upgini 1.2.13a4__tar.gz → 1.2.14a1__tar.gz

{upgini-1.2.13a4 → upgini-1.2.14a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.13a4
+Version: 1.2.14a1
 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-1.2.14a1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.14a1"

{upgini-1.2.13a4 → upgini-1.2.14a1}/src/upgini/autofe/binary.py

@@ -140,13 +140,9 @@ class Distance(PandasOperand):
     has_symmetry_importance: bool = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
-        # Handle None values by replacing them with 0 in the dot product and norm calculations
-        left = left.apply(lambda x: np.array(x) if x is not None else np.zeros_like(right[0]))
-        right = right.apply(lambda x: np.array(x) if x is not None else np.zeros_like(left[0]))
-
         return pd.Series(
             1 - self.__dot(left, right) / (self.__norm(left) * self.__norm(right)), index=left.index
-        )
+        ).astype(np.float64)
 
     # row-wise dot product, handling None values
     def __dot(self, left: pd.Series, right: pd.Series) -> pd.Series:

{upgini-1.2.13a4 → upgini-1.2.14a1}/src/upgini/dataset.py

@@ -253,6 +253,7 @@ class Dataset:  # (pd.DataFrame):
             min_class_percent = self.IMBALANCE_THESHOLD / target_classes_count
             min_class_threshold = min_class_percent * count
 
+            # If min class count less than 30% for binary or (60 / classes_count)% for multiclass
             if min_class_count < min_class_threshold:
                 self.imbalanced = True
                 self.data = balance_undersample(

{upgini-1.2.13a4 → upgini-1.2.14a1}/src/upgini/utils/target_utils.py

@@ -150,30 +150,34 @@ 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(min_sample_threshold - 2 * min_class_count, 0)),
+        )
         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])]
+    # 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-1.2.13a4/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.13a4"