Fixed tests directory

Author: Hitesh Tolani

tests/conf/ssl4eo_l_moco_1.yaml

@@ -8,6 +8,12 @@ model:
     temperature: 0.07
     memory_bank_size: 10
     moco_momentum: 0.999
+    augmentation1:
+      class_path: kornia.augmentation.RandomResizedCrop
+      init_args:
+        size:
+        - 224
+        - 224
 data:
   class_path: SSL4EOLDataModule
   init_args:

tests/data/agb_live_woody_density/Aboveground_Live_Woody_Biomass_Density.geojson

@@ -1 +1 @@
-{"type": "FeatureCollection", "name": "Aboveground_Live_Woody_Biomass_Density", "crs": {"type": "name", "properties": {"name": "urn:ogc:def:crs:OGC:1.3:CRS84"}}, "features": [{"type": "Feature", "properties": {"tile_id": "00N_000E", "download": "tests/data/agb_live_woody_density/00N_000E.tif", "ObjectId": 1, "Shape__Area": 1245542622548.87, "Shape__Length": 4464169.76558139}, "geometry": {"type": "Polygon", "coordinates": [[[0.0, 0.0], [10.0, 0.0], [10.0, -10.0], [0.0, -10.0], [0.0, 0.0]]]}}]}
+{"type": "FeatureCollection", "name": "Aboveground_Live_Woody_Biomass_Density", "crs": {"type": "name", "properties": {"name": "urn:ogc:def:crs:OGC:1.3:CRS84"}}, "features": [{"type": "Feature", "properties": {"tile_id": "00N_000E", "Mg_px_1_download": "tests/data/agb_live_woody_density/00N_000E.tif", "ObjectId": 1, "Shape__Area": 1245542622548.87, "Shape__Length": 4464169.76558139}, "geometry": {"type": "Polygon", "coordinates": [[[0.0, 0.0], [10.0, 0.0], [10.0, -10.0], [0.0, -10.0], [0.0, 0.0]]]}}]}

tests/data/agb_live_woody_density/data.py

@@ -23,7 +23,7 @@
             "type": "Feature",
             "properties": {
                 "tile_id": "00N_000E",
-                "download": os.path.join(
+                "Mg_px_1_download": os.path.join(
                     "tests", "data", "agb_live_woody_density", "00N_000E.tif"
                 ),
                 "ObjectId": 1,
@@ -74,5 +74,5 @@ def create_file(path: str, dtype: str, num_channels: int) -> None:
         json.dump(base_file, f)
 
     for i in base_file["features"]:
-        filepath = os.path.basename(i["properties"]["download"])
+        filepath = os.path.basename(i["properties"]["Mg_px_1_download"])
         create_file(path=filepath, dtype="int32", num_channels=1)

tests/data/nccm/13090442.zip

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+import hashlib
+import os
+import shutil
+
+import numpy as np
+import rasterio
+from rasterio.crs import CRS
+from rasterio.transform import Affine
+
+SIZE = 32
+
+np.random.seed(0)
+files = ["CDL2017_clip.tif", "CDL2018_clip1.tif", "CDL2019_clip.tif"]
+
+
+def create_file(path: str, dtype: str):
+    """Create the testing file."""
+    profile = {
+        "driver": "GTiff",
+        "dtype": dtype,
+        "count": 1,
+        "crs": CRS.from_epsg(4326),
+        "transform": Affine(
+            8.983152841195208e-05,
+            0.0,
+            115.483402043364,
+            0.0,
+            -8.983152841195208e-05,
+            53.531397320113605,
+        ),
+        "height": SIZE,
+        "width": SIZE,
+        "compress": "lzw",
+        "predictor": 2,
+    }
+
+    allowed_values = [0, 1, 2, 3, 15]
+
+    Z = np.random.choice(allowed_values, size=(SIZE, SIZE))
+
+    with rasterio.open(path, "w", **profile) as src:
+        src.write(Z, 1)
+
+
+if __name__ == "__main__":
+    dir = os.path.join(os.getcwd(), "13090442")
+
+    if os.path.exists(dir) and os.path.isdir(dir):
+        shutil.rmtree(dir)
+
+    os.makedirs(dir, exist_ok=True)
+
+    for file in files:
+        create_file(os.path.join(dir, file), dtype="int8")
+
+    # Compress data
+    shutil.make_archive("13090442", "zip", ".", dir)
+
+    # Compute checksums
+    with open("13090442.zip", "rb") as f:
+        md5 = hashlib.md5(f.read()).hexdigest()
+        print(f"13090442.zip: {md5}")

tests/data/nccm/13090442/CDL2017_clip.tif

@@ -14,7 +14,7 @@
 from pytest import MonkeyPatch
 
 import torchgeo.datasets.utils
-from torchgeo.datasets import ADVANCE
+from torchgeo.datasets import ADVANCE, DatasetNotFoundError
 
 
 def download_url(url: str, root: str, *args: str) -> None:
@@ -68,7 +68,7 @@ def test_already_downloaded(self, dataset: ADVANCE) -> None:
         ADVANCE(root=dataset.root, download=True)
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found or corrupted."):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             ADVANCE(str(tmp_path))
 
     def test_mock_missing_module(

tests/data/nccm/13090442/CDL2018_clip1.tif

@@ -15,6 +15,7 @@
 import torchgeo
 from torchgeo.datasets import (
     AbovegroundLiveWoodyBiomassDensity,
+    DatasetNotFoundError,
     IntersectionDataset,
     UnionDataset,
 )
@@ -53,7 +54,7 @@ def test_getitem(self, dataset: AbovegroundLiveWoodyBiomassDensity) -> None:
         assert isinstance(x["mask"], torch.Tensor)
 
     def test_no_dataset(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found"):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             AbovegroundLiveWoodyBiomassDensity(str(tmp_path))
 
     def test_already_downloaded(

tests/data/nccm/13090442/CDL2019_clip.tif

@@ -11,7 +11,13 @@
 import torch.nn as nn
 from rasterio.crs import CRS
 
-from torchgeo.datasets import AsterGDEM, BoundingBox, IntersectionDataset, UnionDataset
+from torchgeo.datasets import (
+    AsterGDEM,
+    BoundingBox,
+    DatasetNotFoundError,
+    IntersectionDataset,
+    UnionDataset,
+)
 
 
 class TestAsterGDEM:
@@ -26,7 +32,7 @@ def dataset(self, tmp_path: Path) -> AsterGDEM:
     def test_datasetmissing(self, tmp_path: Path) -> None:
         shutil.rmtree(tmp_path)
         os.makedirs(tmp_path)
-        with pytest.raises(RuntimeError, match="Dataset not found in"):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             AsterGDEM(str(tmp_path))
 
     def test_getitem(self, dataset: AsterGDEM) -> None:

tests/data/nccm/data.py

@@ -13,7 +13,7 @@
 from pytest import MonkeyPatch
 from torch.utils.data import ConcatDataset
 
-from torchgeo.datasets import BeninSmallHolderCashews
+from torchgeo.datasets import BeninSmallHolderCashews, DatasetNotFoundError
 
 
 class Collection:
@@ -73,7 +73,7 @@ def test_already_downloaded(self, dataset: BeninSmallHolderCashews) -> None:
         BeninSmallHolderCashews(root=dataset.root, download=True, api_key="")
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found or corrupted."):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             BeninSmallHolderCashews(str(tmp_path))
 
     def test_invalid_bands(self) -> None:

tests/datasets/test_advance.py

@@ -13,7 +13,7 @@
 from pytest import MonkeyPatch
 
 import torchgeo.datasets.utils
-from torchgeo.datasets import BigEarthNet
+from torchgeo.datasets import BigEarthNet, DatasetNotFoundError
 
 
 def download_url(url: str, root: str, *args: str, **kwargs: str) -> None:
@@ -134,10 +134,7 @@ def test_already_downloaded_not_extracted(
         )
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        err = "Dataset not found in `root` directory and `download=False`, "
-        "either specify a different `root` directory or use `download=True` "
-        "to automatically download the dataset."
-        with pytest.raises(RuntimeError, match=err):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             BigEarthNet(str(tmp_path))
 
     def test_plot(self, dataset: BigEarthNet) -> None:

tests/datasets/test_agb_live_woody_density.py

@@ -10,7 +10,7 @@
 import pytest
 from _pytest.fixtures import SubRequest
 
-from torchgeo.datasets import BioMassters
+from torchgeo.datasets import BioMassters, DatasetNotFoundError
 
 
 class TestBioMassters:
@@ -36,8 +36,7 @@ def test_invalid_bands(self, dataset: BioMassters) -> None:
             BioMassters(dataset.root, sensors=["S3"])
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        match = "Dataset not found"
-        with pytest.raises(RuntimeError, match=match):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             BioMassters(str(tmp_path))
 
     def test_plot(self, dataset: BioMassters) -> None:

tests/datasets/test_astergdem.py

@@ -16,6 +16,7 @@
 from torchgeo.datasets import (
     BoundingBox,
     CanadianBuildingFootprints,
+    DatasetNotFoundError,
     IntersectionDataset,
     UnionDataset,
 )
@@ -75,7 +76,7 @@ def test_plot_prediction(self, dataset: CanadianBuildingFootprints) -> None:
         dataset.plot(x, suptitle="Prediction")
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found or corrupted."):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             CanadianBuildingFootprints(str(tmp_path))
 
     def test_invalid_query(self, dataset: CanadianBuildingFootprints) -> None:

tests/datasets/test_benin_cashews.py

@@ -15,7 +15,13 @@
 from rasterio.crs import CRS
 
 import torchgeo.datasets.utils
-from torchgeo.datasets import CDL, BoundingBox, IntersectionDataset, UnionDataset
+from torchgeo.datasets import (
+    CDL,
+    BoundingBox,
+    DatasetNotFoundError,
+    IntersectionDataset,
+    UnionDataset,
+)
 
 
 def download_url(url: str, root: str, *args: str, **kwargs: str) -> None:
@@ -111,7 +117,7 @@ def test_plot_prediction(self, dataset: CDL) -> None:
         plt.close()
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found"):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             CDL(str(tmp_path))
 
     def test_invalid_query(self, dataset: CDL) -> None:

tests/datasets/test_bigearthnet.py

@@ -18,6 +18,7 @@
     BoundingBox,
     Chesapeake13,
     ChesapeakeCVPR,
+    DatasetNotFoundError,
     IntersectionDataset,
     UnionDataset,
 )
@@ -70,7 +71,7 @@ def test_already_downloaded(self, tmp_path: Path) -> None:
         Chesapeake13(root)
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found"):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             Chesapeake13(str(tmp_path), checksum=True)
 
     def test_plot(self, dataset: Chesapeake13) -> None:
@@ -193,7 +194,7 @@ def test_already_downloaded(self, tmp_path: Path) -> None:
         ChesapeakeCVPR(root)
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found"):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             ChesapeakeCVPR(str(tmp_path), checksum=True)
 
     def test_out_of_bounds_query(self, dataset: ChesapeakeCVPR) -> None:

tests/datasets/test_biomassters.py

@@ -12,7 +12,7 @@
 import torch.nn as nn
 from pytest import MonkeyPatch
 
-from torchgeo.datasets import CloudCoverDetection
+from torchgeo.datasets import CloudCoverDetection, DatasetNotFoundError
 
 
 class Collection:
@@ -83,7 +83,7 @@ def test_already_downloaded(self, dataset: CloudCoverDetection) -> None:
         CloudCoverDetection(root=dataset.root, split="test", download=True, api_key="")
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found or corrupted."):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             CloudCoverDetection(str(tmp_path))
 
     def test_plot(self, dataset: CloudCoverDetection) -> None:

tests/datasets/test_cbf.py

@@ -12,7 +12,12 @@
 from pytest import MonkeyPatch
 from rasterio.crs import CRS
 
-from torchgeo.datasets import CMSGlobalMangroveCanopy, IntersectionDataset, UnionDataset
+from torchgeo.datasets import (
+    CMSGlobalMangroveCanopy,
+    DatasetNotFoundError,
+    IntersectionDataset,
+    UnionDataset,
+)
 
 
 def download_url(url: str, root: str, *args: str, **kwargs: str) -> None:
@@ -45,7 +50,7 @@ def test_getitem(self, dataset: CMSGlobalMangroveCanopy) -> None:
         assert isinstance(x["mask"], torch.Tensor)
 
     def test_no_dataset(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found"):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             CMSGlobalMangroveCanopy(str(tmp_path))
 
     def test_already_downloaded(self, tmp_path: Path) -> None:

tests/datasets/test_cdl.py

@@ -14,8 +14,7 @@
 from torch.utils.data import ConcatDataset
 
 import torchgeo.datasets.utils
-from torchgeo.datasets import COWCCounting, COWCDetection
-from torchgeo.datasets.cowc import COWC
+from torchgeo.datasets import COWC, COWCCounting, COWCDetection, DatasetNotFoundError
 
 
 def download_url(url: str, root: str, *args: str, **kwargs: str) -> None:
@@ -78,7 +77,7 @@ def test_invalid_split(self) -> None:
             COWCCounting(split="foo")
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found or corrupted."):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             COWCCounting(str(tmp_path))
 
     def test_plot(self, dataset: COWCCounting) -> None:
@@ -142,7 +141,7 @@ def test_invalid_split(self) -> None:
             COWCDetection(split="foo")
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found or corrupted."):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             COWCDetection(str(tmp_path))
 
     def test_plot(self, dataset: COWCDetection) -> None:

tests/datasets/test_chesapeake.py

@@ -13,7 +13,7 @@
 from pytest import MonkeyPatch
 from torch.utils.data import ConcatDataset
 
-from torchgeo.datasets import CV4AKenyaCropType
+from torchgeo.datasets import CV4AKenyaCropType, DatasetNotFoundError
 
 
 class Collection:
@@ -84,7 +84,7 @@ def test_already_downloaded(self, dataset: CV4AKenyaCropType) -> None:
         CV4AKenyaCropType(root=dataset.root, download=True, api_key="")
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found or corrupted."):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             CV4AKenyaCropType(str(tmp_path))
 
     def test_invalid_tile(self, dataset: CV4AKenyaCropType) -> None:

tests/datasets/test_cloud_cover.py

@@ -14,7 +14,7 @@
 from pytest import MonkeyPatch
 from torch.utils.data import ConcatDataset
 
-from torchgeo.datasets import TropicalCyclone
+from torchgeo.datasets import DatasetNotFoundError, TropicalCyclone
 
 
 class Collection:
@@ -80,7 +80,7 @@ def test_invalid_split(self) -> None:
             TropicalCyclone(split="foo")
 
     def test_not_downloaded(self, tmp_path: Path) -> None:
-        with pytest.raises(RuntimeError, match="Dataset not found or corrupted."):
+        with pytest.raises(DatasetNotFoundError, match="Dataset not found"):
             TropicalCyclone(str(tmp_path))
 
     def test_plot(self, dataset: TropicalCyclone) -> None: