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))
# prediction result = stack.predict(estimator=lr, dtype='int16', nodata=0) result_prob = stack.predict_proba(estimator=lr) result.names result_prob.names result.plot() plt.show() result_prob.plot() plt.show() # sampling # extract training data using a random sample df_rand = stack.sample(size=1000, random_state=1) df_rand.plot() plt.show() # extract training data using a stratified random sample from a map containing categorical data # here we are taking 50 samples per category strata = rasterio.open(os.path.join(basedir, 'pyspatialml', 'nc_dataset', 'strata.tif')) df_strata = stack.sample(size=5, strata=strata, random_state=1) df_strata = df_strata.dropna() fig, ax = plt.subplots() ax.imshow(strata.read(1, masked=True), extent=rasterio.plot.plotting_extent(strata)) df_strata.plot(ax=ax, markersize=2, color='red') plt.show() from pyspatialml.transformations import one_hot_encode