included missing docs for mango disease

.github/workflows/ci.yml

@@ -1,6 +1,6 @@
 name: ci
 
-on: [push, pull_request]
+on: [push, pull_request, workflow_dispatch]
 
 jobs:
   test:
@@ -31,10 +31,6 @@ jobs:
           uv venv --python  ${{ matrix.python-version }}
           uv sync --dev
 
-      - name: Run pre-commit
-        continue-on-error: true
-        run: make pre-commit
-
       - name: Run tests
         # For example, using `pytest`
         run: make test

.github/workflows/docs.yml

@@ -1,5 +1,5 @@
 name: docs
-on: [push, pull_request]
+on: [push, pull_request, workflow_dispatch]
 
 permissions:
   contents: read
@@ -14,8 +14,8 @@ concurrency:
 jobs:
   deploy:
     environment:
-        name: documenation
-        url: ${{steps.deployement.outputs.page_url}}
+        name: documentation
+        url: ${{steps.deployment.outputs.page_url}}
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
@@ -25,7 +25,7 @@ jobs:
           git config user.email 41898282+github-actions[bot]@users.noreply.github.com
       - uses: actions/setup-python@v5
         with:
-          python-version: 3.x
+          python-version: '3.12'
       - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
       - uses: actions/cache@v4
         with:

.github/workflows/release_draft.yml

@@ -13,6 +13,7 @@ on:
   # pull_request_target event is required for autolabeler to support PRs from forks
   # pull_request_target:
   #   types: [opened, reopened, synchronize]
+  workflow_dispatch:
 
 permissions:
   contents: read

.github/workflows/update-datasets.yml

@@ -9,6 +9,7 @@ on:
       - agml/_assets/public_datasources.json
     branches:
       - dev
+  workflow_dispatch:
 
 permissions: write-all
 
@@ -18,18 +19,18 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       with:
         ref: dev
-    - name: Set up Python 3.8
-      uses: actions/setup-python@v3
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v5
       with:
-        python-version: "3.8"
+        python-version: "3.10"
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip
+        python -m pip install --upgrade pip uv
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-        python3 setup.py install
+        uv pip install --system -e .
     - name: Configure Git
       run: |
         git config user.name 'github-actions[bot]'

README.md

@@ -204,6 +204,7 @@ to your desired specification.
 [iNatAg](https://github.com/Project-AgML/AgML/blob/main/docs/datasets/iNatAg.md) | Image Classification | 4720903 |
 [iNatAg-mini](https://github.com/Project-AgML/AgML/blob/main/docs/datasets/iNatAg-mini.md) | Image Classification | 560844 |
 [soybean_insect_classification](https://github.com/Project-AgML/AgML/blob/main/docs/datasets/soybean_insect_classification.md) | Image Classification | 6410 |
+[mango_leaf_disease_classification](https://github.com/Project-AgML/AgML/blob/main/docs/datasets/mango_leaf_disease_classification.md) | Image Classification | 4000 |
 
 ## iNatAg and iNatAg-mini
 
@@ -249,4 +250,4 @@ a bug or feature that you would like to see implemented, please don't hesitate t
 See the [contributing guidelines](/CONTRIBUTING.md) for more information.
 
 ## Funding
-This project is partly funded by the [National AI Institute for Food Systems](https://aifs.ucdavis.edu).
+This project is partly funded by the [National AI Institute for Food Systems](https://aifs.ucdavis.ed

agml/data/public.py

@@ -79,6 +79,16 @@ def apply_filters(self, **filters):
         if not filters:
             return self
 
+        # Validate filters against known metadata keys
+        valid_keys = {
+            'location', 'n_images', 'num_images', 'ml_task', 'ag_task', 
+            'sensor_modality', 'real_synthetic', 'platform', 'input_data_format', 
+            'annotation_format', 'docs_url', 'classes', 'parent_dataset'
+        }
+        for key in filters:
+            if key not in valid_keys:
+                raise ValueError(f"Invalid filter: '{key}'. Must be one of {valid_keys}")
+
         filtered_sources = []
         for source, meta in self._sources.items():
             if self._matches(meta, filters):
@@ -95,7 +105,8 @@ def _matches(self, meta, filters):
                     desired = desired.lower()
                 except ValueError:
                     raise ValueError("Location filter must be in the format 'key:value'.")
-                if meta.get('location', {}).get(loc_key) != desired:
+                loc_data = meta.get('location') or {}
+                if loc_data.get(loc_key) != desired:
                     return False
             elif key in ['n_images', 'num_images']:
                 try:
@@ -142,7 +153,7 @@ def __repr__(self):
             table.add_row(
                 source_name,
                 meta.get("ml_task", "N/A"),  # Handle missing 'ml_task'
-                f"{meta['location']['continent']}, {meta['location']['country']}" if "location" in meta else "N/A",
+                f"{meta['location']['continent']}, {meta['location']['country']}" if meta.get("location") else "N/A",
                 str(meta.get("n_images", "N/A")),  # prints N/A if number of images are not there.
             )
 

agml/utils/data.py

@@ -132,6 +132,8 @@ def copyright_print(name, location=None):
     # Create license message
     if not license_info:  # Handle empty license
         license_msg = Text("License: None specified", style="yellow")
+        license_more_info = ""
+        license_url = ""
     else:
         license_msg = Text.assemble(("This dataset is licensed under ", "bold cyan"), (f"{license_info}", "green"))
         if license_info in _LICENSE_TO_URL:

docs/datasets/mango_leaf_disease_classification.md

@@ -0,0 +1,24 @@
+
+# `mango_leaf_disease_classification`
+
+## Dataset Metadata
+
+| Metadata | Value |
+| --- | --- |
+| **Machine Learning Task** | image_classification |
+| **Agricultural Task** | disease_classification |
+| **Location** | Bangladesh, Asia |
+| **Sensor Modality** | RGB |
+| **Real or Synthetic** | real |
+| **Platform** | handheld |
+| **Input Data Format** | JPG |
+| **Annotation Format** | directory_names |
+| **Number of Images** | 4000 |
+| **Documentation** | https://data.mendeley.com/datasets/hxsnvwty3r/1 |
+| **Stats/Mean** | [0.665, 0.690, 0.689] |
+| **Stats/Standard Deviation** | [0.197, 0.186, 0.257] |
+| **Classes** | Anthracnose, Bacterial_Canker, Cutting_Weevil, Die_Back, Gall_Midge, Healthy, Powdery_Mildew, Sooty_Mold |
+
+## Examples
+
+![Example Images for mango_leaf_disease_classification](https://github.com/Project-AgML/AgML/blob/main/docs/sample_images/mango_leaf_disease_classification_examples.png)