datachain 0.2.11__py3-none-any.whl → 0.2.13__py3-none-any.whl

datachain/node.py

@@ -5,7 +5,7 @@ import attrs
 
 from datachain.cache import UniqueId
 from datachain.storage import StorageURI
-from datachain.utils import time_to_str
+from datachain.utils import TIME_ZERO, time_to_str
 
 if TYPE_CHECKING:
     from typing_extensions import Self
@@ -111,13 +111,16 @@ class Node:
         if storage is None:
             storage = self.source
         return UniqueId(
-            storage,
-            self.parent,
-            self.name,
-            self.etag,
-            self.size,
-            self.vtype,
-            self.location,
+            storage=storage,
+            parent=self.parent,
+            name=self.name,
+            size=self.size,
+            version=self.version or "",
+            etag=self.etag,
+            is_latest=self.is_latest,
+            vtype=self.vtype,
+            location=self.location,
+            last_modified=self.last_modified or TIME_ZERO,
         )
 
     @classmethod

datachain/query/dataset.py

@@ -54,6 +54,7 @@ from datachain.utils import (
     batched,
     determine_processes,
     filtered_cloudpickle_dumps,
+    get_datachain_executable,
 )
 
 from .metrics import metrics
@@ -426,7 +427,7 @@ def get_generated_callback(is_generator: bool = False) -> Callback:
 
 
 @frozen
-class UDF(Step, ABC):
+class UDFStep(Step, ABC):
     udf: UDFType
     catalog: "Catalog"
     partition_by: Optional[PartitionByType] = None
@@ -507,13 +508,12 @@ class UDF(Step, ABC):
 
                 # Run the UDFDispatcher in another process to avoid needing
                 # if __name__ == '__main__': in user scripts
-                datachain_exec_path = os.environ.get("DATACHAIN_EXEC_PATH", "datachain")
-
+                exec_cmd = get_datachain_executable()
                 envs = dict(os.environ)
                 envs.update({"PYTHONPATH": os.getcwd()})
                 process_data = filtered_cloudpickle_dumps(udf_info)
                 result = subprocess.run(  # noqa: S603
-                    [datachain_exec_path, "--internal-run-udf"],
+                    [*exec_cmd, "internal-run-udf"],
                     input=process_data,
                     check=False,
                     env=envs,
@@ -635,7 +635,7 @@ class UDF(Step, ABC):
 
 
 @frozen
-class UDFSignal(UDF):
+class UDFSignal(UDFStep):
     is_generator = False
 
     def create_udf_table(self, query: Select) -> "Table":
@@ -730,7 +730,7 @@ class UDFSignal(UDF):
 
 
 @frozen
-class RowGenerator(UDF):
+class RowGenerator(UDFStep):
     """Extend dataset with new rows."""
 
     is_generator = True
@@ -820,8 +820,16 @@ class SQLMutate(SQLClause):
     args: tuple[ColumnElement, ...]
 
     def apply_sql_clause(self, query: Select) -> Select:
-        subquery = query.subquery()
-        return sqlalchemy.select(*subquery.c, *self.args).select_from(subquery)
+        original_subquery = query.subquery()
+        # this is needed for new column to be used in clauses
+        # like ORDER BY, otherwise new column is not recognized
+        subquery = (
+            sqlalchemy.select(*original_subquery.c, *self.args)
+            .select_from(original_subquery)
+            .subquery()
+        )
+
+        return sqlalchemy.select(*subquery.c).select_from(subquery)
 
 
 @frozen
@@ -865,6 +873,18 @@ class SQLCount(SQLClause):
         return sqlalchemy.select(f.count(1)).select_from(query.subquery())
 
 
+@frozen
+class SQLDistinct(SQLClause):
+    args: tuple[ColumnElement, ...]
+    dialect: str
+
+    def apply_sql_clause(self, query):
+        if self.dialect == "sqlite":
+            return query.group_by(*self.args)
+
+        return query.distinct(*self.args)
+
+
 @frozen
 class SQLUnion(Step):
     query1: "DatasetQuery"
@@ -946,12 +966,15 @@ class SQLJoin(Step):
 
         q1_columns = list(q1.c)
         q1_column_names = {c.name for c in q1_columns}
-        q2_columns = [
-            c
-            if c.name not in q1_column_names and c.name != "sys__id"
-            else c.label(self.rname.format(name=c.name))
-            for c in q2.c
-        ]
+
+        q2_columns = []
+        for c in q2.c:
+            if c.name.startswith("sys__"):
+                continue
+
+            if c.name in q1_column_names:
+                c = c.label(self.rname.format(name=c.name))
+            q2_columns.append(c)
 
         res_columns = q1_columns + q2_columns
         predicates = (
@@ -1058,6 +1081,7 @@ class DatasetQuery:
         anon: bool = False,
         indexing_feature_schema: Optional[dict] = None,
         indexing_column_types: Optional[dict[str, Any]] = None,
+        update: Optional[bool] = False,
     ):
         if client_config is None:
             client_config = {}
@@ -1080,10 +1104,12 @@ class DatasetQuery:
         self.session = Session.get(session, catalog=catalog)
 
         if path:
-            self.starting_step = IndexingStep(path, self.catalog, {}, recursive)
+            kwargs = {"update": True} if update else {}
+            self.starting_step = IndexingStep(path, self.catalog, kwargs, recursive)
             self.feature_schema = indexing_feature_schema
             self.column_types = indexing_column_types
         elif name:
+            self.name = name
             ds = self.catalog.get_dataset(name)
             self.version = version or ds.latest_version
             self.feature_schema = ds.get_version(self.version).feature_schema
@@ -1091,9 +1117,6 @@ class DatasetQuery:
             if "sys__id" in self.column_types:
                 self.column_types.pop("sys__id")
             self.starting_step = QueryStep(self.catalog, name, self.version)
-            # attaching to specific dataset
-            self.name = name
-            self.version = version
         else:
             raise ValueError("must provide path or name")
 
@@ -1102,7 +1125,7 @@ class DatasetQuery:
         return bool(re.compile(r"^[a-zA-Z0-9]+://").match(path))
 
     def __iter__(self):
-        return iter(self.results())
+        return iter(self.db_results())
 
     def __or__(self, other):
         return self.union(other)
@@ -1223,13 +1246,16 @@ class DatasetQuery:
         warehouse.close()
         self.temp_table_names = []
 
-    def results(self, row_factory=None, **kwargs):
+    def db_results(self, row_factory=None, **kwargs):
         with self.as_iterable(**kwargs) as result:
             if row_factory:
                 cols = result.columns
                 return [row_factory(cols, r) for r in result]
             return list(result)
 
+    def to_db_records(self) -> list[dict[str, Any]]:
+        return self.db_results(lambda cols, row: dict(zip(cols, row)))
+
     @contextlib.contextmanager
     def as_iterable(self, **kwargs) -> Iterator[ResultIter]:
         try:
@@ -1289,9 +1315,6 @@ class DatasetQuery:
         finally:
             self.cleanup()
 
-    def to_records(self) -> list[dict[str, Any]]:
-        return self.results(lambda cols, row: dict(zip(cols, row)))
-
     def shuffle(self) -> "Self":
         # ToDo: implement shaffle based on seed and/or generating random column
         return self.order_by(C.sys__rand)
@@ -1407,6 +1430,14 @@ class DatasetQuery:
         query.steps.append(SQLOffset(offset))
         return query
 
+    @detach
+    def distinct(self, *args) -> "Self":
+        query = self.clone()
+        query.steps.append(
+            SQLDistinct(args, dialect=self.catalog.warehouse.db.dialect.name)
+        )
+        return query
+
     def as_scalar(self) -> Any:
         with self.as_iterable() as rows:
             row = next(iter(rows))
@@ -1705,10 +1736,13 @@ def _send_result(dataset_query: DatasetQuery) -> None:
 
     columns = preview_args.get("columns") or []
 
-    preview_query = (
-        dataset_query.select(*columns)
-        .limit(preview_args.get("limit", 10))
-        .offset(preview_args.get("offset", 0))
+    if type(dataset_query) is DatasetQuery:
+        preview_query = dataset_query.select(*columns)
+    else:
+        preview_query = dataset_query.select(*columns, _sys=False)
+
+    preview_query = preview_query.limit(preview_args.get("limit", 10)).offset(
+        preview_args.get("offset", 0)
     )
 
     dataset: Optional[tuple[str, int]] = None
@@ -1717,7 +1751,7 @@ def _send_result(dataset_query: DatasetQuery) -> None:
         assert dataset_query.version, "Dataset version should be provided"
         dataset = dataset_query.name, dataset_query.version
 
-    preview = preview_query.to_records()
+    preview = preview_query.to_db_records()
     result = ExecutionResult(preview, dataset, metrics)
     data = attrs.asdict(result)
 

datachain/query/schema.py

@@ -32,6 +32,7 @@ class Column(sa.ColumnClause, metaclass=ColumnMeta):
     inherit_cache: Optional[bool] = True
 
     def __init__(self, text, type_=None, is_literal=False, _selectable=None):
+        """Dataset column."""
         self.name = ColumnMeta.to_db_name(text)
         super().__init__(
             self.name, type_=type_, is_literal=is_literal, _selectable=_selectable
@@ -41,6 +42,7 @@ class Column(sa.ColumnClause, metaclass=ColumnMeta):
         return Column(self.name + DEFAULT_DELIMITER + name)
 
     def glob(self, glob_str):
+        """Search for matches using glob pattern matching."""
         return self.op("GLOB")(glob_str)
 
 

datachain/query/session.py

@@ -28,9 +28,9 @@ class Session:
 
     Parameters:
 
-    `name` (str): The name of the session. Only latters and numbers are supported.
+    name (str): The name of the session. Only latters and numbers are supported.
            It can be empty.
-    `catalog` (Catalog): Catalog object.
+    catalog (Catalog): Catalog object.
     """
 
     GLOBAL_SESSION_CTX: Optional["Session"] = None
@@ -80,9 +80,9 @@ class Session:
         """Creates a Session() object from a catalog.
 
         Parameters:
-            `session` (Session): Optional Session(). If not provided a new session will
+            session (Session): Optional Session(). If not provided a new session will
                     be created. It's needed mostly for simplie API purposes.
-            `catalog` (Catalog): Optional catalog. By default a new catalog is created.
+            catalog (Catalog): Optional catalog. By default a new catalog is created.
         """
         if session:
             return session

datachain/sql/functions/array.py

@@ -5,6 +5,10 @@ from datachain.sql.utils import compiler_not_implemented
 
 
 class cosine_distance(GenericFunction):  # noqa: N801
+    """
+    Takes a column and array and returns the cosine distance between them.
+    """
+
     type = Float()
     package = "array"
     name = "cosine_distance"
@@ -12,6 +16,10 @@ class cosine_distance(GenericFunction):  # noqa: N801
 
 
 class euclidean_distance(GenericFunction):  # noqa: N801
+    """
+    Takes a column and array and returns the Euclidean distance between them.
+    """
+
     type = Float()
     package = "array"
     name = "euclidean_distance"
@@ -19,6 +27,10 @@ class euclidean_distance(GenericFunction):  # noqa: N801
 
 
 class length(GenericFunction):  # noqa: N801
+    """
+    Returns the length of the array.
+    """
+
     type = Int64()
     package = "array"
     name = "length"

datachain/sql/functions/string.py

@@ -5,6 +5,10 @@ from datachain.sql.utils import compiler_not_implemented
 
 
 class length(GenericFunction):  # noqa: N801
+    """
+    Returns the length of the string.
+    """
+
     type = Int64()
     package = "string"
     name = "length"
@@ -12,6 +16,10 @@ class length(GenericFunction):  # noqa: N801
 
 
 class split(GenericFunction):  # noqa: N801
+    """
+    Takes a column and split character and returns an array of the parts.
+    """
+
     type = Array(String())
     package = "string"
     name = "split"

datachain/torch/__init__.py

@@ -1,5 +1,5 @@
 try:
-    from datachain.lib.clip import similarity_scores as clip_similarity_scores
+    from datachain.lib.clip import clip_similarity_scores
     from datachain.lib.image import convert_image, convert_images
     from datachain.lib.pytorch import PytorchDataset, label_to_int
     from datachain.lib.text import convert_text

datachain/utils.py

@@ -427,3 +427,9 @@ def filtered_cloudpickle_dumps(obj: Any) -> bytes:
             for model_class, namespace in model_namespaces.items():
                 # Restore original __pydantic_parent_namespace__ locally.
                 model_class.__pydantic_parent_namespace__ = namespace
+
+
+def get_datachain_executable() -> list[str]:
+    if datachain_exec_path := os.getenv("DATACHAIN_EXEC_PATH"):
+        return [datachain_exec_path]
+    return [sys.executable, "-m", "datachain"]