upgini 1.2.73a3659.dev2__tar.gz → 1.2.74a3818.dev1__tar.gz

{upgini-1.2.73a3659.dev2 → upgini-1.2.74a3818.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.73a3659.dev2
+Version: 1.2.74a3818.dev1
 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-1.2.74a3818.dev1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.74a3818.dev1"

{upgini-1.2.73a3659.dev2 → upgini-1.2.74a3818.dev1}/src/upgini/autofe/binary.py

@@ -146,8 +146,8 @@ class Distance(PandasOperator):
 
     # row-wise dot product, handling None values
     def __dot(self, left: pd.Series, right: pd.Series) -> pd.Series:
-        left = left.apply(lambda x: np.array(x))
-        right = right.apply(lambda x: np.array(x))
+        left = left.apply(lambda x: np.array(x).astype(np.float64))
+        right = right.apply(lambda x: np.array(x).astype(np.float64))
         res = (left.dropna() * right.dropna()).apply(np.sum)
         res = res.reindex(left.index.union(right.index))
         return res

upgini-1.2.74a3818.dev1/src/upgini/autofe/vector.py

@@ -0,0 +1,24 @@
+from typing import List, Optional
+
+import pandas as pd
+
+from upgini.autofe.operator import PandasOperator, VectorizableMixin
+
+
+class Mean(PandasOperator, VectorizableMixin):
+    name: str = "mean"
+    output_type: Optional[str] = "float"
+    is_vector: bool = True
+    group_index: int = 0
+
+    def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
+        return pd.DataFrame(data).T.fillna(0).mean(axis=1)
+
+
+class Sum(PandasOperator, VectorizableMixin):
+    name: str = "sum"
+    is_vector: bool = True
+    group_index: int = 0
+
+    def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
+        return pd.DataFrame(data).T.fillna(0).sum(axis=1)

{upgini-1.2.73a3659.dev2 → upgini-1.2.74a3818.dev1}/src/upgini/metrics.py

@@ -481,7 +481,7 @@ class EstimatorWrapper:
             "logger": logger,
         }
         if estimator is None:
-            params = {}
+            params = {"random_state": DEFAULT_RANDOM_STATE}
             if target_type == ModelTaskType.MULTICLASS:
                 params = _get_add_params(params, LIGHTGBM_MULTICLASS_PARAMS)
                 params = _get_add_params(params, add_params)

upgini-1.2.73a3659.dev2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.73a3659.dev2"

upgini-1.2.73a3659.dev2/src/upgini/autofe/vector.py

@@ -1,46 +0,0 @@
-from typing import Dict, List, Optional
-
-import pandas as pd
-
-from upgini.autofe.operator import OperatorRegistry, PandasOperator, VectorizableMixin
-
-
-class Mean(PandasOperator, VectorizableMixin):
-    name: str = "mean"
-    output_type: Optional[str] = "float"
-    is_vector: bool = True
-    group_index: int = 0
-
-    def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
-        return pd.DataFrame(data).T.fillna(0).mean(axis=1)
-
-
-class Sum(PandasOperator, VectorizableMixin):
-    name: str = "sum"
-    is_vector: bool = True
-    group_index: int = 0
-
-    def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
-        return pd.DataFrame(data).T.fillna(0).sum(axis=1)
-
-
-class OnnxModel(PandasOperator, metaclass=OperatorRegistry):
-    name: str = "onnx"
-    is_vector: bool = True
-    output_type: Optional[str] = "float"
-    model_name: str = ""
-
-    def get_params(self) -> Dict[str, Optional[str]]:
-        res = super().get_params()
-        res.update(
-            {
-                "model_name": self.model_name,
-            }
-        )
-        return res
-
-    # def load_model(self):
-    #     ...
-
-    # def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
-    #     ...