mapreader 1.3.6__tar.gz → 1.3.8__tar.gz

{mapreader-1.3.6 → mapreader-1.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapreader
-Version: 1.3.6
+Version: 1.3.8
 Summary: A computer vision pipeline for the semantic exploration of maps/images at scale
 Home-page: https://github.com/Living-with-machines/MapReader
 Download-URL: https://github.com/Living-with-machines/MapReader/archive/refs/heads/main.zip

{mapreader-1.3.6 → mapreader-1.3.8}/mapreader/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-08-09T14:10:51+0100",
+ "date": "2024-08-12T15:36:33+0100",
  "dirty": false,
  "error": null,
- "full-revisionid": "5ba6c479346a58dc6d937776c895b30d6c21f833",
- "version": "1.3.6"
+ "full-revisionid": "6eed2e27675ba1e8f50986e52d7ba5c25d95dc49",
+ "version": "1.3.8"
 }
 '''  # END VERSION_JSON
 

{mapreader-1.3.6 → mapreader-1.3.8}/mapreader/annotate/annotator.py

@@ -55,6 +55,8 @@ class Annotator:
         Name of the column in which labels are stored in patch DataFrame, by default "label"
     show_context : bool, optional
         Whether to show context when loading patches, by default False
+    border : bool, optional
+        Whether to add a border around the central patch when showing context, by default False
     auto_save : bool, optional
         Whether to automatically save annotations, by default True
     delimiter : str, optional
@@ -108,6 +110,7 @@ class Annotator:
         patch_paths_col: str = "image_path",
         label_col: str = "label",
         show_context: bool = False,
+        border: bool = False,
         auto_save: bool = True,
         delimiter: str = ",",
         sortby: str | None = None,
@@ -255,6 +258,7 @@ class Annotator:
         self.patch_paths_col = patch_paths_col
         self.annotations_file = annotations_file
         self.show_context = show_context
+        self.border = border
         self.auto_save = auto_save
         self.username = username
         self.task_name = task_name
@@ -452,7 +456,7 @@ class Annotator:
 
         self.navbox = widgets.VBox([widgets.HBox([prev_btn, next_btn])])
 
-    def get_queue(
+    def _get_queue(
         self, as_type: str | None = "list"
     ) -> list[int] | (pd.Index | pd.Series):
         """
@@ -520,7 +524,7 @@ class Annotator:
             return indices
         return queue_df
 
-    def get_context(self):
+    def _get_context(self):
         """
         Provides the surrounding context for the patch to be annotated.
 
@@ -531,15 +535,21 @@ class Annotator:
             context.
         """
 
-        def get_path(image_path, dim=True):
+        def get_square(image_path, dim=True, border=False):
             # Resize the image
             im = Image.open(image_path)
 
             # Dim the image
-            if dim in [True, "True"]:
+            if dim in ["True", True]:
                 im_array = np.array(im)
                 im_array = 256 - (256 - im_array) * 0.4  # lighten image
                 im = Image.fromarray(im_array.astype(np.uint8))
+
+            if border in ["True", True] and self.border:
+                w, h = im.size
+                im = ImageOps.expand(im, border=2, fill="red")
+                im = im.resize((w, h))
+
             return im
 
         def get_empty_square(patch_size: tuple[int, int]):
@@ -593,7 +603,10 @@ class Annotator:
 
         # derive ids from items
         ids = [x.index[0] if len(x.index) == 1 else None for x in items]
-        ids = [x != ix for x in ids]
+        # list of booleans, True if not the current patch, False if the current patch
+        # used for dimming the surrounding patches and adding a border to the current patch
+        dim_bools = [x != ix for x in ids]
+        border_bools = [x == ix for x in ids]
 
         # derive images from items
         image_paths = [
@@ -601,14 +614,16 @@ class Annotator:
         ]
 
         # zip them
-        image_list = list(zip(image_paths, ids))
+        image_list = list(zip(image_paths, dim_bools, border_bools))
 
         # split them into rows
         per_row = len(deltas)
         images = [
             [
-                get_path(x[0], dim=x[1]) if x[0] else get_empty_square((width, height))
-                for x in lst
+                get_square(image_path, dim=dim, border=border)
+                if image_path
+                else get_empty_square((width, height))
+                for image_path, dim, border in lst
             ]
             for lst in array_split(image_list, per_row)
         ]
@@ -641,6 +656,7 @@ class Annotator:
     def annotate(
         self,
         show_context: bool | None = None,
+        border: bool | None = None,
         sortby: str | None = None,
         ascending: bool | None = None,
         min_values: dict | None = None,
@@ -648,6 +664,7 @@ class Annotator:
         surrounding: int | None = None,
         resize_to: int | None = None,
         max_size: int | None = None,
+        show_vals: list[str] | None = None,
     ) -> None:
         """Annotate at the patch-level of the current patch.
         Renders the annotation interface for the first image.
@@ -657,6 +674,9 @@ class Annotator:
         show_context : bool or None, optional
             Whether or not to display the surrounding context for each image.
             Default is None.
+        border : bool or None, optional
+            Whether or not to display a border around the image (when using `show_context`).
+            Default is None.
         sortby : str or None, optional
             Name of the column to use to sort the patch DataFrame, by default None.
             Default sort order is ``ascending=True``. Pass ``ascending=False`` keyword argument to sort in descending order.
@@ -677,12 +697,18 @@ class Annotator:
         max_size : int or None, optional
             The size in pixels for the longest side to which constrain each
             patch image. Default: 100.
+        resize_to : int or None, optional
+            The size in pixels for the longest side to which resize each patch image. Default: None.
+        show_vals : list[str] or None, optional
+            List of column names to show in the display. By default, None.
 
         Notes
         -----
         This method is a wrapper for the
         :meth:`~.annotate.annotator.Annotate._annotate` method.
         """
+        if border is not None:
+            self.border = border
         if sortby is not None:
             self._sortby = sortby
         if ascending is not None:
@@ -693,8 +719,10 @@ class Annotator:
         if max_values is not None:
             self._max_values = max_values
 
+        self.show_vals = show_vals
+
         # re-set up queue using new min/max values
-        self._queue = self.get_queue()
+        self._queue = self._get_queue()
 
         self._annotate(
             show_context=show_context,
@@ -743,7 +771,7 @@ class Annotator:
             self.max_size = max_size
 
         # re-set up queue
-        self._queue = self.get_queue()
+        self._queue = self._get_queue()
 
         if self._filter_for is not None:
             print(f"[INFO] Filtering for: {self._filter_for}")
@@ -767,7 +795,7 @@ class Annotator:
             Previous index, current index, and path of the current image.
         """
         if self.current_index == len(self._queue):
-            self.render_complete()
+            self._render_complete()
             return
 
         self.previous_index = self.current_index
@@ -777,7 +805,7 @@ class Annotator:
 
         img_path = self.patch_df.at[ix, self.patch_paths_col]
 
-        self.render()
+        self._render()
         return self.previous_index, self.current_index, img_path
 
     def _prev_example(self, *_) -> tuple[int, int, str]:
@@ -790,7 +818,7 @@ class Annotator:
             Previous index, current index, and path of the current image.
         """
         if self.current_index == len(self._queue):
-            self.render_complete()
+            self._render_complete()
             return
 
         if self.current_index > 0:
@@ -801,10 +829,10 @@ class Annotator:
 
         img_path = self.patch_df.at[ix, self.patch_paths_col]
 
-        self.render()
+        self._render()
         return self.previous_index, self.current_index, img_path
 
-    def render(self) -> None:
+    def _render(self) -> None:
         """
         Displays the image at the current index in the annotation interface.
 
@@ -817,7 +845,7 @@ class Annotator:
         """
         # Check whether we have reached the end
         if self.current_index >= len(self) - 1:
-            self.render_complete()
+            self._render_complete()
             return
 
         ix = self._queue[self.current_index]
@@ -841,7 +869,7 @@ class Annotator:
             clear_output(wait=True)
             image = self.get_patch_image(ix)
             if self.show_context:
-                context = self.get_context()
+                context = self._get_context()
                 self._context_image = context
                 display(context.convert("RGB"))
             else:
@@ -852,6 +880,22 @@ class Annotator:
                 text = f'<p><a href="{url}" target="_blank">Click to see entire map.</a></p>'
                 add_ins += [widgets.HTML(text)]
 
+            if self.show_vals:
+                patch_info = []
+                for col in self.show_vals:
+                    if col in self.patch_df.columns:
+                        val = self.patch_df.at[ix, col]
+                        if isinstance(val, float):
+                            val = f"{val:.4g}"
+                        patch_info.append(f"<b>{col}</b>: {val}")
+                add_ins += [
+                    widgets.HTML(
+                        '<p style="text-align: center">'
+                        + "<br>".join(patch_info)
+                        + "</p>"
+                    )
+                ]
+
             value = self.current_index + 1 if self.current_index else 1
             description = f"{value} / {len(self._queue)}"
             add_ins += [
@@ -983,7 +1027,7 @@ class Annotator:
         _filter = ~self.patch_df[self.label_col].isna()
         return self.patch_df[_filter]
 
-    def render_complete(self):
+    def _render_complete(self):
         """
         Renders the completion message once all images have been annotated.
 

{mapreader-1.3.6 → mapreader-1.3.8}/mapreader/classify/load_annotations.py

@@ -25,6 +25,7 @@ class AnnotationsLoader:
 
     def __init__(self):
         self.annotations = pd.DataFrame()
+        self.labels_map = {}
         self.reviewed = pd.DataFrame()
         self.patch_paths_col = None
         self.label_col = None
@@ -33,6 +34,7 @@ class AnnotationsLoader:
     def load(
         self,
         annotations: str | pd.DataFrame,
+        labels_map: dict | None = None,
         delimiter: str | None = ",",
         images_dir: str | None = None,
         remove_broken: bool | None = True,
@@ -52,6 +54,8 @@ class AnnotationsLoader:
         annotations : Union[str, pd.DataFrame]
             The annotations.
             Can either be the path to a csv file or a pandas.DataFrame.
+        labels_map : Optional[dict], optional
+            A dictionary mapping labels to indices. If not provided, labels will be mapped to indices based on the order in which they appear in the annotations dataframe. By default None.
         delimiter : Optional[str], optional
             The delimiter to use when loading the csv file as a dataframe, by default ",".
         images_dir : Optional[str], optional
@@ -132,8 +136,25 @@ class AnnotationsLoader:
 
         self.unique_labels = self.annotations[self.label_col].unique().tolist()
 
-        labels_map = {i: label for i, label in enumerate(self.unique_labels)}
-        self.labels_map = labels_map
+        # if labels_map is explicitly provided
+        if labels_map:
+            self.labels_map = dict(
+                sorted(labels_map.items())
+            )  # sort labels_map by keys
+            if not set(self.unique_labels).issubset(set(labels_map.values())):
+                raise ValueError(
+                    "[ERROR] There are label(s) in the annotations that are not in the labels map. Please check the labels_map."
+                )
+        # if inferring labels_map
+        else:
+            if append:
+                for label in self.unique_labels:
+                    if label not in self.labels_map.values():
+                        self.labels_map[len(self.labels_map)] = label
+            else:
+                # reset labels map
+                labels_map = {i: label for i, label in enumerate(self.unique_labels)}
+                self.labels_map = labels_map
 
         self.annotations["label_index"] = self.annotations[self.label_col].apply(
             self._get_label_index
@@ -861,7 +882,8 @@ Please check your image paths and update them if necessary.'
         Used to generate the ``label_index`` column.
 
         """
-        return self.unique_labels.index(label)
+        index_map = {v: k for k, v in self.labels_map.items()}
+        return index_map[label]
 
     def __str__(self):
         print(f"[INFO] Number of annotations:   {len(self.annotations)}\n")

{mapreader-1.3.6 → mapreader-1.3.8}/mapreader.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapreader
-Version: 1.3.6
+Version: 1.3.8
 Summary: A computer vision pipeline for the semantic exploration of maps/images at scale
 Home-page: https://github.com/Living-with-machines/MapReader
 Download-URL: https://github.com/Living-with-machines/MapReader/archive/refs/heads/main.zip