Added rtd preview action

.github/pull-request-links.yaml

@@ -0,0 +1,16 @@
+name: readthedocs/actions
+on:
+  pull_request_target:
+    types:
+      - opened
+
+permissions:
+  pull-requests: write
+
+jobs:
+  pull-request-links:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: readthedocs/actions/preview@v1
+        with:
+          project-slug: "cleanvision"

docs/source/cleanvision/issue_managers/index.rst

@@ -1,5 +1,6 @@
 Issue Managers
 ==============
+Contains modules for managing data issues of a particular type in Imagelab.
 
 .. automodule:: cleanvision.issue_managers
    :autosummary:

examples/custom_issue_manager.py

@@ -25,13 +25,13 @@ class CustomIssueManager(IssueManager):
 
     def __init__(self) -> None:
         super().__init__()
-        self.params = self.get_default_params()
+        self.params = self._get_default_params()
 
-    def get_default_params(self) -> Dict[str, Any]:
+    def _get_default_params(self) -> Dict[str, Any]:
         return {"threshold": 0.4}
 
-    def update_params(self, params: Dict[str, Any]) -> None:
-        self.params = self.get_default_params()
+    def _update_params(self, params: Dict[str, Any]) -> None:
+        self.params = self._get_default_params()
         non_none_params = {k: v for k, v in params.items() if v is not None}
         self.params = {**self.params, **non_none_params}
 
@@ -65,7 +65,7 @@ def find_issues(
         assert imagelab_info is not None
         assert dataset is not None
 
-        self.update_params(params)
+        self._update_params(params)
 
         raw_scores = []
         for idx in tqdm(dataset.index):

src/cleanvision/issue_managers/duplicate_issue_manager.py

@@ -47,21 +47,23 @@ def compute_hash_wrapper(args: Dict[str, Any]) -> Dict[str, Union[str, int]]:
 
 @register_issue_manager(DUPLICATE)
 class DuplicateIssueManager(IssueManager):
+    """Checks for exact and near duplicates in images."""
+
     issue_name: str = DUPLICATE
     visualization: str = "image_sets"
 
     def __init__(self) -> None:
         super().__init__()
         self.issue_types: List[str] = []
-        self.params = self.get_default_params()
+        self.params = self._get_default_params()
 
-    def get_default_params(self) -> Dict[str, Any]:
+    def _get_default_params(self) -> Dict[str, Any]:
         return {
             IssueType.EXACT_DUPLICATES.value: {"hash_type": "md5"},
             IssueType.NEAR_DUPLICATES.value: {"hash_type": "phash", "hash_size": 8},
         }
 
-    def update_params(self, params: Dict[str, Any]) -> None:
+    def _update_params(self, params: Dict[str, Any]) -> None:
         for issue_type in self.params:
             non_none_params = {
                 k: v for k, v in params.get(issue_type, {}).items() if v is not None
@@ -102,13 +104,34 @@ def find_issues(
         n_jobs: Optional[int] = None,
         **kwargs: Any,
     ) -> None:
+        """Finds exact and near duplicates in the images
+
+        Parameters
+        ----------
+        params: Dict[str, Any], optional
+            Dict of custom hyperparameters for checking duplicate issues. Default value is empty.
+        dataset: Dataset
+            Dataset object on which to run the duplicate checks
+        imagelab_info: Dict[str, Any]
+            imagelab.info dict containing computations for reuse
+        n_jobs: int
+            Number of processing threads used by multiprocessing.
+            Default None sets to the number of cores on your CPU (physical cores if you have psutil package installed, otherwise logical cores).
+            Set this to 1 to disable parallel processing (if its causing issues). Windows users may see a speed-up with n_jobs=1.
+            For :py:class:`TorchDataset` this is set to 1.
+        kwargs: Any
+
+        Returns
+        -------
+
+        """
         super().find_issues(**kwargs)
         assert params is not None
         assert imagelab_info is not None
         assert dataset is not None
 
         self.issue_types = list(params.keys())
-        self.update_params(params)
+        self._update_params(params)
 
         to_compute = self._get_issue_types_to_compute(self.issue_types, imagelab_info)
         issue_type_hash_mapping: Dict[str, Any] = {

src/cleanvision/issue_managers/image_property_issue_manager.py

@@ -54,10 +54,10 @@ class ImagePropertyIssueManager(IssueManager):
     def __init__(self) -> None:
         super().__init__()
         self.issue_types: List[str] = []
-        self.params = self.get_default_params()
+        self.params = self._get_default_params()
         self.image_properties = self._get_image_properties()
 
-    def get_default_params(self) -> Dict[str, Any]:
+    def _get_default_params(self) -> Dict[str, Any]:
         return {
             IssueType.DARK.value: {"threshold": 0.37},
             IssueType.LIGHT.value: {"threshold": 0.05},
@@ -70,7 +70,7 @@ def get_default_params(self) -> Dict[str, Any]:
             IssueType.GRAYSCALE.value: {},
         }
 
-    def update_params(self, params: Dict[str, Any]) -> None:
+    def _update_params(self, params: Dict[str, Any]) -> None:
         for issue_type in self.params:
             non_none_params = {
                 k: v for k, v in params.get(issue_type, {}).items() if v is not None
@@ -132,7 +132,7 @@ def find_issues(
         additional_set = self._get_additional_to_compute_set(self.issue_types)
         self.issue_types = self.issue_types + additional_set
 
-        self.update_params(params)
+        self._update_params(params)
 
         agg_computations = pd.DataFrame(index=dataset.index)
         agg_computations = self._add_prev_computations(agg_computations, imagelab_info)

src/cleanvision/utils/base_issue_manager.py

@@ -49,12 +49,12 @@ def find_issues(self, **kwargs: Any) -> None:
         return
 
     @abstractmethod
-    def get_default_params(self) -> Dict[str, Any]:
+    def _get_default_params(self) -> Dict[str, Any]:
         """Returns default params to be used by the issue_manager"""
         raise NotImplementedError
 
     @abstractmethod
-    def update_params(self, params: Dict[str, Any]) -> None:
+    def _update_params(self, params: Dict[str, Any]) -> None:
         """Sets params for an issue manager. Default params will be overridden by user provided params"""
         raise NotImplementedError
 

tests/test_duplicate_issue_manager.py

@@ -47,7 +47,7 @@ def test_set_params(self, params, expected_params, issue_manager):
         1. If no params are specified for an issue_type, default params are used
         2. If params are specified, those specific params are updated, for the remaining ones default values are used
         """
-        issue_manager.update_params(params)
+        issue_manager._update_params(params)
         assert issue_manager.params == expected_params
 
     @pytest.mark.parametrize(

tests/test_image_property_issue_manager.py

@@ -62,7 +62,7 @@ def test_set_params(self, params, expected_params, issue_manager):
         issue_manager: instance of ImagePropertyIssueManager
 
         """
-        issue_manager.update_params(params)
+        issue_manager._update_params(params)
         assert issue_manager.params == expected_params
 
     @pytest.mark.parametrize(