def __init__(self, verbose, session, engine, lims, msg, imgfolder, img,
colx, coly, colz, colpt, nb_slice, flg_proj, type_Z_data,
params_extraction_db, params_random_deposits, params_kriging,
params_plots):
if not img:
self.img = msg.__class__.__name__
self.nameimg = os.path.join(imgfolder, img)
seq = msg.seq
self.pos, self.seq, self.lims = extract_points(session, seq, colx,
coly, colz, colpt,
flg_proj, lims)
if type_Z_data == "extraction_db":
print("extraction_db")
self.data = self.extract_data_db()
elif type_Z_data == "random_deposits":
print("random_deposits")
self.data, self.deposits = self.generate_random_points()
else:
print("error")
self.slice()
fig, ax = apply_parameters(plut.plotscatterdata,
[self.data, self.nameimg],
params_plots["plotscatterdata"])
ax.scatter(self.deposits[:, 0],
self.deposits[:, 1],
self.deposits[:, 2],
c="r",
s=16 * self.deposits[:, 3])
plt.show()
fig, mu, std = apply_parameters(plut.plotgaussiandist,
[self.data[:, 3], self.nameimg],
params_plots["plotgaussiandist"])
plt.show()
pw = utilities.pairwise(self.pos)
apply_parameters(
plut.laghistogram, [self.data[:, 3], self.nameimg, pw],
params_plots["laghistogram"]) #, namefile = imgnamebase )
kriginginstance = self.train_kriging()
apply_parameters(plut.plotresidualsvario, [
kriginginstance.delta, kriginginstance.sigma,
kriginginstance.epsilon, self.nameimg
])
### TODO : A SUPPRIMER
n_closest_points = 10
# self.plotcolormesh(kriginginstance, backend='loop', n_closest_points=n_closest_points)
apply_parameters(self.plotcolormesh, [kriginginstance],
params_plots["plotcolormesh"])
plt.show()
def kmatrices( data, covfct, u, N=0 ):
'''
Input (data) ndarray, data
(model) modeling function
- spherical
- exponential
- gaussian
(u) unsampled point
(N) number of neighboring points
to consider, if zero use all
'''
# u needs to be two dimensional for cdist()
if np.ndim( u ) == 1:
u = [u]
# distance between u and each data point in P
d = cdist( data[:,:2], u )
# add these distances to P
P = np.hstack(( data, d ))
# if N>0, take the N closest points,
if N > 0:
P = P[d[:,0].argsort()[:N]]
# otherwise, use all of the points
else:
N = len( P )
# apply the covariance model to the distances
k = covfct( P[:,3] )
# check for nan values in k
if np.any( np.isnan( k ) ):
raise ValueError('The vector of covariances, k, contains NaN values')
# cast as a matrix
k = np.matrix( k ).T
# form a matrix of distances between existing data points
K = pairwise( P[:,:2] )
# apply the covariance model to these distances
K = covfct( K.ravel() )
# check for nan values in K
if np.any( np.isnan( K ) ):
raise ValueError('The matrix of covariances, K, contains NaN values')
# re-cast as a NumPy array -- thanks M.L.
K = np.array( K )
# reshape into an array
K = K.reshape(N,N)
# cast as a matrix
K = np.matrix( K )
return K, k, P
def variogram(data, lags, tol, method):
'''
Input: (data) NumPy array where the fris t two columns
are the spatial coordinates, x and y
(lag) the distance, h, between points
(tol) the tolerance we are comfortable with around (lag)
(method) either 'semivariogram', or 'covariogram'
Output: (cv) <2xN> NumPy array of lags and variogram values
'''
# calculate the pairwise distances
pwdist = utilities.pairwise(data)
# create a list of lists of indices of points having the ~same lag
index = [lagindices(pwdist, lag, tol) for lag in lags]
# calculate the variogram at different lags given some tolerance
if method in ['semivariogram', 'semi', 'sv', 's']:
v = [semivariance(data, indices) for indices in index]
elif method in ['covariogram', 'cov', 'co', 'cv', 'c']:
v = [covariance(data, indices) for indices in index]
# bundle the semivariogram values with their lags
return np.array(zip(lags, v)).T
def variogram(data, lags, tol, method):
'''
Input: (data) NumPy array where the fris t two columns
are the spatial coordinates, x and y
(lag) the distance, h, between points
(tol) the tolerance we are comfortable with around (lag)
(method) either 'semivariogram', or 'covariogram'
Output: (cv) <2xN> NumPy array of lags and variogram values
'''
# calculate the pairwise distances
pwdist = utilities.pairwise(data)
# create a list of lists of indices of points having the ~same lag
index = [lagindices(pwdist, lag, tol) for lag in lags]
# calculate the variogram at different lags given some tolerance
if method in ['semivariogram', 'semi', 'sv', 's']:
v = [semivariance(data, indices) for indices in index]
elif method in ['covariogram', 'cov', 'co', 'cv', 'c']:
v = [covariance(data, indices) for indices in index]
# bundle the semivariogram values with their lags
return np.array(list(zip(lags, v))).T
def variogram(data, lags, tol, method):
'''
Input: (data) NumPy array where the first two columns
are the spatial coordinates, x and y
(lag) the distance, h, between points
(tol) the tolerance we are comfortable with around (lag)
(method) either 'semivariogram', or 'covariogram'
Output: (cv) <2xN> NumPy array of lags and variogram values
'''
# calculate the pairwise distances
pwdist = utilities.pairwise(data)
# create a list of lists of indices of points having the ~same lag
index = [lagindices(pwdist, lag, tol) for lag in lags]
# remove empty "lag" sets, prevents zero division error in [co|semi]variance()
index = list(filter(lambda x: len(x) > 0, index))
# calculate the variogram at different lags given some tolerance
if method in ['semivariogram', 'semi', 'sv', 's']:
v = [semivariance(data, indices) for indices in index]
elif method in ['covariogram', 'cov', 'co', 'cv', 'c']:
v = [covariance(data, indices) for indices in index]
# bundle the semivariogram values with their lags
return np.c_[lags, v].T
import scipy.stats as stats
qqdata = stats.probplot(z.por, dist="norm",plot=plt,fit=False)
xh=plt.xlabel('Standard Normal Quantiles')
yh=plt.ylabel('Sorted Porosity Values')
fig=plt.gcf()
fig.set_size_inches(8,8)
th=plt.title('')
# <markdowncell>
# What is the optimal "lag" distance between points? Use the utilities scattergram() function to help determine that distance.
# <codecell>
pw = utilities.pairwise(P)
geoplot.hscattergram(P,pw,1000,500)
geoplot.hscattergram(P,pw,2000,500)
geoplot.hscattergram(P,pw,3000,500)
# <markdowncell>
# Here, we plot the semivariogram and overlay a horizontal line for the sill, $c$.
# <codecell>
tolerance = 250
lags = np.arange( tolerance, 10000, tolerance*2 )
sill = np.var(P[:,2])
geoplot.semivariogram( P, lags, tolerance )