def test_plot_windwave_fit(self):
"""
Plots goodness of fit graphs, for the marginal distribution of X1 and
for the dependence function of X2|X1. Uses wind and wave data.
"""
sample_v, sample_hs, label_v, label_hs = \
read_ecbenchmark_dataset('datasets/1year_dataset_D.txt')
label_v = 'v (m s$^{-1}$)'
# Define the structure of the probabilistic model that will be fitted to the
# dataset.
dist_description_v = {
'name': 'Weibull_Exp',
'dependency': (None, None, None, None),
'width_of_intervals': 2
}
dist_description_hs = {
'name': 'Weibull_Exp',
'fixed_parameters': (None, None, None, 5),
# shape, location, scale, shape2
'dependency': (0, None, 0, None),
# shape, location, scale, shape2
'functions': ('logistics4', None, 'alpha3', None),
# shape, location, scale, shape2
'min_datapoints_for_fit': 50,
'do_use_weights_for_dependence_function': True
}
# Fit the model to the data.
fit = Fit((sample_v, sample_hs),
(dist_description_v, dist_description_hs))
dist0 = fit.mul_var_dist.distributions[0]
fig = plt.figure(figsize=(12.5, 3.5), dpi=150)
ax1 = fig.add_subplot(131)
ax2 = fig.add_subplot(132)
ax3 = fig.add_subplot(133)
plot_marginal_fit(sample_v,
dist0,
fig=fig,
ax=ax1,
label=label_v,
dataset_char='D')
plot_dependence_functions(fit=fit,
fig=fig,
ax1=ax2,
ax2=ax3,
unconditonal_variable_label=label_v)
def test_plot_seastate_fit(self):
"""
Plots goodness of fit graphs, for the marginal distribution of X1 and
for the dependence function of X2|X1. Uses sea state data.
"""
sample_hs, sample_tz, label_hs, label_tz = read_ecbenchmark_dataset()
# Define the structure of the probabilistic model that will be fitted to the
# dataset.
dist_description_hs = {
'name': 'Weibull_Exp',
'dependency': (None, None, None, None),
'width_of_intervals': 0.5
}
dist_description_tz = {
'name': 'Lognormal_SigmaMu',
'dependency': (0, None, 0),
# Shape, Location, Scale
'functions': ('asymdecrease3', None, 'lnsquare2'),
# Shape, Location, Scale
'min_datapoints_for_fit': 50
}
# Fit the model to the data.
fit = Fit((sample_hs, sample_tz),
(dist_description_hs, dist_description_tz))
dist0 = fit.mul_var_dist.distributions[0]
fig = plt.figure(figsize=(12.5, 3.5), dpi=150)
ax1 = fig.add_subplot(131)
ax2 = fig.add_subplot(132)
ax3 = fig.add_subplot(133)
plot_marginal_fit(sample_hs,
dist0,
fig=fig,
ax=ax1,
label='$h_s$ (m)',
dataset_char='A')
plot_dependence_functions(fit=fit,
fig=fig,
ax1=ax2,
ax2=ax3,
unconditonal_variable_label=label_hs)
def test_plot_confidence_interval(self):
"""
Plots a contour's confidence interval.
"""
dataset_d_v, dataset_d_hs, label_v, label_hs = \
read_ecbenchmark_dataset('datasets/1year_dataset_D.txt')
# Read the contours that have beem computed previously from csv files.
folder_name = 'contour-coordinates/'
file_name_median = 'doe_john_years_25_median.txt'
file_name_bottom = 'doe_john_years_25_bottom.txt'
file_name_upper = 'doe_john_years_25_upper.txt'
(contour_v_median,
contour_hs_median) = read_contour(folder_name + file_name_median)
(contour_v_bottom,
contour_hs_bottom) = read_contour(folder_name + file_name_bottom)
(contour_v_upper,
contour_hs_upper) = read_contour(folder_name + file_name_upper)
# Plot the sample, the median contour and the confidence interval.
fig = plt.figure(figsize=(5, 5), dpi=150)
ax = fig.add_subplot(111)
plotted_sample = SamplePlotData(x=np.asarray(dataset_d_v),
y=np.asarray(dataset_d_hs),
ax=ax,
label='dataset D')
contour_labels = [
'50th percentile contour', '2.5th percentile contour',
'97.5th percentile contour'
]
plot_confidence_interval(x_median=contour_v_median,
y_median=contour_hs_median,
x_bottom=contour_v_bottom,
y_bottom=contour_hs_bottom,
x_upper=contour_v_upper,
y_upper=contour_hs_upper,
ax=ax,
x_label=label_v,
y_label=label_hs,
contour_labels=contour_labels,
plotted_sample=plotted_sample)
latitudes = [43.525, 28.508, 25.897, 54.0, 55.0, 59.5 ]
longitudes = [-70.141, -80.185, -89.668, 6.575, 1.175, 4.325]
fig, axs = plt.subplots(2, 3, sharex='row', sharey='row', figsize=(10, 8))
max_hs_of_sample = 0
for i, ax0 in enumerate(axs):
if i == 0:
datasets = datasets_hstz
else:
datasets = datasets_vhs
for j, (dataset_char, ax1) in enumerate(zip(datasets, ax0)):
# Load the environmental data.
file_name_provided = 'datasets/' + dataset_char + '.txt'
file_name_retained = 'datasets-retained/' + dataset_char + 'r.txt'
x1_p, x2_p, x1_label, x2_label = read_ecbenchmark_dataset(file_name_provided)
x1_r, x2_r, x1_label, x2_label = read_ecbenchmark_dataset(file_name_retained)
if i == 1:
x1_p, x2_p = x2_p, x1_p
x1_r, x2_r = x2_r, x1_r
x1_label, x2_label = x2_label, x1_label
max_hs_of_sample = max([max_hs_of_sample, max(x1_p), max(x1_r)])
# Scatter plot
ax1.scatter(x2_p, x1_p, c='black', alpha=0.5, zorder=-2)
ax1.scatter(x2_r, x1_r, marker='v', facecolor='None',
edgecolor='black', alpha=0.5, zorder=-2)
ax1.set_rasterization_zorder(-1)
ax1.set_xlabel(x2_label.capitalize())
dataset_chars = ['A', 'B', 'C']
return_periods = [1, 20]
n_contours_to_analyze = len(legends_for_contribution)
fig, axs = plt.subplots(len(return_periods),
len(dataset_chars),
sharex='row',
sharey='row',
figsize=(10, 8))
max_hs_of_sample = 0
for (return_period, ax0) in zip(return_periods, axs):
for (dataset_char, ax1) in zip(dataset_chars, ax0):
# Load the environmental data.
file_name_provided = 'datasets/' + dataset_char + '.txt'
file_name_retained = 'datasets-retained/' + dataset_char + 'r.txt'
hs_p, tz_p, label_hs, label_tz = read_ecbenchmark_dataset(
file_name_provided)
hs_r, tz_r, label_hs, label_tz = read_ecbenchmark_dataset(
file_name_retained)
max_hs_of_sample = max([max_hs_of_sample, max(hs_p), max(hs_r)])
contours_hs = []
contours_tz = []
max_hs_on_contour = np.empty(n_contours_to_analyze)
for i in range(n_contours_to_analyze):
contribution_nr = i + 1
if 11 >= contribution_nr >= 9:
contribution_nr = 9
elif contribution_nr > 11:
# Because contribution 9 holds 3 sets of contours.
contribution_nr = contribution_nr - 2
folder_name = 'results/exercise-1/contribution-' + str(
if t < 0:
theta[i] = t + 2 * np.pi
return theta
colors_for_contribution = mycorder.mpl_colors
for idx in range(2):
colors_for_contribution.append(colors_for_contribution[8])
colors_for_contribution.append('blue')
fig, axs = plt.subplots(1, 2, sharey=True, figsize=(8, 4))
max_hs_of_sample = 0
# Load the environmental data.
file_name_provided = 'datasets/' + dataset_char + '.txt'
v_p, hs_p, label_v, label_hs = read_ecbenchmark_dataset(file_name_provided)
max_hs_of_sample = max([max_hs_of_sample, max(hs_p)])
contours = []
contours_v = []
contours_hs = []
max_hs_on_contours = np.empty(n_contours_to_analyze)
for i in range(n_contours_to_analyze):
contribution_nr = i + 1
if 11 >= contribution_nr >= 9:
contribution_nr = 9
elif contribution_nr > 11:
# Because contribution 9 holds 3 sets of contours.
contribution_nr = contribution_nr - 2
folder_name = 'results/exercise-1/contribution-' + str(contribution_nr)
file_name = folder_name + '/' + lastname_firstname[i] + '_dataset_' + \
def test_read_dataset(self):
"""
Reads the provided dataset "1year_dataset_A.txt".
"""
sample_hs, sample_tz, label_hs, label_tz = read_ecbenchmark_dataset()
self.assertAlmostEqual(sample_hs[0], 0.2845, delta=0.00001)
from viroconcom.fitting import Fit
from viroconcom.contours import HighestDensityContour, \
sort_points_to_form_continous_line
from viroconcom.plot import plot_contour, SamplePlotData
np.random.seed(9001) # For reproducablity.
# Define the number of years of data that one bootstrap sample should contain.
# In the benchmark 1, 5 and 25 years are used.
NR_OF_YEARS_TO_DRAW = [1, 2, 5]
NR_OF_BOOTSTRAP_SAMPLES = [25, 12, 5]
GRID_CELL_SIZE = 0.05
# Read dataset D.
file_path = 'datasets/D.txt'
dataset_d_v, dataset_d_hs, label_v, label_hs = read_ecbenchmark_dataset(file_path)
# Define the origin (will be used to compute confidence intervals).
v0 = np.mean(dataset_d_v)
hs0 = np.mean(dataset_d_hs)
# Define the structure of the probabilistic model that will be fitted to the
# dataset.
dist_description_v = {'name': 'Weibull_Exp',
'dependency': (None, None, None, None),
'width_of_intervals': 2}
dist_description_hs = {'name': 'Weibull_Exp',
'fixed_parameters': (None, None, None, 5),
# shape, location, scale, shape2
'dependency': (0, None, 0, None),
# shape, location, scale, shape2
def test_plot_contour_and_sample(self):
"""
Plots a contour together with the dataset that has been used to
fit a distribution for the contour.
"""
sample_hs, sample_tz, label_hs, label_tz = read_ecbenchmark_dataset()
# Define the structure of the probabilistic model that will be fitted to the
# dataset.
dist_description_hs = {
'name': 'Weibull_Exp',
'dependency': (None, None, None, None),
'width_of_intervals': 0.5
}
dist_description_tz = {
'name': 'Lognormal_SigmaMu',
'dependency': (0, None, 0),
# Shape, Location, Scale
'functions': ('asymdecrease3', None, 'lnsquare2'),
# Shape, Location, Scale
'min_datapoints_for_fit': 50
}
# Fit the model to the data.
fit = Fit((sample_hs, sample_tz),
(dist_description_hs, dist_description_tz))
contour = IFormContour(fit.mul_var_dist, 20, 1, 50)
contour_hs_20 = contour.coordinates[0][0]
contour_tz_20 = contour.coordinates[0][1]
# Find datapoints that exceed the 20-yr contour.
hs_outside, tz_outside, hs_inside, tz_inside = \
points_outside(contour_hs_20,
contour_tz_20,
np.asarray(sample_hs),
np.asarray(sample_tz))
# Compute the median tz conditonal on hs.
hs = np.linspace(0, 14, 100)
d1 = fit.mul_var_dist.distributions[1]
c1 = d1.scale.a
c2 = d1.scale.b
tz = c1 + c2 * np.sqrt(np.divide(hs, 9.81))
fig = plt.figure(figsize=(5, 5), dpi=150)
ax = fig.add_subplot(111)
# Plot the 20-year contour and the sample.
plotted_sample = SamplePlotData(x=np.asarray(sample_tz),
y=np.asarray(sample_hs),
ax=ax,
x_inside=tz_inside,
y_inside=hs_inside,
x_outside=tz_outside,
y_outside=hs_outside,
return_period=20)
plot_contour(x=contour_tz_20,
y=contour_hs_20,
ax=ax,
contour_label='20-yr IFORM contour',
x_label=label_tz,
y_label=label_hs,
line_style='b-',
plotted_sample=plotted_sample,
x_lim=(0, 19),
upper_ylim=15,
median_x=tz,
median_y=hs,
median_label='median of $T_z | H_s$')
plot_wave_breaking_limit(ax)
e_max_v_c50[i] = max(v)
e_max_hs_c50[i] = max(hs)
elif dataset_char == 'F':
f_max_v_c50[i] = max(v)
f_max_hs_c50[i] = max(hs)
# Load the environmental data and compute their minima and maxima.
empirical_max_hs_abc = np.empty([3, 1])
empirical_min_tz_abc = np.empty([3, 1])
empirical_max_tz_abc = np.empty([3, 1])
empirical_hs1_abc = np.empty([3, 1])
empirical_tz1_abc = np.empty([3, 1])
for i, dataset_char in np.ndenumerate(['A', 'B', 'C']):
file_name_provided = 'datasets/' + dataset_char + '.txt'
file_name_retained = 'datasets-retained/' + dataset_char + 'r.txt'
hs_p, tz_p, lhs, ltz = read_ecbenchmark_dataset(file_name_provided)
hs_r, tz_r, lhs, ltz = read_ecbenchmark_dataset(file_name_retained)
hs = np.append(hs_p, hs_r)
tz = np.append(tz_p, tz_r)
empirical_max_hs_abc[i] = max(hs)
empirical_min_tz_abc[i] = min(tz)
empirical_max_tz_abc[i] = max(tz)
pe_1yr = 1.0 / (365.25 * 24)
empirical_hs1_abc[i] = np.quantile(hs, 1 - pe_1yr)
empirical_tz1_abc[i] = np.quantile(tz, 1 - pe_1yr)
empirical_max_v_def = np.empty([3, 1])
empirical_max_hs_def = np.empty([3, 1])
empirical_v1_def = np.empty([3, 1])
empirical_hs1_def = np.empty([3, 1])
for i, dataset_char in np.ndenumerate(['D', 'E', 'F']):
file_name_provided = 'datasets/' + dataset_char + '.txt'
hs_shape2 = ConstantParam(5)
Hs = ExponentiatedWeibullDistribution(shape=hs_shape,
scale=hs_scale,
shape2=hs_shape2)
distributions = [U10, Hs]
dependencies = [(None, None, None, None), (0, None, 0, None)]
joint_model_4 = MultivariateDistribution(distributions, dependencies)
joint_models = [joint_model_4]
model_names = ['Contribution 4']
u_dim = [0] # Indices of wind speed the different hierarchical joint models.
hs_dim = [1] # Indices of wave height the different hierarchical joint models.
file_name_provided = 'datasets/D.txt'
file_name_retained = 'datasets-retained/Dr.txt'
u_p, hs_p, lu, lhs = read_ecbenchmark_dataset(file_name_provided)
u_r, hs_r, lu, lhs = read_ecbenchmark_dataset(file_name_retained)
u = np.append(u_p, u_r)
hs = np.append(hs_p, hs_r)
fig1, axs1 = plt.subplots(1, 4, figsize=(12, 3))
def ecdf(data):
""" Compute ECDF """
x = np.sort(data)
n = x.size
F = np.arange(1, n + 1) / n
return (x, F)
import matplotlib.pyplot as plt
import numpy as np
from viroconcom.read_write import read_ecbenchmark_dataset, read_contour
from viroconcom.plot import plot_confidence_interval, SamplePlotData
fs = 12
file_name = 'datasets/D.txt'
sample_v, sample_hs, label_v, label_hs = read_ecbenchmark_dataset(file_name)
names = [
'GC_CGS', 'hannesdottir_asta', 'haselsteiner_andreas',
'vanem_DirectSampling'
]
styles = [
'-r',
'-g',
'-k',
'-c',
]
leg_strs = [
'Contribution 2', 'Contribution 3', 'Contribution 4', 'Contribution 9'
]
nums = [2, 3, 4, 9]
prcntl_strs = [
'50th percentile contour', '2.5th percentile contour',
'97.5th percentile contour'
]