upgini 1.1.280a3418.post4__py3-none-any.whl → 1.1.280a3418.post5__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.280a3418-4"
+__version__ = "1.1.280a3418-5"

upgini/autofe/all_operands.py

@@ -1,10 +1,10 @@
 from typing import Dict
 
 from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
-from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded
+from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded, DatePercentile
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
-from upgini.autofe.unary import Abs, Bin, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
+from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -49,7 +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(),
+        DatePercentile(),
     ]
 }
 

upgini/autofe/date.py

@@ -1,4 +1,4 @@
-from typing import Any, Optional, Union
+from typing import Any, List, Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -116,3 +116,34 @@ class DateListDiffBounded(DateListDiff):
     def _agg(self, x):
         x = x[(x >= (self.lower_bound or -np.inf)) & (x < (self.upper_bound or np.inf))]
         return super()._agg(x)
+
+
+class DatePercentile(PandasOperand):
+    name = "date_per"
+    is_binary = True
+    output_type = "float"
+
+    zero_month: Optional[int]
+    zero_year: Optional[int]
+    zero_bounds: Optional[List[float]]
+    step: int = 30
+
+    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        # Assuming that left is a date column, right is a feature column
+        left = pd.to_datetime(left)
+        months = left.dt.month
+        years = left.dt.year
+
+        month_diffs = 12 * (years - (self.zero_year or 0)) + (months - (self.zero_month or 0))
+        bounds = month_diffs.apply(
+            lambda d: np.array(self.zero_bounds if self.zero_bounds is not None else []) + d * 30
+        )
+
+        return right.index.to_series().apply(lambda i: self.__perc(right[i], bounds[i]))
+
+    def __perc(self, f, bounds):
+        hit = np.where(f >= bounds)[0]
+        if hit.size > 0:
+            return np.max(hit) * 10
+        else:
+            return None

upgini/autofe/unary.py

@@ -1,4 +1,3 @@
-from typing import Optional
 import numpy as np
 import pandas as pd
 
@@ -112,25 +111,3 @@ 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: Optional[int]
-    zero_bound_high: Optional[int]
-    step: Optional[int]
-
-    def calculate_unary(self, data: pd.Series) -> pd.Series:
-        high = self.zero_bound_high if self.zero_bound_high is not None else np.inf
-        low = self.zero_bound_low if self.zero_bound_low is not None else -np.inf
-        step = self.step or 1
-
-        res = pd.Series(np.zeros(data.shape), index=data.index, dtype="int")
-        res.update((data[data < low] - low) // step)
-        res.update((data[data >= high] - high) // step + 1)
-
-        return res

{upgini-1.1.280a3418.post4.dist-info → upgini-1.1.280a3418.post5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.280a3418.post4
+Version: 1.1.280a3418.post5
 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.post4.dist-info → upgini-1.1.280a3418.post5.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=n5cs6bnvVUYK6UlCIv1U64HeOfBdjIlM6EqJRD8ZnDM,31
+upgini/__about__.py,sha256=Q1FR3KMCOuNua410sfebGueolQy2Aez075gUP4etVtM,31
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=uiFY-P8te7-zigib1hGWRtW5v0X7chxPM0hJFdixAN8,45623
@@ -13,13 +13,13 @@ upgini/version_validator.py,sha256=RGg87VweujTNlibgsOuqPLIEiBgIOkuXNVTGuNCD234,1
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
 upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/autofe/all_operands.py,sha256=VB8-iuNanjtjo3ho2shDDfWQtXGYekeoPEBzpNy1iWo,2377
+upgini/autofe/all_operands.py,sha256=7UyvmmqGSqQu4kDgoFwQRKY__b9xKDk3Fpp2-H8A7AA,2399
 upgini/autofe/binary.py,sha256=441BRuqMsxlxuw4c8rMZB6h5EpRdVMk-bVa03U7T5Hg,3973
-upgini/autofe/date.py,sha256=Vy1I92fLLYLhuYKJmtuPBMI8cPxE4Uwk40hqE2F2e1A,4224
+upgini/autofe/date.py,sha256=n_Ao51RokgZX4uIff37REa96A_4Oh2BZE2QgTyXKCzw,5208
 upgini/autofe/feature.py,sha256=8ugRW-Ckc-SYNQawgEluoAzJ_oM5v6y9r5Qx_E-C14o,11977
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
 upgini/autofe/operand.py,sha256=xgEIZuFCfckc6LpBqVu1OVK3JEabm1O-LHUsp83EHKA,2806
-upgini/autofe/unary.py,sha256=xV6UC0qktBtf8QbvlOPmChOn3XVi8Q4N2Td_hHuzk5g,3854
+upgini/autofe/unary.py,sha256=v-l3aiE5hj6kurvh6adCQL8W3X9u9a7RVbS_WPR2qlw,3146
 upgini/autofe/vector.py,sha256=dLxfAstJs-gw_OQ1xxoxcM6pVzORlV0HVzdzt7cLXVQ,606
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/data_source/data_source_publisher.py,sha256=taRzyGgrPrTTSGw4Y-Ca5k4bf30aiTa68rxqT9zfqeI,16478
@@ -56,7 +56,7 @@ upgini/utils/sklearn_ext.py,sha256=c23MGSUVfxLnaDWKAxavHgnOtm5dGKkF3YswdWQcFzs,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.280a3418.post4.dist-info/METADATA,sha256=y_juIdRfzSALswWmJAu5ZppO61xK_H2zkzvLWvvrvx8,48129
-upgini-1.1.280a3418.post4.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.280a3418.post4.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.280a3418.post4.dist-info/RECORD,,
+upgini-1.1.280a3418.post5.dist-info/METADATA,sha256=rFBfntuYeUXsUisftZbvZhS-i6MPHagu8WfynRsqjbg,48129
+upgini-1.1.280a3418.post5.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.280a3418.post5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.280a3418.post5.dist-info/RECORD,,