def test_regression(self):
stack = Raster(ms.predictors)
training_pt = gpd.read_file(ms.meuse)
training = stack.extract_vector(
response=training_pt,
columns=['cadmium', 'copper', 'lead', 'zinc'])
# single target regression
regr = RandomForestRegressor(n_estimators=50)
X = training.loc[:, stack.names]
y = training['zinc']
regr.fit(X, y)
single_regr = stack.predict(regr)
self.assertIsInstance(single_regr, Raster)
self.assertEqual(single_regr.count, 1)
# multi-target regression
y = training.loc[:, ['zinc', 'cadmium', 'copper', 'lead']]
regr.fit(X, y)
multi_regr = stack.predict(regr)
self.assertIsInstance(multi_regr, Raster)
self.assertEqual(multi_regr.count, 4)
def test_regression(self):
meuse_predictors = os.listdir(meuse_dir)
meuse_predictors = [
os.path.join(meuse_dir, i) for i in meuse_predictors
if i.endswith('.tif')
]
stack = Raster(meuse_predictors)
self.assertEqual(stack.count, 21)
training_pt = gpd.read_file(os.path.join(meuse_dir, 'meuse.shp'))
training = stack.extract_vector(response=training_pt, field='cadmium')
training['copper'] = stack.extract_vector(response=training_pt,
field='copper')['copper']
training['lead'] = stack.extract_vector(response=training_pt,
field='lead')['lead']
training['zinc'] = stack.extract_vector(response=training_pt,
field='zinc')['zinc']
# single target regression
regr = RandomForestRegressor(n_estimators=50)
X = training.loc[:, stack.names]
y = training['zinc']
regr.fit(X, y)
single_regr = stack.predict(regr)
self.assertIsInstance(single_regr, Raster)
self.assertEqual(single_regr.count, 1)
# multi-target regression
y = training.loc[:, ['zinc', 'cadmium', 'copper', 'lead']]
regr.fit(X, y)
multi_regr = stack.predict(regr)
self.assertIsInstance(multi_regr, Raster)
self.assertEqual(multi_regr.count, 4)
def test_classification(self):
stack = Raster(self.predictors)
training_pt = gpd.read_file(nc.points)
df_points = stack.extract_vector(response=training_pt, columns='id')
clf = RandomForestClassifier(n_estimators=50)
X = df_points.drop(columns=['id', 'geometry'])
y = df_points.id
clf.fit(X, y)
# classification
cla = stack.predict(estimator=clf, dtype='int16', nodata=0)
self.assertIsInstance(cla, Raster)
self.assertEqual(cla.count, 1)
self.assertEqual(cla.read(masked=True).count(), 135092)
# class probabilities
probs = stack.predict_proba(estimator=clf)
self.assertIsInstance(cla, Raster)
self.assertEqual(probs.count, 7)
for _, layer in probs:
self.assertEqual(layer.read(masked=True).count(), 135092)
# spatial cross-validation from sklearn.cluster import KMeans # create 10 spatial clusters based on clustering of the training data point x,y coordinates clusters = KMeans(n_clusters=34, n_jobs=-1) clusters.fit(df_polygons.geometry.bounds.iloc[:, 0:2]) # cross validate scores = cross_validate( lr, X, y, groups=clusters.labels_, scoring='accuracy', cv=3, n_jobs=1) scores['test_score'].mean() # 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()
# create 10 spatial clusters based on clustering of the training data point x,y coordinates clusters = KMeans(n_clusters=34, n_jobs=-1) clusters.fit(df_polygons.geometry.bounds.iloc[:, 0:2]) # cross validate scores = cross_validate( lr, X, y, groups=clusters.labels_, scoring='accuracy', cv=3, n_jobs=1) scores['test_score'].mean() # prediction df = stack.read(as_df=True, masked=True) result = stack.predict(estimator=lr, dtype='int16', nodata=0) result = stack.predict(estimator=lr, dtype='int16', nodata=0, as_df=True) 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()