datachain 0.1.13__py3-none-any.whl → 0.2.0__py3-none-any.whl

datachain/query/dataset.py

@@ -56,13 +56,13 @@ from datachain.storage import Storage, StorageURI
 from datachain.utils import batched, determine_processes
 
 from .batch import RowBatch
+from .metrics import metrics
 from .schema import C, UDFParamSpec, normalize_param
 from .session import Session
 from .udf import UDFBase, UDFClassWrapper, UDFFactory, UDFType
 
 if TYPE_CHECKING:
     import pandas as pd
-    from pandas.core.interchange.dataframe_protocol import DataFrame as DataFrameXchg
     from sqlalchemy.sql.elements import ClauseElement
     from sqlalchemy.sql.schema import Table
     from sqlalchemy.sql.selectable import GenerativeSelect
@@ -71,7 +71,6 @@ if TYPE_CHECKING:
     from datachain.catalog import Catalog
     from datachain.data_storage import AbstractWarehouse
     from datachain.dataset import DatasetRecord
-    from datachain.sql.types import SQLType
 
     from .udf import UDFResult
 
@@ -197,7 +196,7 @@ class IndexingStep(StartingStep):
     def apply(self):
         self.catalog.index([self.path], **self.kwargs)
         uri, path = self.parse_path()
-        partial_id, partial_path = self.catalog.metastore.get_valid_partial_id(
+        _partial_id, partial_path = self.catalog.metastore.get_valid_partial_id(
             uri, path
         )
         dataset = self.catalog.get_dataset(Storage.dataset_name(uri, partial_path))
@@ -523,30 +522,23 @@ class UDF(Step, ABC):
                     "cache": self.cache,
                 }
 
-                feature_module_name, feature_file = self.process_feature_module()
-
-                # Write the module content to a .py file
-                with open(f"{feature_module_name}.py", "w") as module_file:
-                    module_file.write(feature_file)
-
-                process_data = dumps(udf_info, recurse=True)
                 # 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")
 
                 envs = dict(os.environ)
                 envs.update({"PYTHONPATH": os.getcwd()})
-                try:
-                    result = subprocess.run(
-                        [datachain_exec_path, "--internal-run-udf"],  # noqa: S603
+                with self.process_feature_module():
+                    process_data = dumps(udf_info, recurse=True)
+                    result = subprocess.run(  # noqa: S603
+                        [datachain_exec_path, "--internal-run-udf"],
                         input=process_data,
                         check=False,
                         env=envs,
                     )
                     if result.returncode != 0:
                         raise RuntimeError("UDF Execution Failed!")
-                finally:
-                    os.unlink(f"{feature_module_name}.py")
+
             else:
                 # Otherwise process single-threaded (faster for smaller UDFs)
                 # Optionally instantiate the UDF instance if a class is provided.
@@ -600,6 +592,7 @@ class UDF(Step, ABC):
             self.catalog.warehouse.close()
             raise
 
+    @contextlib.contextmanager
     def process_feature_module(self):
         # Generate a random name for the feature module
         feature_module_name = "tmp" + _random_string(10)
@@ -611,10 +604,14 @@ class UDF(Step, ABC):
             for name, obj in inspect.getmembers(sys.modules["__main__"], _imports)
             if not (name.startswith("__") and name.endswith("__"))
         ]
+        main_module = sys.modules["__main__"]
+
         # Get the feature classes from the main module
-        feature_classes = dict(
-            inspect.getmembers(sys.modules["__main__"], _feature_predicate)
-        )
+        feature_classes = {
+            name: obj
+            for name, obj in main_module.__dict__.items()
+            if _feature_predicate(obj)
+        }
         # Get the source code of the feature classes
         feature_sources = [source.getsource(cls) for _, cls in feature_classes.items()]
         # Set the module name for the feature classes to the generated name
@@ -626,7 +623,18 @@ class UDF(Step, ABC):
         # Combine the import lines and feature sources
         feature_file = "".join(import_lines) + "\n".join(feature_sources)
 
-        return feature_module_name, feature_file
+        # Write the module content to a .py file
+        with open(f"{feature_module_name}.py", "w") as module_file:
+            module_file.write(feature_file)
+
+        try:
+            yield feature_module_name
+        finally:
+            for cls in feature_classes.values():
+                cls.__module__ = main_module.__name__
+            os.unlink(f"{feature_module_name}.py")
+            # Remove the dynamic module from sys.modules
+            del sys.modules[feature_module_name]
 
     def create_partitions_table(self, query: Select) -> "Table":
         """
@@ -685,8 +693,7 @@ class UDF(Step, ABC):
             )
 
         query, tables = self.process_input_query(query)
-        for t in tables:
-            temp_tables.append(t.name)
+        temp_tables.extend(t.name for t in tables)
         udf_table = self.create_udf_table(_query)
         temp_tables.append(udf_table.name)
         self.populate_udf_table(udf_table, query)
@@ -1120,6 +1127,12 @@ class DatasetQuery:
         indexing_feature_schema: Optional[dict] = None,
         indexing_column_types: Optional[dict[str, Any]] = None,
     ):
+        if client_config is None:
+            client_config = {}
+
+        if anon:
+            client_config["anon"] = True
+
         self.steps: list[Step] = []
         self.catalog = catalog or get_catalog(client_config=client_config)
         self._chunk_index: Optional[int] = None
@@ -1134,22 +1147,14 @@ class DatasetQuery:
         self.column_types: Optional[dict[str, Any]] = None
         self.session = Session.get(session, catalog=catalog)
 
-        if client_config is None:
-            client_config = {}
-
-        if anon:
-            client_config["anon"] = True
-
         if path:
-            self.starting_step = IndexingStep(
-                path, self.catalog, {"client_config": client_config}, recursive
-            )
+            self.starting_step = IndexingStep(path, self.catalog, {}, recursive)
             self.feature_schema = indexing_feature_schema
             self.column_types = indexing_column_types
         elif name:
             ds = self.catalog.get_dataset(name)
             self.version = version or ds.latest_version
-            self.feature_schema = ds.feature_schema
+            self.feature_schema = ds.get_version(self.version).feature_schema
             self.column_types = copy(ds.schema)
             if "id" in self.column_types:
                 self.column_types.pop("id")
@@ -1348,8 +1353,7 @@ class DatasetQuery:
             MapperCls = OrderedMapper if query._order_by_clauses else AsyncMapper  # noqa: N806
             with contextlib.closing(row_iter()) as rows:
                 mapper = MapperCls(get_params, rows, workers=workers)
-                for params in mapper.iterate():
-                    yield params
+                yield from mapper.iterate()
         finally:
             self.cleanup()
 
@@ -1386,82 +1390,6 @@ class DatasetQuery:
         records = self.to_records()
         return pd.DataFrame.from_records(records)
 
-    @classmethod
-    def from_dataframe(
-        cls,
-        df: Union["DataFrameXchg", "pd.DataFrame"],
-        name: str = "",
-        version: Optional[int] = None,
-        catalog: Optional["Catalog"] = None,
-        session: Optional[Session] = None,
-    ) -> "Self":
-        from datachain.utils import dtype_mapper
-
-        catalog = catalog or get_catalog()
-        assert catalog is not None
-        session = Session.get(session, catalog=catalog)
-        assert session is not None
-
-        try:
-            if name and version and catalog.get_dataset(name).has_version(version):
-                raise RuntimeError(f"Dataset {name} already has version {version}")
-        except DatasetNotFoundError:
-            pass
-
-        if not name and version:
-            raise RuntimeError("Cannot set version for temporary datasets")
-
-        import pandas as pd  # noqa: F401
-        from pandas.api.interchange import from_dataframe
-
-        # This is not optimal for dataframes other than pd.DataFrame, as it may copy
-        # all the data to a new dataframe.
-        pd_df = from_dataframe(df)
-
-        dtype: dict[str, type[SQLType]] = {
-            str(pd_df.columns[i]): dtype_mapper(pd_df.iloc[:, i])
-            for i in range(len(pd_df.columns))
-        }
-
-        name = name or session.generate_temp_dataset_name()
-        dataset = catalog.create_dataset(
-            name,
-            version=version,
-            columns=[Column(name, typ) for name, typ in dtype.items()],
-        )
-        version = version or dataset.latest_version
-
-        dr = catalog.warehouse.dataset_rows(dataset)
-        pd_df.to_sql(
-            dr.table.name,
-            catalog.warehouse.db.engine,
-            if_exists="append",
-            index=False,
-            chunksize=10_000,
-            dtype=dtype,
-        )
-
-        catalog.metastore.update_dataset_status(
-            dataset, DatasetStatus.COMPLETE, version=version
-        )
-        catalog.update_dataset_version_with_warehouse_info(dataset, version)
-        return cls(name=name, version=version, catalog=catalog, session=session)
-
-    from_pandas = from_dataframe
-
-    @classmethod
-    def from_parquet(
-        cls,
-        uri: str,
-        *args,
-        **kwargs,
-    ) -> "Self":
-        import pandas as pd
-
-        pd_df = pd.read_parquet(uri, dtype_backend="pyarrow")
-
-        return cls.from_dataframe(pd_df, *args, **kwargs)
-
     def shuffle(self) -> "Self":
         # ToDo: implement shaffle based on seed and/or generating random column
         return self.order_by(C.random)
@@ -1853,6 +1781,7 @@ def _get_output_fd_for_write() -> Union[str, int]:
 class ExecutionResult:
     preview: list[dict] = attrs.field(factory=list)
     dataset: Optional[tuple[str, int]] = None
+    metrics: dict[str, Any] = attrs.field(factory=dict)
 
 
 def _send_result(dataset_query: DatasetQuery) -> None:
@@ -1886,7 +1815,7 @@ def _send_result(dataset_query: DatasetQuery) -> None:
         dataset = dataset_query.name, dataset_query.version
 
     preview = preview_query.to_records()
-    result = ExecutionResult(preview, dataset)
+    result = ExecutionResult(preview, dataset, metrics)
     data = attrs.asdict(result)
 
     with open(_get_output_fd_for_write(), mode="w") as f:

datachain/query/dispatch.py

@@ -257,7 +257,7 @@ class UDFDispatcher:
 
         if self.buffer_size < n_workers:
             raise RuntimeError(
-                f"Parallel run error: buffer size is smaller than "
+                "Parallel run error: buffer size is smaller than "
                 f"number of workers: {self.buffer_size} < {n_workers}"
             )
 

datachain/query/metrics.py

@@ -0,0 +1,19 @@
+from typing import Optional, Union
+
+metrics: dict[str, Union[str, int, float, bool, None]] = {}
+
+
+def set(key: str, value: Union[str, int, float, bool, None]) -> None:  # noqa: PYI041
+    """Set a metric value."""
+    if not isinstance(key, str):
+        raise TypeError("Key must be a string")
+    if not key:
+        raise ValueError("Key must not be empty")
+    if not isinstance(value, (str, int, float, bool, type(None))):
+        raise TypeError("Value must be a string, int, float or bool")
+    metrics[key] = value
+
+
+def get(key: str) -> Optional[Union[str, int, float, bool]]:
+    """Get a metric value."""
+    return metrics[key]

datachain/query/schema.py

@@ -18,20 +18,30 @@ if TYPE_CHECKING:
     from datachain.dataset import RowDict
 
 
+DEFAULT_DELIMITER = "__"
+
+
 class ColumnMeta(type):
+    @staticmethod
+    def to_db_name(name: str) -> str:
+        return name.replace(".", DEFAULT_DELIMITER)
+
     def __getattr__(cls, name: str):
-        return cls(name)
+        return cls(ColumnMeta.to_db_name(name))
 
 
 class Column(sa.ColumnClause, metaclass=ColumnMeta):
     inherit_cache: Optional[bool] = True
 
     def __init__(self, text, type_=None, is_literal=False, _selectable=None):
-        self.name = text
+        self.name = ColumnMeta.to_db_name(text)
         super().__init__(
-            text, type_=type_, is_literal=is_literal, _selectable=_selectable
+            self.name, type_=type_, is_literal=is_literal, _selectable=_selectable
         )
 
+    def __getattr__(self, name: str):
+        return Column(self.name + DEFAULT_DELIMITER + name)
+
     def glob(self, glob_str):
         return self.op("GLOB")(glob_str)
 

datachain/sql/__init__.py

@@ -7,10 +7,10 @@ from .selectable import select, values
 
 __all__ = [
     "column",
+    "functions",
     "literal",
     "select",
     "values",
-    "functions",
 ]
 
 default_setup()

datachain/utils.py

@@ -18,9 +18,6 @@ from dateutil.parser import isoparse
 
 if TYPE_CHECKING:
     import pandas as pd
-    import pyarrow as pa
-
-    from datachain.sql.types import SQLType
 
 NUL = b"\0"
 TIME_ZERO = datetime.fromtimestamp(0, tz=timezone.utc)
@@ -78,7 +75,7 @@ class DataChainDir:
             if create:
                 instance.init()
             else:
-                NotADirectoryError(root)
+                raise NotADirectoryError(root)
         return instance
 
 
@@ -363,121 +360,3 @@ class JSONSerialize(json.JSONEncoder):
             return str(obj)
 
         return super().default(obj)
-
-
-def dtype_mapper(col: Union["pd.Index", "pd.Series"]) -> type["SQLType"]:  # noqa: PLR0911
-    from pandas import ArrowDtype
-    from pandas.api.types import infer_dtype
-
-    from datachain.sql.types import (
-        Binary,
-        Boolean,
-        DateTime,
-        Float,
-        Float32,
-        Float64,
-        Int,
-        Int32,
-        Int64,
-        String,
-        UInt64,
-    )
-
-    if isinstance(col.dtype, ArrowDtype):
-        return arrow_type_mapper(col.dtype.pyarrow_dtype)
-
-    col_type = infer_dtype(col, skipna=True)
-
-    if col_type in ("datetime", "datetime64"):
-        return DateTime
-    if col_type == "bytes":
-        return Binary
-    if col_type == "floating":
-        if col.dtype == "float32":
-            return Float32
-        if col.dtype == "float64":
-            return Float64
-        return Float
-    if col_type == "integer":
-        if col.dtype.name.lower() in ("int8", "int16", "int32"):
-            return Int32
-        if col.dtype.name.lower() == "int64":
-            return Int64
-        if col.dtype.name.lower().startswith("uint"):
-            return UInt64
-        return Int
-    if col_type == "boolean":
-        return Boolean
-    if col_type == "date":
-        return DateTime
-    if col_type in (
-        "complex",
-        "time",
-        "timedelta",
-        "timedelta64",
-        "period",
-        "interval",
-    ):
-        raise ValueError(f"{col_type!r} datatypes not supported")
-    return String
-
-
-def arrow_type_mapper(col_type: "pa.DataType") -> type["SQLType"]:  # noqa: PLR0911,C901
-    try:
-        import pyarrow as pa
-    except ImportError as exc:
-        raise ImportError(
-            "Missing required dependency pyarrow for inferring types"
-        ) from exc
-
-    from datachain.sql.types import (
-        JSON,
-        Array,
-        Binary,
-        Boolean,
-        DateTime,
-        Float,
-        Float32,
-        Float64,
-        Int,
-        Int32,
-        Int64,
-        String,
-        UInt64,
-    )
-
-    if pa.types.is_timestamp(col_type):
-        return DateTime
-    if pa.types.is_binary(col_type):
-        return Binary
-    if pa.types.is_floating(col_type):
-        if pa.types.is_float32(col_type):
-            return Float32
-        if pa.types.is_float64(col_type):
-            return Float64
-        return Float
-    if pa.types.is_integer(col_type):
-        if (
-            pa.types.is_int8(col_type)
-            or pa.types.is_int16(col_type)
-            or pa.types.is_int32(col_type)
-        ):
-            return Int32
-        if pa.types.is_int64(col_type):
-            return Int64
-        if pa.types.is_unsigned_integer(col_type):
-            return UInt64
-        return Int
-    if pa.types.is_boolean(col_type):
-        return Boolean
-    if pa.types.is_date(col_type):
-        return DateTime
-    if pa.types.is_string(col_type):
-        return String
-    if pa.types.is_list(col_type):
-        return Array(arrow_type_mapper(col_type.value_type))  # type: ignore[return-value]
-    if pa.types.is_struct(col_type) or pa.types.is_map(col_type):
-        return JSON
-    if isinstance(col_type, pa.lib.DictionaryType):
-        return arrow_type_mapper(col_type.value_type)  # type: ignore[return-value]
-    raise ValueError(f"{col_type!r} datatypes not supported")

{datachain-0.1.13.dist-info → datachain-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.1.13
+Version: 0.2.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -44,12 +44,19 @@ Requires-Dist: torch >=2.1.0 ; extra == 'cv'
 Requires-Dist: torchvision ; extra == 'cv'
 Requires-Dist: transformers >=4.36.0 ; extra == 'cv'
 Provides-Extra: dev
-Requires-Dist: datachain[tests] ; extra == 'dev'
-Requires-Dist: mypy ==1.10.0 ; extra == 'dev'
+Requires-Dist: datachain[docs,tests] ; extra == 'dev'
+Requires-Dist: mypy ==1.10.1 ; extra == 'dev'
 Requires-Dist: types-python-dateutil ; extra == 'dev'
 Requires-Dist: types-PyYAML ; extra == 'dev'
 Requires-Dist: types-requests ; extra == 'dev'
 Requires-Dist: types-ujson ; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: mkdocs >=1.5.2 ; extra == 'docs'
+Requires-Dist: mkdocs-gen-files >=0.5.0 ; extra == 'docs'
+Requires-Dist: mkdocs-material >=9.3.1 ; extra == 'docs'
+Requires-Dist: mkdocs-section-index >=0.3.6 ; extra == 'docs'
+Requires-Dist: mkdocstrings-python >=1.6.3 ; extra == 'docs'
+Requires-Dist: mkdocs-literate-nav >=0.6.1 ; extra == 'docs'
 Provides-Extra: remote
 Requires-Dist: datachain[pandas] ; extra == 'remote'
 Requires-Dist: lz4 ; extra == 'remote'

{datachain-0.1.13.dist-info → datachain-0.2.0.dist-info}/RECORD

@@ -1,82 +1,83 @@
 datachain/__init__.py,sha256=9a0qX6tqyA9KC3ahLmGarqlRTZJXhM7HijAWpfUaOnQ,102
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
-datachain/_version.py,sha256=S22EPqqZRb53L2H7sobVA3TUXv9skvkYd-YtLuHuV6M,413
-datachain/asyn.py,sha256=opARBVZJxTKU3EGYd-8gcpNXoshuCfVz_b0ut3oxC50,7641
+datachain/_version.py,sha256=H-qsvrxCpdhaQzyddR-yajEqI71hPxLa4KxzpP3uS1g,411
+datachain/asyn.py,sha256=CKCFQJ0CbB3r04S7mUTXxriKzPnOvdUaVPXjM8vCtJw,7644
 datachain/cache.py,sha256=FaPWrqWznPffmskTb1pdPkt2jAMMf__9FC2zEnP0vDU,4022
-datachain/cli.py,sha256=1mBozBJS9Nq-EeahxwyKH8ef64E2v93o0CAEzxjcbkY,32209
+datachain/cli.py,sha256=FLKRimIq917Dq0EmG3yLzMTqDaMA0vyCRUREOobUspY,32256
 datachain/cli_utils.py,sha256=jrn9ejGXjybeO1ur3fjdSiAyCHZrX0qsLLbJzN9ErPM,2418
 datachain/config.py,sha256=PfC7W5yO6HFO6-iMB4YB-0RR88LPiGmD6sS_SfVbGso,1979
-datachain/dataset.py,sha256=4ksFJlfo_CEmt5xqXPca-hhQL1syFpKxCl_ZOhTS30s,14506
+datachain/dataset.py,sha256=MZezyuJWNj_3PEtzr0epPMNyWAOTrhTSPI5FmemV6L4,14470
 datachain/error.py,sha256=GY9KYTmb7GHXn2gGHV9X-PBhgwLj3i7VpK7tGHtAoGM,1279
-datachain/listing.py,sha256=-Cm74Ne2Q36QuCpA22feDA_v-7uPqkwAOg-QzkiZAGQ,8243
-datachain/node.py,sha256=jCBvwiEUYSKQa27Tb6RORgaUjoiz7mOX63NQmP7JQY0,5703
+datachain/listing.py,sha256=1arE_9gpjhHqGQCpQZj_mLoocrZWRNDHJ-bkPc08NQs,8247
+datachain/node.py,sha256=fHe7k5ajI2g2qnzsG-_NQR_T-QdBYctVeEa8c8dsu_Y,5703
 datachain/nodes_fetcher.py,sha256=kca19yvu11JxoVY1t4_ydp1FmchiV88GnNicNBQ9NIA,831
 datachain/nodes_thread_pool.py,sha256=ZyzBvUImIPmi4WlKC2SW2msA0UhtembbTdcs2nx29A0,3191
-datachain/progress.py,sha256=cFKpoPon4iRjc4C213j5fKdl-Ga_80rUaKlS67kMa_Y,4550
+datachain/progress.py,sha256=7_8FtJs770ITK9sMq-Lt4k4k18QmYl4yIG_kCoWID3o,4559
 datachain/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/storage.py,sha256=RiSJLYdHUjnrEWkLBKPcETHpAxld_B2WxLg711t0aZI,3733
-datachain/utils.py,sha256=FW1LR5qCL5BtCYk-B-6LUCCMq8zOobkKKMrLqfFfCAg,13535
-datachain/catalog/__init__.py,sha256=Gkto1V7rUbVjJmgMEnB_VpVeHOfV47IQh1fSjEKnit4,409
-datachain/catalog/catalog.py,sha256=7ZqCsyr7W4enOIX6jiLJbBfFZvjkqjI1E_NOyL3V3AA,78585
+datachain/utils.py,sha256=DV-_OON2OomEbxuQuK1lE_2qNTf28QByNcNcEhYsilE,10202
+datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
+datachain/catalog/catalog.py,sha256=5WkICtTYCN5xSMGDd5djLnEBw8kkcDf-IpFYf7kfeuQ,78654
 datachain/catalog/datasource.py,sha256=D-VWIVDCM10A8sQavLhRXdYSCG7F4o4ifswEF80_NAQ,1412
-datachain/catalog/loader.py,sha256=FTI9s1b8iX0_TffSAx1mwm-ucsRV14NHX-F1xtTXRSE,7310
+datachain/catalog/loader.py,sha256=GJ8zhEYkC7TuaPzCsjJQ4LtTdECu-wwYzC12MikPOMQ,7307
 datachain/catalog/subclass.py,sha256=B5R0qxeTYEyVAAPM1RutBPSoXZc8L5mVVZeSGXki9Sw,2096
 datachain/client/__init__.py,sha256=T4wiYL9KIM0ZZ_UqIyzV8_ufzYlewmizlV4iymHNluE,86
-datachain/client/azure.py,sha256=5yRxhejOpifYWswbyKZ1Y8pWb6v0K2DfnvVNB_ywF0w,920
+datachain/client/azure.py,sha256=rxvF5erntGD32Y3DYK_TUCsyV2ALfuWWTnE8IWGwKEo,2542
 datachain/client/fileslice.py,sha256=bT7TYco1Qe3bqoc8aUkUZcPdPofJDHlryL5BsTn9xsY,3021
-datachain/client/fsspec.py,sha256=kSr_fgqpWB5YljM9my7R6FzJ59AxHg3nrriR9f6C-4Y,13389
+datachain/client/fsspec.py,sha256=F1Iyyw0iTrp2wQTFeignGtaHpm5Rg_cvbKaIzBX5aSc,13390
 datachain/client/gcs.py,sha256=ucX8e6JrqlFY-f80zkv084vxnKdtxpO32QJ-RG8Nv1s,4454
-datachain/client/local.py,sha256=FwtlrUdpKi1jdqk43XTK8uEPsAqy57Kf9X1FldxFxyk,5148
+datachain/client/local.py,sha256=NQVkLTJQ-a7Udavqbh_4uT-IejfZQYn10j22owz9sis,5150
 datachain/client/s3.py,sha256=TmW4f7VUM5CMZjSmgyFQFKeMUGrXt2SLoLEbLOUleiU,6296
-datachain/data_storage/__init__.py,sha256=arlkQIj2J0ozcT_GvNDxm6PLT9NeabHvIsxPNDY_TxQ,398
+datachain/data_storage/__init__.py,sha256=cEOJpyu1JDZtfUupYucCDNFI6e5Wmp_Oyzq6rZv32Y8,398
 datachain/data_storage/db_engine.py,sha256=mxOoWP4ntBMgLeTAk4dlEeIJArAz4x_tFrHytcAfLpo,3341
 datachain/data_storage/id_generator.py,sha256=VlDALKijggegAnNMJwuMETJgnLoPYxpkrkld5DNTPQw,3839
 datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s,383
-datachain/data_storage/metastore.py,sha256=GnJH2NlFngdj30aK9CSaimJNnh_x_pSjntWUnvQuI2A,53649
-datachain/data_storage/schema.py,sha256=pF3KBi-8Pz3n5jRYoJpDR3gF8qUFdyAu2XR58J4Fyuo,8724
+datachain/data_storage/metastore.py,sha256=y-4fYvuOPnWeYxAvqhDnw6CdlTvQiurg0Gg4TaG9LR0,54074
+datachain/data_storage/schema.py,sha256=FrhmeZ_btT1CfVisa4ScabS11ixZ3xn3d_whvVsBtDA,8700
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
 datachain/data_storage/sqlite.py,sha256=eHTiJ0VIxU-chnhKNTN14EsaSnw5LAaxTLi9aMCZpl4,24978
-datachain/data_storage/warehouse.py,sha256=sQLOrv6DH8UcWH1aqlg3YJKmaHr696XkVafBxccZZ3U,33213
+datachain/data_storage/warehouse.py,sha256=tL2mYoXVZe-coKLTRXEJ0sMdEr2BD0GwgIWip5PP5CM,33300
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datachain/lib/arrow.py,sha256=7lAas8hSh3vL7S7s2KOlkYn4viQpfVbM_FQ_hLCh5oc,2593
 datachain/lib/cached_stream.py,sha256=BQI6gpJ2y7_-jqQo_0VB9ntbkOVISvj9wlDwGDQbqw8,3537
 datachain/lib/claude.py,sha256=iAauA1zNVNONpLzUo1t0QN5PZ5Ot6cZkfib7Ka_c638,1969
-datachain/lib/dc.py,sha256=MAy1Bsxknaz2aduZ28ffuq88x8Ja8QHA59CsyyiUlZE,27048
-datachain/lib/feature.py,sha256=C5lxQ_Ef4rL0-mef4A4EeoqB0rcNZ0ExRE26ehx20RM,14196
-datachain/lib/feature_registry.py,sha256=hg_S_9JPEYaQ-8PI64mU0sEhSJ-rcrKtwQk5TPBotEw,1570
-datachain/lib/feature_utils.py,sha256=6wbKZ2xq08b751EFBRJy1OZLqWYd_gxq9A_Em_aMFk4,4713
-datachain/lib/file.py,sha256=ZNGzmJSq7PNVxLhGLNdR9YSYkP-1ZeqY_yhDMcDNfkI,8586
+datachain/lib/dc.py,sha256=szYQC4FOoYDMlSEDAPWZ25z4Nn-WeoaKiqKwwXbOJws,35355
+datachain/lib/feature.py,sha256=KiPiMrU8ec-bJuUs70Xh4jytZdzKk9puQNQnx03K-po,12057
+datachain/lib/feature_registry.py,sha256=YQsLYChNkYK6p2MpcVfAyBybtfN5EMiOJ8LIYakjmeQ,1602
+datachain/lib/feature_utils.py,sha256=LIK233IWGWFhuav5Rm8de0xIOSnuwA1ubk6OYrxrfN0,4712
+datachain/lib/file.py,sha256=K0jH8Q5Xle2TiVDTCzmopku_7Lh-IVufV_mgtaCNHYI,8744
 datachain/lib/gpt4_vision.py,sha256=idyXVZVWzltstGaVIu5RYE5UNbdqcPEjIWy81O1MwkM,2922
 datachain/lib/hf_image_to_text.py,sha256=HiPSWzJRDT-vnz9DXJbJBNCMNl9wmpxiSS3PbbVz8SE,3310
 datachain/lib/hf_pipeline.py,sha256=f0AH_XCziOF1OKN3d1w1swTBLaeajMJ8xgdsX37i5-o,2287
-datachain/lib/image.py,sha256=gb-My4rx5zMwOlDkcu_2G8GtRAMfsRvd7-QWUBErDw8,3486
+datachain/lib/image.py,sha256=l2lgUR3YQzjpBmTJewzUtL5zJsLDQH32lbbaLu9WvWA,3631
 datachain/lib/image_transform.py,sha256=NXWtnVOcofWBgl_YMxb4ABpaT7JTBMx7tLKvErH1IC4,3024
 datachain/lib/iptc_exif_xmp.py,sha256=xrbxFeY-wRP6T5JsUgE3EXfTxKvZVymRaRD_VIfxD0A,2236
-datachain/lib/meta_formats.py,sha256=-JAS47NOO6rx1vmr0Cy-G_txxmTvMflXfzJiFD7rWlQ,5742
-datachain/lib/parquet.py,sha256=_MbRBzcgLLLegjKZNGF9Rm9IkYRSy0IqOksVjL1nntg,917
+datachain/lib/meta_formats.py,sha256=wIVVLRLp45Zk4vjZRd_P1UtD24vpDCb-vILWtcsACwk,6630
 datachain/lib/pytorch.py,sha256=oU16XXAyAmiiabe1IoQoID00-u3uZ5GhCN48uAl6WDs,5421
 datachain/lib/reader.py,sha256=rPXXNoTUdm6PQwkAlaU-nOBreP_q4ett_EjFStrA_W0,1727
-datachain/lib/settings.py,sha256=mVtzyA_y9JA-6chMv1baggDvgeFsaUszySp660Gu4gw,2854
-datachain/lib/signal_schema.py,sha256=WPKHzgZ6HatbDQ2IN_L0JPi46n6acfHpkq91DYdlgSg,11753
+datachain/lib/settings.py,sha256=6Nkoh8riETrftYwDp3aniK53Dsjc07MdztL8N0cW1D8,2849
+datachain/lib/signal_schema.py,sha256=KaH194dAH8Zt8FtlNAgdVqcZlJc42y7RbcB37ldPPAY,11688
 datachain/lib/text.py,sha256=EEZrYohADi5rAGg3aLLRwtvyAV9js_yWAGhr2C3QbwI,2424
-datachain/lib/udf.py,sha256=PeZ-UbprfxlmgVbzH4FtNib3kIhTi9C869QM8RuM5dw,6292
-datachain/lib/udf_signature.py,sha256=1cOMcGXHbdBjyBRkvNxIEt9A_CoyiADxio2wkYu8U5M,7140
+datachain/lib/udf.py,sha256=kPc_6fQ4DzbiYiXvbps7QPlJWTu9MSCS8eUfGqOhjG4,6124
+datachain/lib/udf_signature.py,sha256=DAWMQ0dvFkKabpY5MV5K2q9YmOSTKfiV8KuUBs_6kMg,7258
 datachain/lib/unstructured.py,sha256=9Y6rAelXdYqkNbPaqz6DhXjhS8d6qXcP0ieIsWkzvkk,1143
 datachain/lib/utils.py,sha256=YQKzuW096SGe7QwHwdyS47k_9l2Rh73b-wBqt1-niw4,213
 datachain/lib/vfile.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/webdataset.py,sha256=JouI5WORgkl-am_DwQwWqO8RI1UwgbUPWsauZZj2Fmc,8221
-datachain/lib/webdataset_laion.py,sha256=tHn3Zhqx7Eb5Ywy_mobs6jDI0o_pFUbsuHqv0W_aNho,2840
+datachain/lib/webdataset_laion.py,sha256=HAtSCbVvEQqzKkoRamRxDKaQALSB3QmJRU2yWRFNxwY,2147
 datachain/query/__init__.py,sha256=tv-spkjUCYamMN9ys_90scYrZ8kJ7C7d1MTYVmxGtk4,325
 datachain/query/batch.py,sha256=sOMxXbaNii7lVyFIEZ2noqbhy_S8qtZ-WWxrka72shc,3474
-datachain/query/builtins.py,sha256=RyVEPZEuC7K1vlulrsaUjATLG_tZEvYYW7N5i6Fg-tQ,2781
-datachain/query/dataset.py,sha256=2DZAaEwX9gQlQgrRY3t-ymXN9SUkN_3XN0AfMFT6Mto,66861
-datachain/query/dispatch.py,sha256=9zcwKkLIuK5-xyRSQNw3yTqYLMHVbuZIn6KcB0g_ZBQ,13107
+datachain/query/builtins.py,sha256=ZKNs49t8Oa_OaboCBIEqtXZt7c1Qe9OR_C_HpoDriIU,2781
+datachain/query/dataset.py,sha256=c0ZoNEjAMmn0BdSnRm8XRWEsbaMH3xa_jd6FBJQDY1o,64576
+datachain/query/dispatch.py,sha256=fEk1qalxAb5JJhN-iq0Mg9MyWve4XoN1Q7uvrX4mJY4,13106
+datachain/query/metrics.py,sha256=vsECqbZfoSDBnvC3GQlziKXmISVYDLgHP1fMPEOtKyo,640
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
-datachain/query/schema.py,sha256=CGu9NBIFvX4iHQnaThLLxwWndxqkyUtYmo2JBgnZ4YQ,7660
+datachain/query/schema.py,sha256=tWlUiu9eiS5y8BTQaPI2raGclt0YzcO3DoUN1OkwnrE,7946
 datachain/query/session.py,sha256=e4_vv4RqAjU-g3KK0avgLd9MEsmJBzRVEj1w8v7fP1k,3663
 datachain/query/udf.py,sha256=0WkBPW5ymZbOGMimSXpVWVc8whjTuYfRrnxPWNHabSk,7127
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/remote/studio.py,sha256=bZb85WjtqMNFBoRuPbH-TEGpAyz0afROR7E9UgIef_Y,7438
-datachain/sql/__init__.py,sha256=AUU_NHscXxNt8gfI9WZg08x41JaI4aQNpBlUr6HA4rU,303
+datachain/sql/__init__.py,sha256=A2djrbQwSMUZZEIKGnm-mnRA-NDSbiDJNpAmmwGNyIo,303
 datachain/sql/selectable.py,sha256=fBM-wS1TUA42kVEAAiwqGtibIevyZAEritwt8PZGyLQ,1589
 datachain/sql/types.py,sha256=BzUm0nCcMPASvdqpQouX5bdVcK3G3DBfeeNhau7X_hA,10234
 datachain/sql/utils.py,sha256=rzlJw08etivdrcuQPqNVvVWhuVSyUPUQEEc6DOhu258,818
@@ -92,9 +93,9 @@ datachain/sql/sqlite/__init__.py,sha256=TAdJX0Bg28XdqPO-QwUVKy8rg78cgMileHvMNot7
 datachain/sql/sqlite/base.py,sha256=XVxn4pB-N4pPfiby5uVvfH7feNzRKlBNzsc5eyKPvhI,10965
 datachain/sql/sqlite/types.py,sha256=oP93nLfTBaYnN0z_4Dsv-HZm8j9rrUf1esMM-z3JLbg,1754
 datachain/sql/sqlite/vector.py,sha256=stBeEW6fbVbILmAtV4khjXdJIGT13HkRWJeCoqIOk50,315
-datachain-0.1.13.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.1.13.dist-info/METADATA,sha256=aqjqnY-YxqDJZhpkKaPQ35QZkehWOcsGIdqNzdLRw-0,13972
-datachain-0.1.13.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91
-datachain-0.1.13.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.1.13.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.1.13.dist-info/RECORD,,
+datachain-0.2.0.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.2.0.dist-info/METADATA,sha256=iMX8hWEMXu-4MtXlD_SVwW3ija6bOLqSbeQvHoiMNfQ,14344
+datachain-0.2.0.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
+datachain-0.2.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.2.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.2.0.dist-info/RECORD,,

{datachain-0.1.13.dist-info → datachain-0.2.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (70.1.1)
+Generator: setuptools (70.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any