hirundo 0.1.8__py3-none-any.whl → 0.1.16__py3-none-any.whl

{hirundo-0.1.8.dist-info → hirundo-0.1.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: hirundo
-Version: 0.1.8
+Version: 0.1.16
 Summary: This package is used to interface with Hirundo's platform. It provides a simple API to optimize your ML datasets.
 Author-email: Hirundo <dev@hirundo.io>
 License: MIT License
@@ -31,7 +31,6 @@ Requires-Dist: typer>=0.12.3
 Requires-Dist: httpx>=0.27.0
 Requires-Dist: stamina>=24.2.0
 Requires-Dist: httpx-sse>=0.4.0
-Requires-Dist: pandas>=2.2.2
 Requires-Dist: tqdm>=4.66.5
 Provides-Extra: dev
 Requires-Dist: pyyaml>=6.0.1; extra == "dev"
@@ -47,17 +46,28 @@ Requires-Dist: stamina>=24.2.0; extra == "dev"
 Requires-Dist: httpx-sse>=0.4.0; extra == "dev"
 Requires-Dist: pytest>=8.2.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.23.6; extra == "dev"
-Requires-Dist: uv; extra == "dev"
+Requires-Dist: uv>=0.5.8; extra == "dev"
 Requires-Dist: pre-commit>=3.7.1; extra == "dev"
-Requires-Dist: ruff==0.6.5; extra == "dev"
+Requires-Dist: virtualenv>=20.6.6; extra == "dev"
+Requires-Dist: ruff>=0.11.6; extra == "dev"
 Requires-Dist: bumpver; extra == "dev"
+Requires-Dist: platformdirs>=4.3.6; extra == "dev"
+Requires-Dist: safety>=3.2.13; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: sphinx>=7.4.7; extra == "docs"
 Requires-Dist: sphinx-autobuild>=2024.4.16; extra == "docs"
 Requires-Dist: sphinx-click>=5.0.1; extra == "docs"
-Requires-Dist: autodoc-pydantic>=2.2.0; extra == "docs"
+Requires-Dist: autodoc_pydantic>=2.2.0; extra == "docs"
 Requires-Dist: furo; extra == "docs"
 Requires-Dist: sphinx-multiversion; extra == "docs"
+Requires-Dist: esbonio; extra == "docs"
+Requires-Dist: starlette>0.40.0; extra == "docs"
+Requires-Dist: markupsafe>=3.0.2; extra == "docs"
+Provides-Extra: pandas
+Requires-Dist: pandas>=2.2.2; extra == "pandas"
+Provides-Extra: polars
+Requires-Dist: polars>=1.0.0; extra == "polars"
+Dynamic: license-file
 
 # Hirundo
 
@@ -66,7 +76,7 @@ This package exposes access to Hirundo APIs for dataset optimization for Machine
 Dataset optimization is currently available for datasets labelled for classification and object detection.
 
 
-Support dataset storage integrations include:
+Support dataset storage configs include:
    - Google Cloud (GCP) Storage
    - Amazon Web Services (AWS) S3
    - Git LFS (Large File Storage) repositories (e.g. GitHub or HuggingFace)
@@ -107,27 +117,33 @@ You can install the codebase with a simple `pip install hirundo` to install the
 ## Usage
 
 Classification example:
-```
-from hirundo.dataset_optimization import OptimizationDataset
-from hirundo.enum import LabellingType
-from hirundo.storage import StorageIntegration, StorageLink, StorageTypes
+```python
+from hirundo import (
+    HirundoCSV,
+    LabelingType,
+    OptimizationDataset,
+    StorageGCP,
+    StorageConfig,
+    StorageTypes,
+)
 
+gcp_bucket = StorageGCP(
+    bucket_name="cifar100bucket",
+    project="Hirundo-global",
+    credentials_json=json.loads(os.environ["GCP_CREDENTIALS"]),
+)
 test_dataset = OptimizationDataset(
     name="TEST-GCP cifar 100 classification dataset",
-    labelling_type=LabellingType.SingleLabelClassification,
-    dataset_storage=StorageLink(
-        storage_integration=StorageIntegration(
-            name="cifar100bucket",
-            type=StorageTypes.GCP,
-            gcp=StorageGCP(
-                bucket_name="cifar100bucket",
-                project="Hirundo-global",
-                credentials_json=json.loads(os.environ["GCP_CREDENTIALS"]),
-            ),
-        ),
-        path="/pytorch-cifar/data",
+    labeling_type=LabelingType.SINGLE_LABEL_CLASSIFICATION,
+    storage_config=StorageConfig(
+        name="cifar100bucket",
+        type=StorageTypes.GCP,
+        gcp=gcp_bucket,
+    ),
+    data_root_url=gcp_bucket.get_url(path="/pytorch-cifar/data"),
+    labeling_info=HirundoCSV(
+        csv_url=gcp_bucket.get_url(path="/pytorch-cifar/data/cifar100.csv"),
     ),
-    dataset_metadata_path="cifar100.csv",
     classes=cifar100_classes,
 )
 
@@ -139,29 +155,53 @@ print(results)
 
 Object detection example:
 
-```
-from hirundo.dataset_optimization import OptimizationDataset
-from hirundo.enum import LabellingType
-from hirundo.storage import StorageIntegration, StorageLink, StorageTypes
+```python
+from hirundo import (
+    GitRepo,
+    HirundoCSV,
+    LabelingType,
+    OptimizationDataset,
+    StorageGit,
+    StorageConfig,
+    StorageTypes,
+)
 
+git_storage = StorageGit(
+    repo=GitRepo(
+        name="BDD-100k-validation-dataset",
+        repository_url="https://huggingface.co/datasets/hirundo-io/bdd100k-validation-only",
+    ),
+    branch="main",
+)
 test_dataset = OptimizationDataset(
-    name=f"TEST-HuggingFace-BDD-100k-validation-OD-validation-dataset{unique_id}",
-    labelling_type=LabellingType.ObjectDetection,
-    dataset_storage=StorageLink(
-        storage_integration=StorageIntegration(
-            name=f"BDD-100k-validation-dataset{unique_id}",
-            type=StorageTypes.GIT,
-            git=StorageGit(
-                repo=GitRepo(
-                    name=f"BDD-100k-validation-dataset{unique_id}",
-                    repository_url="https://git@hf.co/datasets/hirundo-io/bdd100k-validation-only",
-                ),
-                branch="main",
-            ),
+    name="TEST-HuggingFace-BDD-100k-validation-OD-validation-dataset",
+    labeling_type=LabelingType.OBJECT_DETECTION,
+    storage_config=StorageConfig(
+        name="BDD-100k-validation-dataset",
+        type=StorageTypes.GIT,
+        git=git_storage,
+    ),
+    data_root_url=git_storage.get_url(path="/BDD100K Val from Hirundo.zip/bdd100k"),
+    labeling_info=HirundoCSV(
+        csv_url=git_storage.get_url(
+            path="/BDD100K Val from Hirundo.zip/bdd100k/bdd100k.csv"
         ),
-        path="/BDD100K Val from Hirundo.zip/bdd100k",
     ),
-    dataset_metadata_path="bdd100k.csv",
+    classes=[
+        "traffic light",
+        "traffic sign",
+        "car",
+        "pedestrian",
+        "bus",
+        "truck",
+        "rider",
+        "bicycle",
+        "motorcycle",
+        "train",
+        "other vehicle",
+        "other person",
+        "trailer",
+    ],
 )
 
 test_dataset.run_optimization()
@@ -173,4 +213,4 @@ Note: Currently we only support the main CPython release 3.9, 3.10 and 3.11. PyP
 
 ## Further documentation
 
-To learn about mroe how to use this library, please visit the [http://docs.hirundo.io/](documentation) or see the Google Colab examples.
+To learn more about how to use this library, please visit the [http://docs.hirundo.io/](documentation) or see the Google Colab examples.

hirundo-0.1.16.dist-info/RECORD

@@ -0,0 +1,23 @@
+hirundo/__init__.py,sha256=qKC89bNReZSjGtmf7l3PZD2JoptyVphpsD0Kf2PNXvY,1035
+hirundo/__main__.py,sha256=wcCrL4PjG51r5wVKqJhcoJPTLfHW0wNbD31DrUN0MWI,28
+hirundo/_constraints.py,sha256=gRv7fXwtjPGqYWIhkVYxu1B__3PdlYRqFyDkTpa9f74,1032
+hirundo/_dataframe.py,sha256=sXEEbCNcLi83wyU9ii884YikCzfASo_3nnrDxhuCv7U,758
+hirundo/_env.py,sha256=efX2sjvYlHkFr2Lcstelei67YSTFpVGT0l08ZsfiMuE,622
+hirundo/_headers.py,sha256=3hybpD_X4SODv3cFZPt9AjGY2vvZaag5OKT3z1SHSjA,521
+hirundo/_http.py,sha256=izlnuxStyPugjTAbD8Lo30tA4lZJ5d3kOENNduqrbX4,573
+hirundo/_iter_sse_retrying.py,sha256=U331_wZRIbVzi-jnMqo8bp9jBC8MtFBLEs-X0ZvhSDw,4634
+hirundo/_timeouts.py,sha256=gE58NU0t2e4KgKq2sk5rZcezDJAkgvRIbM5AVYFY6Ho,86
+hirundo/cli.py,sha256=5Tn0eXZGG92BR9HJYUaYozjFbS1t6UTw_I2R0tZBE04,7824
+hirundo/dataset_enum.py,sha256=ZEYBP-lrlVqfNWptlmw7JgLNhCyDirtWWPtoMvtg2AE,531
+hirundo/dataset_optimization.py,sha256=jR4ZOlKKl05jrA4cq9L1IQuKVPJ3ytXkhOJEg6efFqI,31390
+hirundo/dataset_optimization_results.py,sha256=A9YyF5zaZXVtzeDE08I_05v90dhZQADpSjDcS_6eLMc,1129
+hirundo/git.py,sha256=6h1hFPlw5FfYMGWXPCitnTqGICmBKmQtb5qKGe3Icmk,6580
+hirundo/logger.py,sha256=MUqrYp0fBlxWFhGl6P5t19_uqO7T_PNhrLN5bqY3i7s,275
+hirundo/storage.py,sha256=kO-LWlQAM3qTnALEl8s79AiFMYqCG9Sem4MIFQcyvAg,15950
+hirundo/unzip.py,sha256=XJqvt2m5pWR-G-fnzgW75VOdd-K4_Rw2r4wiEhZgKZA,8245
+hirundo-0.1.16.dist-info/licenses/LICENSE,sha256=fusGGjqT2RGlU6kbkaOk7d-gDnsjk17wq67AO0mwBZI,1065
+hirundo-0.1.16.dist-info/METADATA,sha256=CxdCbzafRuVRf1BGsS_tgjodO0g745uuNBl7y4UFMj8,8501
+hirundo-0.1.16.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+hirundo-0.1.16.dist-info/entry_points.txt,sha256=4ZtnA_Nl1Af8fLnHp3lwjbGDEGU1S6ujb_JwtuQ7ZPM,44
+hirundo-0.1.16.dist-info/top_level.txt,sha256=cmyNqrNZOAYxnywJGFI1AJBLe4SkH8HGsfFx6ncdrbI,8
+hirundo-0.1.16.dist-info/RECORD,,

{hirundo-0.1.8.dist-info → hirundo-0.1.16.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.1.0)
+Generator: setuptools (79.0.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

hirundo/enum.py

@@ -1,20 +0,0 @@
-from enum import Enum
-
-
-class LabellingType(str, Enum):
-    """
-    Enum indicate what type of labelling is used for the given dataset.
-    Supported types are:
-    """
-
-    SingleLabelClassification = "SingleLabelClassification"
-    ObjectDetection = "ObjectDetection"
-
-
-class DatasetMetadataType(str, Enum):
-    """
-    Enum indicate what type of metadata is provided for the given dataset.
-    Supported types are:
-    """
-
-    HirundoCSV = "HirundoCSV"

hirundo-0.1.8.dist-info/RECORD

@@ -1,20 +0,0 @@
-hirundo/__init__.py,sha256=EINZmdlmNjdW_dM85wksapRxGL-pPC49OYvKUBRtxQk,707
-hirundo/__main__.py,sha256=wcCrL4PjG51r5wVKqJhcoJPTLfHW0wNbD31DrUN0MWI,28
-hirundo/_constraints.py,sha256=-RAUV9GnCsaT9pLGSqYglKOeK0joPBBexGTo87j5nkI,425
-hirundo/_env.py,sha256=dXUFPeEL1zPe-eBdWD4_WZvlgiY2cpWuVDzf41Qjuto,609
-hirundo/_headers.py,sha256=ggTyBwVT3nGyPidCcmYMX6pv0idzMxCI2S1BJQE-Bbs,253
-hirundo/_http.py,sha256=INrHX7ncpXS9vdyjrske3B5vUKL5ke9SIY6daffahtE,350
-hirundo/_iter_sse_retrying.py,sha256=0u-jJe5vHCZegImKBB1rpI9O1BnN7oWJytdabl34ih4,3345
-hirundo/_timeouts.py,sha256=IfX8-mrLp809-A_xSLv1DhIqZnO-Qvy4FcTtOtvqLog,42
-hirundo/cli.py,sha256=4-pdV483zqRJl8d-R9p_9YOGlehOnoMJzb3XAAdPRb0,6634
-hirundo/dataset_optimization.py,sha256=I2AzkSns_MLwlwI4mGGxaJB6OUG3pv7VJ5uFAtcJdTM,21825
-hirundo/enum.py,sha256=-3w09g-_yRYIMiM8VA_Nb07WoQXf5IjyERTGonzNDs0,457
-hirundo/git.py,sha256=Dbp0ALJYhLDgkmI_5u9iVyE_xEHIxoUTeZdpU8iau_4,4884
-hirundo/logger.py,sha256=MUqrYp0fBlxWFhGl6P5t19_uqO7T_PNhrLN5bqY3i7s,275
-hirundo/storage.py,sha256=xifT6xuFCJpVp5wB-ZZkzKz9HbVcMNrllj10vXlU1vU,9845
-hirundo-0.1.8.dist-info/LICENSE,sha256=fusGGjqT2RGlU6kbkaOk7d-gDnsjk17wq67AO0mwBZI,1065
-hirundo-0.1.8.dist-info/METADATA,sha256=heoP6t876hsxEih-RzaIjGtcLZl8UOpcwExnjQ8thU4,7841
-hirundo-0.1.8.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-hirundo-0.1.8.dist-info/entry_points.txt,sha256=4ZtnA_Nl1Af8fLnHp3lwjbGDEGU1S6ujb_JwtuQ7ZPM,44
-hirundo-0.1.8.dist-info/top_level.txt,sha256=cmyNqrNZOAYxnywJGFI1AJBLe4SkH8HGsfFx6ncdrbI,8
-hirundo-0.1.8.dist-info/RECORD,,