mapreader 1.1.0__tar.gz → 1.1.1__tar.gz

{mapreader-1.1.0 → mapreader-1.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapreader
-Version: 1.1.0
+Version: 1.1.1
 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
@@ -83,6 +83,9 @@ Requires-Dist: flake8<7.0.0,>=6.0.0; extra == "dev"
     </a>
     <a href="https://zenodo.org/badge/latestdoi/430661738"><img src="https://zenodo.org/badge/430661738.svg" alt="DOI"></a>
     <br/>
+    <a href="https://codecov.io/github/Living-with-machines/MapReader" >
+    <img src="https://codecov.io/github/Living-with-machines/MapReader/graph/badge.svg?token=38GQ3O1GB5"/>
+    </a>
 </p>
 
 

{mapreader-1.1.0 → mapreader-1.1.1}/README.md

@@ -18,6 +18,9 @@
     </a>
     <a href="https://zenodo.org/badge/latestdoi/430661738"><img src="https://zenodo.org/badge/430661738.svg" alt="DOI"></a>
     <br/>
+    <a href="https://codecov.io/github/Living-with-machines/MapReader" >
+    <img src="https://codecov.io/github/Living-with-machines/MapReader/graph/badge.svg?token=38GQ3O1GB5"/>
+    </a>
 </p>
 
 

{mapreader-1.1.0 → mapreader-1.1.1}/mapreader/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2023-12-14T11:30:18+0000",
+ "date": "2024-01-08T14:36:56+0000",
  "dirty": false,
  "error": null,
- "full-revisionid": "8eda75e8ddc1b4d5bb22cc2fcf5ebc0954947d71",
- "version": "1.1.0"
+ "full-revisionid": "8997b4d7fe7c82d5579ffd13daaa90e7253fc0c2",
+ "version": "1.1.1"
 }
 '''  # END VERSION_JSON
 

{mapreader-1.1.0 → mapreader-1.1.1}/mapreader/annotate/annotator.py

@@ -22,8 +22,6 @@ from ..load.loader import load_patches
 
 warnings.filterwarnings("ignore", category=UserWarning)
 
-MAX_SIZE = 1000
-
 _CENTER_LAYOUT = widgets.Layout(
     display="flex", flex_flow="column", align_items="center"
 )
@@ -64,8 +62,23 @@ class Annotator(pd.DataFrame):
     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.
-    **kwargs
-        Additional keyword arguments
+    ascending : bool, optional
+        Whether to sort the DataFrame in ascending order when using the ``sortby`` argument, by default True.
+    username : str or None, optional
+        Username to use when saving annotations file, by default None.
+        If not provided, a random string is generated.
+    task_name : str or None, optional
+        Name of the annotation task, by default None.
+    min_values : dict, optional
+        A dictionary consisting of column names (keys) and minimum values as floating point values (values), by default None.
+    max_values : dict, optional
+        A dictionary consisting of column names (keys) and maximum values as floating point values (values), by default None.
+    surrounding : int, optional
+        The number of surrounding images to show for context, by default 1.
+    max_size : int, optional
+        The size in pixels for the longest side to which constrain each patch image, by default 1000.
+    resize_to : int or None, optional
+        The size in pixels for the longest side to which resize each patch image, by default None.
 
     Raises
     ------
@@ -79,21 +92,6 @@ class Annotator(pd.DataFrame):
         If labels provided are not in the form of a list
     SyntaxError
         If labels provided are not in the form of a list
-
-    Notes
-    -----
-
-    Additional kwargs:
-
-    - ``username``: Username to use when saving annotations file. Default: Randomly generated string.
-    - ``task_name``: Name of the annotation task. Default: "task".
-    - ``min_values``: A dictionary consisting of column names (keys) and minimum values as floating point values (values). Default: {}.
-    - ``max_values``: A dictionary consisting of column names (keys) and maximum values as floating point values (values). Default: {}.
-    - ``buttons_per_row``: Number of buttons to display per row. Default: None.
-    - ``ascending``: Whether to sort the DataFrame in ascending order. Default: True.
-    - ``surrounding``: The number of surrounding images to show for context. Default: 1.
-    - ``max_size``: The size in pixels for the longest side to which constrain each patch image. Default: 1000.
-    - ``resize_to``: The size in pixels for the longest side to which resize each patch image. Default: None.
     """
 
     def __init__(
@@ -111,7 +109,14 @@ class Annotator(pd.DataFrame):
         auto_save: bool = True,
         delimiter: str = ",",
         sortby: str | None = None,
-        **kwargs,
+        ascending: bool = True,
+        username: str | None = None,
+        task_name: str | None = None,
+        min_values: dict | None = None,
+        max_values: dict | None = None,
+        surrounding: int = 1,
+        max_size: int = 1000,
+        resize_to: int | None = None,
     ):
         if labels is None:
             labels = []
@@ -174,10 +179,6 @@ class Annotator(pd.DataFrame):
         # Check for url column and add to patch dataframe
         if "url" in parent_df.columns:
             patch_df = patch_df.join(parent_df["url"], on="parent_id")
-        else:
-            raise ValueError(
-                "[ERROR] Metadata (parent data) should contain a 'url' column."
-            )
 
         # Add label column if not present
         if label_col not in patch_df.columns:
@@ -195,13 +196,12 @@ class Annotator(pd.DataFrame):
         )
 
         # Set up annotations file
-        username = kwargs.get(
-            "username",
-            "".join(
+        if not username:
+            username = "".join(
                 [random.choice(string.ascii_letters + string.digits) for n in range(30)]
-            ),
-        )
-        task_name = kwargs.get("task_name", "task")
+            )
+        if not task_name:
+            task_name = "task"
         id = hashlib.md5(image_list.encode("utf-8")).hexdigest()
 
         annotations_file = task_name.replace(" ", "_") + f"_#{username}#-{id}.csv"
@@ -269,9 +269,7 @@ class Annotator(pd.DataFrame):
         # Sort by sortby column if provided
         if isinstance(sortby, str):
             if sortby in self.columns:
-                self.sort_values(
-                    sortby, ascending=kwargs.get("ascending", True), inplace=True
-                )
+                self.sort_values(sortby, ascending=ascending, inplace=True)
             else:
                 raise ValueError(f"[ERROR] {sortby} is not a column in the DataFrame.")
         elif sortby is not None:
@@ -287,9 +285,8 @@ class Annotator(pd.DataFrame):
         self.task_name = task_name
 
         # set up for the annotator
-        self.buttons_per_row = kwargs.get("buttons_per_row", None)
-        self._min_values = kwargs.get("min_values", {})
-        self._max_values = kwargs.get("max_values", {})  # pixel_bounds = x0, y0, x1, y1
+        self._min_values = min_values or {}
+        self._max_values = max_values or {}
 
         self.patch_width, self.patch_height = self.get_patch_size()
 
@@ -297,25 +294,24 @@ class Annotator(pd.DataFrame):
         Path(annotations_dir).mkdir(parents=True, exist_ok=True)
 
         # Set up standards for context display
-        self.surrounding = kwargs.get("surrounding", 1)
-        self.max_size = kwargs.get("max_size", MAX_SIZE)
-        self.resize_to = kwargs.get("resize_to", None)
+        self.surrounding = surrounding
+        self.max_size = max_size
+        self.resize_to = resize_to
 
         # set up buttons
         self._buttons = []
 
         # Set max buttons
-        if not self.buttons_per_row:
-            if (len(self._labels) % 2) == 0:
-                if len(self._labels) > 4:
-                    self.buttons_per_row = 4
-                else:
-                    self.buttons_per_row = 2
+        if (len(self._labels) % 2) == 0:
+            if len(self._labels) > 4:
+                self.buttons_per_row = 4
             else:
-                if len(self._labels) == 3:
-                    self.buttons_per_row = 3
-                else:
-                    self.buttons_per_row = 5
+                self.buttons_per_row = 2
+        else:
+            if len(self._labels) == 3:
+                self.buttons_per_row = 3
+            else:
+                self.buttons_per_row = 5
 
         # Set indices
         self.current_index = -1

{mapreader-1.1.0 → mapreader-1.1.1}/mapreader/classify/load_annotations.py

@@ -180,6 +180,8 @@ class AnnotationsLoader:
         if os.path.isfile(annotations):
             print(f'[INFO] Reading "{annotations}"')
             annotations = pd.read_csv(annotations, sep=delimiter, index_col=0)
+            if annotations.index.name in ["name", "image_id"]:
+                annotations.reset_index(inplace=True, drop=False)
         else:
             raise ValueError(f'[ERROR] "{annotations}" cannot be found.')
 

{mapreader-1.1.0 → mapreader-1.1.1}/mapreader/load/images.py

@@ -7,11 +7,12 @@ except ImportError:
 
 import os
 import random
+import re
 import warnings
+from ast import literal_eval
 from glob import glob
 from typing import Literal
 
-import matplotlib.image as mpimg
 import matplotlib.patches as patches
 import matplotlib.pyplot as plt
 import numpy as np
@@ -21,9 +22,13 @@ import rasterio
 from PIL import Image, ImageStat
 from pyproj import Transformer
 from rasterio.plot import reshape_as_raster
-from shapely.geometry import box
+from shapely import wkt
+from shapely.geometry import Polygon, box
 from tqdm.auto import tqdm
 
+from mapreader.download.data_structures import GridBoundingBox, GridIndex
+from mapreader.download.downloader_utils import get_polygon_from_grid_bb
+
 os.environ[
     "USE_PYGEOS"
 ] = "0"  # see here https://github.com/geopandas/geopandas/issues/2691
@@ -419,7 +424,7 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
                 data_series = metadata_df[metadata_df[image_id_col] == key].squeeze()
                 for column, item in data_series.items():
                     try:
-                        self.images[tree_level][key][column] = eval(item)
+                        self.images[tree_level][key][column] = literal_eval(item)
                     except:
                         self.images[tree_level][key][column] = item
 
@@ -466,9 +471,12 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
             plt.subplot(num_samples // 3 + 1, 3, i + 1)
             img = Image.open(self.images[tree_level][image_id]["image_path"])
             plt.title(image_id, size=8)
-            plt.imshow(
-                img,
-            )
+
+            # check if grayscale
+            if len(img.getbands()) == 1:
+                plt.imshow(img, cmap="gray", vmin=0, vmax=255)
+            else:
+                plt.imshow(img)
             plt.xticks([])
             plt.yticks([])
 
@@ -509,6 +517,20 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
         for image_id in image_ids:
             self._add_shape_id(image_id=image_id)
 
+    def add_coords_from_grid_bb(self, verbose: bool = False) -> None:
+        print("[INFO] Adding coordinates, tree level: parent")
+
+        parent_list = self.list_parents()
+
+        for parent_id in parent_list:
+            if "grid_bb" not in self.parents[parent_id].keys():
+                print(
+                    f"[WARNING] No grid bounding box found for {parent_id}. Suggestion: run add_metadata or add_geo_info."  # noqa
+                )
+                continue
+
+            self._add_coords_from_grid_bb_id(image_id=parent_id, verbose=verbose)
+
     def add_coord_increments(self, verbose: bool | None = False) -> None:
         """
         Adds coordinate increments to each image at the parent level.
@@ -652,15 +674,42 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
         tree_level = self._get_tree_level(image_id)
 
         try:
-            myimg = mpimg.imread(self.images[tree_level][image_id]["image_path"])
+            img = Image.open(self.images[tree_level][image_id]["image_path"])
             # shape = (hwc)
-            myimg_shape = myimg.shape
-            self.images[tree_level][image_id]["shape"] = myimg_shape
+            height = img.height
+            width = img.width
+            channels = len(img.getbands())
+
+            self.images[tree_level][image_id]["shape"] = (height, width, channels)
         except OSError:
             raise ValueError(
                 f'[ERROR] Problem with "{image_id}". Please either redownload or remove from list of images to load.'
             )
 
+    def _add_coords_from_grid_bb_id(
+        self, image_id: int | str, verbose: bool = False
+    ) -> None:
+        grid_bb = self.parents[image_id]["grid_bb"]
+
+        if isinstance(grid_bb, str):
+            cell1, cell2 = re.findall(r"\(.*?\)", grid_bb)
+
+            z1, x1, y1 = literal_eval(cell1)
+            z2, x2, y2 = literal_eval(cell2)
+
+            cell1 = GridIndex(x1, y1, z1)
+            cell2 = GridIndex(x2, y2, z2)
+
+            grid_bb = GridBoundingBox(cell1, cell2)
+
+        if isinstance(grid_bb, GridBoundingBox):
+            polygon = get_polygon_from_grid_bb(grid_bb)
+            coordinates = polygon.bounds
+            self.parents[image_id]["coordinates"] = coordinates
+
+        else:
+            raise ValueError(f"[ERROR] Unexpected grid_bb format for {image_id}.")
+
     def _add_coord_increments_id(
         self, image_id: int | str, verbose: bool | None = False
     ) -> None:
@@ -759,19 +808,19 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
                 self._add_coord_increments_id(parent_id)
 
             # get min_x and min_y and pixel-wise dlon and dlat for parent image
-            parent_min_x = self.parents[parent_id]["coordinates"][0]
-            parent_min_y = self.parents[parent_id]["coordinates"][1]
+            parent_min_x, parent_min_y, parent_max_x, parent_max_y = self.parents[
+                parent_id
+            ]["coordinates"]
             dlon = self.parents[parent_id]["dlon"]
             dlat = self.parents[parent_id]["dlat"]
 
-            # get patch bounds
             pixel_bounds = self.patches[image_id]["pixel_bounds"]
 
             # get patch coords
             min_x = (pixel_bounds[0] * dlon) + parent_min_x
-            min_y = (pixel_bounds[1] * dlat) + parent_min_y
+            min_y = parent_max_y - (pixel_bounds[3] * dlat)
             max_x = (pixel_bounds[2] * dlon) + parent_min_x
-            max_y = (pixel_bounds[3] * dlat) + parent_min_y
+            max_y = parent_max_y - (pixel_bounds[1] * dlat)
 
             self.patches[image_id]["coordinates"] = (min_x, min_y, max_x, max_y)
             self.patches[image_id]["crs"] = self.parents[parent_id]["crs"]
@@ -837,6 +886,7 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
             self._print_if_verbose(
                 f"[INFO] Reading 'coordinates' from {image_id}.", verbose
             )
+
             min_x, min_y, max_x, max_y = self.images[tree_level][image_id][
                 "coordinates"
             ]
@@ -1440,7 +1490,12 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
 
                 fig = plt.figure(figsize=figsize)
                 plt.axis("off")
-                plt.imshow(img, zorder=1)
+
+                # check if grayscale
+                if len(img.getbands()) == 1:
+                    plt.imshow(img, cmap="gray", vmin=0, vmax=255, zorder=1)
+                else:
+                    plt.imshow(img, zorder=1)
 
                 if column_to_plot:
                     print(
@@ -1558,7 +1613,11 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
                     parent_path = parent_images[parent_id]["image_path"]
                     parent_image = Image.open(parent_path)
 
-                    ax.imshow(parent_image)
+                    # check if grayscale
+                    if len(parent_image.getbands()) == 1:
+                        ax.imshow(parent_image, cmap="gray", vmin=0, vmax=255)
+                    else:
+                        ax.imshow(parent_image)
 
                 if save_kml_dir:
                     os.makedirs(save_kml_dir, exist_ok=True)
@@ -2076,6 +2135,116 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
         tree_level = "parent" if bool(self.parents.get(image_id)) else "patch"
         return tree_level
 
+    def save_parents_as_geotiffs(
+        self,
+        rewrite: bool = False,
+        verbose: bool = False,
+        crs: str | None = None,
+    ) -> None:
+        """Save all parents in MapImages instance as geotiffs.
+
+        Parameters
+        ----------
+        rewrite : bool, optional
+            Whether to rewrite files if they already exist, by default False
+        verbose : bool, optional
+            Whether to print verbose outputs, by default False
+        crs : str, optional
+            The CRS of the coordinates.
+            If None, the method will first look for ``crs`` in the parents dictionary and use those. If ``crs`` cannot be found in the dictionary, the method will use "EPSG:4326".
+            By default None.
+        """
+
+        parents_list = self.list_parents()
+
+        for parent_id in tqdm(parents_list):
+            self._save_parent_as_geotiff(parent_id, rewrite, verbose, crs)
+
+    def _save_parent_as_geotiff(
+        self,
+        parent_id: str,
+        rewrite: bool = False,
+        verbose: bool = False,
+        crs: str | None = None,
+    ) -> None:
+        """Save a parent image as a geotiff.
+
+        Parameters
+        ----------
+        parent_id : str
+            The ID of the parent to write.
+        rewrite : bool, optional
+            Whether to rewrite files if they already exist, by default False
+        verbose : bool, optional
+            Whether to print verbose outputs, by default False
+        crs : Optional[str], optional
+            The CRS of the coordinates.
+            If None, the method will first look for ``crs`` in the parents dictionary and use those. If ``crs`` cannot be found in the dictionary, the method will use "EPSG:4326".
+            By default None.
+
+        Raises
+        ------
+        ValueError
+            If parent directory does not exist.
+        """
+
+        parent_path = self.parents[parent_id]["image_path"]
+        parent_dir = os.path.dirname(parent_path)
+
+        if not os.path.exists(parent_dir):
+            raise ValueError(f'[ERROR] Parent directory "{parent_dir}" does not exist.')
+
+        parent_id_no_ext = os.path.splitext(parent_id)[0]
+        geotiff_path = f"{parent_dir}/{parent_id_no_ext}.tif"
+
+        self.parents[parent_id]["geotiff_path"] = geotiff_path
+
+        if os.path.isfile(f"{geotiff_path}"):
+            if not rewrite:
+                self._print_if_verbose(
+                    f"[INFO] File already exists: {geotiff_path}.", verbose
+                )
+                return
+
+        self._print_if_verbose(
+            f"[INFO] Creating: {geotiff_path}.",
+            verbose,
+        )
+
+        if "shape" not in self.parents[parent_id].keys():
+            self._add_shape_id(parent_id)
+        height, width, channels = self.parents[parent_id]["shape"]
+
+        if "coordinates" not in self.parents[parent_id].keys():
+            print(self.parents[parent_id].keys())
+            raise ValueError(f"[ERROR] Cannot locate coordinates for {parent_id}")
+        coords = self.parents[parent_id]["coordinates"]
+
+        if not crs:
+            crs = self.parents[parent_id].get("crs", "EPSG:4326")
+
+        parent_affine = rasterio.transform.from_bounds(*coords, width, height)
+        parent = Image.open(parent_path)
+
+        with rasterio.open(
+            f"{geotiff_path}",
+            "w",
+            driver="GTiff",
+            height=parent.height,
+            width=parent.width,
+            count=channels,
+            transform=parent_affine,
+            dtype="uint8",
+            nodata=0,
+            crs=crs,
+        ) as dst:
+            if len(parent.getbands()) == 1:
+                parent_array = np.array(parent)
+                dst.write(parent_array, indexes=1)
+            else:
+                parent_array = reshape_as_raster(parent)
+                dst.write(parent_array)
+
     def save_patches_as_geotiffs(
         self,
         rewrite: bool | None = False,
@@ -2152,10 +2321,12 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
             verbose,
         )
 
+        # get shape
         if "shape" not in self.patches[patch_id].keys():
             self._add_shape_id(patch_id)
         height, width, channels = self.patches[patch_id]["shape"]
 
+        # get coords
         if "coordinates" not in self.patches[patch_id].keys():
             self._add_patch_coords_id(patch_id)
         coords = self.patches[patch_id]["coordinates"]
@@ -2165,7 +2336,6 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
 
         patch_affine = rasterio.transform.from_bounds(*coords, width, height)
         patch = Image.open(patch_path)
-        patch_array = reshape_as_raster(patch)
 
         with rasterio.open(
             f"{geotiff_path}",
@@ -2179,7 +2349,12 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
             nodata=0,
             crs=crs,
         ) as dst:
-            dst.write(patch_array)
+            if len(patch.getbands()) == 1:
+                patch_array = np.array(patch)
+                dst.write(patch_array, indexes=1)
+            else:
+                patch_array = reshape_as_raster(patch)
+                dst.write(patch_array)
 
     def save_patches_to_geojson(
         self,
@@ -2213,6 +2388,10 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
             self.add_patch_polygons()
             _, patch_df = self.convert_images()
 
+        patch_df["polygon"] = patch_df["polygon"].apply(
+            lambda x: x if isinstance(x, Polygon) else wkt.loads(x)
+        )
+
         if not crs:
             if "crs" in patch_df.columns:
                 if len(patch_df["crs"].unique()) == 1:
@@ -2220,14 +2399,16 @@ See https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes for mor
             else:
                 crs = "EPSG:4326"
 
+        if "image_id" in patch_df.columns:
+            patch_df.drop(columns=["image_id"], inplace=True)
         patch_df.reset_index(names="image_id", inplace=True)
 
         # drop pixel stats columns
         patch_df.drop(columns=patch_df.filter(like="pixel", axis=1), inplace=True)
-        # drop tuple columns - cause errors
+        # change tuple columns to strings
         for col in patch_df.columns:
             if isinstance(patch_df[col][0], tuple):
-                patch_df.drop(columns=col, inplace=True)
+                patch_df[col] = patch_df[col].apply(str)
 
         geo_patch_df = geopd.GeoDataFrame(patch_df, geometry="polygon", crs=crs)
         geo_patch_df.to_file(geojson_fname, driver="GeoJSON")

{mapreader-1.1.0 → mapreader-1.1.1}/mapreader.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapreader
-Version: 1.1.0
+Version: 1.1.1
 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
@@ -83,6 +83,9 @@ Requires-Dist: flake8<7.0.0,>=6.0.0; extra == "dev"
     </a>
     <a href="https://zenodo.org/badge/latestdoi/430661738"><img src="https://zenodo.org/badge/430661738.svg" alt="DOI"></a>
     <br/>
+    <a href="https://codecov.io/github/Living-with-machines/MapReader" >
+    <img src="https://codecov.io/github/Living-with-machines/MapReader/graph/badge.svg?token=38GQ3O1GB5"/>
+    </a>
 </p>
 
 

{mapreader-1.1.0 → mapreader-1.1.1}/tests/test_annotator.py

@@ -211,16 +211,6 @@ def test_init_dfs_value_error(load_dfs):
         )
 
 
-def test_no_url_col(load_dfs):
-    parent_df, patch_df, _ = load_dfs
-    parent_df = parent_df.drop(columns=["url"])
-    with pytest.raises(ValueError, match="should contain a 'url' column"):
-        Annotator(
-            patch_df=patch_df,
-            parent_df=parent_df,
-        )
-
-
 def test_no_image_path_col(load_dfs):
     parent_df, patch_df, _ = load_dfs
     patch_df = patch_df.drop(columns=["image_path"])
@@ -255,3 +245,13 @@ def test_fpaths_metadata_filenotfound_error(load_dfs, sample_dir):
             parent_paths=f"{sample_dir}/cropped_74488689.png",
             metadata_path="fake_df.csv",
         )
+
+
+def test_unknown_arg_error(load_dfs):
+    parent_df, patch_df, _ = load_dfs
+    with pytest.raises(TypeError):
+        Annotator(
+            patch_df=patch_df,
+            parent_df=parent_df,
+            fake_arg=1,
+        )

{mapreader-1.1.0 → mapreader-1.1.1}/tests/test_sheet_downloader.py

@@ -1,9 +1,12 @@
 from __future__ import annotations
 
 import os
+from ast import literal_eval
 from pathlib import Path
 
+import pandas as pd
 import pytest
+from pytest import approx
 from shapely.geometry import LineString, MultiPolygon, Polygon
 
 from mapreader import SheetDownloader
@@ -286,11 +289,54 @@ def test_download_all(sheet_downloader, tmp_path):
     sd.download_all_map_sheets(maps_path, metadata_fname)
     assert os.path.exists(f"{maps_path}/map_102352861.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 5
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb\n"
-    assert csv[3].startswith("2,map_102352861.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 4
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+    ]
+    assert list(df["name"]) == [
+        "map_101602026.png",
+        "map_101602038.png",
+        "map_102352861.png",
+        "map_91617032.png",
+    ]
+    # test coords
+    assert literal_eval(df.loc[0, "coordinates"]) == approx(
+        (-1.0546875, 53.33087298301705, -0.703125, 53.54030739150021), rel=1e-6
+    )
+
+    sd.get_grid_bb(14)
+    maps_path = tmp_path / "test_maps_14/"
+    metadata_fname = "test_metadata.csv"
+    sd.download_all_map_sheets(maps_path, metadata_fname)
+    assert os.path.exists(f"{maps_path}/map_102352861.png")
+    assert os.path.exists(f"{maps_path}/{metadata_fname}")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 4
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+    ]
+    assert list(df["name"]) == [
+        "map_101602026.png",
+        "map_101602038.png",
+        "map_102352861.png",
+        "map_91617032.png",
+    ]
+    # test coords
+    assert literal_eval(df.loc[0, "coordinates"]) == approx(
+        (-0.98876953125, 53.448806835427575, -0.90087890625, 53.48804553605621),
+        rel=1e-6,
+    )
 
 
 def test_download_all_kwargs(sheet_downloader, tmp_path):
@@ -304,12 +350,27 @@ def test_download_all_kwargs(sheet_downloader, tmp_path):
     }
     sd.download_all_map_sheets(maps_path, metadata_fname, **kwargs)
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 5
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb,test1,test2\n"
-    assert "Six_Inch_GB_WFS.132" in csv[4]
-    assert "2021" in csv[4]
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 4
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+        "test1",
+        "test2",
+    ]
+    assert list(df["name"]) == [
+        "map_101602026.png",
+        "map_101602038.png",
+        "map_102352861.png",
+        "map_91617032.png",
+    ]
+    assert df.loc[3, "published_date"] == 2021
+    assert df.loc[3, "test1"] == "test"
+    assert df.loc[3, "test2"] == "Six_Inch_GB_WFS.132"
 
 
 def test_download_by_wfs_ids(sheet_downloader, tmp_path):
@@ -322,27 +383,32 @@ def test_download_by_wfs_ids(sheet_downloader, tmp_path):
     )  # test single wfs_id
     assert os.path.exists(f"{maps_path}/map_101602026.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 2
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb\n"
-    assert csv[1].startswith("0,map_101602026.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 1
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+    ]
+    assert df.loc[0, "name"] == "map_101602026.png"
 
     sd.download_map_sheets_by_wfs_ids(
         [16320, 16321], maps_path, metadata_fname
     )  # test list of wfs_ids
     assert os.path.exists(f"{maps_path}/map_101602038.png")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 3  # should have only downloaded/added one extra map
-
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 2  # should have only downloaded/added one extra map
+    assert df.loc[1, "name"] == "map_101602038.png"
     sd.download_map_sheets_by_wfs_ids(
         16320, maps_path, metadata_fname, overwrite=True
     )  # test overwrite
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb\n"
-    assert csv[1].startswith("0,map_101602026.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 2
+    assert df.loc[0, "name"] == "map_101602026.png"
+    assert df.loc[1, "name"] == "map_101602038.png"
 
 
 def test_download_by_wfs_ids_errors(sheet_downloader, tmp_path):
@@ -378,19 +444,25 @@ def test_download_by_polygon(sheet_downloader, tmp_path):
     )  # test mode = 'within'
     assert os.path.exists(f"{maps_path}/map_101602026.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 2
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb\n"
-    assert csv[1].startswith("0,map_101602026.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 1
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+    ]
+    assert df.loc[0, "name"] == "map_101602026.png"
 
     sd.download_map_sheets_by_polygon(
         polygon, maps_path, metadata_fname, mode="intersects"
     )  # test mode = 'intersects', now 2 maps
     assert os.path.exists(f"{maps_path}/map_101602038.png")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 3  # should have only downloaded/added one extra map
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 2  # should have only downloaded/added one extra map
+    assert df.loc[1, "name"] == "map_101602038.png"
 
 
 def test_download_by_polygon_errors(sheet_downloader, tmp_path):
@@ -417,11 +489,17 @@ def test_download_by_coords(sheet_downloader, tmp_path):
     sd.download_map_sheets_by_coordinates((-0.99, 53.43), maps_path, metadata_fname)
     assert os.path.exists(f"{maps_path}/map_101602038.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 2
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb\n"
-    assert csv[1].startswith("0,map_101602038.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 1
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+    ]
+    assert df.loc[0, "name"] == "map_101602038.png"
 
 
 def test_download_by_coords_errors(sheet_downloader, tmp_path):
@@ -442,11 +520,17 @@ def test_download_by_line(sheet_downloader, tmp_path):
     sd.download_map_sheets_by_line(line, maps_path, metadata_fname)
     assert os.path.exists(f"{maps_path}/map_101602026.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 3
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb\n"
-    assert csv[1].startswith("0,map_101602026.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 2
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+    ]
+    assert list(df["name"]) == ["map_101602026.png", "map_101602038.png"]
 
 
 def test_download_by_line_errors(sheet_downloader, tmp_path):
@@ -469,30 +553,34 @@ def test_download_by_string(sheet_downloader, tmp_path):
     )  # test w/ keys list
     assert os.path.exists(f"{maps_path}/map_91617032.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 2
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb\n"
-    assert csv[1].startswith("0,map_91617032.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 1
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+    ]
+    assert df.loc[0, "name"] == "map_91617032.png"
 
     sd.download_map_sheets_by_string(
         "Six_Inch_GB_WFS.16320", "id", maps_path, metadata_fname
     )  # test append + w/ keys as string
     assert os.path.exists(f"{maps_path}/map_101602026.png")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 3
-    assert csv[2].startswith("1,map_101602026.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 2
+    assert df.loc[1, "name"] == "map_101602026.png"
 
     sd.download_map_sheets_by_string(
         "III.SW", path_save=maps_path, metadata_fname=metadata_fname
     )  # test w/ no keys
     assert os.path.exists(f"{maps_path}/map_101602038.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 4
-    assert csv[3].startswith("2,map_101602038.png")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 3
+    assert df.loc[2, "name"] == "map_101602038.png"
 
 
 def test_download_by_string_value_errors(sheet_downloader, tmp_path):
@@ -531,12 +619,17 @@ def test_download_by_queries(sheet_downloader, tmp_path):
     assert os.path.exists(f"{maps_path}/map_101602026.png")
     assert os.path.exists(f"{maps_path}/map_91617032.png")
     assert os.path.exists(f"{maps_path}/{metadata_fname}")
-    with open(f"{maps_path}/{metadata_fname}") as f:
-        csv = f.readlines()
-    assert len(csv) == 3
-    assert csv[0] == ",name,url,coordinates,crs,published_date,grid_bb\n"
-    assert csv[1].startswith("0,map_101602026.png,")
-    assert csv[2].startswith("1,map_91617032.png,")
+    df = pd.read_csv(f"{maps_path}/{metadata_fname}", sep=",", index_col=0)
+    assert len(df) == 2
+    assert list(df.columns) == [
+        "name",
+        "url",
+        "coordinates",
+        "crs",
+        "published_date",
+        "grid_bb",
+    ]
+    assert list(df["name"]) == ["map_101602026.png", "map_91617032.png"]
 
 
 def test_download_by_queries_errors(sheet_downloader, tmp_path):