hafnia 0.4.3__tar.gz → 0.5.1__tar.gz

{hafnia-0.4.3 → hafnia-0.5.1}/.github/workflows/build.yaml

@@ -21,8 +21,8 @@ jobs:
     outputs:
       package-version: ${{ steps.extract-version.outputs.package_version }}
     steps:
-      - uses: actions/checkout@v5.0.0
-      - uses: actions/setup-python@v6.0.0
+      - uses: actions/checkout@v6.0.1
+      - uses: actions/setup-python@v6.1.0
         with:
           python-version-file: ${{ inputs.python-version-file }}
 
@@ -49,7 +49,7 @@ jobs:
         run: uv build
 
       - name: Upload package artifact
-        uses: actions/upload-artifact@v5.0.0
+        uses: actions/upload-artifact@v6.0.0
         with:
           name: python-package
           path: dist/

{hafnia-0.4.3 → hafnia-0.5.1}/.github/workflows/check_release.yaml

@@ -20,7 +20,7 @@ jobs:
       make_release: ${{ steps.check_release.outputs.make_release }}
     steps:
       - name: Download package artifact
-        uses: actions/download-artifact@v6.0.0
+        uses: actions/download-artifact@v7.0.0
         with:
             name: python-package
             path: dist/

{hafnia-0.4.3 → hafnia-0.5.1}/.github/workflows/ci_cd.yaml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     needs: lint
     steps:
-      - uses: actions/checkout@v5.0.0
+      - uses: actions/checkout@v6.0.1
       - name: Run Trivy vulnerability scanner
         uses: aquasecurity/trivy-action@0.33.1
         with:

{hafnia-0.4.3 → hafnia-0.5.1}/.github/workflows/lint.yaml

@@ -10,8 +10,8 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5.0.0
-      - uses: actions/setup-python@v6.0.0
+      - uses: actions/checkout@v6.0.1
+      - uses: actions/setup-python@v6.1.0
         with:
           python-version-file: ${{ inputs.python-version-file }}
       - uses: pre-commit/action@v3.0.1

{hafnia-0.4.3 → hafnia-0.5.1}/.github/workflows/publish_docker.yaml

@@ -24,14 +24,14 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5.0.0
-      - uses: actions/setup-python@v6.0.0
+      - uses: actions/checkout@v6.0.1
+      - uses: actions/setup-python@v6.1.0
         id: python
         with:
           python-version-file: ${{ inputs.python-version-file }}
 
       - name: Download package artifact
-        uses: actions/download-artifact@v6.0.0
+        uses: actions/download-artifact@v7.0.0
         with:
           name: python-package
           path: dist/
@@ -47,7 +47,7 @@ jobs:
             echo "aws_region=${{ secrets.STAGE_AWS_REGION }}" >> $GITHUB_OUTPUT
           fi
       - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v5.1.0
+        uses: aws-actions/configure-aws-credentials@v5.1.1
         with:
           role-to-assume: arn:aws:iam::${{ steps.env-vars.outputs.aws_account_id }}:role/${{ secrets.AWS_ROLE_NAME }}
           aws-region: ${{ steps.env-vars.outputs.aws_region }} 

{hafnia-0.4.3 → hafnia-0.5.1}/.github/workflows/publish_pypi.yaml

@@ -17,7 +17,7 @@ jobs:
       contents: read
     steps:
       - name: Download package artifact
-        uses: actions/download-artifact@v6.0.0
+        uses: actions/download-artifact@v7.0.0
         with:
           name: python-package
           path: dist/

{hafnia-0.4.3 → hafnia-0.5.1}/.github/workflows/tests.yaml

@@ -15,8 +15,8 @@ jobs:
       matrix:
         os: [ubuntu-latest, windows-latest]
     steps:
-      - uses: actions/checkout@v5.0.0
-      - uses: actions/setup-python@v6.0.0
+      - uses: actions/checkout@v6.0.1
+      - uses: actions/setup-python@v6.1.0
         with:
           python-version-file: ${{ inputs.python-version-file }}
       - name: Install uv
@@ -32,6 +32,8 @@ jobs:
         run: |
           mkdir -p ~/.hafnia
           echo "$HAFNIA_CONFIG" | jq . > ~/.hafnia/config.json
+      - name: Check hafnia configuration by download
+        run: uv run hafnia dataset download mnist --force
       - name: Run tests
         run: uv run pytest tests 
 

{hafnia-0.4.3 → hafnia-0.5.1}/.vscode/settings.json

@@ -23,7 +23,7 @@
     "python.testing.pytestArgs": [
         "tests",
         "-vv",
-        "--durations=20",
+        "--durations=20"
     ],
     "python.testing.unittestEnabled": false,
     "python.testing.pytestEnabled": true,

{hafnia-0.4.3 → hafnia-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hafnia
-Version: 0.4.3
+Version: 0.5.1
 Summary: Python SDK for communication with Hafnia platform.
 Author-email: Milestone Systems <hafniaplatform@milestone.dk>
 License-File: LICENSE
@@ -10,7 +10,7 @@ Requires-Dist: click>=8.1.8
 Requires-Dist: emoji>=2.14.1
 Requires-Dist: flatten-dict>=0.4.2
 Requires-Dist: keyring>=25.6.0
-Requires-Dist: mcp==1.16.0
+Requires-Dist: mcp>=1.23.0
 Requires-Dist: mlflow>=3.4.0
 Requires-Dist: more-itertools>=10.7.0
 Requires-Dist: opencv-python-headless>=4.11.0.86
@@ -209,7 +209,7 @@ DatasetInfo(
 ```
 
 You can iterate and access samples in the dataset using the `HafniaDataset` object.
-Each sample contain image and annotations information. 
+Each sample contain image and annotations information.
 
 ```python
 from hafnia.dataset.hafnia_dataset import HafniaDataset, Sample

{hafnia-0.4.3 → hafnia-0.5.1}/README.md

@@ -180,7 +180,7 @@ DatasetInfo(
 ```
 
 You can iterate and access samples in the dataset using the `HafniaDataset` object.
-Each sample contain image and annotations information. 
+Each sample contain image and annotations information.
 
 ```python
 from hafnia.dataset.hafnia_dataset import HafniaDataset, Sample

{hafnia-0.4.3 → hafnia-0.5.1}/examples/example_dataset_recipe.py

@@ -5,13 +5,12 @@ from rich import print as rprint
 from hafnia import utils
 from hafnia.dataset.dataset_names import OPS_REMOVE_CLASS
 from hafnia.dataset.dataset_recipe.dataset_recipe import DatasetRecipe
-from hafnia.dataset.dataset_recipe.recipe_transforms import (
-    SelectSamples,
-    Shuffle,
-    SplitsByRatios,
-)
 from hafnia.dataset.hafnia_dataset import HafniaDataset
 
+COCO_VERSION = "1.0.0"
+MIDWEST_VERSION = "1.0.0"
+MNIST_VERSION = "1.0.0"
+
 ### Introducing DatasetRecipe ###
 # A DatasetRecipe is a recipe for the dataset you want to create.
 # The recipe itself is not executed - this is just a specification of the dataset you want!
@@ -19,10 +18,10 @@ from hafnia.dataset.hafnia_dataset import HafniaDataset
 # The 'DatasetRecipe' interface is similar to the 'HafniaDataset' interface.
 # To demonstrate, we will first create a dataset with the regular 'HafniaDataset' interface.
 # This line will get the "mnist" dataset, shuffle it, and select 20 samples.
-dataset = HafniaDataset.from_name(name="mnist").shuffle().select_samples(n_samples=20)
+dataset = HafniaDataset.from_name(name="mnist", version=MNIST_VERSION).shuffle().select_samples(n_samples=20)
 
 # Now the same dataset is created using the 'DatasetRecipe' interface.
-dataset_recipe = DatasetRecipe.from_name(name="mnist").shuffle().select_samples(n_samples=20)
+dataset_recipe = DatasetRecipe.from_name(name="mnist", version=MNIST_VERSION).shuffle().select_samples(n_samples=20)
 dataset = dataset_recipe.build()
 # Note that the interface is similar, but to actually create the dataset you need to call `build()` on the recipe.
 
@@ -65,8 +64,8 @@ if utils.is_hafnia_configured():  # First ensure you are connected to the hafnia
 # Example: 'DatasetRecipe' by merging multiple dataset recipes
 dataset_recipe = DatasetRecipe.from_merger(
     recipes=[
-        DatasetRecipe.from_name(name="mnist"),
-        DatasetRecipe.from_name(name="mnist"),
+        DatasetRecipe.from_name(name="mnist", version=MNIST_VERSION),
+        DatasetRecipe.from_name(name="mnist", version=MNIST_VERSION),
     ]
 )
 
@@ -75,14 +74,14 @@ dataset_recipe = DatasetRecipe.from_merger(
     recipes=[
         DatasetRecipe.from_merger(
             recipes=[
-                DatasetRecipe.from_name(name="mnist"),
-                DatasetRecipe.from_name(name="mnist"),
+                DatasetRecipe.from_name(name="mnist", version=MNIST_VERSION),
+                DatasetRecipe.from_name(name="mnist", version=MNIST_VERSION),
             ]
         ),
         DatasetRecipe.from_path(path_folder=Path(".data/datasets/mnist"))
         .select_samples(n_samples=30)
         .splits_by_ratios(split_ratios={"train": 0.8, "val": 0.1, "test": 0.1}),
-        DatasetRecipe.from_name(name="mnist").select_samples(n_samples=20).shuffle(),
+        DatasetRecipe.from_name(name="mnist", version=MNIST_VERSION).select_samples(n_samples=20).shuffle(),
     ]
 )
 
@@ -99,14 +98,14 @@ print(dataset_recipe.as_json_str())  # as a JSON string
 # 1) The first step is to use the regular 'HafniaDataset' interface to investigate and understand the datasets
 
 # 1a) Explore 'coco-2017'
-coco = HafniaDataset.from_name("coco-2017")
+coco = HafniaDataset.from_name("coco-2017", version=COCO_VERSION)
 coco.print_stats()  # Print dataset statistics
 coco_class_names = coco.info.get_task_by_primitive("Bbox").class_names  # Get the class names for the bbox task
 # You will notice coco has 80 classes including 'person' and various vehicle classes such as 'car', 'bus', 'truck', etc.
 # but also many unrelated classes such as 'toaster', 'hair drier', etc.
 
 # 1b) Explore 'midwest-vehicle-detection'
-midwest = HafniaDataset.from_name("midwest-vehicle-detection")
+midwest = HafniaDataset.from_name("midwest-vehicle-detection", version=MIDWEST_VERSION)
 midwest.print_stats()  # Print dataset statistics
 midwest_class_names = midwest.info.get_task_by_primitive("Bbox").class_names
 # You will also notice midwest has similar classes, but they are named differently, e.g. 'Persons',
@@ -144,10 +143,10 @@ merged_dataset.print_stats()
 # 3) Once you have verified operations using the 'HafniaDataset' interface, you can convert
 # the operations to a single 'DatasetRecipe'
 merged_recipe = DatasetRecipe.from_merge(
-    recipe0=DatasetRecipe.from_name("coco-2017").class_mapper(
+    recipe0=DatasetRecipe.from_name("coco-2017", version=COCO_VERSION).class_mapper(
         class_mapping=mappings_coco, method="remove_undefined", task_name="object_detection"
     ),
-    recipe1=DatasetRecipe.from_name("midwest-vehicle-detection").class_mapper(
+    recipe1=DatasetRecipe.from_name("midwest-vehicle-detection", version=MIDWEST_VERSION).class_mapper(
         class_mapping=mapping_midwest, task_name="object_detection"
     ),
 ).select_samples_by_class_name(name=["Person", "Vehicle"], task_name="object_detection")
@@ -176,74 +175,3 @@ if utils.is_hafnia_configured():
 # 6) Monitor and manage your experiments
 # 6a) View experiments using the web platform https://staging02.mdi.milestonesys.com/training-aas/experiments
 # 6b) Or use the CLI: 'hafnia experiment ls'
-### DatasetRecipe Implicit Form ###
-# Below we demonstrate the difference between implicit and explicit forms of dataset recipes.
-# Example: Get dataset by name with implicit and explicit forms
-recipe_implicit_form = "mnist"
-recipe_explicit_form = DatasetRecipe.from_name(name="mnist")
-
-# The implicit form can now be loaded and built as a dataset
-dataset_implicit = DatasetRecipe.from_implicit_form(recipe_implicit_form).build()
-# Or directly as a dataset
-dataset_implicit = HafniaDataset.from_recipe(recipe_implicit_form)
-
-
-# Example: Get dataset from path with implicit and explicit forms:
-recipe_implicit_form = Path(".data/datasets/mnist")
-recipe_explicit_form = DatasetRecipe.from_path(path_folder=Path(".data/datasets/mnist"))
-
-# Example: Merge datasets with implicit and explicit forms
-recipe_implicit_form = ("mnist", "mnist")
-recipe_explicit_form = DatasetRecipe.from_merger(
-    recipes=[
-        DatasetRecipe.from_name(name="mnist"),
-        DatasetRecipe.from_name(name="mnist"),
-    ]
-)
-
-# Example: Define a dataset with transformations using implicit and explicit forms
-recipe_implicit_form = ["mnist", SelectSamples(n_samples=20), Shuffle()]
-recipe_explicit_form = DatasetRecipe.from_name(name="mnist").select_samples(n_samples=20).shuffle()
-
-
-# Example: Complex nested example with implicit vs explicit forms
-# Implicit form of a complex dataset recipe
-split_ratio = {"train": 0.8, "val": 0.1, "test": 0.1}
-recipe_implicit_complex = (
-    ("mnist", "mnist"),
-    [Path(".data/datasets/mnist"), SelectSamples(n_samples=30), SplitsByRatios(split_ratios=split_ratio)],
-    ["mnist", SelectSamples(n_samples=20), Shuffle()],
-)
-
-# Explicit form of the same complex dataset recipe
-recipe_explicit_complex = DatasetRecipe.from_merger(
-    recipes=[
-        DatasetRecipe.from_merger(
-            recipes=[
-                DatasetRecipe.from_name(name="mnist"),
-                DatasetRecipe.from_name(name="mnist"),
-            ]
-        ),
-        DatasetRecipe.from_path(path_folder=Path(".data/datasets/mnist"))
-        .select_samples(n_samples=30)
-        .splits_by_ratios(split_ratios=split_ratio),
-        DatasetRecipe.from_name(name="mnist").select_samples(n_samples=20).shuffle(),
-    ]
-)
-
-# The implicit form uses the following rules:
-#    str: Will get a dataset by name -> In explicit form it becomes 'DatasetRecipe.from_name'
-#    Path: Will get a dataset from path -> In explicit form it becomes 'DatasetRecipe.from_path'
-#    tuple: Will merge datasets specified in the tuple -> In explicit form it becomes 'DatasetRecipe.from_merger'
-#    list: Will define a dataset followed by a list of transformations -> In explicit form it becomes chained method calls
-# Generally, we recommend using the explicit form over the implicit form when multiple datasets and transformations are involved.
-
-
-# To convert from implicit to explicit recipe form, you can use the `from_implicit_form` method.
-explicit_recipe_from_implicit = DatasetRecipe.from_implicit_form(recipe_implicit_complex)
-rprint("Converted explicit recipe:")
-rprint(explicit_recipe_from_implicit)
-
-# Verify that the conversion produces the same result
-assert explicit_recipe_from_implicit == recipe_explicit_complex
-rprint("Conversion successful - recipes are equivalent!")

{hafnia-0.4.3 → hafnia-0.5.1}/examples/example_hafnia_dataset.py

@@ -13,6 +13,10 @@ from hafnia.dataset.primitives.bitmask import Bitmask
 from hafnia.dataset.primitives.classification import Classification
 from hafnia.dataset.primitives.polygon import Polygon
 
+MNIST_VERSION = "1.0.0"
+MIDWEST_VERSION = "1.0.0"
+COCO_VERSION = "1.0.0"
+
 # First ensure that you have the Hafnia CLI installed and configured.
 # You can install it via pip:
 #   pip install hafnia
@@ -20,7 +24,11 @@ from hafnia.dataset.primitives.polygon import Polygon
 #   hafnia configure
 
 # Load sample dataset
-dataset = HafniaDataset.from_name("mnist")
+dataset = HafniaDataset.from_name("mnist", version=MNIST_VERSION)
+
+# Use 'from_name' without version-argument to get available versions:
+# dataset = HafniaDataset.from_name("mnist")
+# >>> ValueError: Version must be specified. Available versions: ['1.0.0', '0.0.1']
 
 # Dataset information is stored in 'dataset.info'
 rprint(dataset.info)
@@ -76,7 +84,11 @@ dataset_mapped = dataset.class_mapper(class_mapping=class_mapping_strict)
 dataset_mapped.print_class_distribution()
 
 # Support Chaining Operations (load, shuffle, select samples)
-dataset = HafniaDataset.from_name("midwest-vehicle-detection").shuffle(seed=42).select_samples(n_samples=10)
+dataset = (
+    HafniaDataset.from_name("midwest-vehicle-detection", version=MIDWEST_VERSION)
+    .shuffle(seed=42)
+    .select_samples(n_samples=10)
+)
 
 
 # Write dataset to disk
@@ -88,7 +100,7 @@ dataset.write(path_dataset)
 dataset_again = HafniaDataset.from_path(path_dataset)
 
 ## Dataset importers and exporters ##
-dataset_od = HafniaDataset.from_name("coco-2017").select_samples(n_samples=5, seed=42)
+dataset_od = HafniaDataset.from_name("coco-2017", version=COCO_VERSION).select_samples(n_samples=5, seed=42)
 
 # Export/import dataset to YOLO format
 path_yolo_format = Path(".data/tmp/yolo_dataset")
@@ -138,43 +150,58 @@ path_tmp.mkdir(parents=True, exist_ok=True)
 Image.fromarray(image_with_annotations).save(path_tmp / "sample_with_annotations.png")
 
 
-## Bring-your-own-data: Create a new dataset from samples
+## Create a hafnia dataset from scratch ##
+path_yolo_dataset = Path("tests/data/dataset_formats/format_yolo/train")
+path_class_names = path_yolo_dataset.parent / "obj.names"
+class_names = [line.strip() for line in path_class_names.read_text().splitlines() if line.strip()]
+path_images_file = path_yolo_dataset / "images.txt"
+image_files = [line.strip() for line in path_images_file.read_text().splitlines() if line.strip()]
+
 fake_samples = []
-for i_fake_sample in range(5):
-    bboxes = [Bbox(top_left_x=0.1, top_left_y=0.20, width=0.1, height=0.2, class_name="car")]
-    classifications = [Classification(class_name="vehicle", class_idx=0)]
-    sample = Sample(
-        file_path=f"path/to/image_{i_fake_sample:05}.jpg",
-        height=480,
-        width=640,
-        split="train",
-        tags=["sample"],
-        bboxes=bboxes,
-        classifications=classifications,
-    )
+for image_file in image_files:
+    path_image = path_yolo_dataset / image_file
+    path_bboxes = path_yolo_dataset / image_file.replace(".jpg", ".txt")
+    bboxes: List[Bbox] = []
+    for bboxes_line in path_bboxes.read_text().splitlines():
+        str_parts = bboxes_line.strip().split()
+        class_idx = int(str_parts[0])
+        x_center, y_center, bbox_width, bbox_height = (float(value) for value in str_parts[1:5])
+        bbox = Bbox(
+            top_left_x=x_center - bbox_width / 2,
+            top_left_y=y_center - bbox_height / 2,
+            width=bbox_width,
+            height=bbox_height,
+            class_idx=class_idx,
+            class_name=class_names[class_idx],
+        )
+        bboxes.append(bbox)
+    image = Image.open(path_image)
+    height, width = image.size[1], image.size[0]
+    sample = Sample(file_path=str(path_image), height=height, width=width, split="train", bboxes=bboxes)
     fake_samples.append(sample)
 
 
 fake_dataset_info = DatasetInfo(
-    dataset_name="fake-dataset",
+    dataset_name="custom-dataset",
     version="0.0.1",
-    tasks=[
-        TaskInfo(primitive=Bbox, class_names=["car", "truck", "bus"]),
-        TaskInfo(primitive=Classification, class_names=["vehicle", "pedestrian", "cyclist"]),
-    ],
+    tasks=[TaskInfo(primitive=Bbox, class_names=class_names)],
 )
-fake_dataset = HafniaDataset.from_samples_list(samples_list=fake_samples, info=fake_dataset_info)
+custom_dataset = HafniaDataset.from_samples_list(samples_list=fake_samples, info=fake_dataset_info)
+
+sample = Sample(**custom_dataset[0])
+
+# To visualize and verify dataset is formatted correctly store image with annotations
+image_with_annotations = sample.draw_annotations()
+Image.fromarray(image_with_annotations).save(path_tmp / "custom_dataset_sample.png")  # Save visualization to TM
 
-# Coming soon! Upload your dataset to the Hafnia Platform
-# fake_dataset.upload_to_hafnia()
+# To upload the dataset to Hafnia platform
+# custom_dataset.upload_to_platform(interactive=True, allow_version_overwrite=False)
 
-# Coming soon! Create your own dataset details page in Hafnia
-# fake_dataset.upload_dataset_details()
 
 ## Storing predictions: A hafnia dataset can also be used for storing predictions per sample
 # set 'ground_truth=False' and add 'confidence'.
 bboxes_predictions = [
-    Bbox(top_left_x=10, top_left_y=20, width=100, height=200, class_name="car", ground_truth=False, confidence=0.9)
+    Bbox(top_left_x=0.1, top_left_y=0.2, width=0.3, height=0.4, class_name="car", ground_truth=False, confidence=0.9)
 ]
 
 classifications_predictions = [Classification(class_name="vehicle", class_idx=0, ground_truth=False, confidence=0.95)]

{hafnia-0.4.3 → hafnia-0.5.1}/examples/example_torchvision_dataloader.py

@@ -12,7 +12,8 @@ from hafnia.dataset.hafnia_dataset import HafniaDataset
 if __name__ == "__main__":
     torch.manual_seed(1)
     # Load Hugging Face dataset
-    dataset = HafniaDataset.from_name("midwest-vehicle-detection")
+    MIDWEST_VERSION = "1.0.0"
+    dataset = HafniaDataset.from_name("midwest-vehicle-detection", version=MIDWEST_VERSION)
 
     # Define transforms
     train_transforms = v2.Compose(

{hafnia-0.4.3 → hafnia-0.5.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "hafnia"
-version = "0.4.3"
+version = "0.5.1"
 description = "Python SDK for communication with Hafnia platform."
 readme = "README.md"
 authors = [
@@ -28,7 +28,7 @@ dependencies = [
     "xxhash>=3.5.0",
     "mlflow>=3.4.0",
     "sagemaker-mlflow>=0.1.0",
-    "mcp==1.16.0",
+    "mcp>=1.23.0",
 ]
 
 [dependency-groups]