def test_krige_housing():
import ssl
import urllib
try:
housing = fetch_california_housing()
except (ssl.SSLError, urllib.error.URLError):
ssl._create_default_https_context = ssl._create_unverified_context
try:
housing = fetch_california_housing()
except PermissionError:
# This can raise permission error on Appveyor
pytest.skip("Failed to load california housing dataset")
ssl._create_default_https_context = ssl.create_default_context
# take only first 1000
p = housing["data"][:1000, :-2]
x = housing["data"][:1000, -2:]
target = housing["target"][:1000]
p_train, p_test, y_train, y_test, x_train, x_test = train_test_split(
p, target, x, train_size=0.7, random_state=10
)
for ml_model, krige_method in _methods():
reg_kr_model = RegressionKriging(
regression_model=ml_model, method=krige_method, n_closest_points=2
)
reg_kr_model.fit(p_train, x_train, y_train)
if krige_method == "ordinary":
assert reg_kr_model.score(p_test, x_test, y_test) > 0.5
else:
assert reg_kr_model.score(p_test, x_test, y_test) > 0.0
def regression_kriging_evaluation(year, features_=['all']):
from pykrige.rk import RegressionKriging
from sklearn.model_selection import LeaveOneOut
from sklearn.svm import SVR
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
svr_model = SVR(kernel='rbf', C=10, gamma=0.001)
lr_model = LinearRegression()
rf_model = RandomForestRegressor(n_estimators=2)
Y, D, P, Tf, Gd = extract_raw_samples(year, crime_t=['total'])
coords = get_centroid_ca()
errors = []
for k in range(77):
X_train, X_test, Y_train, Y_test = build_features(Y, D, P, Tf, Y, Gd, Y, k, features=features_, taxi_norm="bydestination")
if k == 0:
print X_train.shape
coords_train = np.delete(coords, k, axis=0)
coords_test = np.array(coords)[k,None]
m_rk = RegressionKriging(regression_model=rf_model)
m_rk.fit(X_train, coords_train, Y_train)
z = m_rk.predict(X_test, coords_test)
errors.append(abs(Y_test - z[0]))
print np.mean(errors), np.mean(errors)/np.mean(Y)
return errors
def test_regression_krige():
np.random.seed(1)
x = np.linspace(-1.0, 1.0, 100)
# create a feature matrix with 5 features
X = np.tile(x, reps=(5, 1)).T
y = (
1
+ 5 * X[:, 0]
- 2 * X[:, 1]
- 2 * X[:, 2]
+ 3 * X[:, 3]
+ 4 * X[:, 4]
+ 2 * (np.random.rand(100) - 0.5)
)
# create lat/lon array
lon = np.linspace(-180.0, 180.0, 10)
lat = np.linspace(-90.0, 90.0, 10)
lon_lat = np.array(list(product(lon, lat)))
X_train, X_test, y_train, y_test, lon_lat_train, lon_lat_test = train_test_split(
X, y, lon_lat, train_size=0.7, random_state=10
)
for ml_model, krige_method in _methods():
reg_kr_model = RegressionKriging(
regression_model=ml_model, method=krige_method, n_closest_points=2
)
reg_kr_model.fit(X_train, lon_lat_train, y_train)
assert reg_kr_model.score(X_test, lon_lat_test, y_test) > 0.25
def test_krige_housing():
try:
housing = fetch_california_housing()
except PermissionError:
# This can raise permission error on Appveyor
pytest.skip('Failed to load california housing dataset')
# take only first 1000
p = housing['data'][:1000, :-2]
x = housing['data'][:1000, -2:]
target = housing['target'][:1000]
p_train, p_test, y_train, y_test, x_train, x_test = \
train_test_split(p, target, x, train_size=0.7,
random_state=10)
for ml_model, krige_method in _methods():
reg_kr_model = RegressionKriging(regression_model=ml_model,
method=krige_method,
n_closest_points=2)
reg_kr_model.fit(p_train, x_train, y_train)
if krige_method == 'ordinary':
assert reg_kr_model.score(p_test, x_test, y_test) > 0.5
else:
assert reg_kr_model.score(p_test, x_test, y_test) > 0.0
def test_krige_housing():
housing = fetch_california_housing()
# take only first 1000
p = housing['data'][:1000, :-2]
x = housing['data'][:1000, -2:]
target = housing['target'][:1000]
p_train, p_test, y_train, y_test, x_train, x_test = \
train_test_split(p, target, x, train_size=0.7,
random_state=10)
for ml_model, krige_method in _methods():
reg_kr_model = RegressionKriging(regression_model=ml_model,
method=krige_method,
n_closest_points=2)
reg_kr_model.fit(p_train, x_train, y_train)
if krige_method == 'ordinary':
assert reg_kr_model.score(p_test, x_test, y_test) > 0.5
else:
assert reg_kr_model.score(p_test, x_test, y_test) > 0.0
def test_regression_krige():
np.random.seed(1)
x = np.linspace(-1., 1., 100)
# create a feature matrix with 5 features
X = np.tile(x, reps=(5, 1)).T
y = 1 + 5*X[:, 0] - 2*X[:, 1] - 2*X[:, 2] + 3*X[:, 3] + 4*X[:, 4] + \
2*(np.random.rand(100) - 0.5)
# create lat/lon array
lon = np.linspace(-180., 180.0, 10)
lat = np.linspace(-90., 90., 10)
lon_lat = np.array(list(product(lon, lat)))
X_train, X_test, y_train, y_test, lon_lat_train, lon_lat_test = \
train_test_split(X, y, lon_lat, train_size=0.7, random_state=10)
for ml_model, krige_method in _methods():
reg_kr_model = RegressionKriging(regression_model=ml_model,
method=krige_method,
n_closest_points=2)
reg_kr_model.fit(X_train, lon_lat_train, y_train)
assert reg_kr_model.score(X_test, lon_lat_test, y_test) > 0.25
def regression_kriging(file):
"""
https://pykrige.readthedocs.io/en/latest/examples/regression_kriging2d.html
:param file:
:return:
"""
svr_model = SVR(C=0.1)
rf_model = RandomForestRegressor(n_estimators=100)
lr_model = LinearRegression(normalize=True,
copy_X=True,
fit_intercept=False)
models = [svr_model, rf_model, lr_model]
for m in models:
print('=' * 40)
print('regression model:', m.__class__.__name__)
m_rk = RegressionKriging(regression_model=m, n_closest_points=10)
m_rk.fit(p_train, x_train, target_train)
print('Regression Score: ',
m_rk.regression_model.score(p_test, target_test))
print('RK score: ', m_rk.score(p_test, x_test, target_test))
# this dataset can occasionally fail to download on Windows
sys.exit(0)
# take the first 5000 as Kriging is memory intensive
p = housing['data'][:5000, :-2]
x = housing['data'][:5000, -2:]
target = housing['target'][:5000]
p_train, p_test, x_train, x_test, target_train, target_test \
= train_test_split(p, x, target, test_size=0.3, random_state=42)
for m in models:
print('=' * 40)
print('regression model:', m.__class__.__name__)
m_rk = RegressionKriging(regression_model=m, n_closest_points=10)
m_rk.fit(p_train, x_train, target_train)
print('Regression Score: ',
m_rk.regression_model.score(p_test, target_test))
print('RK score: ', m_rk.score(p_test, x_test, target_test))
##====================================OUTPUT==================================
# ========================================
# regression model: <class 'sklearn.svm.classes.SVR'>
# Finished learning regression model
# Finished kriging residuals
# Regression Score: -0.034053855457
# RK score: 0.66195576665
# ========================================
# regression model: <class 'sklearn.ensemble.forest.RandomForestRegressor'>
# Finished learning regression model
# this dataset can occasionally fail to download on Windows
sys.exit(0)
# take the first 5000 as Kriging is memory intensive
p = housing['data'][:5000, :-2]
x = housing['data'][:5000, -2:]
target = housing['target'][:5000]
p_train, p_test, x_train, x_test, target_train, target_test \
= train_test_split(p, x, target, test_size=0.3, random_state=42)
for m in models:
print('=' * 40)
print('regression model:', m.__class__.__name__)
m_rk = RegressionKriging(regression_model=m, n_closest_points=10)
m_rk.fit(p_train, x_train, target_train)
print('Regression Score: ', m_rk.regression_model.score(p_test, target_test))
print('RK score: ', m_rk.score(p_test, x_test, target_test))
##====================================OUTPUT==================================
# ========================================
# regression model: <class 'sklearn.svm.classes.SVR'>
# Finished learning regression model
# Finished kriging residuals
# Regression Score: -0.034053855457
# RK score: 0.66195576665
# ========================================
# regression model: <class 'sklearn.ensemble.forest.RandomForestRegressor'>
# Finished learning regression model
# Finished kriging residuals
x_grd = grd.to_numpy()
x_y = x_grd[:, :-1]
##numpy array of surface elevation
z = x_grd[:, -1:]
#%%
#constract a randomforest model
rf_model = RandomForestRegressor(n_estimators=100)
#fit the regression kriging model
m_rk = RegressionKriging(regression_model=rf_model,
n_closest_points=2,
method='ordinary',
variogram_model='spherical')
#%%
m_rk.fit(p, x, sub1.iloc[:, 39])
pred_sph = m_rk.predict(z, x_y)
#%%
sph = pred_sph
#%%
#filter values
sph[sph < 0.3] = 0
sph.resize(src.height, src.width)
show(sph)
#%%
with rio.Env():
# Write an array as a raster band to a new 8-bit file. For
# the new file's profile, we start with the profile of the source