mapreader 1.3.1__tar.gz → 1.3.2__tar.gz

{mapreader-1.3.1 → mapreader-1.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapreader
-Version: 1.3.1
+Version: 1.3.2
 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
@@ -29,7 +29,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: matplotlib<4.0.0,>=3.5.0
 Requires-Dist: numpy<2.0.0,>=1.21.5
-Requires-Dist: pandas<2.0.0,>=1.3.4
+Requires-Dist: pandas>=2.0.0
 Requires-Dist: pyproj<4.0.0,>=3.2.0
 Requires-Dist: azure-storage-blob<13.0.0,>=12.9.0
 Requires-Dist: aiohttp<4.0.0,>=3.8.1
@@ -53,10 +53,11 @@ Requires-Dist: simplekml<2.0.0,>=1.3.6
 Requires-Dist: versioneer>=0.28
 Requires-Dist: tqdm<5.0.0
 Requires-Dist: torchinfo<2.0.0
-Requires-Dist: openpyxl<4.0.0
+Requires-Dist: openpyxl<4.0.0,>=3.1.2
 Requires-Dist: geopandas<1.0.0
 Requires-Dist: pyogrio>=0.7.2
 Requires-Dist: cartopy>=0.22.0
+Requires-Dist: joblib>=1.4.0
 Provides-Extra: dev
 Requires-Dist: pytest<9.0.0; extra == "dev"
 Requires-Dist: pytest-cov<6.0.0,>=4.1.0; extra == "dev"

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader/__init__.py

@@ -31,3 +31,8 @@ from . import _version
 __version__ = _version.get_versions()["version"]
 
 from mapreader.load import geo_utils
+
+import mapreader
+
+def print_version():
+    print(mapreader.__version__)

mapreader-1.3.2/mapreader/__main__.py

@@ -0,0 +1,6 @@
+from __future__ import annotations
+
+from . import print_version
+
+if __name__ == "__main__":
+    print_version()

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-05-03T13:32:40+0100",
+ "date": "2024-05-15T11:10:51+0100",
  "dirty": false,
  "error": null,
- "full-revisionid": "3d7ab10b0f7bc0833e122a65a4d4bd608ca62fcd",
- "version": "1.3.1"
+ "full-revisionid": "282b8733c2c83412b979c2c234adda1432691862",
+ "version": "1.3.2"
 }
 '''  # END VERSION_JSON
 

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader/annotate/annotator.py

@@ -27,7 +27,7 @@ _CENTER_LAYOUT = widgets.Layout(
 )
 
 
-class Annotator(pd.DataFrame):
+class Annotator:
     """
     Annotator class for annotating patches with labels.
 
@@ -227,28 +227,29 @@ class Annotator(pd.DataFrame):
                 delimiter=delimiter,
             )
 
-        # initiate as a DataFrame
-        super().__init__(patch_df)
-
         ## pixel_bounds = x0, y0, x1, y1
-        self["min_x"] = self.pixel_bounds.apply(lambda x: x[0])
-        self["min_y"] = self.pixel_bounds.apply(lambda x: x[1])
-        self["max_x"] = self.pixel_bounds.apply(lambda x: x[2])
-        self["max_y"] = self.pixel_bounds.apply(lambda x: x[3])
+        patch_df["min_x"] = patch_df["pixel_bounds"].apply(lambda x: x[0])
+        patch_df["min_y"] = patch_df["pixel_bounds"].apply(lambda x: x[1])
+        patch_df["max_x"] = patch_df["pixel_bounds"].apply(lambda x: x[2])
+        patch_df["max_y"] = patch_df["pixel_bounds"].apply(lambda x: x[3])
 
         # Sort by sortby column if provided
         if isinstance(sortby, str):
-            if sortby in self.columns:
+            if sortby in patch_df.columns:
                 self._sortby = sortby
                 self._ascending = ascending
             else:
-                raise ValueError(f"[ERROR] {sortby} is not a column in the DataFrame.")
+                raise ValueError(
+                    f"[ERROR] {sortby} is not a column in the patch DataFrame."
+                )
         elif sortby is not None:
             raise ValueError("[ERROR] ``sortby`` must be a string or None.")
         else:
             self._sortby = None
             self._ascending = True
 
+        self.patch_df = patch_df
+
         self._labels = labels
         self.label_col = label_col
         self.patch_paths_col = patch_paths_col
@@ -299,6 +300,9 @@ class Annotator(pd.DataFrame):
         # Setup queue
         self._queue = []
 
+    def __len__(self):
+        return len(self.patch_df)
+
     @staticmethod
     def _load_dataframes(
         patch_paths: str | None = None,
@@ -499,7 +503,7 @@ class Annotator(pd.DataFrame):
 
             return True
 
-        queue_df = self.copy(deep=True)
+        queue_df = self.patch_df.copy(deep=True)
         queue_df = queue_df[queue_df[self.label_col].isna()]  # only unlabelled
         queue_df["eligible"] = queue_df.apply(check_eligibility, axis=1)
 
@@ -562,20 +566,20 @@ class Annotator(pd.DataFrame):
 
         ix = self._queue[self.current_index]
 
-        min_x = self.at[ix, "min_x"]
-        min_y = self.at[ix, "min_y"]
+        min_x = self.patch_df.at[ix, "min_x"]
+        min_y = self.patch_df.at[ix, "min_y"]
 
         # cannot assume all patches are same size
         try:
-            height, width, _ = self.at[ix, "shape"]
+            height, width, _ = self.patch_df.at[ix, "shape"]
         except KeyError:
-            im_path = self.at[ix, self.patch_paths_col]
+            im_path = self.patch_df.at[ix, self.patch_paths_col]
             im = Image.open(im_path)
             height = im.height
             width = im.width
 
-        current_parent = self.at[ix, "parent_id"]
-        parent_frame = self.query(f"parent_id=='{current_parent}'")
+        current_parent = self.patch_df.at[ix, "parent_id"]
+        parent_frame = self.patch_df.query(f"parent_id=='{current_parent}'")
 
         deltas = list(range(-self.surrounding, self.surrounding + 1))
         y_and_x = list(
@@ -770,7 +774,7 @@ class Annotator(pd.DataFrame):
 
         ix = self._queue[self.current_index]
 
-        img_path = self.at[ix, self.patch_paths_col]
+        img_path = self.patch_df.at[ix, self.patch_paths_col]
 
         self.render()
         return self.previous_index, self.current_index, img_path
@@ -794,7 +798,7 @@ class Annotator(pd.DataFrame):
 
         ix = self._queue[self.current_index]
 
-        img_path = self.at[ix, self.patch_paths_col]
+        img_path = self.patch_df.at[ix, self.patch_paths_col]
 
         self.render()
         return self.previous_index, self.current_index, img_path
@@ -826,7 +830,7 @@ class Annotator(pd.DataFrame):
                 # disable skip button when at last example
                 button.disabled = self.current_index >= len(self) - 1
             elif button.description != "submit":
-                if self.at[ix, self.label_col] == button.description:
+                if self.patch_df.at[ix, self.label_col] == button.description:
                     button.icon = "check"
                 else:
                     button.icon = ""
@@ -842,8 +846,8 @@ class Annotator(pd.DataFrame):
             else:
                 display(image.convert("RGB"))
             add_ins = []
-            if "url" in self.loc[ix].keys():
-                url = self.at[ix, "url"]
+            if "url" in self.patch_df.loc[ix].keys():
+                url = self.patch_df.at[ix, "url"]
                 text = f'<p><a href="{url}" target="_blank">Click to see entire map.</a></p>'
                 add_ins += [widgets.HTML(text)]
 
@@ -881,7 +885,7 @@ class Annotator(pd.DataFrame):
         PIL.Image
             A PIL.Image object of the image at the given index.
         """
-        image_path = self.at[ix, self.patch_paths_col]
+        image_path = self.patch_df.at[ix, self.patch_paths_col]
         image = Image.open(image_path)
 
         if self.resize_to is not None:
@@ -907,7 +911,7 @@ class Annotator(pd.DataFrame):
         """
         # ix = self.iloc[self.current_index].name
         ix = self._queue[self.current_index]
-        self.at[ix, self.label_col] = annotation
+        self.patch_df.at[ix, self.label_col] = annotation
         if self.auto_save:
             self._auto_save()
         self._next_example()
@@ -950,7 +954,9 @@ class Annotator(pd.DataFrame):
             A dataframe containing the labelled images and their associated
             label index.
         """
-        filtered_df = self[self[self.label_col].notna()].copy(deep=True)
+        filtered_df = self.patch_df[self.patch_df[self.label_col].notna()].copy(
+            deep=True
+        )
 
         # force image_id to be index (incase of integer index)
         # TODO: Force all indices to be integers so this is not needed
@@ -973,8 +979,8 @@ class Annotator(pd.DataFrame):
 
     @property
     def filtered(self) -> pd.DataFrame:
-        _filter = ~self[self.label_col].isna()
-        return self[_filter]
+        _filter = ~self.patch_df[self.label_col].isna()
+        return self.patch_df[_filter]
 
     def render_complete(self):
         """

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader/classify/classifier.py

@@ -1367,7 +1367,7 @@ Use ``add_criterion`` to define one."
     def _initialize_model(
         self,
         model_name: str,
-        pretrained: bool | None = True,
+        weights: str | None = "DEFAULT",
         last_layer_num_classes: str | int | None = "default",
     ) -> tuple[Any, int, bool]:
         """
@@ -1378,8 +1378,9 @@ Use ``add_criterion`` to define one."
         ----------
         model_name : str
             Name of a PyTorch model. See https://pytorch.org/vision/0.8/models.html for options.
-        pretrained : bool, optional
-            Use pretrained version, by default ``True``
+        weights : str, optional
+            Weights to load into the model. If ``"DEFAULT"``, loads the default weights for the chosen model.
+            By default, ``"DEFAULT"``.
         last_layer_num_classes : str or int, optional
             Number of elements in the last layer. If ``"default"``, sets it to
             the number of classes. By default, ``"default"``.
@@ -1408,8 +1409,7 @@ Use ``add_criterion`` to define one."
 
         # Initialize these variables which will be set in this if statement.
         # Each of these variables is model specific.
-        model_dw = models.__getattribute__(model_name)
-        model_dw = model_dw(pretrained)
+        model_dw = models.get_model(model_name, weights=weights)
         input_size = (224, 224)
         is_inception = False
 

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader/classify/load_annotations.py

@@ -395,7 +395,9 @@ Please check your image paths and update them if necessary.'
                 )
                 iter_ids.append(annots2review.iloc[image_idx].name)
                 # Add to reviewed
-                self.reviewed = self.reviewed.append(annots2review.iloc[image_idx])
+                self.reviewed = pd.concat(
+                    [self.reviewed, annots2review.iloc[image_idx : image_idx + 1]]
+                )
                 try:
                     self.reviewed.drop_duplicates(subset=[deduplicate_col])
                 except Exception:
@@ -416,9 +418,14 @@ Please check your image paths and update them if necessary.'
             ]:
                 list_input_ids = user_input_ids.split(",")
                 print(
-                    f"[INFO] Options for labels (or create a new label):{list(self.annotations[self.label_col].unique())}"
+                    f"[INFO] Options for labels:{list(self.annotations[self.label_col].unique())}"
                 )
                 input_label = input("Enter new label:  ")
+                if input_label not in list(self.annotations[self.label_col].unique()):
+                    print(
+                        f'[ERROR] Label "{input_label}" not found in the annotations. Please enter a valid label.'
+                    )
+                    continue
 
                 for input_id in list_input_ids:
                     input_id = int(input_id)

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader/download/sheet_downloader.py

@@ -1289,7 +1289,6 @@ Try passing coordinates (min_x, max_x, min_y, max_y) instead or leave blank to a
                 pass
 
             for feature in features:
-                text_id = feature["wfs_id_no"]
                 coords = np.array(feature["geometry"]["coordinates"][0][0])
 
                 # Plot coordinates
@@ -1302,6 +1301,7 @@ Try passing coordinates (min_x, max_x, min_y, max_y) instead or leave blank to a
                 )
 
                 if add_id:
+                    text_id = feature["wfs_id_no"]
                     plt.text(
                         np.mean(coords[:, 0]) - 0.15,
                         np.mean(coords[:, 1]) - 0.05,

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader/load/images.py

@@ -1392,7 +1392,6 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
                 min_x, min_y, max_x, max_y = self.patches[patch]["pixel_bounds"]
                 if width != max_x - min_x:
                     width = max_x - min_x
-                img = img.crop((0, 0, width, height))
                 if height != max_y - min_y:
                     height = max_y - min_y
                 img = img.crop((0, 0, width, height))
@@ -1400,22 +1399,24 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
                 bands = img.getbands()
 
                 if calc_mean:
-                    if all(f"mean_pixel_{band}" in patch_keys for band in bands):
+                    if "mean_pixel" in patch_keys:
                         calc_mean = False
                 if calc_std:
-                    if all(f"std_pixel_{band}" in patch_keys for band in bands):
+                    if "std_pixel" in patch_keys:
                         calc_std = False
 
                 img_stat = ImageStat.Stat(img)
 
                 if calc_mean:
                     img_mean = img_stat.mean
+                    self.patches[patch]["mean_pixel"] = np.mean(img_mean) / 255
                     for i, band in enumerate(bands):
                         # Calculate mean pixel values
                         self.patches[patch][f"mean_pixel_{band}"] = img_mean[i] / 255
 
                 if calc_std:
                     img_std = img_stat.stddev
+                    self.patches[patch]["std_pixel"] = np.mean(img_std) / 255
                     for i, band in enumerate(bands):
                         # Calculate std pixel values
                         self.patches[patch][f"std_pixel_{band}"] = img_std[i] / 255

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader/process/post_process.py

@@ -8,8 +8,8 @@ import pandas as pd
 from tqdm import tqdm
 
 
-class PatchDataFrame(pd.DataFrame):
-    """A class for storing patch dataframes.
+class PostProcessor:
+    """A class for post-processing predictions on patches using the surrounding context.
 
     Parameters
     ----------
@@ -56,12 +56,16 @@ class PatchDataFrame(pd.DataFrame):
         else:
             patch_df[["min_x", "min_y", "max_x", "max_y"]] = [*patch_df["pixel_bounds"]]
 
-        super().__init__(patch_df)
+        # set the patch_df attribute
+        self.patch_df = patch_df
 
         self.labels_map = labels_map
         self._label_patches = None
         self.context = {}
 
+    def __len__(self):
+        return len(self.patch_df)
+
     def get_context(
         self,
         labels: str | list,
@@ -75,7 +79,9 @@ class PatchDataFrame(pd.DataFrame):
         """
         if isinstance(labels, str):
             labels = [labels]
-        self._label_patches = self[self["predicted_label"].isin(labels)]
+        self._label_patches = self.patch_df[
+            self.patch_df["predicted_label"].isin(labels)
+        ]
 
         for id in tqdm(self._label_patches.index):
             if id not in self.context:
@@ -89,28 +95,36 @@ class PatchDataFrame(pd.DataFrame):
         id,
     ):
         """Get the context of the patch with the specified index."""
-        parent_id = self.loc[id, "parent_id"]
-        min_x = self.loc[id, "min_x"]
-        min_y = self.loc[id, "min_y"]
-        max_x = self.loc[id, "max_x"]
-        max_y = self.loc[id, "max_y"]
+        parent_id = self.patch_df.loc[id, "parent_id"]
+        min_x = self.patch_df.loc[id, "min_x"]
+        min_y = self.patch_df.loc[id, "min_y"]
+        max_x = self.patch_df.loc[id, "max_x"]
+        max_y = self.patch_df.loc[id, "max_y"]
 
         context_grid = [
             *product(
-                [(self["min_x"], min_x), (min_x, max_x), (max_x, self["max_x"])],
-                [(self["min_y"], min_y), (min_y, max_y), (max_y, self["max_y"])],
+                [
+                    (self.patch_df["min_x"], min_x),
+                    (min_x, max_x),
+                    (max_x, self.patch_df["max_x"]),
+                ],
+                [
+                    (self.patch_df["min_y"], min_y),
+                    (min_y, max_y),
+                    (max_y, self.patch_df["max_y"]),
+                ],
             )
         ]
         # reshape to min_x, min_y, max_x, max_y
         context_grid = [(x[0][0], x[1][0], x[0][1], x[1][1]) for x in context_grid]
 
         context_list = [
-            self[
-                (self["min_x"] == context_loc[0])
-                & (self["min_y"] == context_loc[1])
-                & (self["max_x"] == context_loc[2])
-                & (self["max_y"] == context_loc[3])
-                & (self["parent_id"] == parent_id)
+            self.patch_df[
+                (self.patch_df["min_x"] == context_loc[0])
+                & (self.patch_df["min_y"] == context_loc[1])
+                & (self.patch_df["max_x"] == context_loc[2])
+                & (self.patch_df["max_y"] == context_loc[3])
+                & (self.patch_df["parent_id"] == parent_id)
             ]
             for context_loc in context_grid
         ]
@@ -163,7 +177,10 @@ class PatchDataFrame(pd.DataFrame):
         """Update the predictions of the patch with the specified index."""
         context_list = self.context[id]
 
-        context_df = self[self.index.isin(context_list)]
+        context_df = self.patch_df[self.patch_df.index.isin(context_list)].copy(
+            deep=True
+        )
+
         # drop central patch from context
         context_df.drop(index=id, inplace=True)
 
@@ -172,11 +189,11 @@ class PatchDataFrame(pd.DataFrame):
 
         prefix = "" if inplace else "new_"
         if (not any(context_df["predicted_label"].isin(labels))) & (
-            self.loc[id, "conf"] < conf
+            self.patch_df.loc[id, "conf"] < conf
         ):
-            self.loc[id, f"{prefix}predicted_label"] = remap[
-                self.loc[id, "predicted_label"]
+            self.patch_df.loc[id, f"{prefix}predicted_label"] = remap[
+                self.patch_df.loc[id, "predicted_label"]
             ]
-            self.loc[id, f"{prefix}pred"] = label_index_dict[
-                self.loc[id, f"{prefix}predicted_label"]
+            self.patch_df.loc[id, f"{prefix}pred"] = label_index_dict[
+                self.patch_df.loc[id, f"{prefix}predicted_label"]
             ]

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapreader
-Version: 1.3.1
+Version: 1.3.2
 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
@@ -29,7 +29,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: matplotlib<4.0.0,>=3.5.0
 Requires-Dist: numpy<2.0.0,>=1.21.5
-Requires-Dist: pandas<2.0.0,>=1.3.4
+Requires-Dist: pandas>=2.0.0
 Requires-Dist: pyproj<4.0.0,>=3.2.0
 Requires-Dist: azure-storage-blob<13.0.0,>=12.9.0
 Requires-Dist: aiohttp<4.0.0,>=3.8.1
@@ -53,10 +53,11 @@ Requires-Dist: simplekml<2.0.0,>=1.3.6
 Requires-Dist: versioneer>=0.28
 Requires-Dist: tqdm<5.0.0
 Requires-Dist: torchinfo<2.0.0
-Requires-Dist: openpyxl<4.0.0
+Requires-Dist: openpyxl<4.0.0,>=3.1.2
 Requires-Dist: geopandas<1.0.0
 Requires-Dist: pyogrio>=0.7.2
 Requires-Dist: cartopy>=0.22.0
+Requires-Dist: joblib>=1.4.0
 Provides-Extra: dev
 Requires-Dist: pytest<9.0.0; extra == "dev"
 Requires-Dist: pytest-cov<6.0.0,>=4.1.0; extra == "dev"

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader.egg-info/SOURCES.txt

@@ -4,6 +4,7 @@ setup.cfg
 setup.py
 versioneer.py
 mapreader/__init__.py
+mapreader/__main__.py
 mapreader/_version.py
 mapreader.egg-info/PKG-INFO
 mapreader.egg-info/SOURCES.txt

mapreader-1.3.2/mapreader.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+mapreader = mapreader:print_version

{mapreader-1.3.1 → mapreader-1.3.2}/mapreader.egg-info/requires.txt

@@ -1,6 +1,6 @@
 matplotlib<4.0.0,>=3.5.0
 numpy<2.0.0,>=1.21.5
-pandas<2.0.0,>=1.3.4
+pandas>=2.0.0
 pyproj<4.0.0,>=3.2.0
 azure-storage-blob<13.0.0,>=12.9.0
 aiohttp<4.0.0,>=3.8.1
@@ -24,10 +24,11 @@ simplekml<2.0.0,>=1.3.6
 versioneer>=0.28
 tqdm<5.0.0
 torchinfo<2.0.0
-openpyxl<4.0.0
+openpyxl<4.0.0,>=3.1.2
 geopandas<1.0.0
 pyogrio>=0.7.2
 cartopy>=0.22.0
+joblib>=1.4.0
 
 [dev]
 pytest<9.0.0

{mapreader-1.3.1 → mapreader-1.3.2}/setup.py

@@ -30,7 +30,7 @@ setuptools.setup(
     install_requires=[
         "matplotlib>=3.5.0,<4.0.0",
         "numpy>=1.21.5,<2.0.0",
-        "pandas>=1.3.4,<2.0.0",
+        "pandas>=2.0.0",
         "pyproj>=3.2.0,<4.0.0",
         "azure-storage-blob>=12.9.0,<13.0.0",
         "aiohttp>=3.8.1,<4.0.0",
@@ -54,10 +54,11 @@ setuptools.setup(
         "versioneer>=0.28",
         "tqdm<5.0.0",
         "torchinfo<2.0.0",
-        "openpyxl<4.0.0",
+        "openpyxl>=3.1.2,<4.0.0",
         "geopandas<1.0.0",
         "pyogrio>=0.7.2",
         "cartopy>=0.22.0",
+        "joblib>=1.4.0",
     ],
     extras_require={
         "dev": [
@@ -89,7 +90,7 @@ setuptools.setup(
     ],
     entry_points={
         "console_scripts": [
-            "mapreader = mapreader.mapreader:main",
+            "mapreader = mapreader:print_version",
         ],
     },
 )

{mapreader-1.3.1 → mapreader-1.3.2}/tests/test_annotator.py

@@ -35,7 +35,7 @@ def test_init_with_dfs(load_dfs):
         auto_save=False,
     )
     assert len(annotator) == 9
-    assert isinstance(annotator.iloc[0]["coordinates"], tuple)
+    assert isinstance(annotator.patch_df.iloc[0]["coordinates"], tuple)
 
 
 def test_init_with_csvs(load_dfs):
@@ -48,7 +48,7 @@ def test_init_with_csvs(load_dfs):
         auto_save=False,
     )
     assert len(annotator) == 9
-    assert isinstance(annotator.iloc[0]["coordinates"], tuple)
+    assert isinstance(annotator.patch_df.iloc[0]["coordinates"], tuple)
 
 
 def test_init_with_fpaths(load_dfs, sample_dir):
@@ -62,7 +62,7 @@ def test_init_with_fpaths(load_dfs, sample_dir):
         auto_save=False,
     )
     assert len(annotator) == 9
-    assert "mean_pixel_R" in annotator.columns
+    assert "mean_pixel_R" in annotator.patch_df.columns
 
 
 def test_init_with_fpaths_tsv(load_dfs, sample_dir):
@@ -77,7 +77,7 @@ def test_init_with_fpaths_tsv(load_dfs, sample_dir):
         delimiter="\t",
     )
     assert len(annotator) == 9
-    assert "mean_pixel_R" in annotator.columns
+    assert "mean_pixel_R" in annotator.patch_df.columns
 
 
 def test_no_labels(load_dfs):

mapreader-1.3.2/tests/test_post_processing.py

@@ -0,0 +1,171 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+import pandas as pd
+import pytest
+
+from mapreader.process.post_process import PostProcessor
+
+
+@pytest.fixture
+def sample_dir():
+    return Path(__file__).resolve().parent / "sample_files"
+
+
+@pytest.fixture
+def patch_df(sample_dir):
+    return pd.read_csv(f"{sample_dir}/post_processing_patch_df.csv", index_col=0)
+
+
+@pytest.fixture
+def labels_map():
+    return {0: "no", 1: "railspace", 2: "building", 3: "railspace&building"}
+
+
+def test_init(labels_map, patch_df):
+    patches = PostProcessor(patch_df, labels_map=labels_map)
+    assert isinstance(patches, PostProcessor)
+    assert len(patches) == 81
+    assert patches.labels_map == labels_map
+
+
+def test_init_errors(patch_df, labels_map):
+    with pytest.raises(ValueError, match="must contain the following columns"):
+        PostProcessor(patch_df.drop(columns=["parent_id", "pred"]), labels_map)
+
+
+def test_init_imaged_id_col(patch_df, labels_map):
+    # e.g. if you have integer index
+    patches = PostProcessor(patch_df.reset_index(drop=False), labels_map)
+    assert isinstance(patches, PostProcessor)
+    assert patches.patch_df.index.name == "image_id"
+
+    patch_df["image_id"] = patch_df.index
+    patches = PostProcessor(patch_df, labels_map)
+    assert isinstance(patches, PostProcessor)
+    assert patches.patch_df.index.name == "image_id"
+    assert len(patches) == 81
+    assert "image_id" in patches.patch_df.columns
+
+
+def test_get_context(patch_df, labels_map):
+    patches = PostProcessor(patch_df, labels_map=labels_map)
+    # labels as str
+    patches.get_context("railspace")
+    assert len(patches.context) == 10
+    # labels as list
+    patches.get_context(["railspace", "railspace&building"])
+    assert len(patches.context) == 13
+
+
+def test_update_preds_railspace(patch_df, labels_map):
+    patches = PostProcessor(patch_df, labels_map=labels_map)
+    patches.get_context(["railspace"])
+    remap = {"railspace": "no"}
+    patches.update_preds(remap)
+    assert len(patches.patch_df[patches.patch_df["new_predicted_label"].notna()]) == 1
+    assert (
+        patches.patch_df.loc[
+            "patch-4-7-5-8-#cropped_74488689.png#.png", "new_predicted_label"
+        ]
+        == "no"
+    )
+
+    patches.patch_df.drop(columns=["new_predicted_label", "new_pred"], inplace=True)
+    patches.update_preds(remap, conf=0.8)
+    assert len(patches.patch_df[patches.patch_df["new_predicted_label"].notna()]) == 2
+    assert (
+        patches.patch_df.loc[
+            "patch-1-7-2-8-#cropped_74488689.png#.png", "new_predicted_label"
+        ]
+        == "no"
+    )
+
+    patches.patch_df.drop(columns=["new_predicted_label", "new_pred"], inplace=True)
+    patches.update_preds(remap, conf=1)  # all conf == 1 should remain unchanged
+    assert len(patches.patch_df[patches.patch_df["new_predicted_label"].notna()]) == 3
+    assert (
+        patches.patch_df.loc[
+            "patch-1-4-2-5-#cropped_74488689.png#.png", "new_predicted_label"
+        ]
+        == "no"
+    )
+
+
+def test_update_preds_railspace_railspace_building(patch_df, labels_map):
+    patches = PostProcessor(patch_df, labels_map=labels_map)
+    patches.get_context(["railspace", "railspace&building"])
+    remap = {"railspace": "no", "railspace&building": "building"}
+    patches.update_preds(remap)
+    assert len(patches.patch_df[patches.patch_df["new_predicted_label"].notna()]) == 1
+    assert (
+        patches.patch_df.loc[
+            "patch-7-7-8-8-#cropped_74488689.png#.png", "new_predicted_label"
+        ]
+        == "building"
+    )
+
+    patches.patch_df.drop(columns=["new_predicted_label", "new_pred"], inplace=True)
+    patches.update_preds(remap, conf=0.8)
+    assert len(patches.patch_df[patches.patch_df["new_predicted_label"].notna()]) == 2
+    assert (
+        patches.patch_df.loc[
+            "patch-1-7-2-8-#cropped_74488689.png#.png", "new_predicted_label"
+        ]
+        == "no"
+    )
+    assert (
+        patches.patch_df.loc[
+            "patch-7-7-8-8-#cropped_74488689.png#.png", "new_predicted_label"
+        ]
+        == "building"
+    )
+
+
+def test_update_preds_inplace(patch_df, labels_map):
+    patches = PostProcessor(patch_df, labels_map=labels_map)
+    patches.get_context(["railspace"])
+    remap = {"railspace": "no"}
+    patches.update_preds(remap, inplace=True)
+    assert "new_predicted_label" not in patches.patch_df.columns
+    assert (
+        patches.patch_df.loc[
+            "patch-4-7-5-8-#cropped_74488689.png#.png", "predicted_label"
+        ]
+        == "no"
+    )
+
+
+def test_update_preds_new_label(patch_df, labels_map):
+    patches = PostProcessor(patch_df, labels_map=labels_map)
+    patches.get_context(["railspace"])
+    remap = {"railspace": "new"}
+    patches.update_preds(remap)
+    assert len(patches.patch_df[patches.patch_df["new_predicted_label"].notna()]) == 1
+    assert (
+        patches.patch_df.loc[
+            "patch-4-7-5-8-#cropped_74488689.png#.png", "new_predicted_label"
+        ]
+        == "new"
+    )
+    assert (
+        patches.patch_df.loc["patch-4-7-5-8-#cropped_74488689.png#.png", "new_pred"]
+        == 4
+    )
+    assert patches.labels_map[4] == "new"
+
+
+def test_update_preds_errors(patch_df, labels_map):
+    patches = PostProcessor(patch_df, labels_map=labels_map)
+    remap = {"railspace": "no"}
+    with pytest.raises(ValueError, match="run `get_context` first"):
+        patches.update_preds(remap)
+
+    patches.get_context(["fake"])
+    with pytest.raises(ValueError, match="No patches to update"):
+        patches.update_preds(remap)
+
+    patches.get_context(["railspace"])
+    with pytest.raises(ValueError, match="must specify a remap"):
+        patches.update_preds(remap={"fake": "no"})

{mapreader-1.3.1 → mapreader-1.3.2}/tests/test_sheet_downloader.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import os
-import re
 from ast import literal_eval
 from pathlib import Path
 
@@ -504,11 +503,6 @@ def test_download_same_image_names(sheet_downloader, tmp_path, capfd):
     sd.download_map_sheets_by_wfs_ids(
         [107, 116], maps_path, metadata_fname, overwrite=True
     )  # 107 and 116 both refer to https://maps.nls.uk/view/101603986
-    out, _ = capfd.readouterr()
-    assert re.search(
-        r"\[INFO\] Downloaded \".*\/test_maps\/map_101603986.png\"\n\[INFO\] Downloaded \".*\/test_maps\/map_101603986_1.png\"\n$",
-        out,
-    )
     assert os.path.exists(f"{maps_path}/map_101603986.png")
     assert os.path.exists(f"{maps_path}/map_101603986_1.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")

mapreader-1.3.1/mapreader.egg-info/entry_points.txt

@@ -1,2 +0,0 @@
-[console_scripts]
-mapreader = mapreader.mapreader:main

mapreader-1.3.1/tests/test_post_processing.py

@@ -1,152 +0,0 @@
-from __future__ import annotations
-
-from pathlib import Path
-
-import pandas as pd
-import pytest
-
-from mapreader.process.post_process import PatchDataFrame
-
-
-@pytest.fixture
-def sample_dir():
-    return Path(__file__).resolve().parent / "sample_files"
-
-
-@pytest.fixture
-def patch_df(sample_dir):
-    return pd.read_csv(f"{sample_dir}/post_processing_patch_df.csv", index_col=0)
-
-
-@pytest.fixture
-def labels_map():
-    return {0: "no", 1: "railspace", 2: "building", 3: "railspace&building"}
-
-
-def test_init(labels_map, patch_df):
-    patches = PatchDataFrame(patch_df, labels_map=labels_map)
-    assert isinstance(patches, PatchDataFrame)
-    assert len(patches) == 81
-    assert patches.labels_map == labels_map
-
-
-def test_init_errors(patch_df, labels_map):
-    with pytest.raises(ValueError, match="must contain the following columns"):
-        PatchDataFrame(patch_df.drop(columns=["parent_id", "pred"]), labels_map)
-
-
-def test_init_imaged_id_col(patch_df, labels_map):
-    # e.g. if you have integer index
-    patches = PatchDataFrame(patch_df.reset_index(drop=False), labels_map)
-    assert isinstance(patches, PatchDataFrame)
-    assert patches.index.name == "image_id"
-
-    patch_df["image_id"] = patch_df.index
-    patches = PatchDataFrame(patch_df, labels_map)
-    assert isinstance(patches, PatchDataFrame)
-    assert patches.index.name == "image_id"
-    assert len(patches) == 81
-    assert "image_id" in patches.columns
-
-
-def test_get_context(patch_df, labels_map):
-    patches = PatchDataFrame(patch_df, labels_map=labels_map)
-    # labels as str
-    patches.get_context("railspace")
-    assert len(patches.context) == 10
-    # labels as list
-    patches.get_context(["railspace", "railspace&building"])
-    assert len(patches.context) == 13
-
-
-def test_update_preds_railspace(patch_df, labels_map):
-    patches = PatchDataFrame(patch_df, labels_map=labels_map)
-    patches.get_context(["railspace"])
-    remap = {"railspace": "no"}
-    patches.update_preds(remap)
-    assert len(patches[patches["new_predicted_label"].notna()]) == 1
-    assert (
-        patches.loc["patch-4-7-5-8-#cropped_74488689.png#.png", "new_predicted_label"]
-        == "no"
-    )
-
-    patches.drop(columns=["new_predicted_label", "new_pred"], inplace=True)
-    patches.update_preds(remap, conf=0.8)
-    assert len(patches[patches["new_predicted_label"].notna()]) == 2
-    assert (
-        patches.loc["patch-1-7-2-8-#cropped_74488689.png#.png", "new_predicted_label"]
-        == "no"
-    )
-
-    patches.drop(columns=["new_predicted_label", "new_pred"], inplace=True)
-    patches.update_preds(remap, conf=1)  # all conf == 1 should remain unchanged
-    assert len(patches[patches["new_predicted_label"].notna()]) == 3
-    assert (
-        patches.loc["patch-1-4-2-5-#cropped_74488689.png#.png", "new_predicted_label"]
-        == "no"
-    )
-
-
-def test_update_preds_railspace_railspace_building(patch_df, labels_map):
-    patches = PatchDataFrame(patch_df, labels_map=labels_map)
-    patches.get_context(["railspace", "railspace&building"])
-    remap = {"railspace": "no", "railspace&building": "building"}
-    patches.update_preds(remap)
-    assert len(patches[patches["new_predicted_label"].notna()]) == 1
-    assert (
-        patches.loc["patch-7-7-8-8-#cropped_74488689.png#.png", "new_predicted_label"]
-        == "building"
-    )
-
-    patches.drop(columns=["new_predicted_label", "new_pred"], inplace=True)
-    patches.update_preds(remap, conf=0.8)
-    assert len(patches[patches["new_predicted_label"].notna()]) == 2
-    assert (
-        patches.loc["patch-1-7-2-8-#cropped_74488689.png#.png", "new_predicted_label"]
-        == "no"
-    )
-    assert (
-        patches.loc["patch-7-7-8-8-#cropped_74488689.png#.png", "new_predicted_label"]
-        == "building"
-    )
-
-
-def test_update_preds_inplace(patch_df, labels_map):
-    patches = PatchDataFrame(patch_df, labels_map=labels_map)
-    patches.get_context(["railspace"])
-    remap = {"railspace": "no"}
-    patches.update_preds(remap, inplace=True)
-    assert "new_predicted_label" not in patches.columns
-    assert (
-        patches.loc["patch-4-7-5-8-#cropped_74488689.png#.png", "predicted_label"]
-        == "no"
-    )
-
-
-def test_update_preds_new_label(patch_df, labels_map):
-    patches = PatchDataFrame(patch_df, labels_map=labels_map)
-    patches.get_context(["railspace"])
-    remap = {"railspace": "new"}
-    patches.update_preds(remap)
-    assert len(patches[patches["new_predicted_label"].notna()]) == 1
-    assert (
-        patches.loc["patch-4-7-5-8-#cropped_74488689.png#.png", "new_predicted_label"]
-        == "new"
-    )
-    assert patches.loc["patch-4-7-5-8-#cropped_74488689.png#.png", "new_pred"] == 4
-    assert patches.labels_map[4] == "new"
-
-
-def test_update_preds_errors(patch_df, labels_map):
-    patches = PatchDataFrame(patch_df, labels_map=labels_map)
-    remap = {"railspace": "no"}
-    with pytest.raises(ValueError, match="run `get_context` first"):
-        patches.update_preds(remap)
-
-    patches.get_context(["fake"])
-    with pytest.raises(ValueError, match="No patches to update"):
-        patches.update_preds(remap)
-
-    patches.get_context(["railspace"])
-    with pytest.raises(ValueError, match="must specify a remap"):
-        patches.update_preds(remap={"fake": "no"})