upgini 1.1.262a3250.post5__tar.gz → 1.1.263__tar.gz

{upgini-1.1.262a3250.post5/src/upgini.egg-info → upgini-1.1.263}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.262a3250.post5
+Version: 1.1.263
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.262a3250.post5 → upgini-1.1.263}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.262a3250.post5"
+version = "1.1.263"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.262a3250.post5 → upgini-1.1.263}/src/upgini/autofe/all_operands.py

@@ -1,5 +1,5 @@
 from typing import Dict
-from upgini.autofe.date import DateDiff, DateDiffFuture
+from upgini.autofe.date import DateDiff, DateDiffType2
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
 from upgini.autofe.unary import Abs, Log, Residual, Sqrt, Square, Sigmoid, Floor, Freq
@@ -37,7 +37,7 @@ ALL_OPERANDS: Dict[str, Operand] = {
         Operand(name="GroupByThenFreq", output_type="float", is_grouping=True),
         Sim(),
         DateDiff(),
-        DateDiffFuture(),
+        DateDiffType2(),
     ]
 }
 

{upgini-1.1.262a3250.post5 → upgini-1.1.263}/src/upgini/autofe/date.py

@@ -34,8 +34,8 @@ class DateDiff(PandasOperand, DateDiffMixin):
         return x
 
 
-class DateDiffFuture(PandasOperand, DateDiffMixin):
-    name = "date_diff_future"
+class DateDiffType2(PandasOperand, DateDiffMixin):
+    name = "date_diff_type2"
     is_binary = True
     has_symmetry_importance = True
     is_vectorizable = False

{upgini-1.1.262a3250.post5 → upgini-1.1.263}/src/upgini/dataset.py

@@ -60,7 +60,7 @@ class Dataset:  # (pd.DataFrame):
     FIT_SAMPLE_WITH_EVAL_SET_ROWS = 200_000
     FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD = 200_000
     MIN_SAMPLE_THRESHOLD = 5_000
-    IMBALANCE_THESHOLD = 0.4
+    IMBALANCE_THESHOLD = 0.6
     BINARY_BOOTSTRAP_LOOPS = 5
     MULTICLASS_BOOTSTRAP_LOOPS = 2
     MIN_TARGET_CLASS_ROWS = 100

{upgini-1.1.262a3250.post5 → upgini-1.1.263/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.262a3250.post5
+Version: 1.1.263
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.262a3250.post5 → upgini-1.1.263}/tests/test_autofe_operands.py

@@ -1,5 +1,5 @@
 import pandas as pd
-from upgini.autofe.date import DateDiff, DateDiffFuture
+from upgini.autofe.date import DateDiff, DateDiffType2
 
 from datetime import datetime
 from pandas.testing import assert_series_equal
@@ -22,18 +22,6 @@ def test_date_diff_future():
         columns=["date1", "date2"],
     )
 
-    operand = DateDiffFuture()
+    operand = DateDiffType2()
     expected_result = pd.Series([61.0, 182.0])
     assert_series_equal(operand.calculate_binary(df.date2, df.date1), expected_result)
-
-
-def test_real():
-    from upgini.autofe.feature import Feature
-
-    df = pd.read_parquet("../ml-backend.worktrees/BACK-3250/test")
-    feature = Feature.from_formula(
-        "date_diff_future(date_0e8763,sber_spasibo_msisdn_ads_v2_1914333223_marketing_phone_birth_date)"
-    )
-    feature.op = feature.op.copy(update={"left_unit": "ms"})
-    res = feature.calculate(df)
-    pass