def linear_trans_opt(param, *args):
"""
Computes the Log Marginal Likelihood using standard GP regression by first performing transformation of the data set
:param param: transform_mat
:param args:
:return:
"""
# Define arguments
x_scatter = args[0]
y_scatter = args[1]
c = args[2]
kernel = args[3]
# Define parameters to be optimized - the matrix variables
transform_mat = param
# Begin transformation of the regression window
xy_scatter = np.vstack(
(x_scatter, y_scatter)) # Create the sample points to be rotated
xy_scatter_transformed = fn.transform_array(transform_mat, xy_scatter, c)
x_points_trans = xy_scatter_transformed[0]
y_points_trans = xy_scatter_transformed[1]
# 1. Obtain the maximum range in x and y in the transformed space - to define the regression window
x_down = min(x_points_trans)
x_up = max(x_points_trans)
y_down = min(y_points_trans)
y_up = max(y_points_trans)
# --------------------- Conduct binning into transformed space - the x and y quad lengths will be different
# ChangeParam
quads_on_side = 20 # define the number of quads along each dimension
k_mesh, y_edges, x_edges = np.histogram2d(y_points_trans,
x_points_trans,
bins=quads_on_side,
range=[[y_down, y_up],
[x_down, x_up]])
x_mesh_plot, y_mesh_plot = np.meshgrid(
x_edges, y_edges) # creating mesh-grid for use
x_mesh = x_mesh_plot[:-1, :
-1] # Removing extra rows and columns due to edges
y_mesh = y_mesh_plot[:-1, :-1]
x_quad = fn.row_create(x_mesh) # Creating the rows from the mesh
y_quad = fn.row_create(y_mesh)
xy_quad = np.vstack((x_quad, y_quad))
k_quad = fn.row_create(k_mesh)
# Start Optimization
arguments = (xy_quad, k_quad, kernel)
# Initialise kernel hyper-parameters - arbitrary value but should be as close to actual value as possible
initial_hyperparameters = np.array([1, 1, 1, 1])
# An optimization process is embedded within another optimization process
solution = scopt.minimize(fun=short_log_integrand_data,
args=arguments,
x0=initial_hyperparameters,
method='Nelder-Mead',
options={
'xatol': 1,
'fatol': 100,
'disp': True,
'maxfev': 500
})
print('Last function evaluation is ',
solution.fun) # This will be a negative value
neg_log_likelihood = solution.fun # We want to minimize the mirror image
return neg_log_likelihood
def linear_trans_skinny_opt(param, *args):
"""
Computes the Log Marginal Likelihood using standard GP regression by first performing transformation of the data set
This finds the average log marginal likelihood instead of the combined log_likelhood, and will find this average
while adapting to the number of quadrats in the regression window after transformation
:param param: transform_mat - matrix variables to be optimized
:param args: x and y coordinates of scatter points,, center, kernel type, and array containing vertices
the right order
:return: the average log likelihood by dividing total log likelihood with number of selected quadrats
"""
# Define original required arguments
xy_scatter = args[0]
c = args[1]
kernel = args[2]
vertex_array = args[
3] # Have to be in the right order in the original mathematical space
# Define parameters to be optimized - the matrix variables
transform_mat = param
# Begin transformation of the regression window
xy_scatter_transformed = fn.transform_array(transform_mat, xy_scatter, c)
x_points_trans = xy_scatter_transformed[0]
y_points_trans = xy_scatter_transformed[1]
# 1. Obtain the maximum range in x and y in the transformed space - to define the regression window
x_down = min(x_points_trans)
x_up = max(x_points_trans)
y_down = min(y_points_trans)
y_up = max(y_points_trans)
# Conduct binning into transformed space - the x and y quad lengths will be different
# ChangeParam
quads_on_side = 20 # define the number of quads along each dimension
k_mesh, y_edges, x_edges = np.histogram2d(y_points_trans,
x_points_trans,
bins=quads_on_side,
range=[[y_down, y_up],
[x_down, x_up]])
x_mesh_plot, y_mesh_plot = np.meshgrid(
x_edges, y_edges) # creating mesh-grid for use
x_mesh = x_mesh_plot[:-1, :
-1] # Removing extra rows and columns due to edges
y_mesh = y_mesh_plot[:-1, :-1]
x_quad = fn.row_create(x_mesh) # Creating the rows from the mesh
y_quad = fn.row_create(y_mesh)
xy_quad = np.vstack((x_quad, y_quad))
k_quad = fn.row_create(k_mesh)
# Selection of quadrats that fall inside the polygon
# Transform the vertices using the same transformation matrix
transformed_vertices = fn.transform_array(transform_mat, vertex_array,
center)
# Create polygon and
polygon = mpath.Path(np.transpose(transformed_vertices))
polygon_indicator = polygon.contains_points(np.transpose(xy_quad),
transform=None,
radius=1.0)
x_quad_polygon = x_quad[polygon_indicator]
y_quad_polygon = y_quad[polygon_indicator]
xy_quad_polygon = np.vstack((x_quad_polygon, y_quad_polygon))
k_quad_polygon = k_quad[polygon_indicator]
# Begin Optimization using selected quadrats
arguments = (xy_quad_polygon, k_quad_polygon, kernel)
# Initialise kernel hyper-parameters - arbitrary value but should be as close to actual value as possible
initial_hyperparameters = np.array([1, 1, 1, 1])
# An optimization process is embedded within another optimization process
solution = scopt.minimize(fun=short_log_integrand_data,
args=arguments,
x0=initial_hyperparameters,
method='Nelder-Mead',
options={
'xatol': 1,
'fatol': 100,
'disp': True,
'maxfev': 1000
})
positive_log_likelihood = solution.fun # We want to minimize the mirror image
selected_quadrats_n = k_quad_polygon.size
avg_positive_log_likelihood = positive_log_likelihood / selected_quadrats_n
print('Last function evaluation is ',
solution.fun) # This will be a negative value
print('The number of selected quadrats inside polygon is',
selected_quadrats_n)
return avg_positive_log_likelihood
# Initialise Array containing Frobenius Norm
frob_norm = np.zeros_like(element_skew)
start_iteration = time.clock()
# Over here, I am not trying to optimize for matrix variables, but just optimizing for the kernel
for i in range(iterate_count):
# initial_mat_var = np.array([mat_element[a], 0, mat_element[c], mat_element[d]])
start_iteration = time.clock()
initial_mat_var = np.array([element_skew[i], 0, 0, element_skew[i]])
frob_norm[i] = fn.frob_norm(initial_mat_var)
print(' ------------- Start of Current Iteration', i + 1)
print('The Current Matrix Variables are', initial_mat_var)
print('The Current Frobenius Norm is', frob_norm[i])
xy_scatter_transformed = fn.transform_array(initial_mat_var, xy_within_box,
center)
x_points_trans = xy_scatter_transformed[0]
y_points_trans = xy_scatter_transformed[1]
# Obtain the maximum range in x and y in the transformed space
# Transform the vertices
transformed_vertices = fn.transform_array(initial_mat_var, vertices,
center)
x_down = min(transformed_vertices[0])
x_up = max(transformed_vertices[0])
y_down = min(transformed_vertices[1])
y_up = max(transformed_vertices[1])
# ChangeParam - create histogram in transformed space before quadrat selection
quads_on_side = 20 # define the number of quads along each dimension
# ------------------------------------------ End of Regression Window Selection before Transformation
# ------------------------------------------ Start of Performing Transformation
xy_within_box = np.vstack(
(x_within_box, y_within_box)) # Create the sample points to be rotated
# Initialise kernel hyperparameters
initial_hyperparameters = np.array([1, 1, 1, 1])
# ChangeParam *** IMPORTANT
# transform_matrix_array = np.array([0.3, 3.5, 3.5, 0.3])
# transform_matrix_array = np.array([1, 0, 0, 1])
transform_matrix_array = np.array([0.30, 0.93, 0.65, -0.23])
transformed_xy_within_box = fn.transform_array(transform_matrix_array,
xy_within_box, center)
x_points_trans = transformed_xy_within_box[0]
y_points_trans = transformed_xy_within_box[1]
vertices = np.array([[x_lower, x_lower, x_upper, x_upper],
[y_lower, y_upper, y_upper, y_lower]])
print('The Original Vertices are', vertices)
# Transform the vertices using the same transformation matrix
transformed_vertices = fn.transform_array(transform_matrix_array, vertices,
center)
print('The Transformed Vertices are', transformed_vertices)
# 1. Obtain the maximum range in x and y in the transformed space
x_min = min(transformed_vertices[0])
x_max = max(transformed_vertices[0])
# Initialise Log Likelihood Array and Frobenius Norm array
likelihood_matrix = np.zeros((alpha_array.size, beta_array.size))
frob_matrix = np.zeros((alpha_array.size, beta_array.size))
start_iteration = time.clock()
# iterate for each value of alpha
for i in range(alpha_array.size):
for j in range(beta_array.size):
transform_matrix_array = np.array(
[alpha_array[i], beta_array[j], beta_array[j], alpha_array[i]])
# transform_matrix_array = np.array([0, alpha_array[i], alpha_array[i], 0])
frob_matrix[i, j] = np.sqrt(sum(transform_matrix_array**2))
# ChangeParam - Conduct the transformation
transformed_xy_within_box = fn.transform_array(transform_matrix_array,
xy_within_box, center)
x_points_trans = transformed_xy_within_box[0]
y_points_trans = transformed_xy_within_box[1]
# 1. Obtain the maximum range in x and y in the transformed space
x_min = min(x_points_trans)
x_max = max(x_points_trans)
y_min = min(y_points_trans)
y_max = max(y_points_trans)
print('x range is', x_max - x_min)
print('y range is', y_max -
y_min) # Display regression window size at each iteration
# ChangeParam
quads_on_side = 10 # define the number of quads along each dimension
# Create index of the maximum log likelihood
opt_index = np.argmax(log_likelihood_array)
max_likelihood = log_likelihood_array[opt_index]
opt_matrix_variables = matrix_variables_mat[opt_index, :]
print('The optimal points are at', matrix_variables_mat)
print('The globally-optimal matrix variables are', opt_matrix_variables)
print('The globally-optimal log marginal likelihood is', max_likelihood)
print('The kernel is ', ker)
print('The year is', year)
# Perform the transformation using the optimized matrix variables
xy_within_box = np.vstack((x_within_box, y_within_box))
# Perform transformation using the optimal matrix variables that were tabulated beforehand
transformed_xy = fn.transform_array(opt_matrix_variables, xy_within_box,
center)
# Split coordinates for plotting
transformed_x = transformed_xy[0]
transformed_y = transformed_xy[1]
# This is the plot including all scatter points in Brazil
scatter_plot_fig = plt.figure()
scatter_plot = scatter_plot_fig.add_subplot(111)
scatter_plot.scatter(x_within_box,
y_within_box,
marker='o',
color='red',
s=0.3)
scatter_plot.scatter(x_points, y_points, marker='o', color='black', s=0.3)
scatter_plot.scatter(transformed_x,
elif transform == 'special':
transform_matrix_array = np.array(
[-0.30117594, 0.92893405, -0.65028918, -0.2277159])
elif transform == 'line':
transform_matrix_array = np.array([1, 1, 1, 1])
else:
transform_matrix_array = np.array([1, 0, 0, 1])
frob_norm = fn.frob_norm(transform_matrix_array)
print('The optimal Transformation Matrix Variables are',
transform_matrix_array)
print('The optimal Frobenius Norm is', frob_norm)
# ChangeParam - Conduct the transformation about the center of the regression window
transformed_xy_within_box = fn.transform_array(transform_matrix_array,
xy_within_box, center)
x_points_trans = transformed_xy_within_box[0]
y_points_trans = transformed_xy_within_box[1]
# Obtain the maximum range in x and y in the transformed space - to define the regression window
# This is to maximise the number of selected quadrats
x_min = min(x_points_trans)
x_max = max(x_points_trans)
y_min = min(y_points_trans)
y_max = max(y_points_trans)
# First create a regression window with 20 x 20 quadrats before selecting the relevant quadrats
# ChangeParam
quads_on_side = 30 # define the number of quads along each dimension for the large regression window
k_mesh, y_edges, x_edges = np.histogram2d(y_points_trans,
x_points_trans,