upgini 1.2.25a1__tar.gz → 1.2.27__tar.gz

{upgini-1.2.25a1 → upgini-1.2.27}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.25a1
+Version: 1.2.27
 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-1.2.25a1 → upgini-1.2.27}/pyproject.toml

@@ -52,12 +52,6 @@ dependencies = [
     "levenshtein>=0.25.1",
 ]
 
-[tool.setuptools]
-include-package-data = true
-
-[tool.setuptools.package-data]
-"upgini" = ["utils/Roboto-Regular.ttf"]
-
 [project.urls]
 "Bug Reports" = "https://github.com/upgini/upgini/issues"
 Homepage = "https://upgini.com/"

upgini-1.2.27/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.27"

upgini-1.2.27/src/upgini/__init__.py

@@ -0,0 +1,5 @@
+from upgini.features_enricher import FeaturesEnricher  # noqa: F401
+from upgini.metadata import SearchKey, CVType, RuntimeParameters, ModelTaskType  # noqa: F401
+import warnings
+
+warnings.filterwarnings("ignore", category=UserWarning, module="_distutils_hack")

{upgini-1.2.25a1 → upgini-1.2.27}/src/upgini/features_enricher.py

@@ -2546,9 +2546,11 @@ class FeaturesEnricher(TransformerMixin):
             self.fit_generated_features.extend(generator.generated_features)
 
         # Checks that need validated date
-
-        if not is_dates_distribution_valid(df, self.fit_search_keys):
-            self.__log_warning(bundle.get("x_unstable_by_date"))
+        try:
+            if not is_dates_distribution_valid(df, self.fit_search_keys):
+                self.__log_warning(bundle.get("x_unstable_by_date"))
+        except Exception:
+            self.logger.exception("Failed to check dates distribution validity")
 
         if (
             is_numeric_dtype(df[self.TARGET_NAME])
@@ -3194,9 +3196,8 @@ class FeaturesEnricher(TransformerMixin):
 
         return df
 
-    @staticmethod
     def _add_current_date_as_key(
-        df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: logging.Logger, bundle: ResourceBundle
+        self, df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: logging.Logger, bundle: ResourceBundle
     ) -> pd.DataFrame:
         if (
             set(search_keys.values()) == {SearchKey.PHONE}
@@ -3204,9 +3205,7 @@ class FeaturesEnricher(TransformerMixin):
             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)
+            self.__log_warning(bundle.get("current_date_added"))
             df[FeaturesEnricher.CURRENT_DATE] = datetime.date.today()
             search_keys[FeaturesEnricher.CURRENT_DATE] = SearchKey.DATE
             converter = DateTimeSearchKeyConverter(FeaturesEnricher.CURRENT_DATE)
@@ -4041,15 +4040,19 @@ class FeaturesEnricher(TransformerMixin):
         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.__log_warning(self.bundle.get("train_unstable_target").format(train_psi))
+        train_psi_result = calculate_psi(part1[self.TARGET_NAME], part2[self.TARGET_NAME])
+        if isinstance(train_psi_result, Exception):
+            self.logger.exception("Failed to calculate train PSI", train_psi_result)
+        elif train_psi_result > 0.2:
+            self.__log_warning(self.bundle.get("train_unstable_target").format(train_psi_result))
 
         # 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.__log_warning(self.bundle.get("eval_unstable_target").format(train_test_psi))
+            train_test_psi_result = calculate_psi(train[self.TARGET_NAME], eval1[self.TARGET_NAME])
+            if isinstance(train_test_psi_result, Exception):
+                self.logger.exception("Failed to calculate test PSI", train_test_psi_result)
+            elif train_test_psi_result > 0.2:
+                self.__log_warning(self.bundle.get("eval_unstable_target").format(train_test_psi_result))
 
     def _dump_python_libs(self):
         try:

{upgini-1.2.25a1 → upgini-1.2.27}/src/upgini/resource_bundle/strings.properties

@@ -9,7 +9,7 @@ search_stopped=Search request stopped
 polling_search_task=\nRunning search request, search_id={}
 polling_unregister_information=We'll send email notification once it's completed, just use your personal api_key from profile.upgini.com
 ads_upload_finish=Thank you for your submission!\nWe'll check your data sharing proposal and get back to you
-demo_dataset_info=Demo training dataset detected. Registration for an API key is not required.
+demo_dataset_info=Demo training dataset detected. Registration for an API key is not required.\n
 transform_usage_info=You use Trial access to Upgini data enrichment. Limit for Trial: {} rows. You have already enriched: {} rows.
 transform_usage_warning=You are trying to launch enrichment for {} rows, which will exceed the rest limit {}.
 

{upgini-1.2.25a1 → upgini-1.2.27}/src/upgini/utils/display_utils.py

@@ -169,7 +169,6 @@ def make_html_report(
         from pkg_resources import resource_filename
         font_path = resource_filename('upgini.utils', 'Roboto-Regular.ttf')
 
-    print(font_path)
     return f"""<html>
         <head>
             <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />

{upgini-1.2.25a1 → upgini-1.2.27}/src/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
@@ -229,22 +229,25 @@ def balance_undersample(
     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])
 
-    # 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]
+        if is_bool_dtype(df):
+            df = np.where(df, 1, 0)
 
-    # Calculate the base distribution
-    train_distribution = expected.value_counts(bins=bins, normalize=True).sort_index().values
+        # 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 target distribution
-    test_distribution = actual.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 PSI
-    try:
+        # 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))
-    except Exception:
-        return np.nan
+    except Exception as e:
+        return e

upgini-1.2.25a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.25a1"

upgini-1.2.25a1/src/upgini/__init__.py

@@ -1,13 +0,0 @@
-import os
-
-from upgini.features_enricher import FeaturesEnricher  # noqa: F401
-from upgini.metadata import SearchKey, CVType, RuntimeParameters, ModelTaskType  # noqa: F401
-# from .lazy_import import LazyImport
-
-os.environ["SETUPTOOLS_USE_DISTUTILS"] = "stdlib"
-
-# FeaturesEnricher = LazyImport("upgini.features_enricher", "FeaturesEnricher")
-# SearchKey = LazyImport("upgini.metadata", "SearchKey")
-# RuntimeParameters = LazyImport("upgini.metadata", "RuntimeParameters")
-# CVType = LazyImport("upgini.metadata", "CVType")
-# ModelTaskType = LazyImport("upgini.metadata", "ModelTaskType")