datachain 0.6.9__py3-none-any.whl → 0.6.11__py3-none-any.whl

datachain/catalog/catalog.py

@@ -603,9 +603,10 @@ class Catalog:
         )
 
         lst = Listing(
+            self.metastore.clone(),
             self.warehouse.clone(),
             Client.get_client(list_uri, self.cache, **self.client_config),
-            self.get_dataset(list_ds_name),
+            dataset_name=list_ds_name,
             object_name=object_name,
         )
 
@@ -698,9 +699,13 @@ class Catalog:
 
                     client = self.get_client(source, **client_config)
                     uri = client.uri
-                    st = self.warehouse.clone()
                     dataset_name, _, _, _ = DataChain.parse_uri(uri, self.session)
-                    listing = Listing(st, client, self.get_dataset(dataset_name))
+                    listing = Listing(
+                        self.metastore.clone(),
+                        self.warehouse.clone(),
+                        client,
+                        dataset_name=dataset_name,
+                    )
                     rows = DatasetQuery(
                         name=dataset.name, version=ds_version, catalog=self
                     ).to_db_records()
@@ -1354,6 +1359,13 @@ class Catalog:
             # we will create new one if it doesn't exist
             pass
 
+        if dataset and version and dataset.has_version(version):
+            """No need to communicate with Studio at all"""
+            dataset_uri = create_dataset_uri(remote_dataset_name, version)
+            print(f"Local copy of dataset {dataset_uri} already present")
+            _instantiate_dataset()
+            return
+
         remote_dataset = self.get_remote_dataset(remote_dataset_name)
         # if version is not specified in uri, take the latest one
         if not version:

datachain/data_storage/sqlite.py

@@ -747,8 +747,12 @@ class SQLiteWarehouse(AbstractWarehouse):
 
         ids = self.db.execute(select_ids).fetchall()
 
-        select_q = query.with_only_columns(
-            *[c for c in query.selected_columns if c.name != "sys__id"]
+        select_q = (
+            query.with_only_columns(
+                *[c for c in query.selected_columns if c.name != "sys__id"]
+            )
+            .offset(None)
+            .limit(None)
         )
 
         for batch in batched_it(ids, 10_000):

datachain/lib/dc.py

@@ -642,6 +642,59 @@ class DataChain:
         }
         return chain.gen(**signal_dict)  # type: ignore[misc, arg-type]
 
+    def explode(
+        self,
+        col: str,
+        model_name: Optional[str] = None,
+        object_name: Optional[str] = None,
+    ) -> "DataChain":
+        """Explodes a column containing JSON objects (dict or str DataChain type) into
+           individual columns based on the schema of the JSON. Schema is inferred from
+           the first row of the column.
+
+        Args:
+            col: the name of the column containing JSON to be exploded.
+            model_name: optional generated model name.  By default generates the name
+                automatically.
+            object_name: optional generated object column name. By default generates the
+                name automatically.
+
+        Returns:
+            DataChain: A new DataChain instance with the new set of columns.
+        """
+        import json
+
+        import pyarrow as pa
+
+        from datachain.lib.arrow import schema_to_output
+
+        json_value = next(self.limit(1).collect(col))
+        json_dict = (
+            json.loads(json_value) if isinstance(json_value, str) else json_value
+        )
+
+        if not isinstance(json_dict, dict):
+            raise TypeError(f"Column {col} should be a string or dict type with JSON")
+
+        schema = pa.Table.from_pylist([json_dict]).schema
+        output = schema_to_output(schema, None)
+
+        if not model_name:
+            model_name = f"{col.title()}ExplodedModel"
+
+        model = dict_to_data_model(model_name, output)
+
+        def json_to_model(json_value: Union[str, dict]):
+            json_dict = (
+                json.loads(json_value) if isinstance(json_value, str) else json_value
+            )
+            return model.model_validate(json_dict)
+
+        if not object_name:
+            object_name = f"{col}_expl"
+
+        return self.map(json_to_model, params=col, output={object_name: model})
+
     @classmethod
     def datasets(
         cls,

datachain/listing.py

@@ -1,6 +1,7 @@
 import glob
 import os
 from collections.abc import Iterable, Iterator
+from functools import cached_property
 from itertools import zip_longest
 from typing import TYPE_CHECKING, Optional
 
@@ -15,28 +16,34 @@ from datachain.utils import suffix_to_number
 if TYPE_CHECKING:
     from datachain.catalog.datasource import DataSource
     from datachain.client import Client
-    from datachain.data_storage import AbstractWarehouse
+    from datachain.data_storage import AbstractMetastore, AbstractWarehouse
     from datachain.dataset import DatasetRecord
 
 
 class Listing:
     def __init__(
         self,
+        metastore: "AbstractMetastore",
         warehouse: "AbstractWarehouse",
         client: "Client",
-        dataset: Optional["DatasetRecord"],
+        dataset_name: Optional["str"] = None,
+        dataset_version: Optional[int] = None,
         object_name: str = "file",
     ):
+        self.metastore = metastore
         self.warehouse = warehouse
         self.client = client
-        self.dataset = dataset  # dataset representing bucket listing
+        self.dataset_name = dataset_name  # dataset representing bucket listing
+        self.dataset_version = dataset_version  # dataset representing bucket listing
         self.object_name = object_name
 
     def clone(self) -> "Listing":
         return self.__class__(
+            self.metastore.clone(),
             self.warehouse.clone(),
             self.client,
-            self.dataset,
+            self.dataset_name,
+            self.dataset_version,
             self.object_name,
         )
 
@@ -53,12 +60,22 @@ class Listing:
     def uri(self):
         from datachain.lib.listing import listing_uri_from_name
 
-        return listing_uri_from_name(self.dataset.name)
+        assert self.dataset_name
 
-    @property
+        return listing_uri_from_name(self.dataset_name)
+
+    @cached_property
+    def dataset(self) -> "DatasetRecord":
+        assert self.dataset_name
+        return self.metastore.get_dataset(self.dataset_name)
+
+    @cached_property
     def dataset_rows(self):
+        dataset = self.dataset
         return self.warehouse.dataset_rows(
-            self.dataset, self.dataset.latest_version, object_name=self.object_name
+            dataset,
+            self.dataset_version or dataset.latest_version,
+            object_name=self.object_name,
         )
 
     def expand_path(self, path, use_glob=True) -> list[Node]:

datachain/sql/sqlite/types.py

@@ -36,7 +36,14 @@ def convert_array(arr):
 
 
 def adapt_np_array(arr):
-    return orjson.dumps(arr, option=orjson.OPT_SERIALIZE_NUMPY).decode("utf-8")
+    def _json_serialize(obj):
+        if isinstance(obj, np.ndarray):
+            return obj.tolist()
+        return obj
+
+    return orjson.dumps(
+        arr, option=orjson.OPT_SERIALIZE_NUMPY, default=_json_serialize
+    ).decode("utf-8")
 
 
 def adapt_np_generic(val):

datachain/toolkit/__init__.py

@@ -0,0 +1,3 @@
+from .split import train_test_split
+
+__all__ = ["train_test_split"]

datachain/toolkit/split.py

@@ -0,0 +1,67 @@
+from datachain import C, DataChain
+
+
+def train_test_split(dc: DataChain, weights: list[float]) -> list[DataChain]:
+    """
+    Splits a DataChain into multiple subsets based on the provided weights.
+
+    This function partitions the rows or items of a DataChain into disjoint subsets,
+    ensuring that the relative sizes of the subsets correspond to the given weights.
+    It is particularly useful for creating training, validation, and test datasets.
+
+    Args:
+        dc (DataChain):
+            The DataChain instance to split.
+        weights (list[float]):
+            A list of weights indicating the relative proportions of the splits.
+            The weights do not need to sum to 1; they will be normalized internally.
+            For example:
+            - `[0.7, 0.3]` corresponds to a 70/30 split;
+            - `[2, 1, 1]` corresponds to a 50/25/25 split.
+
+    Returns:
+        list[DataChain]:
+            A list of DataChain instances, one for each weight in the weights list.
+
+    Examples:
+        Train-test split:
+        ```python
+        from datachain import DataChain
+        from datachain.toolkit import train_test_split
+
+        # Load a DataChain from a storage source (e.g., S3 bucket)
+        dc = DataChain.from_storage("s3://bucket/dir/")
+
+        # Perform a 70/30 train-test split
+        train, test = train_test_split(dc, [0.7, 0.3])
+
+        # Save the resulting splits
+        train.save("dataset_train")
+        test.save("dataset_test")
+        ```
+
+        Train-test-validation split:
+        ```python
+        train, test, val = train_test_split(dc, [0.7, 0.2, 0.1])
+        train.save("dataset_train")
+        test.save("dataset_test")
+        val.save("dataset_val")
+        ```
+
+    Note:
+        The splits are random but deterministic, based on Dataset `sys__rand` field.
+    """
+    if len(weights) < 2:
+        raise ValueError("Weights should have at least two elements")
+    if any(weight < 0 for weight in weights):
+        raise ValueError("Weights should be non-negative")
+
+    weights_normalized = [weight / sum(weights) for weight in weights]
+
+    return [
+        dc.filter(
+            C("sys__rand") % 1000 >= round(sum(weights_normalized[:index]) * 1000),
+            C("sys__rand") % 1000 < round(sum(weights_normalized[: index + 1]) * 1000),
+        )
+        for index, _ in enumerate(weights_normalized)
+    ]

{datachain-0.6.9.dist-info → datachain-0.6.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.6.9
+Version: 0.6.11
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -82,7 +82,7 @@ Requires-Dist: pytest <9,>=8 ; extra == 'tests'
 Requires-Dist: pytest-sugar >=0.9.6 ; extra == 'tests'
 Requires-Dist: pytest-cov >=4.1.0 ; extra == 'tests'
 Requires-Dist: pytest-mock >=3.12.0 ; extra == 'tests'
-Requires-Dist: pytest-servers[all] >=0.5.7 ; extra == 'tests'
+Requires-Dist: pytest-servers[all] >=0.5.8 ; extra == 'tests'
 Requires-Dist: pytest-benchmark[histogram] ; extra == 'tests'
 Requires-Dist: pytest-xdist >=3.3.1 ; extra == 'tests'
 Requires-Dist: virtualenv ; extra == 'tests'

{datachain-0.6.9.dist-info → datachain-0.6.11.dist-info}/RECORD

@@ -8,7 +8,7 @@ datachain/config.py,sha256=g8qbNV0vW2VEKpX-dGZ9pAn0DAz6G2ZFcr7SAV3PoSM,4272
 datachain/dataset.py,sha256=0IN-5y723y-bnFlieKtOFZLCjwX_yplFo3q0DV7LRPw,14821
 datachain/error.py,sha256=bxAAL32lSeMgzsQDEHbGTGORj-mPzzpCRvWDPueJNN4,1092
 datachain/job.py,sha256=Jt4sNutMHJReaGsj3r3scueN5aESLGfhimAa8pUP7Is,1271
-datachain/listing.py,sha256=AV23WZq-k6e2zeeNBhVQP1-2PrwNCYidO0HBDKzpVaA,7152
+datachain/listing.py,sha256=TgKg25ZWAP5enzKgw2_2GUPJVdnQUh6uySHB5SJrUY4,7773
 datachain/node.py,sha256=i7_jC8VcW6W5VYkDszAOu0H-rNBuqXB4UnLEh4wFzjc,5195
 datachain/nodes_fetcher.py,sha256=F-73-h19HHNGtHFBGKk7p3mc0ALm4a9zGnzhtuUjnp4,1107
 datachain/nodes_thread_pool.py,sha256=uPo-xl8zG5m9YgODjPFBpbcqqHjI-dcxH87yAbj_qco,3192
@@ -18,7 +18,7 @@ datachain/studio.py,sha256=6kxF7VxPAbh9D7_Bk8_SghS5OXrwUwSpDaw19eNCTP4,4083
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=-mSFowjIidJ4_sMXInvNHLn4rK_QnHuIlLuH1_lMGmI,13897
 datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
-datachain/catalog/catalog.py,sha256=Iwb562grttdGcrNVHCna_n7e884BqwGhQwAgYagBwyg,57347
+datachain/catalog/catalog.py,sha256=J1nUWLI4RYCvvR6fB4neQBtB7V-CTh4PM71irhNmJc4,57817
 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
@@ -36,14 +36,14 @@ datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s
 datachain/data_storage/metastore.py,sha256=5b7o_CSHC2djottebYn-Hq5q0yaSLOKPIRCnaVRvjsU,36056
 datachain/data_storage/schema.py,sha256=scANMQqozita3HjEtq7eupMgh6yYkrZHoXtfuL2RoQg,9879
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=wb8xlMJYYyt59wft0psJj587d-AwpNThzIqspVcKnRI,27388
+datachain/data_storage/sqlite.py,sha256=CspRUlYsIcubgzvcQxTACnmcuKESSLZcqCl0dcrtRiA,27471
 datachain/data_storage/warehouse.py,sha256=xwMaR4jBpR13vjG3zrhphH4z2_CFLNj0KPF0LJCXCJ8,30727
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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=q0EW9tj5jXGSD9Lzct9zbH4P1lfIGd_cIWqhnMxv7Q0,2464
-datachain/lib/dc.py,sha256=RQ8p95rzCMRY4ygFecO_hhQ3IgQHmbLXNqhcaINvGcI,85841
+datachain/lib/dc.py,sha256=BmRgCt5fXvBqlFV07KN-nWszueRyCkC7td1x7T4BZ7k,87688
 datachain/lib/file.py,sha256=lHxE1wOGR4QJBQ3AYjhPLwpX72dOi06vkcwA-WSAGlg,14817
 datachain/lib/hf.py,sha256=BW2NPpqxkpPwkSaGlppT8Rbs8zPpyYC-tR6htY08c-0,5817
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
@@ -101,12 +101,14 @@ datachain/sql/functions/random.py,sha256=vBwEEj98VH4LjWixUCygQ5Bz1mv1nohsCG0-ZTE
 datachain/sql/functions/string.py,sha256=DYgiw8XSk7ge7GXvyRI1zbaMruIizNeI-puOjriQGZQ,1148
 datachain/sql/sqlite/__init__.py,sha256=TAdJX0Bg28XdqPO-QwUVKy8rg78cgMileHvMNot7d04,166
 datachain/sql/sqlite/base.py,sha256=aHSZVvh4XSVkvZ07h3jMoRlHI4sWD8y3SnmGs9xMG9Y,14375
-datachain/sql/sqlite/types.py,sha256=yzvp0sXSEoEYXs6zaYC_2YubarQoZH-MiUNXcpuEP4s,1573
+datachain/sql/sqlite/types.py,sha256=lPXS1XbkmUtlkkiRxy_A_UzsgpPv2VSkXYOD4zIHM4w,1734
 datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
+datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
+datachain/toolkit/split.py,sha256=6FcEJgUsJsUcCqKW5aXuJy4DvbcQ7_dFbsfNPhn8EVg,2377
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.6.9.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.6.9.dist-info/METADATA,sha256=McKhuW43_7Q3iJKxueIYbk-rpYF6rbIKeFinzeeUzMo,18037
-datachain-0.6.9.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-datachain-0.6.9.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.6.9.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.6.9.dist-info/RECORD,,
+datachain-0.6.11.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.6.11.dist-info/METADATA,sha256=L9Z8Hr_bTC8AWCl3bjakzsdej3lgFMCsFJ6wDdE1heU,18038
+datachain-0.6.11.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
+datachain-0.6.11.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.6.11.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.6.11.dist-info/RECORD,,