datachain 0.6.5__py3-none-any.whl → 0.6.6__py3-none-any.whl

datachain/lib/dc.py

@@ -981,10 +981,23 @@ class DataChain:
 
     @resolve_columns
     def order_by(self, *args, descending: bool = False) -> "Self":
-        """Orders by specified set of signals.
+        """Orders by specified set of columns.
 
         Parameters:
             descending (bool): Whether to sort in descending order or not.
+
+        Example:
+            ```py
+            dc.order_by("similarity_score", descending=True).limit(10)
+            ```
+
+        Note:
+            Order is not guaranteed when steps are added after an `order_by` statement.
+            I.e. when using `from_dataset` an `order_by` statement should be used if
+            the order of the records in the chain is important.
+            Using `order_by` directly before `limit`, `collect` and `collect_flatten`
+            will give expected results.
+            See https://github.com/iterative/datachain/issues/477 for further details.
         """
         if descending:
             args = tuple(sqlalchemy.desc(a) for a in args)
@@ -1179,7 +1192,7 @@ class DataChain:
                           a tuple of row values.
         """
         db_signals = self._effective_signals_schema.db_signals()
-        with self._query.select(*db_signals).as_iterable() as rows:
+        with self._query.ordered_select(*db_signals).as_iterable() as rows:
             if row_factory:
                 rows = (row_factory(db_signals, r) for r in rows)
             yield from rows
@@ -1270,7 +1283,7 @@ class DataChain:
         chain = self.select(*cols) if cols else self
         signals_schema = chain._effective_signals_schema
         db_signals = signals_schema.db_signals()
-        with self._query.select(*db_signals).as_iterable() as rows:
+        with self._query.ordered_select(*db_signals).as_iterable() as rows:
             for row in rows:
                 ret = signals_schema.row_to_features(
                     row, catalog=chain.session.catalog, cache=chain._settings.cache
@@ -1678,7 +1691,7 @@ class DataChain:
 
         model_name = model_name or object_name or ""
         hf_features = next(iter(ds_dict.values())).features
-        output = output | get_output_schema(hf_features, model_name)
+        output = output | get_output_schema(hf_features)
         model = dict_to_data_model(model_name, output)
         if object_name:
             output = {object_name: model}

datachain/lib/hf.py

@@ -138,17 +138,15 @@ def convert_feature(val: Any, feat: Any, anno: Any) -> Any:  # noqa: PLR0911
         return HFAudio(**val)
 
 
-def get_output_schema(
-    features: Features, model_name: str = "", stream: bool = True
-) -> dict[str, DataType]:
+def get_output_schema(features: Features) -> dict[str, DataType]:
     """Generate UDF output schema from huggingface datasets features."""
     fields_dict = {}
     for name, val in features.items():
-        fields_dict[name] = _feature_to_chain_type(name, val)  # type: ignore[assignment]
-    return fields_dict  # type: ignore[return-value]
+        fields_dict[name] = _feature_to_chain_type(name, val)
+    return fields_dict
 
 
-def _feature_to_chain_type(name: str, val: Any) -> type:  # noqa: PLR0911
+def _feature_to_chain_type(name: str, val: Any) -> DataType:  # noqa: PLR0911
     if isinstance(val, Value):
         return arrow_type_mapper(val.pa_type)
     if isinstance(val, ClassLabel):

datachain/query/dataset.py

@@ -1276,6 +1276,27 @@ class DatasetQuery:
         query.steps.append(SQLSelect((*args, *named_args)))
         return query
 
+    @detach
+    def ordered_select(self, *args, **kwargs) -> "Self":
+        """
+        Select the given columns or expressions using a subquery whilst
+        maintaining query ordering (only applicable if last step was order_by).
+
+        If used with no arguments, this simply creates a subquery and
+        select all columns from it.
+
+        Example:
+            >>> ds.ordered_select(C.name, C.size * 10)
+            >>> ds.ordered_select(C.name, size10x=C.size * 10)
+        """
+        named_args = [v.label(k) for k, v in kwargs.items()]
+        query = self.clone()
+        order_by = query.last_step if query.is_ordered else None
+        query.steps.append(SQLSelect((*args, *named_args)))
+        if order_by:
+            query.steps.append(order_by)
+        return query
+
     @detach
     def select_except(self, *args) -> "Self":
         """
@@ -1338,7 +1359,7 @@ class DatasetQuery:
         query = self.clone(new_table=False)
         if (
             query.steps
-            and (last_step := query.steps[-1])
+            and (last_step := query.last_step)
             and isinstance(last_step, SQLLimit)
         ):
             query.steps[-1] = SQLLimit(min(n, last_step.n))
@@ -1591,3 +1612,11 @@ class DatasetQuery:
         finally:
             self.cleanup()
         return self.__class__(name=name, version=version, catalog=self.catalog)
+
+    @property
+    def is_ordered(self) -> bool:
+        return isinstance(self.last_step, SQLOrderBy)
+
+    @property
+    def last_step(self) -> Optional[Step]:
+        return self.steps[-1] if self.steps else None

datachain/sql/types.py

@@ -187,6 +187,22 @@ class Int32(Int):
         return read_converter(dialect).int32(value)
 
 
+class UInt32(Int):
+    def load_dialect_impl(self, dialect):
+        return converter(dialect).uint32()
+
+    @staticmethod
+    def default_value(dialect):
+        return type_defaults(dialect).uint32()
+
+    @staticmethod
+    def db_default_value(dialect):
+        return db_defaults(dialect).uint32()
+
+    def on_read_convert(self, value, dialect):
+        return read_converter(dialect).uint32(value)
+
+
 class Int64(Int):
     def load_dialect_impl(self, dialect):
         return converter(dialect).int64()
@@ -395,6 +411,9 @@ class TypeReadConverter:
     def int32(self, value):
         return value
 
+    def uint32(self, value):
+        return value
+
     def int64(self, value):
         return value
 
@@ -446,6 +465,9 @@ class TypeConverter:
     def int32(self):
         return self.int()
 
+    def uint32(self):
+        return self.int()
+
     def int64(self):
         return self.int()
 
@@ -487,6 +509,9 @@ class TypeDefaults:
     def int32(self):
         return None
 
+    def uint32(self):
+        return None
+
     def int64(self):
         return None
 
@@ -528,6 +553,9 @@ class DBDefaults:
     def int32(self):
         return self.int()
 
+    def uint32(self):
+        return self.int()
+
     def int64(self):
         return self.int()
 
@@ -561,6 +589,7 @@ TYPES = [
     Boolean,
     Int,
     Int32,
+    UInt32,
     Int64,
     UInt64,
     Float,

{datachain-0.6.5.dist-info → datachain-0.6.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.6.5
+Version: 0.6.6
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.6.5.dist-info → datachain-0.6.6.dist-info}/RECORD

@@ -43,9 +43,9 @@ datachain/lib/arrow.py,sha256=-hu9tic79a01SY2UBqkA3U6wUr6tnE3T3q5q_BnO93A,9156
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=dau4AlZBhOFvF7pEKMeqCeRkcFFg5KFvTBWW_2CdH5g,2371
 datachain/lib/dataset_info.py,sha256=srPPhI2UHf6hFPBecyFEVw2SS5aPisIIMsvGgKqi7ss,2366
-datachain/lib/dc.py,sha256=pOyE8LqIwo86GrZTSpSMUJAYYwep7nCdIxebkSYlMGo,84484
+datachain/lib/dc.py,sha256=U1evAvSs563OMuUVildoaIOuOFiNB6fZcsN4BI8L9f0,85076
 datachain/lib/file.py,sha256=LjTW_-PDAnoUhvyB4bJ8Y8n__XGqrxvmd9mDOF0Gir8,14875
-datachain/lib/hf.py,sha256=cPnmLuprr0pYABH7KqA5FARQ1JGlywdDwD3yDzVAm4k,5920
+datachain/lib/hf.py,sha256=BW2NPpqxkpPwkSaGlppT8Rbs8zPpyYC-tR6htY08c-0,5817
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
 datachain/lib/listing.py,sha256=cVkCp7TRVpcZKSx-Bbk9t51bQI9Mw0o86W6ZPhAsuzM,3667
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
@@ -73,7 +73,7 @@ datachain/lib/func/aggregate.py,sha256=H1ziFQdaK9zvnxvttfnEzkkyGvEEmMAvmgCsBV6nf
 datachain/lib/func/func.py,sha256=HAJZ_tpiRG2R-et7pr0WnoyNZYtpbPn3_HBuL3RQpbU,4800
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=5fEhORFe7li12SdYddaSK3LyqksMfCHhwN1_A6TfsA4,3485
-datachain/query/dataset.py,sha256=5LJCEpzaJWtWuv5jBheMCQbn9o5El6MiXORLaYcSR44,52924
+datachain/query/dataset.py,sha256=MGArYxioeGvm8w7hQtQAjEI6wsZN_XAoh4-jO4d0U5Q,53926
 datachain/query/dispatch.py,sha256=wjjTWw6sFQbB9SKRh78VbfvwSMgJXCfqJklS3-9KnCU,12025
 datachain/query/metrics.py,sha256=r5b0ygYhokbXp8Mg3kCH8iFSRw0jxzyeBe-C-J_bKFc,938
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
@@ -84,7 +84,7 @@ datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 datachain/remote/studio.py,sha256=yCjK5fYN-OseMwakUc2nWU3ktUJNBWJHHSRBaHAwfPw,8768
 datachain/sql/__init__.py,sha256=A2djrbQwSMUZZEIKGnm-mnRA-NDSbiDJNpAmmwGNyIo,303
 datachain/sql/selectable.py,sha256=fBM-wS1TUA42kVEAAiwqGtibIevyZAEritwt8PZGyLQ,1589
-datachain/sql/types.py,sha256=3aXpoxkmCYbw0Dlta5J1enwS8_FuvjfSqyrNZO-dWj4,13383
+datachain/sql/types.py,sha256=RjgWb4Bh-pxzZpBCAyjbtDociU01ZPQ7l-SPueaRpNA,13991
 datachain/sql/utils.py,sha256=rzlJw08etivdrcuQPqNVvVWhuVSyUPUQEEc6DOhu258,818
 datachain/sql/default/__init__.py,sha256=XQ2cEZpzWiABqjV-6yYHUBGI9vN_UHxbxZENESmVAWw,45
 datachain/sql/default/base.py,sha256=QD-31C6JnyOXzogyDx90sUhm7QvgXIYpeHEASH84igU,628
@@ -100,9 +100,9 @@ datachain/sql/sqlite/base.py,sha256=aHSZVvh4XSVkvZ07h3jMoRlHI4sWD8y3SnmGs9xMG9Y,
 datachain/sql/sqlite/types.py,sha256=yzvp0sXSEoEYXs6zaYC_2YubarQoZH-MiUNXcpuEP4s,1573
 datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.6.5.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.6.5.dist-info/METADATA,sha256=eSh62q8OKalsO_IHYb0M2lT4y0x5z84uX1WVt7_dZlM,17188
-datachain-0.6.5.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-datachain-0.6.5.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.6.5.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.6.5.dist-info/RECORD,,
+datachain-0.6.6.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.6.6.dist-info/METADATA,sha256=Z211Vh59IGXt-dRZTSI9zYgTnvmAmTPbmsfRh_vWE8Q,17188
+datachain-0.6.6.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+datachain-0.6.6.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.6.6.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.6.6.dist-info/RECORD,,