42, imbalance_threshold=0.1, min_sample_threshold=4
-    )
-    # Get full dataset if majority class count (8) less than x5 of minority class count (2)
-    assert_frame_equal(balanced_df, df)
-
-
-def test_balance_undersaampling_multiclass():
-    df = pd.DataFrame({
-        SYSTEM_RECORD_ID: [1, 2, 3, 4, 5, 6],
-        TARGET: ["a", "b", "c", "c", "b", "c"]
-        # a - 1, b - 2, c - 3
-    })
-    balanced_df = balance_undersample(
-        df, TARGET, ModelTaskType.MULTICLASS, 42, imbalance_threshold=0.1, min_sample_threshold=10
-    )
-    # Get full dataset if majority class count (3) less than x2 of 25% class (b) count (2)
-    assert_frame_equal(balanced_df, df)
-
-    df = pd.DataFrame({
-        SYSTEM_RECORD_ID: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11],
-        TARGET: ["a", "b", "c", "c", "c", "b", "c", "d", "d", "d", "c"]
-        # a - 1, b - 2, c - 5, d - 3
-    })
-    balanced_df = balance_undersample(
-        df, TARGET, ModelTaskType.MULTICLASS, 42, imbalance_threshold=0.1, min_sample_threshold=10
-    )
-    expected_df = pd.DataFrame({
-        SYSTEM_RECORD_ID: [1, 2, 3, 4, 5, 6, 8, 9, 10, 11],
-        TARGET: ["a", "b", "c", "c", "c", "b", "d", "d", "d", "c"]
-    })
-    # Get all of 25% quantile class (b) and minor classes (a) and x2 (or all if less) of major classes
-    assert_frame_equal(balanced_df.sort_values(by=SYSTEM_RECORD_ID).reset_index(drop=True), expected_df)