upgini 1.1.280a3418.post2__py3-none-any.whl → 1.2.31__py3-none-any.whl

upgini/utils/target_utils.py

@@ -3,7 +3,7 @@ from typing import Optional, Union
 
 import numpy as np
 import pandas as pd
-from pandas.api.types import is_numeric_dtype
+from pandas.api.types import is_numeric_dtype, is_bool_dtype
 
 from upgini.errors import ValidationError
 from upgini.metadata import SYSTEM_RECORD_ID, ModelTaskType
@@ -24,49 +24,83 @@ def define_task(
 ) -> ModelTaskType:
     if logger is None:
         logger = logging.getLogger()
+
+    # Replace inf and -inf with NaN to handle extreme values correctly
+    y = y.replace([np.inf, -np.inf], np.nan, inplace=False)
+
+    # Drop NaN values from the target
     target = y.dropna()
+
+    # Check if target is numeric and finite
     if is_numeric_dtype(target):
         target = target.loc[np.isfinite(target)]
     else:
+        # If not numeric, drop empty strings as well
         target = target.loc[target != ""]
+
+    # Raise error if there are no valid values left in the target
     if len(target) == 0:
         raise ValidationError(bundle.get("empty_target"))
+
+    # Count unique values in the target
     target_items = target.nunique()
+
+    # Raise error if all target values are the same
     if target_items == 1:
         raise ValidationError(bundle.get("dataset_constant_target"))
+
+    reason = ""  # Will store the reason for selecting the task type
+
+    # Binary classification case: exactly two unique values
     if target_items == 2:
         task = ModelTaskType.BINARY
+        reason = bundle.get("binary_target_reason")
     else:
+        # Attempt to convert target to numeric
         try:
             target = pd.to_numeric(target)
             is_numeric = True
         except Exception:
             is_numeric = False
 
-        # If any value is non numeric - multiclass
+        # If target cannot be converted to numeric, assume multiclass classification
         if not is_numeric:
             task = ModelTaskType.MULTICLASS
+            reason = bundle.get("non_numeric_multiclass_reason")
         else:
+            # Multiclass classification: few unique values and integer encoding
             if target.nunique() <= 50 and is_int_encoding(target.unique()):
                 task = ModelTaskType.MULTICLASS
+                reason = bundle.get("few_unique_label_multiclass_reason")
+            # Regression case: if there is date, assume regression
             elif has_date:
                 task = ModelTaskType.REGRESSION
+                reason = bundle.get("date_search_key_regression_reason")
             else:
+                # Remove zero values and recalculate unique ratio
                 non_zero_target = target[target != 0]
                 target_items = non_zero_target.nunique()
                 target_ratio = target_items / len(non_zero_target)
+
+                # Use unique_ratio to determine whether to classify as regression or multiclass
                 if (
-                    (target.dtype.kind == "f" and np.any(target != target.astype(int)))  # any non integer
+                    (target.dtype.kind == "f" and np.any(target != target.astype(int)))  # Non-integer float values
                     or target_items > 50
-                    or target_ratio > 0.2
+                    or target_ratio > 0.2  # If non-zero values have high ratio of uniqueness
                 ):
                     task = ModelTaskType.REGRESSION
+                    reason = bundle.get("many_unique_label_regression_reason")
                 else:
                     task = ModelTaskType.MULTICLASS
+                    reason = bundle.get("limited_int_multiclass_reason")
 
-    logger.info(f"Detected task type: {task}")
+    # Log or print the reason for the selected task type
+    logger.info(f"Detected task type: {task} (Reason: {reason})")
+
+    # Print task type and reason if silent mode is off
     if not silent:
-        print(bundle.get("target_type_detected").format(task))
+        print(bundle.get("target_type_detected").format(task, reason))
+
     return task
 
 
@@ -81,8 +115,8 @@ def balance_undersample(
     target_column: str,
     task_type: ModelTaskType,
     random_state: int,
-    imbalance_threshold: int = 0.2,
-    min_sample_threshold: int = 5000,
+    binary_min_sample_threshold: int = 5000,
+    multiclass_min_sample_threshold: int = 25000,
     binary_bootstrap_loops: int = 5,
     multiclass_bootstrap_loops: int = 2,
     logger: Optional[logging.Logger] = None,
@@ -96,52 +130,60 @@ def balance_undersample(
     if SYSTEM_RECORD_ID not in df.columns:
         raise Exception("System record id must be presented for undersampling")
 
-    count = len(df)
+    # count = len(df)
     target = df[target_column].copy()
-    target_classes_count = target.nunique()
+    # 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]
+    num_classes = len(vc)
 
-    min_class_percent = imbalance_threshold / target_classes_count
-    min_class_threshold = int(min_class_percent * count)
+    # min_class_percent = imbalance_threshold / target_classes_count
+    # min_class_threshold = int(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)
+        if len(df) > multiclass_min_sample_threshold and max_class_count > (
+            min_class_count * multiclass_bootstrap_loops
+        ):
+
+            # msg = bundle.get("imbalance_multiclass").format(min_class_value, min_class_count)
+            msg = bundle.get("imbalanced_target").format(min_class_value, min_class_count)
             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]
+            for class_value in vc.index:
+                if class_value == min_class_value:
+                    continue
                 class_count = vc[class_value]
-                sample_strategy[class_value] = min(class_count, quantile25_class_cnt * multiclass_bootstrap_loops)
+                sample_size = min(
+                    class_count,
+                    multiclass_bootstrap_loops
+                    * (
+                        min_class_count
+                        + max((multiclass_min_sample_threshold - num_classes * min_class_count) / (num_classes - 1), 0)
+                    ),
+                )
+                sample_strategy[class_value] = int(sample_size)
+            logger.info(f"Rebalance sample strategy: {sample_strategy}. Min class count: {min_class_count}")
             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
-        )
+    elif len(df) > binary_min_sample_threshold:
+        # msg = bundle.get("dataset_rarest_class_less_threshold").format(
+        #     min_class_value, min_class_count, min_class_threshold, min_class_percent * 100
+        # )
+        msg = bundle.get("imbalanced_target").format(min_class_value, min_class_count)
         logger.warning(msg)
         print(msg)
         if warning_counter:
@@ -150,48 +192,62 @@ def balance_undersample(
         # 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)
+        # sample_size = min(len(majority_class), min_sample_threshold - min_class_count)
+        sample_size = min(
+            max_class_count,
+            binary_bootstrap_loops * (min_class_count + max(binary_min_sample_threshold - 2 * min_class_count, 0)),
+        )
+        logger.info(
+            f"Min class count: {min_class_count}. Max class count: {max_class_count}."
+            f" Rebalance sample size: {sample_size}"
+        )
         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()
+    # 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
+    #     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])]
+    #     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
 
 
-def calculate_psi(expected: pd.Series, actual: pd.Series) -> float:
-    df = pd.concat([expected, actual])
+def calculate_psi(expected: pd.Series, actual: pd.Series) -> Union[float, Exception]:
+    try:
+        df = pd.concat([expected, actual])
+
+        if is_bool_dtype(df):
+            df = np.where(df, 1, 0)
 
-    # 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]
+        # 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 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 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))
+        # Calculate the PSI
+        return np.sum((train_distribution - test_distribution) * np.log(train_distribution / test_distribution))
+    except Exception as e:
+        return e

upgini/utils/warning_counter.py

@@ -4,6 +4,7 @@ class WarningCounter:
 
     def increment(self):
         self._count += 1
+        return self._count
 
     def reset(self):
         self._count = 0

upgini/version_validator.py

@@ -1,5 +1,6 @@
 import json
 import threading
+from typing import Callable, Optional
 
 import requests
 
@@ -30,15 +31,18 @@ def get_version(package, url_pattern=URL_PATTERN):
     return version
 
 
-def validate_version(logger: logging.Logger):
+def validate_version(logger: logging.Logger, warning_function: Optional[Callable[[str], None]] = None):
     def task():
         try:
             current_version = parse(__version__)
             latest_version = get_version("upgini")
-            if current_version < latest_version:  # type: ignore
+            if current_version < latest_version:
                 msg = bundle.get("version_warning").format(current_version, latest_version)
-                logger.warning(msg)
-                print(msg)
+                if warning_function:
+                    warning_function(msg)
+                else:
+                    logger.warning(msg)
+                    print(msg)
         except Exception:
             logger.warning("Failed to validate version", exc_info=True)
 

{upgini-1.1.280a3418.post2.dist-info → upgini-1.2.31.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.280a3418.post2
+Version: 1.2.31
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -22,15 +22,17 @@ 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: <3.11,>=3.8
+Requires-Python: <3.12,>=3.8
 Requires-Dist: catboost>=1.0.3
 Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0
-Requires-Dist: lightgbm>=3.3.2
-Requires-Dist: numpy>=1.19.0
+Requires-Dist: jarowinkler>=2.0.0
+Requires-Dist: levenshtein>=0.25.1
+Requires-Dist: numpy<=1.26.4,>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0
-Requires-Dist: pydantic<2.0.0,>=1.8.2
+Requires-Dist: pydantic<3.0.0,>1.0.0
 Requires-Dist: pyjwt>=2.8.0
+Requires-Dist: python-bidi==0.4.2
 Requires-Dist: python-dateutil>=2.8.0
 Requires-Dist: python-json-logger>=2.0.2
 Requires-Dist: requests>=2.8.0
@@ -130,7 +132,7 @@ Description-Content-Type: text/markdown
 |Consumer Confidence index| 44 |22|-|Monthly|date, country|No
 |World economic indicators|191 |41|-|Monthly|date, country|No
 |Markets data|-|17|-|Monthly|date, datetime|No
-|World mobile & fixed broadband network coverage and perfomance |167|-|3|Monthly|country, postal/ZIP code|No
+|World mobile & fixed broadband network coverage and performance |167|-|3|Monthly|country, postal/ZIP code|No
 |World demographic data |90|-|2|Annual|country, postal/ZIP code|No
 |World house prices |44|-|3|Annual|country, postal/ZIP code|No
 |Public social media profile data |104|-|-|Monthly|date, email/HEM, phone |Yes
@@ -143,7 +145,7 @@ Description-Content-Type: text/markdown
 
 ## 💼 Tutorials
 
-###  [Search of relevant external features & Automated feature generation for Salary predicton task (use as a template)](https://github.com/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb)
+###  [Search of relevant external features & Automated feature generation for Salary prediction task (use as a template)](https://github.com/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb)
 
 * The goal is to predict salary for data science job postning based on information about employer and job description.
 * Following this guide, you'll learn how to **search & auto generate new relevant features with Upgini library**
@@ -257,7 +259,9 @@ We do dataset verification and cleaning under the hood, but still there are some
 *Search keys* columns will be used to match records from all potential external data sources / features.   
 Define one or multiple columns as a search keys with `FeaturesEnricher` class initialization.  
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -343,7 +347,9 @@ enricher = FeaturesEnricher(
 
 For the meaning types <tt>SearchKey.DATE</tt>/<tt>SearchKey.DATETIME</tt> with dtypes <tt>object</tt> or <tt>string</tt> you have to clarify date/datetime format by passing <tt>date_format</tt> parameter to `FeaturesEnricher`. For example:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -364,7 +370,9 @@ df["date"] = df.date.astype("datetime64").dt.tz_localize("Europe/Warsaw")
 
 Single country for the whole training dataset can be passed with `country_code` parameter:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -383,7 +391,8 @@ Create instance of the `FeaturesEnricher` class and call:
 Let's try it out!
 ```python
 import pandas as pd
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
 
 # load labeled training dataset to initiate search
 train_df = pd.read_csv("customer_churn_prediction_train.csv")
@@ -474,7 +483,9 @@ We detect ML task under the hood based on label column values. Currently we supp
 
 But for certain search datasets you can pass parameter to `FeaturesEnricher` with correct ML taks type:
 ```python
-from upgini import ModelTaskType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, ModelTaskType
+
 enricher = FeaturesEnricher(
 	search_keys={"subscription_activation_date": SearchKey.DATE},
 	model_task_type=ModelTaskType.REGRESSION
@@ -487,7 +498,9 @@ enricher = FeaturesEnricher(
 
 To initiate feature search you can pass cross-validation type parameter to `FeaturesEnricher` with time series specific CV type:
 ```python
-from upgini.metadata import CVType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, CVType
+
 enricher = FeaturesEnricher(
 	search_keys={"sales_date": SearchKey.DATE},
 	cv=CVType.time_series
@@ -621,7 +634,9 @@ But you can easily define new split by passing child of BaseCrossValidator to pa
 
 Example with more tips-and-tricks:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(search_keys={"registration_date": SearchKey.DATE})
 
 # Fit with default setup for metrics calculation
@@ -794,7 +809,7 @@ You may publish ANY data which you consider as royalty / license free ([Open Dat
 2. Copy *Upgini API key* from profile and upload your data from Upgini python library with this key:
 ```python
 import pandas as pd
-from upgini import SearchKey
+from upgini.metadata import SearchKey
 from upgini.ads import upload_user_ads
 import os
 os.environ["UPGINI_API_KEY"] = "your_long_string_api_key_goes_here"
@@ -839,4 +854,4 @@ Some convenient ways to start contributing are:
 - [More perks for registered users](https://profile.upgini.com)
 
 <sup>😔 Found mistype or a bug in code snippet? Our bad! <a href="https://github.com/upgini/upgini/issues/new?assignees=&title=readme%2Fbug">
-Please report it here.</a></sup>
+Please report it here</a></sup>

upgini-1.2.31.dist-info/RECORD

@@ -0,0 +1,65 @@
+upgini/__about__.py,sha256=ZMRxZM_8KClqm4X0jGVzsRbSK2eN35eEoOdQFqr5IU0,23
+upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
+upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
+upgini/dataset.py,sha256=iPFiMJtk4HF1ytw9wCQr8H9RfoOKj_TIo8XYZKWgcMc,31331
+upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
+upgini/features_enricher.py,sha256=lNfu5Z40NmkkGJScKAwe_0VBtL8liePifuAlKE_flfA,192053
+upgini/http.py,sha256=plZGTGoi1h2edd8Cnjt4eYB8t4NbBGnZz7DtPTByiNc,42885
+upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
+upgini/metadata.py,sha256=lUa2xYhBhnCeTqNt6lWc9iP_YuikYGIsDSn8Vwyjv1I,11235
+upgini/metrics.py,sha256=hr7UwLphbZ_FEglLuO2lzr_pFgxOJ4c3WBeg7H-fNqY,35521
+upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
+upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
+upgini/version_validator.py,sha256=h1GViOWzULy5vf6M4dpTJuIk-4V38UCrTY1sb9yLa5I,1594
+upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
+upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
+upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+upgini/autofe/all_operands.py,sha256=cCCB44qvkmuWyiRM5Xykx8tkHPIjQthrWyj67STWN80,2578
+upgini/autofe/binary.py,sha256=zMhtHVuGUAFLUqem-XiXqJj-GRXxS88tdz8tFuDfSNM,7659
+upgini/autofe/date.py,sha256=OpFc3Al0xO3qlESn2Uokfxw51ArVqmh3xngWwdrsaqE,9762
+upgini/autofe/feature.py,sha256=eL7wABUhDKZzv3E-RPJNcyGwSfB0UptcfU2RbvsOks4,15082
+upgini/autofe/groupby.py,sha256=r-xl_keZZgm_tpiEoDhjYSkT6NHv7a4cRQR4wJ4uCp8,3263
+upgini/autofe/operand.py,sha256=uk883RaNqgXqtkaRqA1re1d9OFnnpv0JVvelYx09Yw0,2943
+upgini/autofe/unary.py,sha256=T3E7F3dA_7o_rkdCFq7JV6nHLzcoHLHQTcxO7y5Opa4,4646
+upgini/autofe/vector.py,sha256=ehcZUDqV71TfbU8EmKfdYp603gS2dJY_-fpr10ho5sI,663
+upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+upgini/data_source/data_source_publisher.py,sha256=X-8aGtVgzGmxyXkMVBoBLIGDMb4lYQaGZbxDnOd4A3Q,22516
+upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
+upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
+upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
+upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
+upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
+upgini/resource_bundle/strings.properties,sha256=bKw_rjZZTomLJhQBqiM7_P2EoRq45_Ng2gP4WE6MRBE,26921
+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
+upgini/sampler/random_under_sampler.py,sha256=TIbm7ATo-bCMF-IiS5sZeDC1ad1SYg0eY_rRmg84yIQ,4024
+upgini/sampler/utils.py,sha256=PYOk3kKSnFlyxcpdtDNLBEEhTB4lO_iP7pQHqeUcmAc,20211
+upgini/utils/Roboto-Regular.ttf,sha256=kqYnZjMRQMpbyLulIChCLSdgYa1XF8GsUIoRi2Gcauw,168260
+upgini/utils/__init__.py,sha256=O_KgzKiJjW3g4NoqZ7lAxUpoHcBi_gze6r3ndEjCH74,842
+upgini/utils/base_search_key_detector.py,sha256=Inc6iGG-VXQdejWFfbekIkZk2ahC4k7CdGqzOkie6Bs,1021
+upgini/utils/blocked_time_series.py,sha256=Uqr3vp4YqNclj2-PzEYqVy763GSXHn86sbpIl1UOB4s,3382
+upgini/utils/country_utils.py,sha256=lY-eXWwFVegdVENFttbvLcgGDjFO17Sex8hd2PyJaRk,6937
+upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
+upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
+upgini/utils/datetime_utils.py,sha256=F61i2vZCB6eUy4WwodDyPi50XKPbhOHsxDrU6tGa6CM,13133
+upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
+upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
+upgini/utils/email_utils.py,sha256=GbnhHJn1nhUBytmK6PophYqaoq4t7Lp6i0-O0Gd3RV8,5265
+upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
+upgini/utils/feature_info.py,sha256=Tp_2g5-rCjY4NpzKhzxwNxuqH5FFL8vG94OU5kH6wzk,6702
+upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
+upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
+upgini/utils/ip_utils.py,sha256=Q6vb7Sr5Khx3Sq3eENjW2qCXKej_S5jZbneH6zEOkzQ,5171
+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/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,44511
+upgini/utils/target_utils.py,sha256=PU77nIhTz7IHbC4rpTpxrVxib6cdpRL9F1dhkjIffLY,10225
+upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
+upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
+upgini-1.2.31.dist-info/METADATA,sha256=_OJUvR8p-0uuVdltUq34yo_W5OZZvKOlID5OHlYY9Do,48578
+upgini-1.2.31.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.31.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.31.dist-info/RECORD,,