class TestSample(TestCase):
def setUp(self) -> None:
predictors = [nc.band1, nc.band2, nc.band3, nc.band4, nc.band5, nc.band7]
self.stack = Raster(predictors)
self.strata = Raster(nc.strata)
def tearDown(self) -> None:
self.stack.close()
self.strata.close()
def test_sample_strata(self):
# extract using a strata raster and returning two arrays
size = 100
categories = self.strata.read(masked=True).flatten()
categories = categories[~categories.mask]
n_categories = np.unique(categories).shape[0]
n_samples = size * n_categories
X, xy = self.stack.sample(size=size, strata=self.strata, return_array=True)
self.assertEqual(X.shape, (n_samples, 6))
self.assertEqual(xy.shape, (n_samples, 2))
# extract using a strata raster and returning a dataframe
samples = self.stack.sample(size=size, strata=self.strata, return_array=False)
self.assertEqual(samples.shape, (n_samples, 7))
def test_sample_no_strata(self):
size = 100
X, xy = self.stack.sample(size=size, return_array=True)
self.assertEqual(X.shape, (size, 6))
self.assertEqual(xy.shape, (size, 2))
samples = self.stack.sample(size=size, return_array=False)
self.assertEqual(samples.shape, (size, 7))
def test_append_with_copy(self):
"""Same tests as above but create a new Raster rather than append
in place
"""
# append another Raster containing a single layer with identical name
stack = Raster(self.predictors)
band7_mean = stack["lsat7_2000_70"].read(masked=True).mean()
result = stack.append(Raster(nc.band7), in_place=False)
# check that original is untouched
self.assertEqual(stack.count, 6)
# check that result contains appended raster
self.assertEqual(list(result.names)[5], "lsat7_2000_70_1")
self.assertEqual(list(result.names)[-1], "lsat7_2000_70_2")
# check that band 7 stats are the same after appending
self.assertEqual(
result.lsat7_2000_70_1.read(masked=True).mean(),
result.lsat7_2000_70_2.read(masked=True).mean(),
band7_mean,
)
# append a multiband raster
result = stack.append(Raster(nc.multiband), in_place=False)
self.assertEqual(list(result.names)[6], "landsat_multiband_1")
stack.close()
# append multiple rasters
stack = Raster(self.predictors)
new_stack = stack.append(
[Raster(nc.band5), Raster(nc.band7)], in_place=False)
self.assertEqual(new_stack.count, 8)
class TestToCrs(TestCase):
def setUp(self) -> None:
# inputs
self.predictors = [
nc.band1, nc.band2, nc.band3, nc.band4, nc.band5, nc.band7
]
self.stack = Raster(self.predictors)
training_py = gpd.read_file(nc.polygons)
self.crop_bounds = training_py.loc[0, "geometry"].bounds
# outputs
self.cropped = None
def tearDown(self) -> None:
self.stack.close()
self.cropped.close()
def test_crop_defaults(self):
self.cropped = self.stack.crop(self.crop_bounds)
# check raster object
self.assertIsInstance(self.cropped, Raster)
self.assertEqual(self.cropped.count, self.stack.count)
self.assertEqual(self.cropped.read(masked=True).count(), 1440)
# test nodata value is recognized
self.assertEqual(self.cropped.read(masked=True).min(), 35.0)
self.assertEqual(self.cropped.read(masked=True).max(), 168.0)
def test_crop_in_memory(self):
self.cropped = self.stack.crop(self.crop_bounds, in_memory=True)
self.assertIsInstance(self.cropped, Raster)
class TestPlotting(TestCase):
def setUp(self) -> None:
self.predictors = [
nc.band1, nc.band2, nc.band3, nc.band4, nc.band5, nc.band7
]
self.stack = Raster(self.predictors)
self.stack_single = Raster(self.predictors[0])
def tearDown(self) -> None:
self.stack.close()
self.stack_single.close()
def test_plotting_raster(self):
# test basic raster matrix plot
p = self.stack.plot()
self.assertIsInstance(p, np.ndarray)
# test with arguments
p = self.stack.plot(
cmap="plasma",
norm=mpl.colors.Normalize(vmin=10, vmax=100),
title_fontsize=10,
label_fontsize=10,
names=["band1", "band2", "band3", "band4", "band5", "band7"],
figsize=(10, 5),
legend_kwds={"orientation": "horizontal"})
self.assertIsInstance(p, np.ndarray)
def test_plotting_single(self):
p = self.stack_single.plot(legend_kwds={
"orientation": "horizontal",
"fraction": 0.04
})
self.assertIsInstance(p, mpl.axes.Subplot)
def test_append_inplace(self):
"""Append another Raster containing a single layer with identical name
This test should cause the Raster object to automatically rename the
duplicated names as "lsat7_2000_70_1", "lsat7_2000_70_2", etc.
Appending a multi-band raster should result in a new layer with the
multi-band name "landsat_multiband_1", "landsat_multiband_2", etc.
A list of Rasters can be passed to append() to append multiple rasters
"""
# append a single band raster with the same name
stack = Raster(self.predictors)
band7_mean = stack["lsat7_2000_70"].read(masked=True).mean()
stack.append(Raster(nc.band7), in_place=True)
self.assertEqual(list(stack.names)[5], "lsat7_2000_70_1")
self.assertEqual(list(stack.names)[-1], "lsat7_2000_70_2")
self.assertEqual(
stack.lsat7_2000_70_1.read(masked=True).mean(),
stack.lsat7_2000_70_2.read(masked=True).mean(),
band7_mean,
)
# append a multiband raster
stack = Raster(self.predictors)
stack.append(Raster(nc.multiband), in_place=True)
self.assertEqual(list(stack.names)[6], "landsat_multiband_1")
stack.close()
# append multiple rasters
stack = Raster(self.predictors)
stack.append([Raster(nc.band5), Raster(nc.band7)], in_place=True)
self.assertEqual(stack.count, 8)
def test_subset_multiple_layers(self):
stack = Raster(self.predictors + [nc.multiband])
# Subset multiple layers using a slice of index positions
# - returns a Raster object
self.assertIsInstance(stack.iloc[0:2], Raster)
# Subset multiple layers using a list of index positions
# - returns a Raster object
self.assertIsInstance(stack.iloc[[0, 1, 2]], Raster)
# Subset multiple layers using a list of labels
# - returns a Raster object
subset_raster = stack[["lsat7_2000_10", "lsat7_2000_70"]]
self.assertIsInstance(subset_raster, Raster)
self.assertListEqual(list(subset_raster.names),
["lsat7_2000_10", "lsat7_2000_70"])
# Check that label and integer subset return the same layers
self.assertListEqual(
list(stack.iloc[0:3].names),
list(stack[["lsat7_2000_10", "lsat7_2000_20",
"lsat7_2000_30"]].names),
)
stack.close()
class TestCalc(TestCase):
def setUp(self) -> None:
predictors = [nc.band1, nc.band2, nc.band3, nc.band4, nc.band5, nc.band7]
self.stack = Raster(predictors)
self.result = None
def tearDown(self) -> None:
self.stack.close()
self.result.close()
self.stack = None
self.result = None
def test_calc_with_2d_output(self):
def compute_outputs_2d_array(arr):
return arr[0, :, :] + arr[1, :, :]
self.result = self.stack.apply(compute_outputs_2d_array)
self.assertIsInstance(self.result, Raster)
self.assertEqual(self.result.count, 1)
self.assertEqual(self.result.read(masked=True).count(), 183418)
def test_calc_with_2d_output_coerce_dtype(self):
def compute_outputs_2d_array(arr):
return arr[0, :, :] + arr[1, :, :]
self.result = self.stack.apply(compute_outputs_2d_array, dtype=np.int16)
self.assertIsInstance(self.result, Raster)
self.assertEqual(self.result.count, 1)
self.assertEqual(self.result.read(masked=True).count(), 183418)
def test_calc_with_3d_output(self):
def compute_outputs_3d_array(arr):
arr[0, :, :] = arr[0, :, :] + arr[1, ::]
return arr
self.result = self.stack.apply(compute_outputs_3d_array)
self.assertIsInstance(self.result, Raster)
self.assertEqual(self.result.count, 6)
self.assertEqual(self.result.read(masked=True).count(), 1052182)
def test_calc_with_multiprocessing(self):
def compute_outputs_2d_array(arr):
return arr[0, :, :] + arr[1, :, :]
self.result = self.stack.apply(compute_outputs_2d_array)
self.assertIsInstance(self.result, Raster)
self.assertEqual(self.result.count, 1)
self.assertEqual(self.result.read(masked=True).count(), 183418)
def test_calc_in_memory(self):
def compute_outputs_2d_array(arr):
return arr[0, :, :] + arr[1, :, :]
self.result = self.stack.apply(compute_outputs_2d_array, in_memory=True)
self.assertIsInstance(self.result, Raster)
self.assertEqual(self.result.count, 1)
self.assertEqual(self.result.read(masked=True).count(), 183418)
class TestIntersect(TestCase):
def setUp(self) -> None:
# inputs
self.predictors = [nc.band1, nc.band2, nc.band3, nc.band4, nc.band5,
nc.band7]
self.stack = Raster(self.predictors)
# test results
self.result = None
def tearDown(self) -> None:
self.stack.close()
self.result.close()
def test_intersect_defaults(self):
self.result = self.stack.intersect()
# check raster object
self.assertIsInstance(self.result, Raster)
self.assertEqual(self.result.count, self.stack.count)
self.assertEqual(self.result.read(masked=True).count(), 810552)
# test nodata value is recognized
self.assertEqual(self.result.read(masked=True).min(), 1.0)
self.assertEqual(self.result.read(masked=True).max(), 255.0)
def test_intersect_custom_dtype(self):
self.result = self.stack.intersect(dtype=np.int16)
# check raster object
self.assertIsInstance(self.result, Raster)
self.assertEqual(self.result.count, self.stack.count)
self.assertEqual(self.result.read(masked=True).count(), 810552)
# test nodata value is recognized
self.assertEqual(self.result.read(masked=True).min(), 1)
self.assertEqual(self.result.read(masked=True).max(), 255)
def test_intersect_custom_nodata(self):
self.result = self.stack.intersect(dtype=np.int16, nodata=-999)
# check raster object
self.assertIsInstance(self.result, Raster)
self.assertEqual(self.result.count, self.stack.count)
self.assertEqual(self.result.read(masked=True).count(), 810552)
# test nodata value is recognized
self.assertEqual(self.result.read(masked=True).min(), 1)
self.assertEqual(self.result.read(masked=True).max(), 255)
def test_intersect_in_memory(self):
self.result = self.stack.intersect(in_memory=True)
# check raster object
self.assertIsInstance(self.result, Raster)
def test_drop_inplace(self):
stack = Raster(self.predictors)
stack.drop(labels="lsat7_2000_50", in_place=True)
# check that Raster object is returned
self.assertIsInstance(stack, Raster)
# check that RasterLayer has been dropped
self.assertEqual(stack.count, 5)
self.assertNotIn("lsat7_2000_50", stack.names)
stack.close()
class TestToCrs(TestCase):
def setUp(self) -> None:
# test inputs
predictors = [
nc.band1, nc.band2, nc.band3, nc.band4, nc.band5, nc.band7
]
self.stack = Raster(predictors)
# test results
self.stack_prj = None
def tearDown(self) -> None:
self.stack.close()
self.stack_prj.close()
def test_to_crs_defaults(self):
self.stack_prj = self.stack.to_crs({"init": "EPSG:4326"})
# check raster object
self.assertIsInstance(self.stack_prj, Raster)
self.assertEqual(self.stack_prj.count, self.stack.count)
self.assertEqual(self.stack_prj.read(masked=True).count(), 1012061)
# test nodata value is recognized
self.assertEqual(
self.stack_prj.read(masked=True).min(),
self.stack.read(masked=True).min())
self.assertEqual(
self.stack_prj.read(masked=True).max(),
self.stack.read(masked=True).max())
def test_to_crs_custom_nodata(self):
self.stack_prj = self.stack.to_crs({"init": "EPSG:4326"}, nodata=-999)
# check raster object
self.assertIsInstance(self.stack_prj, Raster)
self.assertEqual(self.stack_prj.count, self.stack.count)
self.assertEqual(self.stack_prj.read(masked=True).count(), 1012061)
# test nodata value is recognized
self.assertEqual(
self.stack_prj.read(masked=True).min(),
self.stack.read(masked=True).min())
self.assertEqual(
self.stack_prj.read(masked=True).max(),
self.stack.read(masked=True).max())
def test_to_crs_in_memory(self):
self.stack_prj = self.stack.to_crs({"init": "EPSG:4326"},
in_memory=True)
# check raster object
self.assertIsInstance(self.stack_prj, Raster)
def test_drop_with_copy(self):
stack = Raster(self.predictors)
names = stack.names
result = stack.drop(labels="lsat7_2000_50", in_place=False)
# check that Raster object is returned
self.assertIsInstance(result, Raster)
# check that RasterLayer has been dropped
self.assertEqual(result.count, 5)
self.assertNotIn("lsat7_2000_50", result.names)
# check that original raster is unaffected
self.assertEqual(stack.count, 6)
self.assertEqual(stack.names, names)
stack.close()
result.close()
def test_indexing(self):
stack = Raster(self.predictors + [nc.multiband])
# replace band 1 with band 7
band7_mean = stack["lsat7_2000_70"].read(masked=True).mean()
stack.iloc[0] = Raster(nc.band7).iloc[0]
self.assertEqual(stack.iloc[0].read(masked=True).mean(), band7_mean)
self.assertEqual(stack["lsat7_2000_10"].read(masked=True).mean(),
band7_mean)
self.assertEqual(stack["lsat7_2000_10"].read(masked=True).mean(),
band7_mean)
self.assertEqual(
stack.lsat7_2000_10.read(masked=True).mean(), band7_mean)
stack.close()
def test_append_inplace(self):
# append another Raster containing a single layer with identical name
stack = Raster(self.predictors)
band7_mean = stack["lsat7_2000_70"].read(masked=True).mean()
stack.append(Raster(nc.band7), in_place=True)
self.assertEqual(stack.names[5], "lsat7_2000_70_1")
self.assertEqual(stack.names[-1], "lsat7_2000_70_2")
self.assertEqual(
stack.lsat7_2000_70_1.read(masked=True).mean(),
stack.lsat7_2000_70_2.read(masked=True).mean(),
band7_mean,
)
# append a multiband raster
stack = Raster(self.predictors)
stack.append(Raster(nc.multiband), in_place=True)
self.assertEqual(stack.names[6], "landsat_multiband_1")
stack.close()
def test_subset_single_layer(self):
stack = Raster(self.predictors + [nc.multiband])
# Subset a single layer using an index position - returns a RasterLayer
self.assertIsInstance(stack.iloc[0], RasterLayer)
# Subset a single layer using a label - returns a RasterLayer
self.assertIsInstance(stack["lsat7_2000_10"], RasterLayer)
# Subset a single layer using an attribute - returns a RasterLayer
self.assertIsInstance(stack.lsat7_2000_10, RasterLayer)
# Check that the raster values are the same as the original values
# after subsetting
self.assertEqual(
stack.lsat7_2000_10.read(masked=True).mean(), 80.56715262406088)
self.assertEqual(
stack.lsat7_2000_70.read(masked=True).mean(), 59.17773813401238)
stack.close()
class TestAlter(TestCase):
def setUp(self) -> None:
predictors = [
nc.band1, nc.band2, nc.band3, nc.band4, nc.band5, nc.band7
]
self.stack = Raster(predictors)
points = gpd.read_file(nc.points)
data = self.stack.extract_vector(points)
self.data = data.dropna()
def tearDown(self) -> None:
self.stack.close()
def test_alter(self):
scaler = StandardScaler()
scaler.fit(self.data.drop(columns=["geometry"]).values)
out = self.stack.alter(scaler)
self.assertIsInstance(out, Raster)
self.assertEqual(out.shape, self.stack.shape)
def test_naming(self):
stack = Raster(self.predictors + [nc.multiband])
# check unique naming when stacking multiband raster
self.assertEqual(stack.count, 11)
expected_names = [
"lsat7_2000_10",
"lsat7_2000_20",
"lsat7_2000_30",
"lsat7_2000_40",
"lsat7_2000_50",
"lsat7_2000_70",
"landsat_multiband_1",
"landsat_multiband_2",
"landsat_multiband_3",
"landsat_multiband_4",
"landsat_multiband_5",
]
self.assertListEqual(list(stack.names), expected_names)
stack.close()
def test_append_with_copy(self):
# append another Raster containing a single layer with identical name
stack = Raster(self.predictors)
band7_mean = stack["lsat7_2000_70"].read(masked=True).mean()
result = stack.append(Raster(nc.band7), in_place=False)
# check that original is untouched
self.assertEqual(stack.count, 6)
# check that result contains appended raster
self.assertEqual(result.names[5], "lsat7_2000_70_1")
self.assertEqual(result.names[-1], "lsat7_2000_70_2")
# check that band 7 stats are the same after appending
self.assertEqual(
result.lsat7_2000_70_1.read(masked=True).mean(),
result.lsat7_2000_70_2.read(masked=True).mean(),
band7_mean,
)
# append a multiband raster
result = stack.append(Raster(nc.multiband), in_place=False)
self.assertEqual(result.names[6], "landsat_multiband_1")
stack.close()
class TestMask(TestCase):
def setUp(self) -> None:
# test inputs
training_py = gpd.read_file(nc.polygons)
self.mask_py = training_py.iloc[0:1, :]
predictors = [
nc.band1, nc.band2, nc.band3, nc.band4, nc.band5, nc.band7
]
self.stack = Raster(predictors)
# test results
self.masked_object = None
def tearDown(self) -> None:
self.stack.close()
self.masked_object.close()
def test_mask_defaults(self):
self.masked_object = self.stack.mask(self.mask_py)
# check raster object
self.assertIsInstance(self.masked_object, Raster)
self.assertEqual(self.masked_object.count, self.stack.count)
self.assertEqual(self.masked_object.read(masked=True).count(), 738)
# test nodata value is recognized
self.assertEqual(self.masked_object.read(masked=True).min(), 38.0)
self.assertEqual(self.masked_object.read(masked=True).max(), 168.0)
def test_mask_inverted(self):
self.masked_object = self.stack.mask(self.mask_py, invert=True)
# check raster object
self.assertIsInstance(self.masked_object, Raster)
self.assertEqual(self.masked_object.count, self.stack.count)
self.assertEqual(self.masked_object.read(masked=True).count(), 1051444)
# test nodata value is recognized
self.assertEqual(self.masked_object.read(masked=True).min(), 1.0)
self.assertEqual(self.masked_object.read(masked=True).max(), 255.0)
def test_mask_custom_dtype(self):
self.masked_object = self.stack.mask(self.mask_py, dtype=np.int16)
# check raster object
self.assertIsInstance(self.masked_object, Raster)
self.assertEqual(self.masked_object.count, self.stack.count)
self.assertEqual(self.masked_object.read(masked=True).count(), 738)
# test nodata value is recognized
self.assertEqual(self.masked_object.read(masked=True).min(), 38)
self.assertEqual(self.masked_object.read(masked=True).max(), 168)
def test_mask_custom_nodata(self):
self.masked_object = self.stack.mask(self.mask_py, nodata=-99999)
# check raster object
self.assertIsInstance(self.masked_object, Raster)
self.assertEqual(self.masked_object.count, self.stack.count)
self.assertEqual(self.masked_object.read(masked=True).count(), 738)
# test nodata value is recognized
self.assertEqual(self.masked_object.read(masked=True).min(), 38.0)
self.assertEqual(self.masked_object.read(masked=True).max(), 168.0)
def test_mask_in_memory(self):
self.masked_object = self.stack.mask(self.mask_py, in_memory=True)
# check raster object
self.assertIsInstance(self.masked_object, Raster)
class TestExtract(TestCase):
def setUp(self) -> None:
self.predictors = [
nc.band1, nc.band2, nc.band3, nc.band4, nc.band5, nc.band7
]
self.extracted_grass = pd.read_table(nc.extracted_pixels,
delimiter=" ")
self.stack = Raster(self.predictors)
def tearDown(self) -> None:
self.stack.close()
def test_extract_points(self):
training_pt = geopandas.read_file(nc.points)
# check that extracted training data as a DataFrame match known values
df = self.stack.extract_vector(gdf=training_pt)
df = df.dropna()
training_pt = training_pt.dropna()
self.assertTrue(
(df["lsat7_2000_10"].values == training_pt["b1"].values).all())
self.assertTrue(
(df["lsat7_2000_20"].values == training_pt["b2"].values).all())
self.assertTrue(
(df["lsat7_2000_30"].values == training_pt["b3"].values).all())
self.assertTrue(
(df["lsat7_2000_40"].values == training_pt["b4"].values).all())
self.assertTrue(
(df["lsat7_2000_50"].values == training_pt["b5"].values).all())
self.assertTrue(
(df["lsat7_2000_70"].values == training_pt["b7"].values).all())
def test_extract_polygons(self):
# extract training data from polygons
training_py = geopandas.read_file(nc.polygons)
df = self.stack.extract_vector(gdf=training_py)
df = df.dropna()
df = df.merge(
right=training_py.loc[:, ("id", "label")],
left_on="geometry_idx",
right_on="index",
right_index=True,
)
# compare to extracted data using GRASS GIS
self.assertEqual(df.shape[0], self.extracted_grass.shape[0])
self.assertAlmostEqual(df["lsat7_2000_10"].mean(),
self.extracted_grass["b1"].mean(),
places=2)
self.assertAlmostEqual(df["lsat7_2000_20"].mean(),
self.extracted_grass["b2"].mean(),
places=2)
self.assertAlmostEqual(df["lsat7_2000_30"].mean(),
self.extracted_grass["b3"].mean(),
places=2)
self.assertAlmostEqual(df["lsat7_2000_40"].mean(),
self.extracted_grass["b4"].mean(),
places=2)
self.assertAlmostEqual(df["lsat7_2000_50"].mean(),
self.extracted_grass["b5"].mean(),
places=2)
self.assertAlmostEqual(df["lsat7_2000_70"].mean(),
self.extracted_grass["b7"].mean(),
places=2)
def test_extract_lines(self):
# extract training data from lines
training_py = geopandas.read_file(nc.polygons)
training_lines = deepcopy(training_py)
training_lines["geometry"] = training_lines.geometry.boundary
df = self.stack.extract_vector(gdf=training_lines).dropna()
# check shapes of extracted pixels
self.assertEqual(df.shape[0], 948)
def test_extract_raster(self):
# extract training data from labelled pixels
with rasterio.open(nc.labelled_pixels) as src:
df = self.stack.extract_raster(src)
df = df.dropna()
self.assertEqual(df.shape[0], self.extracted_grass.shape[0])
self.assertAlmostEqual(df["lsat7_2000_10"].mean(),
self.extracted_grass["b1"].mean(),
places=3)
self.assertAlmostEqual(df["lsat7_2000_20"].mean(),
self.extracted_grass["b2"].mean(),
places=3)
self.assertAlmostEqual(df["lsat7_2000_30"].mean(),
self.extracted_grass["b3"].mean(),
places=3)
self.assertAlmostEqual(df["lsat7_2000_40"].mean(),
self.extracted_grass["b4"].mean(),
places=3)
self.assertAlmostEqual(df["lsat7_2000_50"].mean(),
self.extracted_grass["b5"].mean(),
places=3)
self.assertAlmostEqual(df["lsat7_2000_70"].mean(),
self.extracted_grass["b7"].mean(),
places=3)
