upgini 1.1.290__py3-none-any.whl → 1.1.290a3232.post1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.290"
+__version__ = "1.1.290a3232-1"

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, DatePercentile
 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, Floor, Freq, Log, Residual, Scale, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -50,6 +50,7 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
         DatePercentile(),
+        Scale(),
     ]
 }
 

upgini/autofe/unary.py

@@ -1,5 +1,6 @@
 import numpy as np
 import pandas as pd
+from sklearn.preprocessing import robust_scale
 
 from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
@@ -111,3 +112,15 @@ 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 Scale(PandasOperand, VectorizableMixin):
+    name = "scale"
+    is_unary = True
+    output_type = "float"
+
+    def calculate_unary(self, data: pd.Series) -> pd.Series:
+        return pd.Series(robust_scale(data), index=data.index, name=data.name)
+
+    def calculate_group(self, data: pd.DataFrame, **kwargs) -> pd.DataFrame:
+        return pd.DataFrame(robust_scale(data), index=data.index, columns=data.columns)

upgini/utils/datetime_utils.py

@@ -82,19 +82,19 @@ class DateTimeSearchKeyConverter:
         elif isinstance(df[self.date_column].values[0], datetime.date):
             df[self.date_column] = pd.to_datetime(df[self.date_column], errors="coerce")
         elif is_period_dtype(df[self.date_column]):
-            df[self.date_column] = df[self.date_column].dt.to_timestamp()
+            df[self.date_column] = pd.to_datetime(df[self.date_column].astype("string"))
         elif is_numeric_dtype(df[self.date_column]):
             # 315532801 - 2524608001    - seconds
             # 315532801000 - 2524608001000 - milliseconds
             # 315532801000000 - 2524608001000000 - microseconds
             # 315532801000000000 - 2524608001000000000 - nanoseconds
-            if df[self.date_column].apply(lambda x: 10 ** 16 < x).all():
+            if df[self.date_column].apply(lambda x: 10**16 < x).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="ns")
-            elif df[self.date_column].apply(lambda x: 10 ** 14 < x < 10 ** 16).all():
+            elif df[self.date_column].apply(lambda x: 10**14 < x < 10**16).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="us")
-            elif df[self.date_column].apply(lambda x: 10 ** 11 < x < 10 ** 14).all():
+            elif df[self.date_column].apply(lambda x: 10**11 < x < 10**14).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="ms")
-            elif df[self.date_column].apply(lambda x: 0 < x < 10 ** 11).all():
+            elif df[self.date_column].apply(lambda x: 0 < x < 10 * 11).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="s")
             else:
                 msg = self.bundle.get("unsupported_date_type").format(self.date_column)
@@ -185,10 +185,7 @@ def is_time_series(df: pd.DataFrame, date_col: str) -> bool:
 def is_blocked_time_series(df: pd.DataFrame, date_col: str, search_keys: List[str]) -> bool:
     df = df.copy()
     seconds = "datetime_seconds"
-    if is_period_dtype(df[date_col]):
-        df[date_col] = df[date_col].dt.to_timestamp()
-    else:
-        df[date_col] = pd.to_datetime(df[date_col])
+    df[date_col] = pd.to_datetime(df[date_col])
     df[date_col] = df[date_col].dt.tz_localize(None)
     df[seconds] = (df[date_col] - df[date_col].dt.floor("D")).dt.seconds
 
@@ -251,9 +248,7 @@ def validate_dates_distribution(
             if col in search_keys:
                 continue
             try:
-                if is_period_dtype(X[col]):
-                    pass
-                elif pd.__version__ >= "2.0.0":
+                if pd.__version__ >= "2.0.0":
                     # Format mixed to avoid massive warnings
                     pd.to_datetime(X[col], format="mixed")
                 else:
@@ -266,9 +261,7 @@ def validate_dates_distribution(
     if maybe_date_col is None:
         return
 
-    if is_period_dtype(X[maybe_date_col]):
-        dates = X[maybe_date_col].dt.to_timestamp().dt.date
-    elif pd.__version__ >= "2.0.0":
+    if pd.__version__ >= "2.0.0":
         dates = pd.to_datetime(X[maybe_date_col], format="mixed").dt.date
     else:
         dates = pd.to_datetime(X[maybe_date_col]).dt.date

{upgini-1.1.290.dist-info → upgini-1.1.290a3232.post1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.290
+Version: 1.1.290a3232.post1
 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-1.1.290.dist-info → upgini-1.1.290a3232.post1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=14vdpqxzfW78z-avOfaHW_WatncVnDB1LrWtzjXSghM,24
+upgini/__about__.py,sha256=SDsUMCDGdgycHBSyFToeEcF3TmvsEtCl-63CS7TpVBc,31
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
@@ -13,13 +13,13 @@ upgini/version_validator.py,sha256=ddSKUK_-eGJB3NgrqOMoWJU-OxQ253WsNLp8aqJkaIM,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=7UyvmmqGSqQu4kDgoFwQRKY__b9xKDk3Fpp2-H8A7AA,2399
+upgini/autofe/all_operands.py,sha256=RHz7uLrcrcXeli8R4DhGZ2NhwGhNyWJhmSpFT_F3l5A,2423
 upgini/autofe/binary.py,sha256=441BRuqMsxlxuw4c8rMZB6h5EpRdVMk-bVa03U7T5Hg,3973
 upgini/autofe/date.py,sha256=qzk0NT332Q0vR1eRwTuNiMSrGE3ulh6Ic3QLBZqSdvw,7284
 upgini/autofe/feature.py,sha256=_V9B74B3ue7eAYXSOt9JKhVC9klkAKks22MwnBRye_w,12487
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
 upgini/autofe/operand.py,sha256=JjEVT1U3kY9NDjUPMdoki7Oa8hMDG0-_h_NklVjIFyc,2882
-upgini/autofe/unary.py,sha256=v-l3aiE5hj6kurvh6adCQL8W3X9u9a7RVbS_WPR2qlw,3146
+upgini/autofe/unary.py,sha256=1EgesKM8M1Lm2Z5VrlgXj3aI0Z88hZnJDbuPaYJyyj4,3614
 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=B4fJ1owDCF5ZZ0Ca9ywi_CXVt4iPvABh5BGTnXdXmHk,16635
@@ -41,7 +41,7 @@ upgini/utils/blocked_time_series.py,sha256=Uqr3vp4YqNclj2-PzEYqVy763GSXHn86sbpIl
 upgini/utils/country_utils.py,sha256=yE8oRgMpXuJxPfQm4fioY6dg6700HgVnHSk4Cv9sUyM,6511
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
-upgini/utils/datetime_utils.py,sha256=Ujmu1ouwSFtG5SywQXJlmtDnGigAnIWPdE5Vx5NvgUM,10951
+upgini/utils/datetime_utils.py,sha256=-LsDTThsGKsTZ57V1uNiHtLcoTtqktk5tui4WnqggJo,10673
 upgini/utils/deduplicate_utils.py,sha256=6AbARehUCghJZ4PppFtrej2s3gFRruh41MEm6mzakHs,8607
 upgini/utils/display_utils.py,sha256=A2ouB5eiZ-Kyt9ykYxkLQwyoRPrdYeJymwNTiajtFXs,10990
 upgini/utils/email_utils.py,sha256=PLufTO97Pg9PPsNqB9agcM6M98MIxKUgIgNn2mVwSQ0,3520
@@ -56,7 +56,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,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-1.1.290.dist-info/METADATA,sha256=hCW_dnkYOifgc0LJpt9mktkSzt5Y038uJLk8k_cdIQM,48117
-upgini-1.1.290.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.290.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.290.dist-info/RECORD,,
+upgini-1.1.290a3232.post1.dist-info/METADATA,sha256=xp8PeULHddcPJBU_-5296G5KMf3gU03lRwqlYErPD2Q,48128
+upgini-1.1.290a3232.post1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.290a3232.post1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.290a3232.post1.dist-info/RECORD,,