def _move_interface_orientation(self, new_df):
# Check rows tht have changed
b_i = (
new_df.xs('interfaces')[self.geo_data._columns_i_1].sort_index() !=
_gempy.get_data(self.geo_data, itype='interfaces')[
self.geo_data._columns_i_1].sort_index()).any(1)
# Get indices of changed rows
ind_i = new_df.xs('interfaces').index[b_i].tolist()
# Check rows tht have changed
b_o = (
new_df.xs('orientations')[self.geo_data._columns_o_1].sort_index()
!= _gempy.get_data(self.geo_data, itype='orientations')[
self.geo_data._columns_o_1].sort_index()).any(1)
# Get indices of changed rows
ind_o = new_df.xs('orientations').index[b_o].tolist()
# Modify df
self.geo_data.set_new_df(new_df)
# Move widgets
self.vv.SphereCallbak_move_changes(ind_i)
self.vv.planesCallback_move_changes(ind_o)
def input_data(value=0,
interface_Z_modifier=interface_Z_modifier,
geo_data_stoch_init=geo_data_stoch_init,
verbose=0):
# First we extract from our original intep_data object the numerical data that is necessary for the interpolation.
# geo_data_stoch is a pandas Dataframe
geo_data_stoch = gp.get_data(geo_data_stoch_init, numeric=True)
# Now we loop each id which share the same uncertainty variable. In this case, each layer.
for e, gID in enumerate(group_ids):
# First we obtain a boolean array with trues where the id coincide
sel = gp.get_data(interp_data.geo_data_res,
verbosity=2)['group_id'] == gID
# We add to the original Z value (its mean) the stochastic bit in the correspondant groups id
geo_data_stoch.loc[sel, 'Z'] += np.array(interface_Z_modifier[e])
if verbose > 0:
print(geo_data_stoch)
# then return the input data to be input into the modeling function. Due to the way pymc2 stores the traces
# We need to save the data as numpy arrays
return [
geo_data_stoch.xs('interfaces')[["X", "Y", "Z"]].values,
geo_data_stoch.xs('orientations').values
]
def test_set_orientations():
# Importing the data from CSV-files and setting extent and resolution
geo_data = gp.create_data(
[0, 2000, 0, 2000, 0, 2000], [50, 50, 50],
path_o=input_path +
'/input_data/tut_chapter1/simple_fault_model_orientations.csv',
path_i=input_path +
'/input_data/tut_chapter1/simple_fault_model_points.csv')
gp.get_data(geo_data)
# Assigning series to formations as well as their order (timewise)
gp.set_series(
geo_data, {
"Fault_Series": 'Main_Fault',
"Strat_Series":
('Sandstone_2', 'Siltstone', 'Shale', 'Sandstone_1')
},
order_series=["Fault_Series", 'Strat_Series'],
order_formations=[
'Main_Fault',
'Sandstone_2',
'Siltstone',
'Shale',
'Sandstone_1',
],
verbose=0)
gp.set_orientation_from_interfaces(geo_data, [0, 1, 2])
def test_issue_569(data_path):
surface_points_df = df = pd.read_csv(data_path + "/coordinates_mwe.csv")
orientations_df = pd.read_csv(data_path + "/orientations_mwe.csv")
geo_model = gp.create_model("Deltatest")
gp.init_data(geo_model, [
df.X.min() - 50,
df.X.max() + 50,
df.Y.min() - 50,
df.Y.max() + 50,
df.Z.min() - 50,
df.Z.max() + 50,
], [50, 50, 50],
surface_points_df=surface_points_df,
orientations_df=orientations_df,
default_values=True)
fault_list = []
series = {
"Strat_Series":
surface_points_df.loc[
~surface_points_df["formation"].str.contains("fault"),
"formation"].unique().tolist()
}
for fault in surface_points_df.loc[
surface_points_df["formation"].str.contains("fault"),
"formation"].unique():
series[fault] = fault
fault_list.append(fault)
gp.map_stack_to_surfaces(geo_model, series, remove_unused_series=True)
geo_model.set_is_fault(fault_list)
geo_model.reorder_features(['fault_a', 'fault_b', 'Strat_Series'])
geo_model.add_surfaces("basement")
plot = gp.plot_2d(geo_model,
show_lith=False,
show_boundaries=True,
direction=['z'])
plt.show(block=False)
gp.set_interpolator(
geo_model,
compile_theano=True,
theano_optimizer='fast_compile',
)
gp.get_data(geo_model, 'kriging')
sol = gp.compute_model(geo_model, sort_surfaces=True)
gp.plot_2d(geo_model, show_scalar=True, series_n=0)
gp.plot_2d(geo_model, series_n=0)
gp.plot_3d(geo_model, image=True)
def load_model():
geo_model = gp.create_model('Model_Tuto1-1')
# Importing the data from CSV-files and setting extent and resolution
gp.init_data(geo_model, [0, 2000., 0, 2000., 0, 2000.], [50 ,50 ,50],
path_o = input_path+"/simple_fault_model_orientations.csv",
path_i = input_path+"/simple_fault_model_points.csv", default_values=True)
gp.get_data(geo_model, 'surface_points').head()
return geo_model
def set_geometric_data(geo_model: Model, surface_points_df=None,
orientations_df=None, **kwargs):
""" Function to set directly pandas.Dataframes to the gempy geometric data objects
Args:
geo_model: [s0]
surface_points_df: A pn.Dataframe object with X, Y, Z, and surface columns
orientations_df: A pn.Dataframe object with X, Y, Z, surface columns and pole or orientation columns
**kwargs:
Returns:
Modified df
"""
r_ = None
if surface_points_df is not None:
geo_model.set_surface_points(surface_points_df, **kwargs)
r_ = 'surface_points'
elif orientations_df is not None:
geo_model.set_orientations(orientations_df, **kwargs)
r_ = 'data' if r_ == 'surface_points' else 'orientations'
else:
raise AttributeError('You need to pass at least one dataframe')
return get_data(geo_model, itype=r_)
def observe_df(self, geo_data = None, itype='all'):
if not geo_data:
geo_data = self.geo_data
self._original_df = copy.deepcopy(_gempy.get_data(geo_data, itype=itype))
qgrid_widget = geo_data.interactive_df_open(itype=itype)
qgrid_widget.observe(self.qgrid_callBack, names=['_df'])
return qgrid_widget
def test_load_model_df():
verbose = True
df_i = pn.DataFrame(np.random.randn(6,3), columns='X Y Z'.split())
df_i['formation'] = ['surface_1' for _ in range(3)] + ['surface_2' for _ in range(3)]
df_o = pn.DataFrame(np.random.randn(6,6), columns='X Y Z azimuth dip polarity'.split())
df_o['formation'] = ['surface_1' for _ in range(3)] + ['surface_2' for _ in range(3)]
geo_model = gp.create_model('test')
# Importing the data directly from the dataframes
gp.init_data(geo_model, [0, 2000., 0, 2000., 0, 2000.], [50, 50, 50],
surface_points_df=df_i, orientations_df=df_o, default_values=True)
df_cmp_i = gp.get_data(geo_model, 'surface_points')
df_cmp_o = gp.get_data(geo_model, 'orientations')
if verbose:
print(df_cmp_i.head())
print(df_cmp_o.head())
assert not df_cmp_i.empty, 'data was not set to dataframe'
assert not df_cmp_o.empty, 'data was not set to dataframe'
assert df_cmp_i.shape[0] == 6, 'data was not set to dataframe'
assert df_cmp_o.shape[0] == 6, 'data was not set to dataframe'
# try without the default_values command
geo_model = gp.create_model('test')
# Importing the data directly from the dataframes
gp.init_data(geo_model, [0, 2000., 0, 2000., 0, 2000.], [50 ,50 ,50],
surface_points_df=df_i, orientations_df=df_o)
df_cmp_i2 = gp.get_data(geo_model, 'surface_points')
df_cmp_o2 = gp.get_data(geo_model, 'orientations')
if verbose:
print(df_cmp_i2.head())
print(df_cmp_o2.head())
assert not df_cmp_i2.empty, 'data was not set to dataframe'
assert not df_cmp_o2.empty, 'data was not set to dataframe'
assert df_cmp_i2.shape[0] == 6, 'data was not set to dataframe'
assert df_cmp_o2.shape[0] == 6, 'data was not set to dataframe'
return geo_model
def observe_df(self, geo_data=None, itype='all'):
if not geo_data:
geo_data = self.geo_data
self._original_df = copy.deepcopy(
_gempy.get_data(geo_data, itype=itype))
qgrid_widget = geo_data.interactive_df_open(itype=itype)
qgrid_widget.observe(self.qgrid_callBack, names=['_df'])
return qgrid_widget
def _move_interface_orientation(self, new_df):
# Check rows tht have changed
b_i = (new_df.xs('interfaces')[self.geo_data._columns_i_1].sort_index() != _gempy.get_data(
self.geo_data, itype='interfaces')[self.geo_data._columns_i_1].sort_index()).any(1)
# Get indices of changed rows
ind_i = new_df.xs('interfaces').index[b_i].tolist()
# Check rows tht have changed
b_o = (new_df.xs('orientations')[self.geo_data._columns_o_1].sort_index() != _gempy.get_data(
self.geo_data, itype='orientations')[self.geo_data._columns_o_1].sort_index()).any(1)
# Get indices of changed rows
ind_o = new_df.xs('orientations').index[b_o].tolist()
# Modify df
self.geo_data.set_new_df(new_df)
# Move widgets
self.vv.SphereCallbak_move_changes(ind_i)
self.vv.planesCallback_move_changes(ind_o)
def input_data(value = 0,
interface_Z_modifier = interface_Z_modifier,
geo_data_stoch_init = geo_data_stoch_init,
verbose=0):
# First we extract from our original intep_data object the numerical data that is necessary for the interpolation.
# geo_data_stoch is a pandas Dataframe
geo_data_stoch = gp.get_data(geo_data_stoch_init, numeric=True)
# Now we loop each id which share the same uncertainty variable. In this case, each layer.
for e, gID in enumerate(group_ids):
# First we obtain a boolean array with trues where the id coincide
sel = gp.get_data(interp_data.geo_data_res, verbosity=2)['group_id'] == gID
# We add to the original Z value (its mean) the stochastic bit in the correspondant groups id
geo_data_stoch.loc[sel, 'Z'] += np.array(interface_Z_modifier[e])
if verbose > 0:
print(geo_data_stoch)
# then return the input data to be input into the modeling function. Due to the way pymc2 stores the traces
# We need to save the data as numpy arrays
return [geo_data_stoch.xs('interfaces')[["X", "Y", "Z"]].values, geo_data_stoch.xs('orientations').values]
def test_set_orientations():
# Importing the data from CSV-files and setting extent and resolution
geo_data = gp.create_data(
extent=[0, 2000, 0, 2000, 0, 2000],
resolution=[50, 50, 50],
path_o=input_path +
'/input_data/tut_chapter1/simple_fault_model_orientations.csv',
path_i=input_path +
'/input_data/tut_chapter1/simple_fault_model_points.csv')
gp.get_data(geo_data)
# Assigning series to formations as well as their order (timewise)
gp.map_stack_to_surfaces(geo_data, {
"Fault_Series": 'Main_Fault',
"Strat_Series": ('Sandstone_2', 'Siltstone')
})
geo_data._orientations.create_orientation_from_surface_points(
geo_data.surface_points, [0, 1, 2])
gp.set_orientation_from_surface_points(geo_data, [0, 1, 2])
def load_model():
verbose = False
geo_model = gp.create_model('Model_Tuto1-1')
# Importing the data from CSV-files and setting extent and resolution
gp.init_data(geo_model, [0, 2000., 0, 2000., 0, 2000.], [50 ,50 ,50],
path_o=input_path+"/simple_fault_model_orientations.csv",
path_i=input_path+"/simple_fault_model_points.csv", default_values=True)
df_cmp_i = gp.get_data(geo_model, 'surface_points')
df_cmp_o = gp.get_data(geo_model, 'orientations')
df_o = pn.read_csv(input_path + "/simple_fault_model_orientations.csv")
df_i = pn.read_csv(input_path + "/simple_fault_model_points.csv")
assert not df_cmp_i.empty, 'data was not set to dataframe'
assert not df_cmp_o.empty, 'data was not set to dataframe'
assert df_cmp_i.shape[0] == df_i.shape[0], 'data was not set to dataframe'
assert df_cmp_o.shape[0] == df_o.shape[0], 'data was not set to dataframe'
if verbose:
gp.get_data(geo_model, 'surface_points').head()
return geo_model
def _move_interface(self, new_df):
if self.verbose > 0:
print(self.geo_data._columns_i_1, new_df.columns)
# Check rows tht have changed
b_i = (new_df[self.geo_data._columns_i_1].sort_index() != _gempy.get_data(
self.geo_data, itype='interfaces')[self.geo_data._columns_i_1].sort_index()).any(1)
# Get indices of changed rows
ind_i = new_df.index[b_i].tolist()
if self.verbose > 0:
print('I am in modifing', ind_i)
# Modify df
self.geo_data.set_new_df(new_df)
# Move sphere widget to new position
self.vv.SphereCallbak_move_changes(ind_i)
def _move_interface(self, new_df):
if self.verbose > 0:
print(self.geo_data._columns_i_1, new_df.columns)
# Check rows tht have changed
b_i = (new_df[self.geo_data._columns_i_1].sort_index() != _gempy.get_data(
self.geo_data, itype='interfaces')[self.geo_data._columns_i_1].sort_index()).any(1)
# Get indices of changed rows
ind_i = new_df.index[b_i].tolist()
if self.verbose > 0:
print('I am in modifing', ind_i)
# Modify df
self.geo_data.set_new_df(new_df)
# Move sphere widget to new position
self.vv.SphereCallbak_move_changes(ind_i)
def test_get_data(load_model):
geo_model = load_model
gp.get_data(geo_model, 'orientations').head()
"simple_fault_model_orientations.csv",
path_i=data_path + "/data/input_data/getting_started/"
"simple_fault_model_points.csv",
default_values=True)
# %%
geo_model.surfaces
# %%
# The input data can then be listed using the command ``get_data``. Note
# that the order of formations and respective allocation to series is
# still completely arbitrary. We will fix this in the following.
#
# %%
gp.get_data(geo_model, 'surface_points').head()
# %%
gp.get_data(geo_model, 'orientations').head()
# %%
# Declaring the sequential order of geological formations
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#
# - TODO update this section
#
# We want our geological units to appear in the correct order relative to
# age. Such order might for example be given by a depositional sequence of
# stratigraphy, unconformities due to erosion or other lithological
# genesis events such as igneous intrusions. A similar age-related order
# is to be declared for the faults in our model. In GemPy, the function
def test_get_data(self, one_fault_model):
print(gp.get_data(one_fault_model))
print(gp.get_data(one_fault_model, itype='additional_data'))
def test_ch1(theano_f_1f):
# Importing the data from CSV-files and setting extent and resolution
geo_data = gp.create_data(
[0, 2000, 0, 2000, 0, 2000], [50, 50, 50],
path_o=input_path +
'/input_data/tut_chapter1/simple_fault_model_orientations.csv',
path_i=input_path +
'/input_data/tut_chapter1/simple_fault_model_points.csv')
gp.get_data(geo_data)
# Assigning series to formations as well as their order (timewise)
gp.set_series(
geo_data, {
"Fault_Series": 'Main_Fault',
"Strat_Series":
('Sandstone_2', 'Siltstone', 'Shale', 'Sandstone_1')
},
order_series=["Fault_Series", 'Strat_Series'],
order_formations=[
'Main_Fault',
'Sandstone_2',
'Siltstone',
'Shale',
'Sandstone_1',
],
verbose=0)
gp.get_sequential_pile(geo_data)
print(gp.get_grid(geo_data))
gp.get_data(geo_data, 'interfaces').head()
gp.get_data(geo_data, 'orientations')
gp.plot_data(geo_data, direction='y')
# interp_data = gp.InterpolatorData(geo_data, u_grade=[1,1],
# output='geology', compile_theano=True,
# theano_optimizer='fast_compile',
# verbose=[])
interp_data = theano_f_1f
interp_data.update_interpolator(geo_data)
gp.get_kriging_parameters(interp_data) # Maybe move this to an extra part?
lith_block, fault_block = gp.compute_model(interp_data)
gp.plot_section(geo_data,
lith_block[0],
cell_number=25,
direction='y',
plot_data=True)
gp.plot_scalar_field(geo_data,
lith_block[1],
cell_number=25,
N=15,
direction='y',
plot_data=False)
gp.plot_scalar_field(geo_data,
lith_block[1],
cell_number=25,
N=15,
direction='z',
plot_data=False)
gp.plot_section(geo_data,
fault_block[0],
cell_number=25,
plot_data=True,
direction='y')
gp.plot_scalar_field(geo_data,
fault_block[1],
cell_number=25,
N=20,
direction='y',
plot_data=False)
ver, sim = gp.get_surfaces(interp_data,
lith_block[1],
fault_block[1],
original_scale=True)
# Cropping a cross-section to visualize in 2D #REDO this part?
bool_b = np.array(ver[1][:, 1] > 999) * np.array(ver[1][:, 1] < 1001)
bool_r = np.array(ver[1][:, 1] > 1039) * np.array(ver[1][:, 1] < 1041)
# Plotting section
gp.plot_section(geo_data, lith_block[0], 25, plot_data=True)
ax = plt.gca()
# Adding grid
ax.set_xticks(np.linspace(0, 2000, 100, endpoint=False))
ax.set_yticks(np.linspace(0, 2000, 100, endpoint=False))
plt.grid()
plt.ylim(1000, 1600)
plt.xlim(500, 1100)
# Plotting vertices
ax.plot(ver[1][bool_r][:, 0],
ver[1][bool_r][:, 2],
'.',
color='b',
alpha=.9)
ax.get_xaxis().set_ticklabels([])
ver_s, sim_s = gp.get_surfaces(interp_data,
lith_block[1],
fault_block[1],
original_scale=True)
def test_get_data(self, geo_model):
print(gp.get_data(geo_model))
print(gp.get_data(geo_model, itype='additional_data'))
}, remove_unused_series=True)
# geo_model.series
geo_model.set_is_fault(['Fault_Series'])
geo_model.faults.faults_relations_df
# gp.plot.plot_data(geo_model, direction='y')
# gp.plot.plot_3D(geo_model)
gp.set_interpolation_data(geo_model,
compile_theano=True,
theano_optimizer='fast_compile',
verbose=[])
gp.get_data(geo_model, 'kriging')
geo_model.additional_data.structure_data
sol = gp.compute_model(geo_model, compute_mesh=True, sort_surfaces=False)
gp.plot.plot_section(geo_model, cell_number=25,
direction='y', show_data=True)
ver , sim = gp.get_surfaces(geo_model)
for i in range(len(ver)):
fig = plt.figure()
x, y, z = ver[i][:, 0], ver[i][:, 1], ver[i][:, 2]
X, Y = np.meshgrid(x, y)
Z = np.array([z])
Z = np.repeat(Z, Z.shape[1], axis=0)
ax = fig.gca(projection='3d')
import gempy as gp
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
data_path = '../../data/GemPy/'
geo_model = gp.create_model('Permo_Carb_Trough')
gp.init_data(geo_model, [0, 30000., 0, 10., -7000, 1000.], [100, 1, 100],
path_o = data_path+'line82_foliations.csv',
path_i = data_path+'line82_interfaces.csv', default_values=False)
#%%
# Show data
gp.get_data(geo_model, 'surface_points').head()
gp.plot.plot_data(geo_model, direction='y')
#%%
# Assign formations to series
gp.map_series_to_surfaces(geo_model,
{"Fault7_series": 'Fault7',
"Fault1_series": 'Fault1',
"Fault6_series": 'Fault6',
"Fault2_series": 'Fault2',
"Fault5_series": 'Fault5',
"Fault3_series": 'Fault3',
"Fault4_series": 'Fault4',
"Post_tectonic_series": ('Quaternary', 'Tertiary', 'Mesozoic'),
def test_ch3_a(theano_f):
# set cube size and model extent
cs = 50
extent = (3000, 200, 2000) # (x, y, z)
res = (120, 4, 80)
# initialize geo_data object
geo_data = gp.create_data(
[0, extent[0], 0, extent[1], 0, extent[2]],
resolution=[
res[0], # number of voxels
res[1],
res[2]
])
geo_data.set_interfaces(pn.read_csv(
input_path + "/input_data/tut_chapter3/tutorial_ch3_interfaces",
index_col="Unnamed: 0"),
append=True)
geo_data.set_orientations(
pn.read_csv(input_path +
"/input_data/tut_chapter3/tutorial_ch3_foliations",
index_col="Unnamed: 0"))
# let's have a look at the upper five interface data entries in the dataframe
gp.get_data(geo_data, 'interfaces', verbosity=1).head()
# Original pile
gp.get_sequential_pile(geo_data)
# Ordered pile
gp.set_order_formations(geo_data,
['Layer 2', 'Layer 3', 'Layer 4', 'Layer 5'])
gp.get_sequential_pile(geo_data)
# and at all of the foliation data
gp.get_data(geo_data, 'orientations', verbosity=0)
gp.plot_data(geo_data, direction="y")
plt.xlim(0, 3000)
plt.ylim(0, 2000)
gp.data_to_pickle(
geo_data,
os.path.dirname(__file__) + "/ch3-pymc2_tutorial_geo_data")
#interp_data = gp.InterpolatorData(geo_data, u_grade=[1], compile_theano=True)
interp_data = theano_f
interp_data.update_interpolator(geo_data)
# Afterwards we can compute the geological model
lith_block, fault_block = gp.compute_model(interp_data)
# And plot a section:
gp.plot_section(geo_data, lith_block[0], 2, plot_data=True)
import pymc
# Checkpoint in case you did not execute the cells above
geo_data = gp.read_pickle(
os.path.dirname(__file__) + "/ch3-pymc2_tutorial_geo_data.pickle")
gp.get_data(geo_data, 'orientations', verbosity=1).head()
# So let's assume the vertical location of our layer interfaces is uncertain, and we want to represent this
# uncertainty by using a normal distribution. To define a normal distribution, we need a mean and a measure
# of deviation (e.g. standard deviation). For convenience the input data is already grouped by a "group_id" value,
# which allows us to collectively modify data that belongs together. In this example we want to treat the vertical
# position of each layer interface, on each side of the anticline, as uncertain. Therefore, we want to perturbate
# the respective three points on each side of the anticline collectively.
# These are our unique group id's, the number representing the layer, and a/b the side of the anticline.
group_ids = geo_data.interfaces["group_id"].dropna().unique()
print(group_ids)
# As a reminder, GemPy stores data in two main objects, an InputData object (called geo_data in the tutorials) and
# a InpterpolatorInput object (interp_data) in tutorials. geo_data contains the original data while interp_data the
# data prepared (and compiled) to compute the 3D model.
#
# Since we do not want to compile our code at every new stochastic realization, from here on we will need to work
# with thte interp_data. And remember that to improve float32 to stability we need to work with rescaled data
# (between 0 and 1). Therefore all the stochastic data needs to be rescaled accordingly. The object interp_data
# contains a property with the rescale factor (see below. As default depends on the model extent), or it is
# possible to add the stochastic data to the pandas dataframe of the geo_data---when the InterpolatorInput object
# is created the rescaling happens under the hood.
interface_Z_modifier = []
# We rescale the standard deviation
std = 20. / interp_data.rescaling_factor
# loop over the unique group id's and create a pymc.Normal distribution for each
for gID in group_ids:
stoch = pymc.Normal(gID + '_stoch', 0, 1. / std**2)
interface_Z_modifier.append(stoch)
# Let's have a look at one:
# sample from a distribtion
samples = [interface_Z_modifier[3].rand() for i in range(10000)]
# plot histogram
plt.hist(samples, bins=24, normed=True)
plt.xlabel("Z modifier")
plt.vlines(0, 0, 0.01)
plt.ylabel("n")
# Now we need to somehow sample from these distribution and put them into GemPy
# ## Input data handling
#
# First we need to write a function which modifies the input data for each iteration of the stochastic simulation.
# As this process is highly dependant on the simulation (e.g. what input parameters you want modified in which way),
# this process generally can't be automated.
#
# The idea is to change the column Z (in this case) of the rescaled dataframes in our interp_data object (which can
# be found in interp_data.geo_data_res). First we simply create the pandas Dataframes we are interested on:
import copy
# First we extract from our original intep_data object the numerical data that is necessary for the interpolation.
# geo_data_stoch is a pandas Dataframe
# This is the inital model so it has to be outside the stochastic frame
geo_data_stoch_init = copy.deepcopy(interp_data.geo_data_res)
gp.get_data(geo_data_stoch_init, numeric=True).head()
@pymc.deterministic(trace=True)
def input_data(value=0,
interface_Z_modifier=interface_Z_modifier,
geo_data_stoch_init=geo_data_stoch_init,
verbose=0):
# First we extract from our original intep_data object the numerical data that is necessary for the interpolation.
# geo_data_stoch is a pandas Dataframe
geo_data_stoch = gp.get_data(geo_data_stoch_init, numeric=True)
# Now we loop each id which share the same uncertainty variable. In this case, each layer.
for e, gID in enumerate(group_ids):
# First we obtain a boolean array with trues where the id coincide
sel = gp.get_data(interp_data.geo_data_res,
verbosity=2)['group_id'] == gID
# We add to the original Z value (its mean) the stochastic bit in the correspondant groups id
geo_data_stoch.loc[sel, 'Z'] += np.array(interface_Z_modifier[e])
if verbose > 0:
print(geo_data_stoch)
# then return the input data to be input into the modeling function. Due to the way pymc2 stores the traces
# We need to save the data as numpy arrays
return [
geo_data_stoch.xs('interfaces')[["X", "Y", "Z"]].values,
geo_data_stoch.xs('orientations').values
]
# ## Modeling function
@pymc.deterministic(trace=False)
def gempy_model(value=0, input_data=input_data, verbose=True):
# modify input data values accordingly
interp_data.geo_data_res.interfaces[["X", "Y", "Z"]] = input_data[0]
# Gx, Gy, Gz are just used for visualization. The theano function gets azimuth dip and polarity!!!
interp_data.geo_data_res.orientations[[
"G_x", "G_y", "G_z", "X", "Y", "Z", 'dip', 'azimuth', 'polarity'
]] = input_data[1]
try:
# try to compute model
lb, fb = gp.compute_model(interp_data)
if True:
gp.plot_section(interp_data.geo_data_res,
lb[0],
0,
plot_data=True)
return lb, fb
except np.linalg.linalg.LinAlgError as err:
# if it fails (e.g. some input data combinations could lead to
# a singular matrix and thus break the chain) return an empty model
# with same dimensions (just zeros)
if verbose:
print("Exception occured.")
return np.zeros_like(lith_block), np.zeros_like(fault_block)
# We then create a pymc model with the two deterministic functions (*input_data* and *gempy_model*), as well as all
# the prior parameter distributions stored in the list *interface_Z_modifier*:
params = [input_data, gempy_model, *interface_Z_modifier]
model = pymc.Model(params)
# Then we set the number of iterations:
# Then we create an MCMC chain (in pymc an MCMC chain without a likelihood function is essentially a Monte Carlo
# forward simulation) and specify an hdf5 database to store the results in
RUN = pymc.MCMC(model,
db="hdf5",
dbname=os.path.dirname(__file__) + "/ch3-pymc2.hdf5")
# and we are finally able to run the simulation:
RUN.sample(iter=100, verbose=0)
def test_ch1(theano_f_1f):
# Importing the data from CSV-files and setting extent and resolution
geo_data = gp.create_data([0, 2000, 0, 2000, 0, 2000], [50, 50, 50],
path_o=input_path+'/input_data/tut_chapter1/simple_fault_model_orientations.csv',
path_i=input_path+'/input_data/tut_chapter1/simple_fault_model_points.csv')
gp.get_data(geo_data)
# Assigning series to formations as well as their order (timewise)
gp.set_series(geo_data, {"Fault_Series":'Main_Fault',
"Strat_Series": ('Sandstone_2','Siltstone',
'Shale', 'Sandstone_1')},
order_series = ["Fault_Series", 'Strat_Series'],
order_formations=['Main_Fault',
'Sandstone_2','Siltstone',
'Shale', 'Sandstone_1',
], verbose=0)
gp.get_sequential_pile(geo_data)
print(gp.get_grid(geo_data))
gp.get_data(geo_data, 'interfaces').head()
gp.get_data(geo_data, 'orientations')
gp.plot_data(geo_data, direction='y')
# interp_data = gp.InterpolatorData(geo_data, u_grade=[1,1],
# output='geology', compile_theano=True,
# theano_optimizer='fast_compile',
# verbose=[])
interp_data = theano_f_1f
interp_data.update_interpolator(geo_data)
gp.get_kriging_parameters(interp_data) # Maybe move this to an extra part?
lith_block, fault_block = gp.compute_model(interp_data)
gp.plot_section(geo_data, lith_block[0], cell_number=25, direction='y', plot_data=True)
gp.plot_scalar_field(geo_data, lith_block[1], cell_number=25, N=15,
direction='y', plot_data=False)
gp.plot_scalar_field(geo_data, lith_block[1], cell_number=25, N=15,
direction='z', plot_data=False)
gp.plot_section(geo_data, fault_block[0], cell_number=25, plot_data=True, direction='y')
gp.plot_scalar_field(geo_data, fault_block[1], cell_number=25, N=20,
direction='y', plot_data=False)
ver, sim = gp.get_surfaces(interp_data,lith_block[1], fault_block[1], original_scale=True)
# Cropping a cross-section to visualize in 2D #REDO this part?
bool_b = np.array(ver[1][:,1] > 999)* np.array(ver[1][:,1] < 1001)
bool_r = np.array(ver[1][:,1] > 1039)* np.array(ver[1][:,1] < 1041)
# Plotting section
gp.plot_section(geo_data, lith_block[0], 25, plot_data=True)
ax = plt.gca()
# Adding grid
ax.set_xticks(np.linspace(0, 2000, 100, endpoint=False))
ax.set_yticks(np.linspace(0, 2000, 100, endpoint=False))
plt.grid()
plt.ylim(1000,1600)
plt.xlim(500,1100)
# Plotting vertices
ax.plot(ver[1][bool_r][:, 0], ver[1][bool_r][:, 2], '.', color='b', alpha=.9)
ax.get_xaxis().set_ticklabels([])
ver_s, sim_s = gp.get_surfaces(interp_data,lith_block[1],
fault_block[1],
original_scale=True)
def test_get_data(self, model_complex):
print(gp.get_data(model_complex))
print(gp.get_data(model_complex, itype='additional_data'))
def test_ch3_a(theano_f):
# set cube size and model extent
cs = 50
extent = (3000, 200, 2000) # (x, y, z)
res = (120, 4, 80)
# initialize geo_data object
geo_data = gp.create_data([0, extent[0],
0, extent[1],
0, extent[2]],
resolution=[res[0], # number of voxels
res[1],
res[2]])
geo_data.set_interfaces(pn.read_csv(input_path+"/input_data/tut_chapter3/tutorial_ch3_interfaces",
index_col="Unnamed: 0"), append=True)
geo_data.set_orientations(pn.read_csv(input_path+"/input_data/tut_chapter3/tutorial_ch3_foliations",
index_col="Unnamed: 0"))
# let's have a look at the upper five interface data entries in the dataframe
gp.get_data(geo_data, 'interfaces', verbosity=1).head()
# Original pile
gp.get_sequential_pile(geo_data)
# Ordered pile
gp.set_order_formations(geo_data, ['Layer 2', 'Layer 3', 'Layer 4','Layer 5'])
gp.get_sequential_pile(geo_data)
# and at all of the foliation data
gp.get_data(geo_data, 'orientations', verbosity=0)
gp.plot_data(geo_data, direction="y")
plt.xlim(0,3000)
plt.ylim(0,2000);
gp.data_to_pickle(geo_data, os.path.dirname(__file__)+"/ch3-pymc2_tutorial_geo_data")
#interp_data = gp.InterpolatorData(geo_data, u_grade=[1], compile_theano=True)
interp_data = theano_f
interp_data.update_interpolator(geo_data)
# Afterwards we can compute the geological model
lith_block, fault_block = gp.compute_model(interp_data)
# And plot a section:
gp.plot_section(geo_data, lith_block[0], 2, plot_data = True)
import pymc
# Checkpoint in case you did not execute the cells above
geo_data = gp.read_pickle(os.path.dirname(__file__)+"/ch3-pymc2_tutorial_geo_data.pickle")
gp.get_data(geo_data, 'orientations', verbosity=1).head()
# So let's assume the vertical location of our layer interfaces is uncertain, and we want to represent this
# uncertainty by using a normal distribution. To define a normal distribution, we need a mean and a measure
# of deviation (e.g. standard deviation). For convenience the input data is already grouped by a "group_id" value,
# which allows us to collectively modify data that belongs together. In this example we want to treat the vertical
# position of each layer interface, on each side of the anticline, as uncertain. Therefore, we want to perturbate
# the respective three points on each side of the anticline collectively.
# These are our unique group id's, the number representing the layer, and a/b the side of the anticline.
group_ids = geo_data.interfaces["group_id"].dropna().unique()
print(group_ids)
# As a reminder, GemPy stores data in two main objects, an InputData object (called geo_data in the tutorials) and
# a InpterpolatorInput object (interp_data) in tutorials. geo_data contains the original data while interp_data the
# data prepared (and compiled) to compute the 3D model.
#
# Since we do not want to compile our code at every new stochastic realization, from here on we will need to work
# with thte interp_data. And remember that to improve float32 to stability we need to work with rescaled data
# (between 0 and 1). Therefore all the stochastic data needs to be rescaled accordingly. The object interp_data
# contains a property with the rescale factor (see below. As default depends on the model extent), or it is
# possible to add the stochastic data to the pandas dataframe of the geo_data---when the InterpolatorInput object
# is created the rescaling happens under the hood.
interface_Z_modifier = []
# We rescale the standard deviation
std = 20./interp_data.rescaling_factor
# loop over the unique group id's and create a pymc.Normal distribution for each
for gID in group_ids:
stoch = pymc.Normal(gID+'_stoch', 0, 1./std**2)
interface_Z_modifier.append(stoch)
# Let's have a look at one:
# sample from a distribtion
samples = [interface_Z_modifier[3].rand() for i in range(10000)]
# plot histogram
plt.hist(samples, bins=24, normed=True);
plt.xlabel("Z modifier")
plt.vlines(0, 0, 0.01)
plt.ylabel("n");
# Now we need to somehow sample from these distribution and put them into GemPy
# ## Input data handling
#
# First we need to write a function which modifies the input data for each iteration of the stochastic simulation.
# As this process is highly dependant on the simulation (e.g. what input parameters you want modified in which way),
# this process generally can't be automated.
#
# The idea is to change the column Z (in this case) of the rescaled dataframes in our interp_data object (which can
# be found in interp_data.geo_data_res). First we simply create the pandas Dataframes we are interested on:
import copy
# First we extract from our original intep_data object the numerical data that is necessary for the interpolation.
# geo_data_stoch is a pandas Dataframe
# This is the inital model so it has to be outside the stochastic frame
geo_data_stoch_init = copy.deepcopy(interp_data.geo_data_res)
gp.get_data(geo_data_stoch_init, numeric=True).head()
@pymc.deterministic(trace=True)
def input_data(value = 0,
interface_Z_modifier = interface_Z_modifier,
geo_data_stoch_init = geo_data_stoch_init,
verbose=0):
# First we extract from our original intep_data object the numerical data that is necessary for the interpolation.
# geo_data_stoch is a pandas Dataframe
geo_data_stoch = gp.get_data(geo_data_stoch_init, numeric=True)
# Now we loop each id which share the same uncertainty variable. In this case, each layer.
for e, gID in enumerate(group_ids):
# First we obtain a boolean array with trues where the id coincide
sel = gp.get_data(interp_data.geo_data_res, verbosity=2)['group_id'] == gID
# We add to the original Z value (its mean) the stochastic bit in the correspondant groups id
geo_data_stoch.loc[sel, 'Z'] += np.array(interface_Z_modifier[e])
if verbose > 0:
print(geo_data_stoch)
# then return the input data to be input into the modeling function. Due to the way pymc2 stores the traces
# We need to save the data as numpy arrays
return [geo_data_stoch.xs('interfaces')[["X", "Y", "Z"]].values, geo_data_stoch.xs('orientations').values]
# ## Modeling function
@pymc.deterministic(trace=False)
def gempy_model(value=0,
input_data=input_data, verbose=True):
# modify input data values accordingly
interp_data.geo_data_res.interfaces[["X", "Y", "Z"]] = input_data[0]
# Gx, Gy, Gz are just used for visualization. The theano function gets azimuth dip and polarity!!!
interp_data.geo_data_res.orientations[["G_x", "G_y", "G_z", "X", "Y", "Z", 'dip', 'azimuth', 'polarity']] = input_data[1]
try:
# try to compute model
lb, fb = gp.compute_model(interp_data)
if True:
gp.plot_section(interp_data.geo_data_res, lb[0], 0, plot_data=True)
return lb, fb
except np.linalg.linalg.LinAlgError as err:
# if it fails (e.g. some input data combinations could lead to
# a singular matrix and thus break the chain) return an empty model
# with same dimensions (just zeros)
if verbose:
print("Exception occured.")
return np.zeros_like(lith_block), np.zeros_like(fault_block)
# We then create a pymc model with the two deterministic functions (*input_data* and *gempy_model*), as well as all
# the prior parameter distributions stored in the list *interface_Z_modifier*:
params = [input_data, gempy_model, *interface_Z_modifier]
model = pymc.Model(params)
# Then we set the number of iterations:
# Then we create an MCMC chain (in pymc an MCMC chain without a likelihood function is essentially a Monte Carlo
# forward simulation) and specify an hdf5 database to store the results in
RUN = pymc.MCMC(model, db="hdf5", dbname=os.path.dirname(__file__)+"/ch3-pymc2.hdf5")
# and we are finally able to run the simulation:
RUN.sample(iter=100, verbose=0)
# %%
model.map_stack_to_surfaces({
"Fault_Series":
'Main_Fault',
"Strat_Series": ('Sandstone_2', 'Siltstone', 'Shale', 'Sandstone_1')
})
# %%
model._surfaces.df['series']
# %%
model.surfaces
# %%
gp.get_data(model, 'surface points')
# %%
model.stack
# %%
# In the case of having faults we need to assign wich series are faults:
#
# %%
model.faults
# %%
model.set_is_fault(['Fault_Series'])
# %%
