datachain 0.7.6__py3-none-any.whl → 0.7.7__py3-none-any.whl

datachain/func/__init__.py

@@ -1,4 +1,4 @@
-from sqlalchemy import literal
+from sqlalchemy import case, literal
 
 from . import array, path, random, string
 from .aggregate import (
@@ -24,6 +24,7 @@ __all__ = [
     "any_value",
     "array",
     "avg",
+    "case",
     "collect",
     "concat",
     "cosine_distance",

datachain/func/func.py

@@ -2,9 +2,11 @@ import inspect
 from collections.abc import Sequence
 from typing import TYPE_CHECKING, Any, Callable, Optional, Union
 
-from sqlalchemy import BindParameter, ColumnElement, desc
+from sqlalchemy import BindParameter, Case, ColumnElement, desc
+from sqlalchemy.ext.hybrid import Comparator
 
 from datachain.lib.convert.python_to_sql import python_to_sql
+from datachain.lib.convert.sql_to_python import sql_to_python
 from datachain.lib.utils import DataChainColumnError, DataChainParamsError
 from datachain.query.schema import Column, ColumnMeta
 
@@ -71,7 +73,7 @@ class Func(Function):
         return (
             [
                 col
-                if isinstance(col, (Func, BindParameter))
+                if isinstance(col, (Func, BindParameter, Case, Comparator))
                 else ColumnMeta.to_db_name(
                     col.name if isinstance(col, ColumnElement) else col
                 )
@@ -273,6 +275,9 @@ def get_db_col_type(signals_schema: "SignalSchema", col: ColT) -> "DataType":
     if isinstance(col, Func):
         return col.get_result_type(signals_schema)
 
+    if isinstance(col, ColumnElement) and not hasattr(col, "name"):
+        return sql_to_python(col)
+
     return signals_schema.get_column_type(
         col.name if isinstance(col, ColumnElement) else col
     )

datachain/lib/dc.py

@@ -1150,7 +1150,7 @@ class DataChain:
     def group_by(
         self,
         *,
-        partition_by: Union[str, Func, Sequence[Union[str, Func]]],
+        partition_by: Optional[Union[str, Func, Sequence[Union[str, Func]]]] = None,
         **kwargs: Func,
     ) -> "Self":
         """Group rows by specified set of signals and return new signals
@@ -1167,10 +1167,10 @@ class DataChain:
             )
             ```
         """
-        if isinstance(partition_by, (str, Func)):
+        if partition_by is None:
+            partition_by = []
+        elif isinstance(partition_by, (str, Func)):
             partition_by = [partition_by]
-        if not partition_by:
-            raise ValueError("At least one column should be provided for partition_by")
 
         partition_by_columns: list[Column] = []
         signal_columns: list[Column] = []

datachain/query/dataset.py

@@ -966,8 +966,6 @@ class SQLGroupBy(SQLClause):
     def apply_sql_clause(self, query) -> Select:
         if not self.cols:
             raise ValueError("No columns to select")
-        if not self.group_by:
-            raise ValueError("No columns to group by")
 
         subquery = query.subquery()
 

{datachain-0.7.6.dist-info → datachain-0.7.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.7.6
+Version: 0.7.7
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.7.6.dist-info → datachain-0.7.7.dist-info}/RECORD

@@ -37,12 +37,12 @@ datachain/data_storage/schema.py,sha256=-QVlRvD0dfu-ZFUxylEoSnLJLnleMEjVlcAb2OGu
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
 datachain/data_storage/sqlite.py,sha256=D_ZQ0PHmZzHO2dinv4naVJocUDIZUwV4WAz692C1cyk,22521
 datachain/data_storage/warehouse.py,sha256=tjIkU-5JywBR0apCyqTcwSyaRtGxhu2L7IVjrz-55uc,30802
-datachain/func/__init__.py,sha256=4VUt5BaLdBAl_BnAku0Jb8plqd7kDOiYrQTMG3pN0c4,794
+datachain/func/__init__.py,sha256=VAN7N2-eCHgidMCFI-fJTkCwdI1U_NIuCOgYc4sfYUQ,812
 datachain/func/aggregate.py,sha256=7_IPrIwb2XSs3zG4iOr1eTvzn6kNVe2mkzvNzjusDHk,10942
 datachain/func/array.py,sha256=zHDNWuWLA7HVa9FEvQeHhVi00_xqenyleTqcLwkXWBI,5477
 datachain/func/base.py,sha256=wA0sBQAVyN9LPxoo7Ox83peS0zUVnyuKxukwAcjGLfY,534
 datachain/func/conditional.py,sha256=mQroxsoExpBW84Zm5dAYP4OpBblWmzfnF2qJq9rba54,2223
-datachain/func/func.py,sha256=9wqdxxisoDL0w8qKGQmL6sNdgJeIOzotEUPlxu9t2IQ,12326
+datachain/func/func.py,sha256=GykhTvNbACFSwaSXsgVlDnqR48kpP_GNAxm3bcq1RYg,12560
 datachain/func/path.py,sha256=mqN_mfkwv44z2II7DMTp_fGGw95hmTCNls_TOFNpr4k,3155
 datachain/func/random.py,sha256=pENOLj9rSmWfGCnOsUIaCsVC5486zQb66qfQvXaz9Z4,452
 datachain/func/string.py,sha256=NQzaXXYu7yb72HPADy4WrFlcgvTS77L9x7-qvCKJtnk,4522
@@ -52,7 +52,7 @@ datachain/lib/arrow.py,sha256=b5efxAUaNNYVwtXVJqj07D3zf5KC-BPlLCxKEZbEG6w,9429
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=zS4lmXHVBXc9ntcyea2a1CRLXGSAN_0glXcF88CohgY,2685
 datachain/lib/dataset_info.py,sha256=IjdF1E0TQNOq9YyynfWiCFTeZpbyGfyJvxgJY4YN810,2493
-datachain/lib/dc.py,sha256=J7liATKQBJCkeHanVLr0s3d1t5wxiiiSJuSbuxKBbLg,89527
+datachain/lib/dc.py,sha256=t5y5tsYyU7uuk3gEPPhhcDSZ1tL1aHkKG2W54eHiUq8,89492
 datachain/lib/file.py,sha256=-XMkL6ED1sE7TMhWoMRTEuOXswZJw8X6AEmJDONFP74,15019
 datachain/lib/hf.py,sha256=a-zFpDmZIR4r8dlNNTjfpAKSnuJ9xyRXlgcdENiXt3E,5864
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
@@ -87,7 +87,7 @@ datachain/model/ultralytics/pose.py,sha256=71KBTcoST2wcEtsyGXqLVpvUtqbp9gwZGA15p
 datachain/model/ultralytics/segment.py,sha256=Z1ab0tZRJubSYNH4KkFlzhYeGNTfAyC71KmkQcToHDQ,2760
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=5fEhORFe7li12SdYddaSK3LyqksMfCHhwN1_A6TfsA4,3485
-datachain/query/dataset.py,sha256=o9Ssa47t1IM78qcaoCeTL-rp4fZCpYfR7XFjw2hGWeY,54632
+datachain/query/dataset.py,sha256=J6SbCLnFlZgCxRchc3tVk5tcC7xo1Hp616JGlEZXCDo,54547
 datachain/query/dispatch.py,sha256=fZ0TgGFRcsrYh1iXQoZVjkUl4Xetom9PSHoeDes3IRs,11606
 datachain/query/metrics.py,sha256=r5b0ygYhokbXp8Mg3kCH8iFSRw0jxzyeBe-C-J_bKFc,938
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
@@ -116,9 +116,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=ZgDcrNiKiPXZmKD591_1z9qRIXitu5zwAsoVPB7ykiU,2508
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.7.6.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.7.6.dist-info/METADATA,sha256=KMChqSG7d_lMaF9BYNIgmijvnxZbDm5gCEg980gUGOA,18006
-datachain-0.7.6.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-datachain-0.7.6.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.7.6.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.7.6.dist-info/RECORD,,
+datachain-0.7.7.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.7.7.dist-info/METADATA,sha256=laxYaz9f-PIJ30f3krSjRu45CjyfbnBM8Q4kddXa9dM,18006
+datachain-0.7.7.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+datachain-0.7.7.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.7.7.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.7.7.dist-info/RECORD,,