datachain 0.6.9__tar.gz → 0.6.10__tar.gz

{datachain-0.6.9/src/datachain.egg-info → datachain-0.6.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.6.9
+Version: 0.6.10
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -71,7 +71,7 @@ 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 → datachain-0.6.10}/mkdocs.yml

@@ -15,7 +15,7 @@ validation:
 
 theme:
   name: material
-  custom_dir: overrides
+  custom_dir: docs/overrides
   logo: assets/datachain-white.svg
   favicon: assets/datachain.svg
   icon:

{datachain-0.6.9 → datachain-0.6.10}/pyproject.toml

@@ -82,7 +82,7 @@ tests = [
   "pytest-sugar>=0.9.6",
   "pytest-cov>=4.1.0",
   "pytest-mock>=3.12.0",
-  "pytest-servers[all]>=0.5.7",
+  "pytest-servers[all]>=0.5.8",
   "pytest-benchmark[histogram]",
   "pytest-xdist>=3.3.1",
   "virtualenv",

{datachain-0.6.9 → datachain-0.6.10}/src/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-0.6.9 → datachain-0.6.10}/src/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-0.6.9 → datachain-0.6.10}/src/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-0.6.10/src/datachain/lib/models/__init__.py

@@ -0,0 +1,6 @@
+from . import ultralytics
+from .bbox import BBox, OBBox
+from .pose import Pose, Pose3D
+from .segment import Segments
+
+__all__ = ["BBox", "OBBox", "Pose", "Pose3D", "Segments", "ultralytics"]

datachain-0.6.10/src/datachain/lib/models/bbox.py

@@ -0,0 +1,116 @@
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+
+
+class BBox(DataModel):
+    """
+    A data model for representing bounding boxes.
+
+    Attributes:
+        title (str): The title of the bounding box.
+        coords (list[int]): The coordinates of the bounding box.
+
+    The bounding box is defined by two points:
+        - (x1, y1): The top-left corner of the box.
+        - (x2, y2): The bottom-right corner of the box.
+    """
+
+    title: str = Field(default="")
+    coords: list[int] = Field(default=None)
+
+    @staticmethod
+    def from_list(coords: list[float], title: str = "") -> "BBox":
+        assert len(coords) == 4, "Bounding box coordinates must be a list of 4 floats."
+        assert all(
+            isinstance(value, (int, float)) for value in coords
+        ), "Bounding box coordinates must be integers or floats."
+        return BBox(
+            title=title,
+            coords=[round(c) for c in coords],
+        )
+
+    @staticmethod
+    def from_dict(coords: dict[str, float], title: str = "") -> "BBox":
+        assert (
+            len(coords) == 4
+        ), "Bounding box coordinates must be a dictionary of 4 floats."
+        assert set(coords) == {
+            "x1",
+            "y1",
+            "x2",
+            "y2",
+        }, "Bounding box coordinates must contain keys with coordinates."
+        assert all(
+            isinstance(value, (int, float)) for value in coords.values()
+        ), "Bounding box coordinates must be integers or floats."
+        return BBox(
+            title=title,
+            coords=[
+                round(coords["x1"]),
+                round(coords["y1"]),
+                round(coords["x2"]),
+                round(coords["y2"]),
+            ],
+        )
+
+
+class OBBox(DataModel):
+    """
+    A data model for representing oriented bounding boxes.
+
+    Attributes:
+        title (str): The title of the oriented bounding box.
+        coords (list[int]): The coordinates of the oriented bounding box.
+
+    The oriented bounding box is defined by four points:
+        - (x1, y1): The first corner of the box.
+        - (x2, y2): The second corner of the box.
+        - (x3, y3): The third corner of the box.
+        - (x4, y4): The fourth corner of the box.
+    """
+
+    title: str = Field(default="")
+    coords: list[int] = Field(default=None)
+
+    @staticmethod
+    def from_list(coords: list[float], title: str = "") -> "OBBox":
+        assert (
+            len(coords) == 8
+        ), "Oriented bounding box coordinates must be a list of 8 floats."
+        assert all(
+            isinstance(value, (int, float)) for value in coords
+        ), "Oriented bounding box coordinates must be integers or floats."
+        return OBBox(
+            title=title,
+            coords=[round(c) for c in coords],
+        )
+
+    @staticmethod
+    def from_dict(coords: dict[str, float], title: str = "") -> "OBBox":
+        assert set(coords) == {
+            "x1",
+            "y1",
+            "x2",
+            "y2",
+            "x3",
+            "y3",
+            "x4",
+            "y4",
+        }, "Oriented bounding box coordinates must contain keys with coordinates."
+        assert all(
+            isinstance(value, (int, float)) for value in coords.values()
+        ), "Oriented bounding box coordinates must be integers or floats."
+        return OBBox(
+            title=title,
+            coords=[
+                round(coords["x1"]),
+                round(coords["y1"]),
+                round(coords["x2"]),
+                round(coords["y2"]),
+                round(coords["x3"]),
+                round(coords["y3"]),
+                round(coords["x4"]),
+                round(coords["y4"]),
+            ],
+        )

datachain-0.6.10/src/datachain/lib/models/pose.py

@@ -0,0 +1,108 @@
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+
+
+class Pose(DataModel):
+    """
+    A data model for representing pose keypoints.
+
+    Attributes:
+        x (list[int]): The x-coordinates of the keypoints.
+        y (list[int]): The y-coordinates of the keypoints.
+
+    The keypoints are represented as lists of x and y coordinates, where each index
+    corresponds to a specific body part.
+    """
+
+    x: list[int] = Field(default=None)
+    y: list[int] = Field(default=None)
+
+    @staticmethod
+    def from_list(points: list[list[float]]) -> "Pose":
+        assert len(points) == 2, "Pose coordinates must be a list of 2 lists."
+        points_x, points_y = points
+        assert (
+            len(points_x) == len(points_y) == 17
+        ), "Pose x and y coordinates must have the same length of 17."
+        assert all(
+            isinstance(value, (int, float)) for value in [*points_x, *points_y]
+        ), "Pose coordinates must be integers or floats."
+        return Pose(
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+        )
+
+    @staticmethod
+    def from_dict(points: dict[str, list[float]]) -> "Pose":
+        assert set(points) == {
+            "x",
+            "y",
+        }, "Pose coordinates must contain keys 'x' and 'y'."
+        points_x, points_y = points["x"], points["y"]
+        assert (
+            len(points_x) == len(points_y) == 17
+        ), "Pose x and y coordinates must have the same length of 17."
+        assert all(
+            isinstance(value, (int, float)) for value in [*points_x, *points_y]
+        ), "Pose coordinates must be integers or floats."
+        return Pose(
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+        )
+
+
+class Pose3D(DataModel):
+    """
+    A data model for representing 3D pose keypoints.
+
+    Attributes:
+        x (list[int]): The x-coordinates of the keypoints.
+        y (list[int]): The y-coordinates of the keypoints.
+        visible (list[float]): The visibility of the keypoints.
+
+    The keypoints are represented as lists of x, y, and visibility values,
+    where each index corresponds to a specific body part.
+    """
+
+    x: list[int] = Field(default=None)
+    y: list[int] = Field(default=None)
+    visible: list[float] = Field(default=None)
+
+    @staticmethod
+    def from_list(points: list[list[float]]) -> "Pose3D":
+        assert len(points) == 3, "Pose coordinates must be a list of 3 lists."
+        points_x, points_y, points_v = points
+        assert (
+            len(points_x) == len(points_y) == len(points_v) == 17
+        ), "Pose x, y, and visibility coordinates must have the same length of 17."
+        assert all(
+            isinstance(value, (int, float))
+            for value in [*points_x, *points_y, *points_v]
+        ), "Pose coordinates must be integers or floats."
+        return Pose3D(
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+            visible=points_v,
+        )
+
+    @staticmethod
+    def from_dict(points: dict[str, list[float]]) -> "Pose3D":
+        assert set(points) == {
+            "x",
+            "y",
+            "visible",
+        }, "Pose coordinates must contain keys 'x', 'y', and 'visible'."
+        points_x, points_y, points_v = points["x"], points["y"], points["visible"]
+        assert (
+            len(points_x) == len(points_y) == len(points_v) == 17
+        ), "Pose x, y, and visibility coordinates must have the same length of 17."
+        assert all(
+            isinstance(value, (int, float))
+            for value in [*points_x, *points_y, *points_v]
+        ), "Pose coordinates must be integers or floats."
+        return Pose3D(
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+            visible=points_v,
+        )

datachain-0.6.10/src/datachain/lib/models/segment.py

@@ -0,0 +1,53 @@
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+
+
+class Segments(DataModel):
+    """
+    A data model for representing segments.
+
+    Attributes:
+        title (str): The title of the segments.
+        x (list[int]): The x-coordinates of the segments.
+        y (list[int]): The y-coordinates of the segments.
+
+    The segments are represented as lists of x and y coordinates, where each index
+    corresponds to a specific segment.
+    """
+
+    title: str = Field(default="")
+    x: list[int] = Field(default=None)
+    y: list[int] = Field(default=None)
+
+    @staticmethod
+    def from_list(points: list[list[float]], title: str = "") -> "Segments":
+        assert len(points) == 2, "Segments coordinates must be a list of 2 lists."
+        points_x, points_y = points
+        assert len(points_x) == len(
+            points_y
+        ), "Segments x and y coordinates must have the same length."
+        assert all(
+            isinstance(value, (int, float)) for value in [*points_x, *points_y]
+        ), "Segments coordinates must be integers or floats."
+        return Segments(
+            title=title,
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+        )
+
+    @staticmethod
+    def from_dict(points: dict[str, list[float]], title: str = "") -> "Segments":
+        assert set(points) == {
+            "x",
+            "y",
+        }, "Segments coordinates must contain keys 'x' and 'y'."
+        points_x, points_y = points["x"], points["y"]
+        assert all(
+            isinstance(value, (int, float)) for value in [*points_x, *points_y]
+        ), "Segments coordinates must be integers or floats."
+        return Segments(
+            title=title,
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+        )

datachain-0.6.10/src/datachain/lib/models/ultralytics/__init__.py

@@ -0,0 +1,14 @@
+from .bbox import YoloBBox, YoloBBoxes, YoloOBBox, YoloOBBoxes
+from .pose import YoloPose, YoloPoses
+from .segment import YoloSegment, YoloSegments
+
+__all__ = [
+    "YoloBBox",
+    "YoloBBoxes",
+    "YoloOBBox",
+    "YoloOBBoxes",
+    "YoloPose",
+    "YoloPoses",
+    "YoloSegment",
+    "YoloSegments",
+]

datachain-0.6.10/src/datachain/lib/models/ultralytics/bbox.py

@@ -0,0 +1,189 @@
+"""
+This module contains the YOLO models.
+
+YOLO stands for "You Only Look Once", a family of object detection models that
+are designed to be fast and accurate. The models are trained to detect objects
+in images by dividing the image into a grid and predicting the bounding boxes
+and class probabilities for each grid cell.
+
+More information about YOLO can be found here:
+- https://pjreddie.com/darknet/yolo/
+- https://docs.ultralytics.com/
+"""
+
+from io import BytesIO
+from typing import TYPE_CHECKING
+
+from PIL import Image
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+from datachain.lib.models.bbox import BBox, OBBox
+
+if TYPE_CHECKING:
+    from ultralytics.engine.results import Results
+    from ultralytics.models import YOLO
+
+    from datachain.lib.file import File
+
+
+class YoloBBox(DataModel):
+    """
+    A class representing a bounding box detected by a YOLO model.
+
+    Attributes:
+        cls: The class of the detected object.
+        name: The name of the detected object.
+        confidence: The confidence score of the detection.
+        box: The bounding box of the detected object
+    """
+
+    cls: int = Field(default=-1)
+    name: str = Field(default="")
+    confidence: float = Field(default=0)
+    box: BBox = Field(default=None)
+
+    @staticmethod
+    def from_file(yolo: "YOLO", file: "File") -> "YoloBBox":
+        results = yolo(Image.open(BytesIO(file.read())))
+        if len(results) == 0:
+            return YoloBBox()
+        return YoloBBox.from_result(results[0])
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloBBox":
+        summary = result.summary()
+        if not summary:
+            return YoloBBox()
+        name = summary[0].get("name", "")
+        box = (
+            BBox.from_dict(summary[0]["box"], title=name)
+            if "box" in summary[0]
+            else BBox()
+        )
+        return YoloBBox(
+            cls=summary[0]["class"],
+            name=name,
+            confidence=summary[0]["confidence"],
+            box=box,
+        )
+
+
+class YoloBBoxes(DataModel):
+    """
+    A class representing a list of bounding boxes detected by a YOLO model.
+
+    Attributes:
+        cls: A list of classes of the detected objects.
+        name: A list of names of the detected objects.
+        confidence: A list of confidence scores of the detections.
+        box: A list of bounding boxes of the detected objects
+    """
+
+    cls: list[int]
+    name: list[str]
+    confidence: list[float]
+    box: list[BBox]
+
+    @staticmethod
+    def from_file(yolo: "YOLO", file: "File") -> "YoloBBoxes":
+        results = yolo(Image.open(BytesIO(file.read())))
+        return YoloBBoxes.from_results(results)
+
+    @staticmethod
+    def from_results(results: list["Results"]) -> "YoloBBoxes":
+        cls, names, confidence, box = [], [], [], []
+        for r in results:
+            for s in r.summary():
+                name = s.get("name", "")
+                cls.append(s["class"])
+                names.append(name)
+                confidence.append(s["confidence"])
+                box.append(BBox.from_dict(s.get("box", {}), title=name))
+        return YoloBBoxes(
+            cls=cls,
+            name=names,
+            confidence=confidence,
+            box=box,
+        )
+
+
+class YoloOBBox(DataModel):
+    """
+    A class representing an oriented bounding box detected by a YOLO model.
+
+    Attributes:
+        cls: The class of the detected object.
+        name: The name of the detected object.
+        confidence: The confidence score of the detection.
+        box: The oriented bounding box of the detected object.
+    """
+
+    cls: int = Field(default=-1)
+    name: str = Field(default="")
+    confidence: float = Field(default=0)
+    box: OBBox = Field(default=None)
+
+    @staticmethod
+    def from_file(yolo: "YOLO", file: "File") -> "YoloOBBox":
+        results = yolo(Image.open(BytesIO(file.read())))
+        if len(results) == 0:
+            return YoloOBBox()
+        return YoloOBBox.from_result(results[0])
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloOBBox":
+        summary = result.summary()
+        if not summary:
+            return YoloOBBox()
+        name = summary[0].get("name", "")
+        box = (
+            OBBox.from_dict(summary[0]["box"], title=name)
+            if "box" in summary[0]
+            else OBBox()
+        )
+        return YoloOBBox(
+            cls=summary[0]["class"],
+            name=name,
+            confidence=summary[0]["confidence"],
+            box=box,
+        )
+
+
+class YoloOBBoxes(DataModel):
+    """
+    A class representing a list of oriented bounding boxes detected by a YOLO model.
+
+    Attributes:
+        cls: A list of classes of the detected objects.
+        name: A list of names of the detected objects.
+        confidence: A list of confidence scores of the detections.
+        box: A list of oriented bounding boxes of the detected objects.
+    """
+
+    cls: list[int]
+    name: list[str]
+    confidence: list[float]
+    box: list[OBBox]
+
+    @staticmethod
+    def from_file(yolo: "YOLO", file: "File") -> "YoloOBBoxes":
+        results = yolo(Image.open(BytesIO(file.read())))
+        return YoloOBBoxes.from_results(results)
+
+    @staticmethod
+    def from_results(results: list["Results"]) -> "YoloOBBoxes":
+        cls, names, confidence, box = [], [], [], []
+        for r in results:
+            for s in r.summary():
+                name = s.get("name", "")
+                cls.append(s["class"])
+                names.append(name)
+                confidence.append(s["confidence"])
+                box.append(OBBox.from_dict(s.get("box", {}), title=name))
+        return YoloOBBoxes(
+            cls=cls,
+            name=names,
+            confidence=confidence,
+            box=box,
+        )