Adding South America Soybean Dataset

docs/api/geo_datasets.csv

@@ -20,3 +20,4 @@ Dataset,Type,Source,Size (px),Resolution (m)
 `NLCD`_,Masks,Landsat,-,30
 `Open Buildings`_,Geometries,"Maxar, CNES/Airbus",-,-
 `Sentinel`_,Imagery,Sentinel,"10,000x10,000",10
+`South America Soybean`_,Masks,Sentinel-2,-,10 

tests/data/south_america_soybean/data.py

@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+#os.environ['PROJ_LIB'] = r'E:\Programs\anaconda3\envs\gis\Library\share\proj'
+import hashlib
+import os
+import shutil
+
+import numpy as np
+import rasterio
+from rasterio.crs import CRS
+from rasterio.transform import Affine
+
+SIZE = 32
+wkt = """
+PROJCS["Albers Conical Equal Area",
+    GEOGCS["WGS 84",
+        DATUM["WGS_1984",
+            SPHEROID["WGS 84",6378137,298.257223563,
+                AUTHORITY["EPSG","7030"]],
+            AUTHORITY["EPSG","6326"]],
+        PRIMEM["Greenwich",0,AUTHORITY["EPSG","8901"]],
+        UNIT["degree",0.0174532925199433,AUTHORITY["EPSG","9122"]],
+        AUTHORITY["EPSG","4326"]],
+    PROJECTION["Albers_Conic_Equal_Area"],
+    PARAMETER["latitude_of_center",23],
+    PARAMETER["longitude_of_center",-96],
+    PARAMETER["standard_parallel_1",29.5],
+    PARAMETER["standard_parallel_2",45.5],
+    PARAMETER["false_easting",0],
+    PARAMETER["false_northing",0],
+    UNIT["meters",1],
+    AXIS["Easting",EAST],
+    AXIS["Northing",NORTH]]
+"""
+
+
+np.random.seed(0)
+files = ["South_America_Soybean_2002.tif", "South_America_Soybean_2021.tif"]
+
+def create_file(path: str, dtype: str):
+    """Create the testing file."""
+    profile = {
+        "driver": "GTiff",
+        "dtype": dtype,
+        "count": 1,
+        #"crs": CRS.from_wkt(wkt),
+        "transform": Affine(
+            0.0002499999999999943131,
+            0.0,
+            -82.0005000000000024,
+            0.0,
+            -0.0002499999999999943131,
+            0.0005000000000000,
+        ),
+        "height": SIZE,
+        "width": SIZE,
+        "compress": "lzw",
+        "predictor": 2,
+    }
+
+    allowed_values = [0, 1]
+
+    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(), "SouthAmericaSoybean")
+    print(dir)
+    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("SouthAmericaSoybean", "zip", ".", dir)
+
+    # Compute checksums
+    with open("SouthAmericaSoybean.zip", "rb") as f:
+        md5 = hashlib.md5(f.read()).hexdigest()
+        print(f"SouthAmericaSoybean.zip: {md5}")

tests/datasets/test_south_america_soybean.py

@@ -0,0 +1,110 @@
+import os
+import shutil
+from pathlib import Path
+
+import matplotlib.pyplot as plt
+import pytest
+import torch
+import torch.nn as nn
+from pytest import MonkeyPatch
+from rasterio.crs import CRS
+
+import torchgeo.datasets.utils
+from torchgeo.datasets import south_america_soybean, BoundingBox, IntersectionDataset, UnionDataset
+
+
+def download_url(url: str, root: str, *args: str, **kwargs: str) -> None:
+    shutil.copy(url, root)
+
+
+class TestSouthAmericaSoybean:
+    @pytest.fixture
+    def dataset(self, monkeypatch: MonkeyPatch, tmp_path: Path) -> south_america_soybean:
+        monkeypatch.setattr(torchgeo.datasets.southamerica_soybean, "download_url", download_url)
+        transforms = nn.Identity()
+        md5s = {
+            2002: "8a4a9dcea54b3ec7de07657b9f2c0893",
+            2021: "edff3ada13a1a9910d1fe844d28ae4f",
+        }
+        monkeypatch.setattr(south_america_soybean, "md5s", md5s)
+
+        url = os.path.join("tests", "data", "south_america_soybean", "SouthAmerica_Soybean_{}.tif")
+        monkeypatch.setattr(south_america_soybean, "url", url)
+
+
+        return south_america_soybean(
+            transforms=transforms,
+            download=True,
+            checksum=True,
+            years=[2002, 2021],
+        )
+
+    def test_getitem(self, dataset: south_america_soybean) -> None:
+        x = dataset[dataset.bounds]
+        assert isinstance(x, dict)
+        assert isinstance(x["crs"], CRS)
+        assert isinstance(x["mask"], torch.Tensor)
+
+    def test_classes(self) -> None:
+        root = os.path.join("tests", "data", "southamerica_soybean")
+        classes = list(south_america_soybean.cmap.keys())[0:2]
+        ds = south_america_soybean(root, years=[2021], classes=classes)
+        sample = ds[ds.bounds]
+        mask = sample["mask"]
+        assert mask.max() < len(classes)
+
+    def test_and(self, dataset: south_america_soybean) -> None:
+        ds = dataset & dataset
+        assert isinstance(ds, IntersectionDataset)
+
+    def test_or(self, dataset: south_america_soybean) -> None:
+        ds = dataset | dataset
+        assert isinstance(ds, UnionDataset)
+
+    def test_already_extracted(self, dataset: south_america_soybean) -> None:
+        south_america_soybean(dataset.paths, download=True, years=[2021])
+
+    def test_already_downloaded(self, tmp_path: Path) -> None:
+        pathname = os.path.join("tests", "data", "southamerica_soybean", "SouthAmerica_Soybean_2021.tif")
+        root = str(tmp_path)
+
+        shutil.copy(pathname, root)
+        south_america_soybean(root, years=[2021])
+
+    def test_invalid_year(self, tmp_path: Path) -> None:
+        with pytest.raises(
+            AssertionError,
+            match="south_america_soybean data product only exists for the following years:",
+        ):
+            south_america_soybean(str(tmp_path), years=[1996])
+
+    def test_invalid_classes(self) -> None:
+        with pytest.raises(AssertionError):
+            south_america_soybean(classes=[-1])
+
+        with pytest.raises(AssertionError):
+            south_america_soybean(classes=[11])
+
+    def test_plot(self, dataset: south_america_soybean) -> None:
+        query = dataset.bounds
+        x = dataset[query]
+        dataset.plot(x, suptitle="Test")
+        plt.close()
+
+    def test_plot_prediction(self, dataset: south_america_soybean) -> None:
+        query = dataset.bounds
+        x = dataset[query]
+        x["prediction"] = x["mask"].clone()
+        dataset.plot(x, suptitle="Prediction")
+        plt.close()
+
+    def test_not_downloaded(self, tmp_path: Path) -> None:
+        with pytest.raises(RuntimeError, match="Dataset not found"):
+            south_america_soybean(str(tmp_path))
+
+    def test_invalid_query(self, dataset: south_america_soybean) -> None:
+        query = BoundingBox(0, 0, 0, 0, 0, 0)
+        with pytest.raises(
+            IndexError, match="query: .* not found in index with bounds:"
+        ):
+            dataset[query]

torchgeo/datasets/__init__.py

@@ -92,6 +92,7 @@
 from .sentinel import Sentinel, Sentinel1, Sentinel2
 from .skippd import SKIPPD
 from .so2sat import So2Sat
+from .south_america_soybean import SouthAmericaSoybean
 from .spacenet import (
     SpaceNet,
     SpaceNet1,
@@ -173,6 +174,7 @@
     "Sentinel",
     "Sentinel1",
     "Sentinel2",
+    "SouthAmericaSoybean"
     # NonGeoDataset
     "ADVANCE",
     "BeninSmallHolderCashews",