upgini 1.1.279a2.dev2__tar.gz → 1.1.280a3418.post2__tar.gz

{upgini-1.1.279a2.dev2 → upgini-1.1.280a3418.post2}/.gitignore

@@ -151,4 +151,6 @@ catboost_info/
 build/
 playgroung.ipynb
 fingerprint.js
-envVars.txt
+envVars.txt
+.ruff_cache
+.jupyter

{upgini-1.1.279a2.dev2 → upgini-1.1.280a3418.post2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.279a2.dev2
+Version: 1.1.280a3418.post2
 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-1.1.280a3418.post2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.280a3418-2"

{upgini-1.1.279a2.dev2 → upgini-1.1.280a3418.post2}/src/upgini/autofe/all_operands.py

@@ -4,7 +4,7 @@ from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
 from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
-from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
+from upgini.autofe.unary import Abs, Bin, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -49,6 +49,7 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=30, upper_bound=45),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
+        Bin(),
     ]
 }
 

{upgini-1.1.279a2.dev2 → upgini-1.1.280a3418.post2}/src/upgini/autofe/unary.py

@@ -111,3 +111,21 @@ class Freq(PandasOperand):
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         value_counts = data.value_counts(normalize=True)
         return self._loc(data, value_counts)
+
+
+class Bin(PandasOperand):
+    name = "bin"
+    is_unary = True
+    output_type = "int"
+    input_type = "discrete"
+
+    zero_bound_low: int
+    zero_bound_high: int
+    step: int
+
+    def calculate_unary(self, data: pd.Series) -> pd.Series:
+        res = pd.Series(np.zeros(data.shape), index=data.index, dtype="int")
+        res.update((data[data < self.zero_bound_low] - self.zero_bound_low) // self.step)
+        res.update((data[data >= self.zero_bound_high] - self.zero_bound_high) // self.step + 1)
+
+        return res

upgini-1.1.279a2.dev2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.279a2.dev2"