hirundo 0.1.9__py3-none-any.whl → 0.1.18__py3-none-any.whl

{hirundo-0.1.9.dist-info → hirundo-0.1.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: hirundo
-Version: 0.1.9
+Version: 0.1.18
 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"
@@ -50,13 +49,13 @@ Requires-Dist: pytest-asyncio>=0.23.6; extra == "dev"
 Requires-Dist: uv>=0.5.8; extra == "dev"
 Requires-Dist: pre-commit>=3.7.1; extra == "dev"
 Requires-Dist: virtualenv>=20.6.6; extra == "dev"
-Requires-Dist: ruff>=0.8.2; 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-autobuild>=2024.9.3; extra == "docs"
 Requires-Dist: sphinx-click>=5.0.1; extra == "docs"
 Requires-Dist: autodoc_pydantic>=2.2.0; extra == "docs"
 Requires-Dist: furo; extra == "docs"
@@ -64,6 +63,11 @@ 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>=2.2.3; extra == "pandas"
+Provides-Extra: polars
+Requires-Dist: polars>=1.0.0; extra == "polars"
+Dynamic: license-file
 
 # Hirundo
 
@@ -71,40 +75,62 @@ 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 configs include:
-   - Google Cloud (GCP) Storage
-   - Amazon Web Services (AWS) S3
-   - Git LFS (Large File Storage) repositories (e.g. GitHub or HuggingFace)
+
+- Google Cloud (GCP) Storage
+- Amazon Web Services (AWS) S3
+- Git LFS (Large File Storage) repositories (e.g. GitHub or HuggingFace)
+
+Note: This Python package must be used alongside a Hirundo server, either the SaaS platform, a custom VPC deployment or an on-premises installation.
 
 Optimizing a classification dataset
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Currently ``hirundo`` requires a CSV file with the following columns (all columns are required):
-   - ``image_path``: The location of the image within the dataset ``root``
-   - ``label``: The label of the image, i.e. which the class that was annotated for this image
+Currently `hirundo` requires a CSV file with the following columns (all columns are required):
+
+- `image_path`: The location of the image within the dataset `data_root_url`
+- `class_name`: The semantic label, i.e. the class name of the class that the image was annotated as belonging to
+
+And outputs two Pandas DataFrames with the dataset columns as well as:
+
+Suspect DataFrame (filename: `mislabel_suspects.csv`) columns:
 
-And outputs a CSV with the same columns and:
-   - ``suspect_level``: mislabel suspect level
-   - ``suggested_label``: suggested label
-   - ``suggested_label_conf``: suggested label confidence
+- ``suspect_score``: mislabel suspect score
+- ``suspect_level``: mislabel suspect level
+- ``suspect_rank``: mislabel suspect ranking
+- ``suggested_class_name``: suggested semantic label
+- ``suggested_class_conf``: suggested semantic label confidence
+
+Errors and warnings DataFrame (filename: `invalid_data.csv`) columns:
+
+   - ``status``: status message (one of ``NO_LABELS`` / ``MISSING_IMAGE`` / ``INVALID_IMAGE``)
 
 Optimizing an object detection (OD) dataset
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Currently ``hirundo`` requires a CSV file with the following columns (all columns are required):
-   - ``image_path``: The location of the image within the dataset ``root``
-   - ``bbox_id``: The index of the bounding box within the dataset. Used to indicate label suspects
-   - ``label``: The label of the image, i.e. which the class that was annotated for this image
-   - ``x1``, ``y1``, ``x2``, ``y2``: The bounding box coordinates of the object within the image
 
-And outputs a CSV with the same columns and:
-   - ``suspect_level``: object mislabel suspect level
-   - ``suggested_label``: suggested object label
-   - ``suggested_label_conf``: suggested object label confidence
+- ``image_path``: The location of the image within the dataset ``data_root_url``
+- ``object_id``: The ID of the bounding box within the dataset. Used to indicate object suspects
+- ``class_name``: Object semantic label, i.e. the class name of the object that was annotated
+- ``xmin``: leftmost horizontal pixel coordinate of the object's bounding box
+- ``ymin``: uppermost vertical pixel coordinate of the object's bounding box
+- ``xmax``: rightmost horizontal pixel coordinate of the object's bounding box
+- ``ymax``: lowermost vertical pixel coordinate of the object's bounding box
 
-Note: This Python package must be used alongside a Hirundo server, either the SaaS platform, a custom VPC deployment or an on-premises installation.
 
+And outputs two Pandas DataFrames with the dataset columns as well as:
+
+Suspect DataFrame (filename: `mislabel_suspects.csv`) columns:
+
+- ``suspect_score``: object mislabel suspect score
+- ``suspect_level``: object mislabel suspect level
+- ``suspect_rank``: object mislabel suspect ranking
+- ``suggested_class_name``: suggested object semantic label
+- ``suggested_class_conf``: suggested object semantic label confidence
+
+Errors and warnings DataFrame (filename: `invalid_data.csv`) columns:
+   - ``status``: status message (one of ``NO_LABELS`` / ``MISSING_IMAGE`` / ``INVALID_IMAGE`` / ``INVALID_BBOX`` / ``INVALID_BBOX_SIZE``)
 
 ## Installation
 
@@ -113,6 +139,7 @@ You can install the codebase with a simple `pip install hirundo` to install the
 ## Usage
 
 Classification example:
+
 ```python
 from hirundo import (
     HirundoCSV,
@@ -148,7 +175,6 @@ results = test_dataset.check_run()
 print(results)
 ```
 
-
 Object detection example:
 
 ```python
@@ -165,7 +191,7 @@ from hirundo import (
 git_storage = StorageGit(
     repo=GitRepo(
         name="BDD-100k-validation-dataset",
-        repository_url="https://git@hf.co/datasets/hirundo-io/bdd100k-validation-only.git",
+        repository_url="https://huggingface.co/datasets/hirundo-io/bdd100k-validation-only",
     ),
     branch="main",
 )
@@ -183,21 +209,6 @@ test_dataset = OptimizationDataset(
             path="/BDD100K Val from Hirundo.zip/bdd100k/bdd100k.csv"
         ),
     ),
-    classes=[
-        "traffic light",
-        "traffic sign",
-        "car",
-        "pedestrian",
-        "bus",
-        "truck",
-        "rider",
-        "bicycle",
-        "motorcycle",
-        "train",
-        "other vehicle",
-        "other person",
-        "trailer",
-    ],
 )
 
 test_dataset.run_optimization()
@@ -205,8 +216,8 @@ results = test_dataset.check_run()
 print(results)
 ```
 
-Note: Currently we only support the main CPython release 3.9, 3.10 and 3.11. PyPy support may be introduced in the future.
+Note: Currently we only support the main CPython release 3.9, 3.10, 3.11, 3.12 & 3.13. PyPy support may be introduced in the future.
 
 ## Further documentation
 
-To learn more about 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](https://github.com/Hirundo-io/hirundo-client/tree/main/notebooks).

hirundo-0.1.18.dist-info/RECORD

@@ -0,0 +1,25 @@
+hirundo/__init__.py,sha256=1Uy9UZhaZPQQSMfAOJ0A_Of70tM8_MDq-HHdhrmpO6g,1301
+hirundo/__main__.py,sha256=wcCrL4PjG51r5wVKqJhcoJPTLfHW0wNbD31DrUN0MWI,28
+hirundo/_constraints.py,sha256=tgJfvp7ydyXilT8ViNk837rNRlpOVXLLeCSMt_YUUYA,6013
+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/_urls.py,sha256=0C85EbL0T-Bj25vJwjNs_obUG8ROSADpmbFdTAyhzlw,1375
+hirundo/cli.py,sha256=5Tn0eXZGG92BR9HJYUaYozjFbS1t6UTw_I2R0tZBE04,7824
+hirundo/dataset_enum.py,sha256=QnS3fy1OF4wvUtiIAHubKRhc611idS8huopEEolgqEM,1217
+hirundo/dataset_optimization.py,sha256=fXi8MeI0PWwSyc5NuOzCrkgXT_mz24NV-dGOHDPkBR0,31256
+hirundo/dataset_optimization_results.py,sha256=A9YyF5zaZXVtzeDE08I_05v90dhZQADpSjDcS_6eLMc,1129
+hirundo/git.py,sha256=8LVnF4WCjZsxMHoRaVxbLiDAKpGCBEwlcZp7a30n9Zo,6573
+hirundo/labeling.py,sha256=zXQCaqfdaLIG4qbzFGbb94L3FDdRMpdzHwbrDJE07Yk,5006
+hirundo/logger.py,sha256=MUqrYp0fBlxWFhGl6P5t19_uqO7T_PNhrLN5bqY3i7s,275
+hirundo/storage.py,sha256=y7cr_dngkfZq0gKnwWxrSqUXb1SycGpwFRVmS9Cn3h8,15942
+hirundo/unzip.py,sha256=XJqvt2m5pWR-G-fnzgW75VOdd-K4_Rw2r4wiEhZgKZA,8245
+hirundo-0.1.18.dist-info/licenses/LICENSE,sha256=fusGGjqT2RGlU6kbkaOk7d-gDnsjk17wq67AO0mwBZI,1065
+hirundo-0.1.18.dist-info/METADATA,sha256=F_F0-EfUxVVCcgFue_hwCtxfIfmqBlwnpvzELuhMkAc,9302
+hirundo-0.1.18.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+hirundo-0.1.18.dist-info/entry_points.txt,sha256=4ZtnA_Nl1Af8fLnHp3lwjbGDEGU1S6ujb_JwtuQ7ZPM,44
+hirundo-0.1.18.dist-info/top_level.txt,sha256=cmyNqrNZOAYxnywJGFI1AJBLe4SkH8HGsfFx6ncdrbI,8
+hirundo-0.1.18.dist-info/RECORD,,

{hirundo-0.1.9.dist-info → hirundo-0.1.18.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.6.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

hirundo/enum.py

@@ -1,23 +0,0 @@
-from enum import Enum
-
-
-class LabelingType(str, Enum):
-    """
-    Enum indicate what type of labeling is used for the given dataset.
-    Supported types are:
-    """
-
-    SINGLE_LABEL_CLASSIFICATION = "SingleLabelClassification"
-    OBJECT_DETECTION = "ObjectDetection"
-    SPEECH_TO_TEXT = "SpeechToText"
-
-
-class DatasetMetadataType(str, Enum):
-    """
-    Enum indicate what type of metadata is provided for the given dataset.
-    Supported types are:
-    """
-
-    HIRUNDO_CSV = "HirundoCSV"
-    COCO = "COCO"
-    YOLO = "YOLO"

hirundo-0.1.9.dist-info/RECORD

@@ -1,20 +0,0 @@
-hirundo/__init__.py,sha256=U_wcm3e0r1T66OQ7KHlWaOiwlPxf6e4RkTxA5uvaOOA,781
-hirundo/__main__.py,sha256=wcCrL4PjG51r5wVKqJhcoJPTLfHW0wNbD31DrUN0MWI,28
-hirundo/_constraints.py,sha256=gRv7fXwtjPGqYWIhkVYxu1B__3PdlYRqFyDkTpa9f74,1032
-hirundo/_env.py,sha256=dXUFPeEL1zPe-eBdWD4_WZvlgiY2cpWuVDzf41Qjuto,609
-hirundo/_headers.py,sha256=ggTyBwVT3nGyPidCcmYMX6pv0idzMxCI2S1BJQE-Bbs,253
-hirundo/_http.py,sha256=izlnuxStyPugjTAbD8Lo30tA4lZJ5d3kOENNduqrbX4,573
-hirundo/_iter_sse_retrying.py,sha256=U331_wZRIbVzi-jnMqo8bp9jBC8MtFBLEs-X0ZvhSDw,4634
-hirundo/_timeouts.py,sha256=IfX8-mrLp809-A_xSLv1DhIqZnO-Qvy4FcTtOtvqLog,42
-hirundo/cli.py,sha256=4-pdV483zqRJl8d-R9p_9YOGlehOnoMJzb3XAAdPRb0,6634
-hirundo/dataset_optimization.py,sha256=CuSrauzXiSa4kGBREao3nn-vmLVwMKTeHM7yEXesuso,33756
-hirundo/enum.py,sha256=ZEYBP-lrlVqfNWptlmw7JgLNhCyDirtWWPtoMvtg2AE,531
-hirundo/git.py,sha256=zzpEHGqoQXwOBQzNSmyf5lpUMc2FbomPqiokwMc4M8o,6777
-hirundo/logger.py,sha256=MUqrYp0fBlxWFhGl6P5t19_uqO7T_PNhrLN5bqY3i7s,275
-hirundo/storage.py,sha256=RsEmtbn79_iCY7pE1AKcBoAEqzXNkOc_UPUTaxSE0BM,16075
-hirundo-0.1.9.dist-info/LICENSE,sha256=fusGGjqT2RGlU6kbkaOk7d-gDnsjk17wq67AO0mwBZI,1065
-hirundo-0.1.9.dist-info/METADATA,sha256=8jjs7OGtVZZwFmyfdFGoTxC-de-1V6OLFJW26pYOB2E,8363
-hirundo-0.1.9.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-hirundo-0.1.9.dist-info/entry_points.txt,sha256=4ZtnA_Nl1Af8fLnHp3lwjbGDEGU1S6ujb_JwtuQ7ZPM,44
-hirundo-0.1.9.dist-info/top_level.txt,sha256=cmyNqrNZOAYxnywJGFI1AJBLe4SkH8HGsfFx6ncdrbI,8
-hirundo-0.1.9.dist-info/RECORD,,