datachain 0.6.11__py3-none-any.whl → 0.7.1__py3-none-any.whl

datachain/model/ultralytics/bbox.py

@@ -0,0 +1,147 @@
+from typing import TYPE_CHECKING
+
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+from datachain.model.bbox import BBox, OBBox
+
+if TYPE_CHECKING:
+    from ultralytics.engine.results import Results
+
+
+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
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloBBox":
+        summary = result.summary()
+        if not summary:
+            return YoloBBox(box=BBox())
+        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_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
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloOBBox":
+        summary = result.summary()
+        if not summary:
+            return YoloOBBox(box=OBBox())
+        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_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,
+        )

datachain/model/ultralytics/pose.py

@@ -0,0 +1,113 @@
+from typing import TYPE_CHECKING
+
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+from datachain.model.bbox import BBox
+from datachain.model.pose import Pose3D
+
+if TYPE_CHECKING:
+    from ultralytics.engine.results import Results
+
+
+class YoloPoseBodyPart:
+    """An enumeration of body parts for YOLO pose keypoints."""
+
+    nose = 0
+    left_eye = 1
+    right_eye = 2
+    left_ear = 3
+    right_ear = 4
+    left_shoulder = 5
+    right_shoulder = 6
+    left_elbow = 7
+    right_elbow = 8
+    left_wrist = 9
+    right_wrist = 10
+    left_hip = 11
+    right_hip = 12
+    left_knee = 13
+    right_knee = 14
+    left_ankle = 15
+    right_ankle = 16
+
+
+class YoloPose(DataModel):
+    """
+    A data model for YOLO pose keypoints.
+
+    Attributes:
+        cls: The class of the pose.
+        name: The name of the pose.
+        confidence: The confidence score of the pose.
+        box: The bounding box of the pose.
+        pose: The 3D pose keypoints.
+    """
+
+    cls: int = Field(default=-1)
+    name: str = Field(default="")
+    confidence: float = Field(default=0)
+    box: BBox
+    pose: Pose3D
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloPose":
+        summary = result.summary()
+        if not summary:
+            return YoloPose(box=BBox(), pose=Pose3D())
+        name = summary[0].get("name", "")
+        box = (
+            BBox.from_dict(summary[0]["box"], title=name)
+            if "box" in summary[0]
+            else BBox()
+        )
+        pose = (
+            Pose3D.from_dict(summary[0]["keypoints"])
+            if "keypoints" in summary[0]
+            else Pose3D()
+        )
+        return YoloPose(
+            cls=summary[0]["class"],
+            name=name,
+            confidence=summary[0]["confidence"],
+            box=box,
+            pose=pose,
+        )
+
+
+class YoloPoses(DataModel):
+    """
+    A data model for a list of YOLO pose keypoints.
+
+    Attributes:
+        cls: The classes of the poses.
+        name: The names of the poses.
+        confidence: The confidence scores of the poses.
+        box: The bounding boxes of the poses.
+        pose: The 3D pose keypoints of the poses.
+    """
+
+    cls: list[int]
+    name: list[str]
+    confidence: list[float]
+    box: list[BBox]
+    pose: list[Pose3D]
+
+    @staticmethod
+    def from_results(results: list["Results"]) -> "YoloPoses":
+        cls, names, confidence, box, pose = [], [], [], [], []
+        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))
+                pose.append(Pose3D.from_dict(s.get("keypoints", {})))
+        return YoloPoses(
+            cls=cls,
+            name=names,
+            confidence=confidence,
+            box=box,
+            pose=pose,
+        )

datachain/model/ultralytics/segment.py

@@ -0,0 +1,91 @@
+from typing import TYPE_CHECKING
+
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+from datachain.model.bbox import BBox
+from datachain.model.segment import Segment
+
+if TYPE_CHECKING:
+    from ultralytics.engine.results import Results
+
+
+class YoloSegment(DataModel):
+    """
+    A data model for a single YOLO segment.
+
+    Attributes:
+        cls (int): The class of the segment.
+        name (str): The name of the segment.
+        confidence (float): The confidence of the segment.
+        box (BBox): The bounding box of the segment.
+        segment (Segments): The segments of the segment.
+    """
+
+    cls: int = Field(default=-1)
+    name: str = Field(default="")
+    confidence: float = Field(default=0)
+    box: BBox
+    segment: Segment
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloSegment":
+        summary = result.summary()
+        if not summary:
+            return YoloSegment(box=BBox(), segment=Segment())
+        name = summary[0].get("name", "")
+        box = (
+            BBox.from_dict(summary[0]["box"], title=name)
+            if "box" in summary[0]
+            else BBox()
+        )
+        segment = (
+            Segment.from_dict(summary[0]["segments"], title=name)
+            if "segments" in summary[0]
+            else Segment()
+        )
+        return YoloSegment(
+            cls=summary[0]["class"],
+            name=summary[0]["name"],
+            confidence=summary[0]["confidence"],
+            box=box,
+            segment=segment,
+        )
+
+
+class YoloSegments(DataModel):
+    """
+    A data model for a list of YOLO segments.
+
+    Attributes:
+        cls (list[int]): The classes of the segments.
+        name (list[str]): The names of the segments.
+        confidence (list[float]): The confidences of the segments.
+        box (list[BBox]): The bounding boxes of the segments.
+        segment (list[Segments]): The segments of the segments.
+    """
+
+    cls: list[int]
+    name: list[str]
+    confidence: list[float]
+    box: list[BBox]
+    segment: list[Segment]
+
+    @staticmethod
+    def from_results(results: list["Results"]) -> "YoloSegments":
+        cls, names, confidence, box, segment = [], [], [], [], []
+        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))
+                segment.append(Segment.from_dict(s.get("segments", {}), title=name))
+        return YoloSegments(
+            cls=cls,
+            name=names,
+            confidence=confidence,
+            box=box,
+            segment=segment,
+        )

datachain/node.py

@@ -55,7 +55,7 @@ class Node:
     last_modified: Optional[datetime] = None
     size: int = 0
     location: Optional[str] = None
-    source: StorageURI = StorageURI("")
+    source: StorageURI = StorageURI("")  # noqa: RUF009
     dir_type: int = DirType.FILE
 
     @property

datachain/query/dataset.py

@@ -473,33 +473,31 @@ class UDFStep(Step, ABC):
                 # Otherwise process single-threaded (faster for smaller UDFs)
                 warehouse = self.catalog.warehouse
 
-                with contextlib.closing(
-                    batching(warehouse.dataset_select_paginated, query)
-                ) as udf_inputs:
-                    download_cb = get_download_callback()
-                    processed_cb = get_processed_callback()
-                    generated_cb = get_generated_callback(self.is_generator)
-                    try:
-                        udf_results = self.udf.run(
-                            udf_fields,
-                            udf_inputs,
-                            self.catalog,
-                            self.is_generator,
-                            self.cache,
-                            download_cb,
-                            processed_cb,
-                        )
-                        process_udf_outputs(
-                            warehouse,
-                            udf_table,
-                            udf_results,
-                            self.udf,
-                            cb=generated_cb,
-                        )
-                    finally:
-                        download_cb.close()
-                        processed_cb.close()
-                        generated_cb.close()
+                udf_inputs = batching(warehouse.dataset_select_paginated, query)
+                download_cb = get_download_callback()
+                processed_cb = get_processed_callback()
+                generated_cb = get_generated_callback(self.is_generator)
+                try:
+                    udf_results = self.udf.run(
+                        udf_fields,
+                        udf_inputs,
+                        self.catalog,
+                        self.is_generator,
+                        self.cache,
+                        download_cb,
+                        processed_cb,
+                    )
+                    process_udf_outputs(
+                        warehouse,
+                        udf_table,
+                        udf_results,
+                        self.udf,
+                        cb=generated_cb,
+                    )
+                finally:
+                    download_cb.close()
+                    processed_cb.close()
+                    generated_cb.close()
 
                 warehouse.insert_rows_done(udf_table)
 

datachain/toolkit/split.py

@@ -58,10 +58,14 @@ def train_test_split(dc: DataChain, weights: list[float]) -> list[DataChain]:
 
     weights_normalized = [weight / sum(weights) for weight in weights]
 
+    resolution = 2**31 - 1  # Maximum positive value for a 32-bit signed integer.
+
     return [
         dc.filter(
-            C("sys__rand") % 1000 >= round(sum(weights_normalized[:index]) * 1000),
-            C("sys__rand") % 1000 < round(sum(weights_normalized[: index + 1]) * 1000),
+            C("sys__rand") % resolution
+            >= round(sum(weights_normalized[:index]) * resolution),
+            C("sys__rand") % resolution
+            < round(sum(weights_normalized[: index + 1]) * resolution),
         )
         for index, _ in enumerate(weights_normalized)
     ]

{datachain-0.6.11.dist-info → datachain-0.7.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.6.11
+Version: 0.7.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -19,85 +19,86 @@ License-File: LICENSE
 Requires-Dist: pyyaml
 Requires-Dist: tomlkit
 Requires-Dist: tqdm
-Requires-Dist: numpy <3,>=1
-Requires-Dist: pandas >=2.0.0
+Requires-Dist: numpy<3,>=1
+Requires-Dist: pandas>=2.0.0
 Requires-Dist: pyarrow
 Requires-Dist: typing-extensions
-Requires-Dist: python-dateutil >=2
-Requires-Dist: attrs >=21.3.0
-Requires-Dist: s3fs >=2024.2.0
-Requires-Dist: gcsfs >=2024.2.0
-Requires-Dist: adlfs >=2024.2.0
-Requires-Dist: dvc-data <4,>=3.10
-Requires-Dist: dvc-objects <6,>=4
-Requires-Dist: shtab <2,>=1.3.4
-Requires-Dist: sqlalchemy >=2
-Requires-Dist: multiprocess ==0.70.16
+Requires-Dist: python-dateutil>=2
+Requires-Dist: attrs>=21.3.0
+Requires-Dist: s3fs>=2024.2.0
+Requires-Dist: gcsfs>=2024.2.0
+Requires-Dist: adlfs>=2024.2.0
+Requires-Dist: dvc-data<4,>=3.10
+Requires-Dist: dvc-objects<6,>=4
+Requires-Dist: shtab<2,>=1.3.4
+Requires-Dist: sqlalchemy>=2
+Requires-Dist: multiprocess==0.70.16
 Requires-Dist: cloudpickle
-Requires-Dist: orjson >=3.10.5
-Requires-Dist: pydantic <3,>=2
-Requires-Dist: jmespath >=1.0
-Requires-Dist: datamodel-code-generator >=0.25
-Requires-Dist: Pillow <12,>=10.0.0
-Requires-Dist: msgpack <2,>=1.0.4
+Requires-Dist: orjson>=3.10.5
+Requires-Dist: pydantic<3,>=2
+Requires-Dist: jmespath>=1.0
+Requires-Dist: datamodel-code-generator>=0.25
+Requires-Dist: Pillow<12,>=10.0.0
+Requires-Dist: msgpack<2,>=1.0.4
 Requires-Dist: psutil
-Requires-Dist: huggingface-hub
-Requires-Dist: iterative-telemetry >=0.0.9
+Requires-Dist: huggingface_hub
+Requires-Dist: iterative-telemetry>=0.0.9
 Requires-Dist: platformdirs
-Requires-Dist: dvc-studio-client <1,>=0.21
+Requires-Dist: dvc-studio-client<1,>=0.21
 Requires-Dist: tabulate
-Provides-Extra: dev
-Requires-Dist: datachain[docs,tests] ; extra == 'dev'
-Requires-Dist: mypy ==1.13.0 ; extra == 'dev'
-Requires-Dist: types-python-dateutil ; extra == 'dev'
-Requires-Dist: types-pytz ; extra == 'dev'
-Requires-Dist: types-PyYAML ; extra == 'dev'
-Requires-Dist: types-requests ; extra == 'dev'
-Requires-Dist: types-tabulate ; 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: examples
-Requires-Dist: datachain[tests] ; extra == 'examples'
-Requires-Dist: numpy <2,>=1 ; extra == 'examples'
-Requires-Dist: defusedxml ; extra == 'examples'
-Requires-Dist: accelerate ; extra == 'examples'
-Requires-Dist: unstructured[embed-huggingface,pdf] <0.16.0 ; extra == 'examples'
-Requires-Dist: pdfplumber ==0.11.4 ; extra == 'examples'
-Requires-Dist: huggingface-hub[hf_transfer] ; extra == 'examples'
-Requires-Dist: onnx ==1.16.1 ; extra == 'examples'
-Provides-Extra: hf
-Requires-Dist: numba >=0.60.0 ; extra == 'hf'
-Requires-Dist: datasets[audio,vision] >=2.21.0 ; extra == 'hf'
-Provides-Extra: remote
-Requires-Dist: lz4 ; extra == 'remote'
-Requires-Dist: requests >=2.22.0 ; extra == 'remote'
-Provides-Extra: tests
-Requires-Dist: datachain[hf,remote,torch,vector] ; extra == 'tests'
-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] >=0.5.8 ; extra == 'tests'
-Requires-Dist: pytest-benchmark[histogram] ; extra == 'tests'
-Requires-Dist: pytest-xdist >=3.3.1 ; extra == 'tests'
-Requires-Dist: virtualenv ; extra == 'tests'
-Requires-Dist: dulwich ; extra == 'tests'
-Requires-Dist: hypothesis ; extra == 'tests'
-Requires-Dist: open-clip-torch ; extra == 'tests'
-Requires-Dist: aiotools >=1.7.0 ; extra == 'tests'
-Requires-Dist: requests-mock ; extra == 'tests'
-Requires-Dist: scipy ; extra == 'tests'
+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: torch
-Requires-Dist: torch >=2.1.0 ; extra == 'torch'
-Requires-Dist: torchvision ; extra == 'torch'
-Requires-Dist: transformers >=4.36.0 ; extra == 'torch'
+Requires-Dist: torch>=2.1.0; extra == "torch"
+Requires-Dist: torchvision; extra == "torch"
+Requires-Dist: transformers>=4.36.0; extra == "torch"
+Provides-Extra: remote
+Requires-Dist: lz4; extra == "remote"
+Requires-Dist: requests>=2.22.0; extra == "remote"
 Provides-Extra: vector
-Requires-Dist: usearch ; extra == 'vector'
+Requires-Dist: usearch; extra == "vector"
+Provides-Extra: hf
+Requires-Dist: numba>=0.60.0; extra == "hf"
+Requires-Dist: datasets[audio,vision]>=2.21.0; extra == "hf"
+Provides-Extra: tests
+Requires-Dist: datachain[hf,remote,torch,vector]; extra == "tests"
+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]>=0.5.8; extra == "tests"
+Requires-Dist: pytest-benchmark[histogram]; extra == "tests"
+Requires-Dist: pytest-xdist>=3.3.1; extra == "tests"
+Requires-Dist: virtualenv; extra == "tests"
+Requires-Dist: dulwich; extra == "tests"
+Requires-Dist: hypothesis; extra == "tests"
+Requires-Dist: open_clip_torch; extra == "tests"
+Requires-Dist: aiotools>=1.7.0; extra == "tests"
+Requires-Dist: requests-mock; extra == "tests"
+Requires-Dist: scipy; extra == "tests"
+Provides-Extra: dev
+Requires-Dist: datachain[docs,tests]; extra == "dev"
+Requires-Dist: mypy==1.13.0; extra == "dev"
+Requires-Dist: types-python-dateutil; extra == "dev"
+Requires-Dist: types-pytz; extra == "dev"
+Requires-Dist: types-PyYAML; extra == "dev"
+Requires-Dist: types-requests; extra == "dev"
+Requires-Dist: types-tabulate; extra == "dev"
+Provides-Extra: examples
+Requires-Dist: datachain[tests]; extra == "examples"
+Requires-Dist: numpy<2,>=1; extra == "examples"
+Requires-Dist: defusedxml; extra == "examples"
+Requires-Dist: accelerate; extra == "examples"
+Requires-Dist: unstructured[embed-huggingface,pdf]<0.16.0; extra == "examples"
+Requires-Dist: pdfplumber==0.11.4; extra == "examples"
+Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
+Requires-Dist: onnx==1.16.1; extra == "examples"
+Requires-Dist: ultralytics==8.3.29; extra == "examples"
 
 ================
 |logo| DataChain