datachain 0.7.6__tar.gz → 0.7.7__tar.gz

{datachain-0.7.6/src/datachain.egg-info → datachain-0.7.7}/PKG-INFO

@@ -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 → datachain-0.7.7}/src/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-0.7.6 → datachain-0.7.7}/src/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-0.7.6 → datachain-0.7.7}/src/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-0.7.6 → datachain-0.7.7}/src/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 → datachain-0.7.7/src/datachain.egg-info}/PKG-INFO

@@ -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 → datachain-0.7.7}/tests/unit/lib/test_datachain.py

@@ -2731,6 +2731,49 @@ def test_group_by_multiple_partition_by(test_session):
     )
 
 
+def test_group_by_no_partition_by(test_session):
+    from datachain import func
+
+    ds = (
+        DataChain.from_values(
+            col1=["a", "a", "b", "b", "b", "c"],
+            col2=[1, 2, 1, 2, 1, 2],
+            col3=[1.0, 2.0, 3.0, 4.0, 5.0, 6.0],
+            col4=["1", "2", "3", "4", "5", "6"],
+            session=test_session,
+        )
+        .order_by("col4")
+        .group_by(
+            cnt=func.count(),
+            cnt_col=func.count("col2"),
+            sum=func.sum("col3"),
+            concat=func.concat("col4"),
+            value=func.any_value("col3"),
+            collect=func.collect("col3"),
+        )
+        .save("my-ds")
+    )
+
+    assert ds.signals_schema.serialize() == {
+        "cnt": "int",
+        "cnt_col": "int",
+        "sum": "float",
+        "concat": "str",
+        "value": "float",
+        "collect": "list[float]",
+    }
+    assert ds.to_records() == [
+        {
+            "cnt": 6,
+            "cnt_col": 6,
+            "sum": 21.0,
+            "concat": "123456",
+            "value": 1.0,
+            "collect": [1.0, 2.0, 3.0, 4.0, 5.0, 6.0],
+        },
+    ]
+
+
 def test_group_by_error(test_session):
     from datachain import func
 
@@ -2740,14 +2783,6 @@ def test_group_by_error(test_session):
         session=test_session,
     )
 
-    with pytest.raises(TypeError):
-        dc.group_by(cnt=func.count())
-
-    with pytest.raises(
-        ValueError, match="At least one column should be provided for partition_by"
-    ):
-        dc.group_by(cnt=func.count(), partition_by=())
-
     with pytest.raises(
         ValueError, match="At least one column should be provided for group_by"
     ):
@@ -2770,6 +2805,34 @@ def test_group_by_error(test_session):
         dc.group_by(foo=func.sum("col2"), partition_by="col3")
 
 
+def test_group_by_case(test_session):
+    from datachain import func
+
+    ds = (
+        DataChain.from_values(
+            col1=[1.0, 0.0, 3.2, 0.1, 5.9, -1.0],
+            col2=[0.0, 6.1, -0.05, 3.7, 0.1, -3.0],
+            session=test_session,
+        )
+        .group_by(
+            col1=func.sum(func.case((C("col1") > 0.1, 1), else_=0)),
+            col2=func.sum(func.case((C("col2") < 0.0, 1), else_=0)),
+        )
+        .save("my-ds")
+    )
+
+    assert ds.signals_schema.serialize() == {
+        "col1": "int",
+        "col2": "int",
+    }
+    assert ds.to_records() == [
+        {
+            "col1": 3,
+            "col2": 2,
+        }
+    ]
+
+
 @pytest.mark.parametrize("desc", [True, False])
 def test_window_functions(test_session, desc):
     from datachain import func