upgini 1.2.26__py3-none-any.whl → 1.2.27__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.26"
+__version__ = "1.2.27"

upgini/__init__.py

@@ -1,13 +1,5 @@
-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"
+import warnings
 
-# 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")
+warnings.filterwarnings("ignore", category=UserWarning, module="_distutils_hack")

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])
@@ -4038,15 +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/utils/target_utils.py

@@ -229,25 +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])
 
-    if is_bool_dtype(df):
-        df = np.where(df, 1, 0)
+        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
-    try:
+        # 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-1.2.26.dist-info → upgini-1.2.27.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.26
+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-1.2.26.dist-info → upgini-1.2.27.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=8uhHORUThu_bp8-miLA4O6Em4FxNLHbY_K0t053StGY,23
-upgini/__init__.py,sha256=M64LwQTBa-5Jz24Zm2h8rWwlKQQ1J8nP7gGgIciS0WU,589
+upgini/__about__.py,sha256=JKArgvnX6ljUI_WxYnXTejXGdjsA4KJ3Cy2xBcK4vh4,23
+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=V1zzUHYzmhdouZVdoFBbMH1OIqUCqV1p0mIXfcTvj6Y,193614
+upgini/features_enricher.py,sha256=7xYxcLvxQgDX7vE2gWEbBPceAVeEgBVpu9xtBJvXpoQ,194078
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
@@ -55,10 +55,10 @@ upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,1
 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=8R11IpwHxaEPJ5T2lcxXyeGFDuN6vquwlJep4ack-Ug,10159
+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-1.2.26.dist-info/METADATA,sha256=vPNo6WUZ5Ypkvs0dVfV8i5sch4pCwsC_QkOac5SOZqA,48578
-upgini-1.2.26.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.26.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.26.dist-info/RECORD,,
+upgini-1.2.27.dist-info/METADATA,sha256=iSB1iB7EwBugIUf8DYOz9mEFqGewDAS49-hgYuhtrtU,48578
+upgini-1.2.27.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.27.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.27.dist-info/RECORD,,