datachain 0.4.0__py3-none-any.whl → 0.5.1__py3-none-any.whl

{datachain-0.4.0.dist-info → datachain-0.5.1.dist-info}/RECORD

@@ -2,10 +2,10 @@ datachain/__init__.py,sha256=ofPJ6B-d-ybSDRrE7J6wqF_ZRAB2W9U8l-eeuBtqPLg,865
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=Lg3Ck1PQLjQziMx9KU4atzbEnJXTE0924WMYkhgWtGU,8247
 datachain/cache.py,sha256=s0YHN7qurmQv-eC265TjeureK84TebWWAnL07cxchZQ,2997
-datachain/cli.py,sha256=TQ1OKMulAcsJndKLCyxJpfNqbMWQgOa4Aeihnu36cR8,30095
+datachain/cli.py,sha256=vVK7hNEyF7p5bUTmixkbgS7JYyTSpXeyRZJkWfpYUOw,30164
 datachain/cli_utils.py,sha256=jrn9ejGXjybeO1ur3fjdSiAyCHZrX0qsLLbJzN9ErPM,2418
 datachain/config.py,sha256=PfC7W5yO6HFO6-iMB4YB-0RR88LPiGmD6sS_SfVbGso,1979
-datachain/dataset.py,sha256=HWcFckJpmTU5AGsg8ILW8JInpNQqaWmJoasls18q5kI,14735
+datachain/dataset.py,sha256=w7qqJP7xYrm9CmBSmSezSxUQHZDsHKkwviF8AYUob7o,14671
 datachain/error.py,sha256=vbIbamnFMIojh1UpmxWoA6Omup7WFAFNJnf8xAkGWwI,1146
 datachain/job.py,sha256=Jt4sNutMHJReaGsj3r3scueN5aESLGfhimAa8pUP7Is,1271
 datachain/listing.py,sha256=TkMmBzCiru26x4RaZiagWJTmTGbiy6yGrAsSJMr8cFE,8213
@@ -18,7 +18,7 @@ datachain/storage.py,sha256=RiSJLYdHUjnrEWkLBKPcETHpAxld_B2WxLg711t0aZI,3733
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=KeFSRHsiYthnTu4a6bH-rw04mX1m8krTX0f2NqfQGFI,12114
 datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
-datachain/catalog/catalog.py,sha256=FuKuIiCwPgN5Ea25hnFe_ZFZH9YEUZ2ma9k_Lczk-JU,63867
+datachain/catalog/catalog.py,sha256=BsMyk2RQibQYHgrmovFZeSEpPVMTwgb_7ntVYdc7t-E,64090
 datachain/catalog/datasource.py,sha256=D-VWIVDCM10A8sQavLhRXdYSCG7F4o4ifswEF80_NAQ,1412
 datachain/catalog/loader.py,sha256=-6VelNfXUdgUnwInVyA8g86Boxv2xqhTh9xNS-Zlwig,8242
 datachain/client/__init__.py,sha256=T4wiYL9KIM0ZZ_UqIyzV8_ufzYlewmizlV4iymHNluE,86
@@ -33,31 +33,31 @@ datachain/data_storage/__init__.py,sha256=cEOJpyu1JDZtfUupYucCDNFI6e5Wmp_Oyzq6rZ
 datachain/data_storage/db_engine.py,sha256=81Ol1of9TTTzD97ORajCnP366Xz2mEJt6C-kTUCaru4,3406
 datachain/data_storage/id_generator.py,sha256=lCEoU0BM37Ai2aRpSbwo5oQT0GqZnSpYwwvizathRMQ,4292
 datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s,383
-datachain/data_storage/metastore.py,sha256=Ztw86JbN4-1gobZea1oqAAT2kotvi46pxNRjqncZ7B8,52457
+datachain/data_storage/metastore.py,sha256=HfCxk4lmDUg2Q4WsFNQGMWxllP0mToA00fxkFTwdNIE,52919
 datachain/data_storage/schema.py,sha256=AGbjyEir5UmRZXI3m0jChZogUh5wd8csj6-YlUWaAxQ,8383
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=EBKJncuzcyQfcKFm2mUjvHjHRTODsteM-k_zndunBrw,28834
-datachain/data_storage/warehouse.py,sha256=Vwhu_OfcNAoTtg1BHui80VCzlPeTUjZQL0QWziu8awY,32186
+datachain/data_storage/sqlite.py,sha256=fW08P7AbJ0cDbTbcTKuAGpvMXvBjg-QkGsKT_Dslyws,28383
+datachain/data_storage/warehouse.py,sha256=fXhVfao3NfWFGbbG5uJ-Ga4bX1FiKVfcbDyQgECYfk8,32122
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datachain/lib/arrow.py,sha256=aUsoQmxDmuSnB8Ik9p57Y66gc_dgx6NBqkDDIfLsvno,7630
+datachain/lib/arrow.py,sha256=0R2CYsN82nNa5_03iS6jVix9EKeeqNZNAMgpSQP2hfo,9482
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=gHIjlow84GMRDa78yLL1Ud-N18or21fnTyPEwsatpXY,2045
 datachain/lib/dataset_info.py,sha256=srPPhI2UHf6hFPBecyFEVw2SS5aPisIIMsvGgKqi7ss,2366
-datachain/lib/dc.py,sha256=kabEHnqbcoat7gd-yl0PvmuC6SyKbRa8r7NWKcN6GEQ,68978
+datachain/lib/dc.py,sha256=HLOAkJEKFHJV_PqwSu0Pyl1m7JmUea8_wiMJFr14Nfk,75960
 datachain/lib/file.py,sha256=LjTW_-PDAnoUhvyB4bJ8Y8n__XGqrxvmd9mDOF0Gir8,14875
 datachain/lib/hf.py,sha256=cPnmLuprr0pYABH7KqA5FARQ1JGlywdDwD3yDzVAm4k,5920
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
-datachain/lib/listing.py,sha256=cHPN5-Fq8yb0gP6DARImhmZWxykDDNqhhJujDxEp53A,4104
+datachain/lib/listing.py,sha256=_2oQXh03RAOydeyW3G4OSXCncZaapMGlyGCYcvuUPhc,4145
 datachain/lib/listing_info.py,sha256=36NZ-tXY5Y118wurkajuWWbcE8UCjkRwZlacDtN9F3g,954
 datachain/lib/meta_formats.py,sha256=3f-0vpMTesagS9iMd3y9-u9r-7g0eqYsxmK4fVfNWlw,6635
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
-datachain/lib/pytorch.py,sha256=8LNyFaBrx8zws--MEsFg5g3pb8oLnaQAUlgGvtjKxX4,5960
+datachain/lib/pytorch.py,sha256=W-ARi2xH1f1DUkVfRuerW-YWYgSaJASmNCxtz2lrJGI,6072
 datachain/lib/settings.py,sha256=39thOpYJw-zPirzeNO6pmRC2vPrQvt4eBsw1xLWDFsw,2344
 datachain/lib/signal_schema.py,sha256=iqgubjCBRiUJB30miv05qFX4uU04dA_Pzi3DCUsHZGs,24177
 datachain/lib/tar.py,sha256=3WIzao6yD5fbLqXLTt9GhPGNonbFIs_fDRu-9vgLgsA,1038
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
-datachain/lib/udf.py,sha256=nG7DDuPgZ5ZuijwvDoCq-OZMxlDM8vFNzyxMmik0Y1c,11716
-datachain/lib/udf_signature.py,sha256=gMStcEeYJka5M6cg50Z9orC6y6HzCAJ3MkFqqn1fjZg,7137
+datachain/lib/udf.py,sha256=oHhJWb0gVTxcybGzYDzAeN0Gb1IMhZBoGefncT88dIY,12339
+datachain/lib/udf_signature.py,sha256=GXw24A-Olna6DWCdgy2bC-gZh_gLGPQ-KvjuI6pUjC0,7281
 datachain/lib/utils.py,sha256=5-kJlAZE0D9nXXweAjo7-SP_AWGo28feaDByONYaooQ,463
 datachain/lib/vfile.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/webdataset.py,sha256=o7SHk5HOUWsZ5Ln04xOM04eQqiBHiJNO7xLgyVBrwo8,6924
@@ -70,14 +70,13 @@ datachain/lib/convert/unflatten.py,sha256=Ogvh_5wg2f38_At_1lN0D_e2uZOOpYEvwvB2xd
 datachain/lib/convert/values_to_tuples.py,sha256=YOdbjzHq-uj6-cV2Qq43G72eN2avMNDGl4x5t6yQMl8,3931
 datachain/query/__init__.py,sha256=0NBOZVgIDpCcj1Ci883dQ9A0iiwe03xzmotkOCFbxYc,293
 datachain/query/batch.py,sha256=-vlpINJiertlnaoUVv1C95RatU0F6zuhpIYRufJRo1M,3660
-datachain/query/dataset.py,sha256=F9WEVhDuFm6NQT6l-Vi3PMU-mQVpqwKHMgZIA4eWB18,53602
-datachain/query/dispatch.py,sha256=CFAc09O6UllcyUSSEY1GUlEMPzeO8RYhXinNN4HBl9M,12405
+datachain/query/dataset.py,sha256=1c7y178ccFSeL_WIba0vT87Md_Oo4F8zaTVDjB9Bp3I,53641
+datachain/query/dispatch.py,sha256=JVcZ4REE_GOsqXbar_Cb_fk-pHgQoabQLzXwuu7IhOg,12409
 datachain/query/metrics.py,sha256=r5b0ygYhokbXp8Mg3kCH8iFSRw0jxzyeBe-C-J_bKFc,938
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
 datachain/query/queue.py,sha256=waqM_KzavU8C-G95-4211Nd4GXna_u2747Chgwtgz2w,3839
 datachain/query/schema.py,sha256=I8zLWJuWl5N332ni9mAzDYtcxMJupVPgWkSDe8spNEk,8019
-datachain/query/session.py,sha256=UPH5Z4fzCDsvj81ji0e8GA6Mgra3bOAEpVq4htqOtis,4317
-datachain/query/udf.py,sha256=HB2hbEuiGA4ch9P2mh9iLA5Jj9mRj-4JFy9VfjTLJ8U,3622
+datachain/query/session.py,sha256=kpFFJMfWBnxaMPojMGhJRbk-BOsSYI8Ckl6vvqnx7d0,5787
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/remote/studio.py,sha256=f5s6qSZ9uB4URGUoU_8_W1KZRRQQVSm6cgEBkBUEfuE,7226
 datachain/sql/__init__.py,sha256=A2djrbQwSMUZZEIKGnm-mnRA-NDSbiDJNpAmmwGNyIo,303
@@ -97,9 +96,9 @@ datachain/sql/sqlite/base.py,sha256=WLPHBhZbXbiqPoRV1VgDrXJqku4UuvJpBhYeQ0k5rI8,
 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-0.4.0.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.4.0.dist-info/METADATA,sha256=UmW4n6_qqsTZe_bXdjwCe6n6zWSVq35Kn_-h_u_b0RA,17156
-datachain-0.4.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-datachain-0.4.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.4.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.4.0.dist-info/RECORD,,
+datachain-0.5.1.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.5.1.dist-info/METADATA,sha256=n8TFKjDmTzNBMaW5Oa6MUUUOAQbAjPzkAMaKCW3Y9NU,17156
+datachain-0.5.1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+datachain-0.5.1.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.5.1.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.5.1.dist-info/RECORD,,

datachain/query/udf.py

@@ -1,126 +0,0 @@
-import typing
-from collections.abc import Iterable, Iterator, Sequence
-from dataclasses import dataclass
-from typing import (
-    TYPE_CHECKING,
-    Any,
-)
-
-from fsspec.callbacks import DEFAULT_CALLBACK, Callback
-
-from datachain.dataset import RowDict
-
-from .batch import (
-    Batch,
-    BatchingStrategy,
-    NoBatching,
-    Partition,
-    RowsOutputBatch,
-    UDFInputBatch,
-)
-from .schema import UDFParameter
-
-if TYPE_CHECKING:
-    from datachain.catalog import Catalog
-
-    from .batch import RowsOutput, UDFInput
-
-ColumnType = Any
-
-
-# Specification for the output of a UDF
-UDFOutputSpec = typing.Mapping[str, ColumnType]
-
-# Result type when calling the UDF wrapper around the actual
-# Python function / class implementing it.
-UDFResult = dict[str, Any]
-
-
-@dataclass
-class UDFProperties:
-    """Container for basic UDF properties."""
-
-    params: list[UDFParameter]
-    output: UDFOutputSpec
-    batch: int = 1
-
-    def get_batching(self, use_partitioning: bool = False) -> BatchingStrategy:
-        if use_partitioning:
-            return Partition()
-        if self.batch == 1:
-            return NoBatching()
-        if self.batch > 1:
-            return Batch(self.batch)
-        raise ValueError(f"invalid batch size {self.batch}")
-
-    def signal_names(self) -> Iterable[str]:
-        return self.output.keys()
-
-
-class UDFBase:
-    """A base class for implementing stateful UDFs."""
-
-    def __init__(
-        self,
-        properties: UDFProperties,
-    ):
-        self.properties = properties
-        self.signal_names = properties.signal_names()
-        self.output = properties.output
-
-    def run(
-        self,
-        udf_fields: "Sequence[str]",
-        udf_inputs: "Iterable[RowsOutput]",
-        catalog: "Catalog",
-        is_generator: bool,
-        cache: bool,
-        download_cb: Callback = DEFAULT_CALLBACK,
-        processed_cb: Callback = DEFAULT_CALLBACK,
-    ) -> Iterator[Iterable["UDFResult"]]:
-        for batch in udf_inputs:
-            if isinstance(batch, RowsOutputBatch):
-                n_rows = len(batch.rows)
-                inputs: UDFInput = UDFInputBatch(
-                    [RowDict(zip(udf_fields, row)) for row in batch.rows]
-                )
-            else:
-                n_rows = 1
-                inputs = RowDict(zip(udf_fields, batch))
-            output = self.run_once(catalog, inputs, is_generator, cache, cb=download_cb)
-            processed_cb.relative_update(n_rows)
-            yield output
-
-    def run_once(
-        self,
-        catalog: "Catalog",
-        arg: "UDFInput",
-        is_generator: bool = False,
-        cache: bool = False,
-        cb: Callback = DEFAULT_CALLBACK,
-    ) -> Iterable[UDFResult]:
-        raise NotImplementedError
-
-    def bind_parameters(self, catalog: "Catalog", row: "RowDict", **kwargs) -> list:
-        return [p.get_value(catalog, row, **kwargs) for p in self.properties.params]
-
-    def _process_results(
-        self,
-        rows: Sequence["RowDict"],
-        results: Sequence[Sequence[Any]],
-        is_generator=False,
-    ) -> Iterable[UDFResult]:
-        """Create a list of dictionaries representing UDF results."""
-
-        # outputting rows
-        if is_generator:
-            # each row in results is a tuple of column values
-            return (dict(zip(self.signal_names, row)) for row in results)
-
-        # outputting signals
-        row_ids = [row["sys__id"] for row in rows]
-        return [
-            {"sys__id": row_id} | dict(zip(self.signal_names, signals))
-            for row_id, signals in zip(row_ids, results)
-            if signals is not None  # skip rows with no output
-        ]