mapreader 1.3.5__tar.gz → 1.3.6__tar.gz

{mapreader-1.3.5 → mapreader-1.3.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapreader
-Version: 1.3.5
+Version: 1.3.6
 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
@@ -58,6 +58,7 @@ Requires-Dist: geopandas<1.0.0
 Requires-Dist: pyogrio>=0.7.2
 Requires-Dist: cartopy>=0.22.0
 Requires-Dist: joblib>=1.4.0
+Requires-Dist: opencv-python<5.0.0.0
 Provides-Extra: dev
 Requires-Dist: pytest<9.0.0; extra == "dev"
 Requires-Dist: pytest-cov<6.0.0,>=4.1.0; extra == "dev"

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/__init__.py

@@ -1,17 +1,25 @@
+# download
+from mapreader.download.sheet_downloader import SheetDownloader
+from mapreader.download.downloader import Downloader
+from mapreader.download.downloader_utils import create_polygon_from_latlons, create_line_from_latlons
+
+
+# load
 from mapreader.load.images import MapImages
 from mapreader.load.loader import loader
 from mapreader.load.loader import load_patches
 
-from mapreader.download.sheet_downloader import SheetDownloader
-from mapreader.download.downloader import Downloader
-from mapreader.download.downloader_utils import create_polygon_from_latlons, create_line_from_latlons
+# annotate
+from mapreader.annotate.annotator import Annotator
 
+# classify
 from mapreader.classify.load_annotations import AnnotationsLoader
 from mapreader.classify.datasets import PatchDataset
 from mapreader.classify.datasets import PatchContextDataset
 from mapreader.classify.classifier import ClassifierContainer
 from mapreader.classify import custom_models
 
+# spot_text
 try:
     from mapreader.spot_text.deepsolo_runner import DeepSoloRunner
 except ImportError:
@@ -22,19 +30,26 @@ try:
 except ImportError:
     pass
 
-from mapreader.process import process
-
-from mapreader.annotate.annotator import Annotator
+try:
+    from mapreader.spot_text.maptext_runner import MapTextRunner
+except ImportError:
+    pass
 
-from . import _version
 
-__version__ = _version.get_versions()["version"]
+# post process
+from mapreader.process.context_post_process import ContextPostProcessor
+from mapreader.process.occlusion_analysis import OcclusionAnalyzer
 
+# utils
 from mapreader.load import geo_utils
 
-import mapreader
 
+# version
+from . import _version
+__version__ = _version.get_versions()["version"]
+
+import mapreader
 
 def print_version():
     """Print the current version of mapreader."""
-    print(mapreader.__version__)
+    print(mapreader.__version__)

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-08-02T15:22:56+0100",
+ "date": "2024-08-09T14:10:51+0100",
  "dirty": false,
  "error": null,
- "full-revisionid": "49ac0f1daccf0da74b0570db6ade09578debb164",
- "version": "1.3.5"
+ "full-revisionid": "5ba6c479346a58dc6d937776c895b30d6c21f833",
+ "version": "1.3.6"
 }
 '''  # END VERSION_JSON
 

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/annotate/utils.py

@@ -310,7 +310,10 @@ def annotation_interface(
                     # stream=True so we don't download the whole page, only check if
                     # the page exists
                     response = requests.get(url, stream=True)
-                    assert response.status_code < 400
+                    if not response.status_code < 400:
+                        raise RuntimeError(
+                            f"URL could not get a response: {response.status_code}"
+                        )
                     print()
                     print(f"URL: {url}")
                 except:

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/classify/classifier.py

@@ -86,8 +86,8 @@ class ClassifierContainer:
         The optimizer being used for training the model.
     scheduler : None or torch.optim.lr_scheduler._LRScheduler
         The learning rate scheduler being used for training the model.
-    criterion : None or nn.modules.loss._Loss
-        The criterion to use for training the model.
+    loss_fn : None or nn.modules.loss._Loss
+        The loss function to use for training the model.
     metrics : dict
         A dictionary to store the metrics computed during training.
     last_epoch : int
@@ -159,7 +159,7 @@ class ClassifierContainer:
 
             self.optimizer = None
             self.scheduler = None
-            self.criterion = None
+            self.loss_fn = None
 
             self.metrics = {}
             self.last_epoch = 0
@@ -399,54 +399,54 @@ Use ``initialize_optimizer`` or ``add_optimizer`` to define one."  # noqa
 
         self.scheduler = scheduler
 
-    def add_criterion(
-        self, criterion: str | nn.modules.loss._Loss | None = "cross entropy"
+    def add_loss_fn(
+        self, loss_fn: str | nn.modules.loss._Loss | None = "cross entropy"
     ) -> None:
         """
-        Add a loss criterion to the classifier object.
+        Add a loss function to the classifier object.
 
         Parameters
         ----------
-        criterion : str or torch.nn.modules.loss._Loss
-            The loss criterion to add to the classifier object.
+        loss_fn : str or torch.nn.modules.loss._Loss
+            The loss function to add to the classifier object.
             Accepted string values are "cross entropy" or "ce" (cross-entropy), "bce" (binary cross-entropy) and "mse" (mean squared error).
 
         Returns
         -------
         None
-            The function only modifies the ``criterion`` attribute of the
+            The function only modifies the ``loss_fn`` attribute of the
             classifier and does not return anything.
         """
-        if isinstance(criterion, str):
-            if criterion in ["cross entropy", "ce", "cross_entropy", "cross-entropy"]:
-                criterion = nn.CrossEntropyLoss()
-            elif criterion in [
+        if isinstance(loss_fn, str):
+            if loss_fn in ["cross entropy", "ce", "cross_entropy", "cross-entropy"]:
+                loss_fn = nn.CrossEntropyLoss()
+            elif loss_fn in [
                 "bce",
                 "binary_cross_entropy",
                 "binary cross entropy",
                 "binary cross-entropy",
             ]:
-                criterion = nn.BCELoss()
-            elif criterion in [
+                loss_fn = nn.BCELoss()
+            elif loss_fn in [
                 "mse",
                 "mean_square_error",
                 "mean_squared_error",
                 "mean squared error",
             ]:
-                criterion = nn.MSELoss()
+                loss_fn = nn.MSELoss()
             else:
                 raise NotImplementedError(
-                    '[ERROR] At present, if passing ``criterion`` as a string, criterion can only be "cross entropy" or "ce" (cross-entropy), "bce" (binary cross-entropy) or "mse" (mean squared error).'
+                    '[ERROR] At present, if passing ``loss_fn`` as a string, the loss function can only be "cross entropy" or "ce" (cross-entropy), "bce" (binary cross-entropy) or "mse" (mean squared error).'
                 )
 
-            print(f'[INFO] Using "{criterion}" as criterion.')
+            print(f'[INFO] Using "{loss_fn}" as loss function.')
 
-        elif not isinstance(criterion, nn.modules.loss._Loss):
+        elif not isinstance(loss_fn, nn.modules.loss._Loss):
             raise ValueError(
-                '[ERROR] Please pass ``criterion`` as a string ("cross entropy", "bce" or "mse") or torch.nn loss function (see https://pytorch.org/docs/stable/nn.html).'
+                '[ERROR] Please pass ``loss_fn`` as a string ("cross entropy", "bce" or "mse") or torch.nn loss function (see https://pytorch.org/docs/stable/nn.html).'
             )
 
-        self.criterion = criterion
+        self.loss_fn = loss_fn
 
     def model_summary(
         self,
@@ -643,7 +643,7 @@ Use ``initialize_optimizer`` or ``add_optimizer`` to define one."  # noqa
 
     def train_component_summary(self) -> None:
         """
-        Print a summary of the optimizer, criterion, and trainable model
+        Print a summary of the optimizer, loss function, and trainable model
         components.
 
         Returns:
@@ -655,8 +655,8 @@ Use ``initialize_optimizer`` or ``add_optimizer`` to define one."  # noqa
         print("* Optimizer:")
         print(str(self.optimizer))
         print(divider)
-        print("* Criterion:")
-        print(str(self.criterion))
+        print("* Loss function:")
+        print(str(self.loss_fn))
         print(divider)
         print("* Model:")
         self.model_summary(trainable_col=True)
@@ -783,9 +783,9 @@ Use ``initialize_optimizer`` or ``add_optimizer`` to define one."  # noqa
         Raises
         ------
         ValueError
-            If the criterion is not set. Use the
-            :meth:`~.classify.classifier.ClassifierContainer.add_criterion`
-            method to set the criterion.
+            If the loss function is not set. Use the
+            :meth:`~.classify.classifier.ClassifierContainer.add_loss_fn`
+            method to set the loss function.
 
             If the optimizer is not set and the phase is "train". Use the
             :meth:`~.classify.classifier.ClassifierContainer.initialize_optimizer`
@@ -894,10 +894,10 @@ Use ``initialize_optimizer`` or ``add_optimizer`` to add one."  # noqa
                             #     summing the final output and the auxiliary
                             #     output but in testing we only consider the
                             #     final output.
-                            if self.criterion is None:
+                            if self.loss_fn is None:
                                 raise ValueError(
-                                    "[ERROR] Criterion is not yet defined.\n\n\
-Use ``add_criterion`` to define one."
+                                    "[ERROR] Loss function is not yet defined.\n\n\
+Use ``add_loss_fn`` to define one."
                                 )
 
                             if self.is_inception and (
@@ -910,8 +910,8 @@ Use ``add_criterion`` to define one."
                                 if not isinstance(aux_outputs, torch.Tensor):
                                     aux_outputs = self._get_logits(aux_outputs)
 
-                                loss1 = self.criterion(outputs, label_indices)
-                                loss2 = self.criterion(aux_outputs, label_indices)
+                                loss1 = self.loss_fn(outputs, label_indices)
+                                loss2 = self.loss_fn(aux_outputs, label_indices)
                                 # https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
                                 loss = loss1 + 0.4 * loss2
 
@@ -921,7 +921,7 @@ Use ``add_criterion`` to define one."
                                 if not isinstance(outputs, torch.Tensor):
                                     outputs = self._get_logits(outputs)
 
-                                loss = self.criterion(outputs, label_indices)
+                                loss = self.loss_fn(outputs, label_indices)
 
                             _, pred_label_indices = torch.max(outputs, dim=1)
 

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/classify/load_annotations.py

@@ -451,10 +451,13 @@ Please check your image paths and update them if necessary.'
                     self.reviewed.loc[input_id, "label_index"] = self._get_label_index(
                         input_label
                     )
-                    assert (
+                    if not (
                         self.annotations[self.label_col].value_counts().tolist()
                         == self.annotations["label_index"].value_counts().tolist()
-                    )
+                    ):
+                        raise RuntimeError(
+                            f"[ERROR] Label indices do not match label counts. Please check the label indices for label '{input_label}'."
+                        )
                     print(
                         f'[INFO] Image {input_id} has been relabelled as "{input_label}"'
                     )
@@ -607,12 +610,18 @@ Please check your image paths and update them if necessary.'
                 test_size=float(relative_frac_test),
                 random_state=random_state,
             )
-            assert len(self.annotations) == len(df_train) + len(df_val) + len(df_test)
+            if not len(self.annotations) == len(df_train) + len(df_val) + len(df_test):
+                raise ValueError(
+                    "[ERROR] Number of annotations in the split dataframes does not match the number of annotations in the original dataframe."
+                )
 
         else:
             df_val = df_temp
             df_test = None
-            assert len(self.annotations) == len(df_train) + len(df_val)
+            if not len(self.annotations) == len(df_train) + len(df_val):
+                raise ValueError(
+                    "[ERROR] Number of annotations in the split dataframes does not match the number of annotations in the original dataframe."
+                )
 
         if context_datasets:
             datasets = self.create_patch_context_datasets(

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/download/data_structures.py

@@ -14,8 +14,11 @@ class Coordinate:
         lon : float
             longitude value (in range [-180°, 180°] )
         """
-        assert -90 <= lat <= 90
-        assert -180 <= lon <= 180
+        if not -90 <= lat <= 90:
+            raise ValueError("Latitude must be in range [-90, 90]")
+        if not -180 <= lon <= 180:
+            raise ValueError("Longitude must be in range [-180, 180]")
+
         self.lat = lat
         self.lon = lon
 
@@ -37,9 +40,12 @@ class GridIndex:
         z : int
             Zoom level
         """
-        assert z >= 0
-        assert 0 <= x < 2**z
-        assert 0 <= y < 2**z
+        if not z >= 0:
+            raise ValueError("Zoom level must be greater than or equal to 0")
+        if not 0 <= x < 2**z:
+            raise ValueError(f"X value must be in range [0, {2**z}]")
+        if not 0 <= y < 2**z:
+            raise ValueError(f"Y value must be in range [0, {2**z}]")
         self.x = x
         self.y = y
         self.z = z
@@ -61,7 +67,9 @@ class GridBoundingBox:
         cell1 : GridIndex
         cell2 : GridIndex
         """
-        assert cell1.z == cell2.z, "Can't calculate a grid on different scales yet"
+        if cell1.z != cell2.z:
+            raise NotImplementedError("Can't calculate a grid on different scales yet")
+
         start_x = min(cell1.x, cell2.x)
         end_x = max(cell1.x, cell2.x)
         start_y = min(cell1.y, cell2.y)

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/download/downloader.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import os
 import shutil
+import time
 import urllib
 import urllib.request
 
@@ -144,12 +145,24 @@ class Downloader:
             map_name = self.merger._get_output_name(grid_bb)
         self.downloader.download_tiles(grid_bb, download_in_parallel=False)
         success = self.merger.merge(grid_bb, map_name)
+
         if success:
             print(f'[INFO] Downloaded "{map_name}.png"')
         else:
             print(f'[WARNING] Download of "{map_name}.png" was unsuccessful.')
 
-        shutil.rmtree(DEFAULT_TEMP_FOLDER)
+        # Try to remove the temporary folder
+        try:
+            shutil.rmtree(DEFAULT_TEMP_FOLDER)
+        except PermissionError:
+            # try again
+            time.sleep(5)
+            shutil.rmtree(DEFAULT_TEMP_FOLDER)
+        except OSError:
+            # try again
+            time.sleep(5)
+            shutil.rmtree(DEFAULT_TEMP_FOLDER)
+
         return success
 
     def download_map_by_polygon(
@@ -180,11 +193,12 @@ class Downloader:
             Additional keyword arguments to pass to the `_download_map` method
         """
 
-        assert isinstance(
-            polygon, Polygon
-        ), "[ERROR] \
-Please pass polygon as shapely.geometry.Polygon object.\n\
-[HINT] Use ``create_polygon_from_latlons()`` to create polygon."
+        if type(polygon) is not Polygon:
+            raise ValueError(
+                "[ERROR] \
+    Please pass polygon as shapely.geometry.Polygon object.\n\
+    [HINT] Use ``create_polygon_from_latlons()`` to create polygon."
+            )
 
         min_x, min_y, max_x, max_y = polygon.bounds
 

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/download/downloader_utils.py

@@ -155,6 +155,12 @@ def get_coordinate_from_index(grid_index: GridIndex) -> Coordinate:
     return Coordinate(lat, lon)
 
 
+def _check_z(z):
+    if not z >= 0:
+        raise ValueError("Zoom level must be positive")
+    return True
+
+
 def _get_index_from_coordinate(lon: float, lat: float, z: int) -> tuple[(int, int)]:
     """Generate (x,y) tuple from Coordinate latitudes and longitudes.
 
@@ -163,7 +169,7 @@ def _get_index_from_coordinate(lon: float, lat: float, z: int) -> tuple[(int, in
     Tuple
         (x,y) tuple.
     """
-    assert z >= 0, "Zoom level must be positive"
+    _check_z(z)
     n = 2**z
     x = int((lon + 180) / 360 * n)
     lat_rad = math.radians(lat)
@@ -179,7 +185,7 @@ def _get_coordinate_from_index(x: int, y: int, z: int) -> tuple[(float, float)]:
     Tuple
         (lon, lat) tuple representing the upper left corner of the tile.
     """
-    assert z >= 0, "Zoom level must be positive"
+    _check_z(z)
     n = 2**z
     lon = (x / n) * 360 - 180
     lat_rad = math.atan(math.sinh(math.pi * (1 - 2 * y / n)))

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/download/sheet_downloader.py

@@ -4,6 +4,7 @@ import json
 import os
 import re
 import shutil
+import time
 import urllib
 import urllib.request
 from functools import reduce
@@ -622,7 +623,18 @@ class SheetDownloader:
         else:
             print(f'[WARNING] Download of "{img_path}" was unsuccessful.')
 
-        shutil.rmtree(DEFAULT_TEMP_FOLDER)
+        # Try to remove the temporary folder
+        try:
+            shutil.rmtree(DEFAULT_TEMP_FOLDER)
+        except PermissionError:
+            # try again
+            time.sleep(5)
+            shutil.rmtree(DEFAULT_TEMP_FOLDER)
+        except OSError:
+            # try again
+            time.sleep(5)
+            shutil.rmtree(DEFAULT_TEMP_FOLDER)
+
         return img_path
 
     def _save_metadata(

{mapreader-1.3.5 → mapreader-1.3.6}/mapreader/download/tile_merging.py

@@ -136,9 +136,10 @@ class TileMerger:
                 )
 
         img_size = start_image.size
-        assert (
-            img_size[0] == img_size[1]
-        ), f"Tiles must be quadratic. This tile, however, is rectangular: {img_size}"
+        if not (img_size[0] == img_size[1]):
+            raise ValueError(
+                f"[ERROR] Tiles must be square: {img_size[0]}x{img_size[1]}."
+            )
         tile_size = img_size[0]
         return tile_size
 

mapreader-1.3.5/mapreader/process/post_process.py → mapreader-1.3.6/mapreader/process/context_post_process.py

@@ -8,7 +8,7 @@ import pandas as pd
 from tqdm import tqdm
 
 
-class PostProcessor:
+class ContextPostProcessor:
     """A class for post-processing predictions on patches using the surrounding context.
 
     Parameters