def plot_survival_curves_and_histograms(sim_outcomes_mono, sim_outcomes_combo):
""" draws the survival curves and the histograms of time until HIV deaths
:param sim_outcomes_mono: outcomes of a cohort simulated under mono therapy
:param sim_outcomes_combo: outcomes of a cohort simulated under combination therapy
"""
# get survival curves of both treatments
survival_curves = [
sim_outcomes_mono.nLivingPatients, sim_outcomes_combo.nLivingPatients
]
# graph survival curve
Path.plot_sample_paths(sample_paths=survival_curves,
title='Survival curve',
x_label='Simulation time step (year)',
y_label='Number of alive patients',
legends=['Mono Therapy', 'Combination Therapy'],
color_codes=['green', 'blue'])
# histograms of survival times
set_of_survival_times = [
sim_outcomes_mono.survivalTimes, sim_outcomes_combo.survivalTimes
]
# graph histograms
Hist.plot_histograms(data_sets=set_of_survival_times,
title='Histogram of patient survival time',
x_label='Survival time (year)',
y_label='Counts',
bin_width=1,
legends=['Mono Therapy', 'Combination Therapy'],
color_codes=['green', 'blue'],
transparency=0.6)
def plot_histogram(self, parameter_name, title, x_label=None, y_label=None, x_range=None, folder=''):
""" creates a histogram of one parameter """
Fig.plot_histogram(
data=self.dictOfParamValues[parameter_name],
title=title, x_label=x_label, y_label=y_label,
x_range=x_range, figure_size=HISTOGRAM_FIG_SIZE, file_name=folder+'/'+title
)
def plot_ratio_hist(self, numerator_par_name, denominator_par_names,
title, x_label=None, x_range=None, output_fig_loc='figures_national'):
ratio_obss = self.__calculate_ratio_obss(numerator_par_name, denominator_par_names)
file_name = output_fig_loc + '/Ratio-' + title
# create the histogram of ratio
Fig.plot_histogram(
data=ratio_obss,
title=title,
x_label=x_label,
x_range=x_range,
figure_size=HISTOGRAM_FIG_SIZE,
file_name=file_name)
def plot_histogram(self,
parameter_name,
title,
x_lable=None,
y_lable=None,
x_range=None):
""" creates a histogram of one parameter """
Fig.plot_histogram(self.dictOfParams[parameter_name],
title,
x_lable,
y_lable,
x_range=x_range,
figure_size=HISTOGRAM_FIG_SIZE,
output_type='jpg',
file_name='figures_national\Par-' + title)
def plot_histograms(self, par_names=None, csv_file_name_prior=None, posterior_fig_loc='figures_national'):
""" creates histograms of parameters specified by ids
:param par_names: (list) of parameter names to plot
:param csv_file_name_prior: (string) filename where parameter prior ranges are located
:param posterior_fig_loc: (string) location where posterior figures_national should be located
"""
raise ValueError('Needs to be debugged.')
# clean the directory
IO.delete_files('.png', posterior_fig_loc)
# read prior distributions
dict_of_priors = None
if csv_file_name_prior is not None:
dict_of_priors = self.get_dict_of_priors(prior_info_csv_file=csv_file_name_prior)
if par_names is None:
par_names = self.get_all_parameter_names()
# for all parameters, read sampled parameter values and create the histogram
for par_name in par_names:
# get values for this parameter
par_values = self.dictOfParamValues[par_name]
# get info of this parameter
title, multiplier, x_range = self.get_title_multiplier_x_range_decimal_format(
par_name=par_name, dict_of_priors=dict_of_priors)
# adjust parameter values
par_values = [v*multiplier for v in par_values]
# find the filename the histogram should be saved as
file_name = posterior_fig_loc + '/Par-' + par_name + ' ' + F.proper_file_name(par_name)
# plot histogram
Fig.plot_histogram(
data=par_values,
title=title.replace('!', '\n'),
x_range=x_range,
figure_size=HISTOGRAM_FIG_SIZE,
file_name=file_name
)
def draw_survival_curves_and_histograms(calibrated_model_no_drug,
calibrated_model_with_drug):
""" draws the histograms of average survival time
:param calibrated_model_no_drug: calibrated model simulated when drug is not available
:param calibrated_model_with_drug: calibrated model simulated when drug is available
"""
# get survival curves of both treatments
survival_curves = [
calibrated_model_no_drug.multiCohorts.multiCohortOutcomes.
survivalCurves, calibrated_model_with_drug.multiCohorts.
multiCohortOutcomes.survivalCurves
]
# graph survival curve
Path.plot_sets_of_sample_paths(sets_of_sample_paths=survival_curves,
title='Survival curve',
x_label='Simulation time step',
y_label='Number of alive patients',
legends=['No Drug', 'With Drug'],
color_codes=['blue', 'orange'],
transparency=0.25)
# histograms of average survival times
set_of_survival_times = [
calibrated_model_no_drug.multiCohorts.multiCohortOutcomes.
meanSurvivalTimes, calibrated_model_with_drug.multiCohorts.
multiCohortOutcomes.meanSurvivalTimes
]
# graph histograms
Hist.plot_histograms(data_sets=set_of_survival_times,
title='Histogram of average patient survival time',
x_label='Survival time',
y_label='Counts',
bin_width=0.5,
legends=['No Drug', 'With Drug'],
color_codes=['blue', 'orange'],
transparency=0.5,
x_range=[6, 20])
def plot_survival_curves_and_histograms(sim_outcomes_none, sim_outcomes_anticoag):
""" draws the survival curves and the histograms of time until HIV deaths
:param sim_outcomes_none: outcomes of a cohort simulated under no therapy
:param sim_outcomes_anticoag: outcomes of a cohort simulated under anticoagulation
"""
# get survival curves of both treatments
survival_curves = [
sim_outcomes_none.nLivingPatients,
sim_outcomes_anticoag.nLivingPatients
]
# graph survival curve
Path.plot_sample_paths(
sample_paths=survival_curves,
title='Survival curve',
x_label='Simulation time step (year)',
y_label='Number of alive patients',
legends=['No Therapy', 'Anticoagulation'],
color_codes=['red', 'blue']
)
# histograms of survival times
set_of_strokes = [
sim_outcomes_none.nStrokes,
sim_outcomes_anticoag.nStrokes
]
# graph histograms
Hist.plot_histograms(
data_sets=set_of_strokes,
title='Histogram of number of strokes',
x_label='Number of Strokes',
y_label='Counts',
bin_width=1,
legends=['No Therapy', 'Anticoagulation'],
color_codes=['red', 'blue'],
transparency=0.5
)
def plot_survival_curves_and_histograms(multi_cohort_outcomes_mono,
multi_cohort_outcomes_combo):
""" plot the survival curves and the histograms of survival times
:param multi_cohort_outcomes_mono: outcomes of a multi-cohort simulated under mono therapy
:param multi_cohort_outcomes_combo: outcomes of a multi-cohort simulated under combination therapy
"""
# get survival curves of both treatments
sets_of_survival_curves = [
multi_cohort_outcomes_mono.survivalCurves,
multi_cohort_outcomes_combo.survivalCurves
]
# graph survival curve
Path.plot_sets_of_sample_paths(
sets_of_sample_paths=sets_of_survival_curves,
title='Survival Curves',
x_label='Simulation Time Step (year)',
y_label='Number of Patients Alive',
legends=['Mono Therapy', 'Combination Therapy'],
transparency=0.4,
color_codes=['green', 'blue'])
# histograms of survival times
set_of_survival_times = [
multi_cohort_outcomes_mono.meanSurvivalTimes,
multi_cohort_outcomes_combo.meanSurvivalTimes
]
# graph histograms
Hist.plot_histograms(data_sets=set_of_survival_times,
title='Histograms of Average Patient Survival Time',
x_label='Survival Time (year)',
y_label='Counts',
bin_width=0.25,
x_range=[5.25, 17.75],
legends=['Mono Therapy', 'Combination Therapy'],
color_codes=['green', 'blue'],
transparency=0.5)
def draw_survival_curves_and_histograms(cohort_no_drug, cohort_with_drug):
""" draws the survival curves and the histograms of survival time
:param cohort_no_drug: a cohort simulated when drug is not available
:param cohort_with_drug: a cohort simulated when drug is available
"""
# get survival curves of both treatments
survival_curves = [
cohort_no_drug.cohortOutcomes.nLivingPatients,
cohort_with_drug.cohortOutcomes.nLivingPatients
]
# graph survival curve
Path.plot_sample_paths(sample_paths=survival_curves,
title='Survival curve',
x_label='Simulation time step',
y_label='Number of alive patients',
legends=['No Drug', 'With Drug'],
color_codes=['blue', 'orange'],
transparency=0.5)
# histograms of survival times
set_of_survival_times = [
cohort_no_drug.cohortOutcomes.survivalTimes,
cohort_with_drug.cohortOutcomes.survivalTimes
]
# graph histograms
Hist.plot_histograms(data_sets=set_of_survival_times,
title='Histogram of patient survival time',
x_label='Survival time',
y_label='Counts',
bin_width=2,
legends=['No Drug', 'With Drug'],
color_codes=['blue', 'orange'],
transparency=0.5)
import SimPy.InOutFunctions as IO
import SimPy.Plots.Histogram as Hist
import SimPy.Plots.ProbDist as Plot
import SimPy.RandomVariateGenerators as RVGs
import SimPy.Statistics as Stat
# read weekly number of drinks
cols = IO.read_csv_cols(file_name='dataNumOfDrinks.csv',
n_cols=1,
if_ignore_first_row=True,
if_convert_float=True)
# make a histogram
Hist.plot_histogram(data=cols[0], title='Weekly Number of Drinks', bin_width=1)
# mean and standard deviation
stat = Stat.SummaryStat(name='Weekly number of drinks', data=cols[0])
print('Mean = ', stat.get_mean())
print('StDev = ', stat.get_stdev())
# fit a Poisson distribution
fit_results = RVGs.Poisson.fit_ml(data=cols[0])
print('Fitting a Poisson distribution:', fit_results)
# plot the fitted Poisson distribution
Plot.plot_poisson_fit(data=cols[0],
fit_results=fit_results,
x_label='Weekly number of drinks',
x_range=(0, 40),
bin_width=1)
# simulate all cohorts
multiCohort.simulate(Sets.TIME_STEPS)
# plot the sample paths
Path.plot_sample_paths(
sample_paths=multiCohort.multiCohortOutcomes.survivalCurves,
title='Survival Curves',
x_label='Time-Step (Year)',
y_label='Number Survived',
transparency=0.5)
# plot the histogram of average survival time
Hist.plot_histogram(
data=multiCohort.multiCohortOutcomes.meanSurvivalTimes,
title='Histogram of Mean Survival Time',
x_label='Mean Survival Time (Year)',
y_label='Count',
x_range=[2.5, 21.5],
bin_width=0.5)
# create the histogram of the mortality probabilities
Hist.plot_histogram(
data=mortality_samples,
title='Histogram of Mortality Probabilities',
x_label='Mortality Probability',
y_label='Counts',
x_range=[Sets.PRIOR_L, Sets.PRIOR_U])
# print projected mean survival time (years)
print('Projected mean survival time (years)',
multiCohort.multiCohortOutcomes.statMeanSurvivalTime.get_mean())
import SimPy.Plots.Histogram as Hist
import SimPy.Plots.SamplePaths as Path
# selected therapy
therapy = P.Therapies.COMBO
# create a cohort
myCohort = Cls.Cohort(id=1,
pop_size=D.POP_SIZE,
parameters=P.Parameters(therapy=therapy))
# simulate the cohort over the specified time steps
myCohort.simulate(sim_length=D.SIM_LENGTH)
# plot the sample path (survival curve)
Path.plot_sample_path(sample_path=myCohort.cohortOutcomes.nLivingPatients,
title='Survival Curve',
x_label='Time-Step (Year)',
y_label='Number Survived')
# plot the histogram of survival times
Hist.plot_histogram(data=myCohort.cohortOutcomes.survivalTimes,
title='Histogram of Patient Survival Time',
x_label='Survival Time (Year)',
y_label='Count',
bin_width=1)
# print the outcomes of this simulated cohort
Support.print_outcomes(sim_outcomes=myCohort.cohortOutcomes,
therapy_name=therapy)
pop_sizes=[COHORT_POP_SIZE] *
N_COHORTS, # [COHORT_POP_SIZE, COHORT_POP_SIZE, ..., COHORT_POP_SIZE]
mortality_probs=[MORTALITY_PROB] * N_COHORTS # [p, p, ....]
)
# simulate all cohorts
multiCohort.simulate(TIME_STEPS)
# plot the sample paths
Path.plot_sample_paths(
sample_paths=multiCohort.multiCohortOutcomes.survivalCurves,
title='Survival Curves',
x_label='Time-Step (Year)',
y_label='Number Survived',
transparency=0.5)
# plot the histogram of average survival time
Hist.plot_histogram(data=multiCohort.multiCohortOutcomes.meanSurvivalTimes,
title='Histogram of Mean Survival Time',
x_label='Mean Survival Time (Year)',
y_label='Count')
# print projected mean survival time (years)
print('Projected mean survival time (years)',
multiCohort.multiCohortOutcomes.statMeanSurvivalTime.get_mean())
# print projection interval
print(
'95% projection (prediction, percentile, or uncertainty) interval of average survival time (years)',
multiCohort.multiCohortOutcomes.statMeanSurvivalTime.get_PI(alpha=ALPHA))
def plot_histograms(self,
ids=None,
csv_file_name_prior=None,
posterior_fig_loc='figures_national'):
""" creates histograms of parameters specified by ids
:param ids: (list) list of parameter ids
:param csv_file_name_prior: (string) filename where parameter prior ranges are located
:param posterior_fig_loc: (string) location where posterior figures_national should be located
"""
# clean the directory
IO.delete_files('.png', posterior_fig_loc)
# read prior distributions
if csv_file_name_prior is not None:
priors = IO.read_csv_rows(file_name=csv_file_name_prior,
if_ignore_first_row=True,
delimiter=',',
if_convert_float=True)
# for all parameters, read sampled parameter values and create the histogram
par_id = 0
for key, par_values in self.dictOfParams.items():
# skip these columns
if key in ['Simulation Replication', 'Random Seed']:
continue
# check if the histogram should be created for this parameter
if_show = False
if ids is None:
if_show = True
elif par_id in ids:
if_show = True
# create the histogram
if if_show:
# find prior range
x_range = None
if priors is not None:
try:
x_range = [
float(priors[par_id][Column.LB.value]),
float(priors[par_id][Column.UB.value])
]
except:
print(
'Could not convert string to float to find the prior distribution of parameter:',
par_id)
else:
x_range = None
# find the filename the histogram should be saved as
file_name = posterior_fig_loc + '\Par-' + str(
par_id) + ' ' + F.proper_file_name(key)
# find title
if priors[par_id][Column.TITLE.value] in ('', None):
title = priors[par_id][Column.NAME.value]
else:
title = priors[par_id][Column.TITLE.value]
# find multiplier
if priors[par_id][Column.MULTIPLIER.value] in ('', None):
multiplier = 1
else:
multiplier = float(priors[par_id][Column.MULTIPLIER.value])
x_range = [x * multiplier for x in x_range]
par_values = [v * multiplier for v in par_values]
# plot histogram
Fig.plot_histogram(data=par_values,
title=title.replace('!', '\n'),
x_range=x_range,
figure_size=HISTOGRAM_FIG_SIZE,
file_name=file_name)
# move to the next parameter
par_id += 1
def plot_pairwise(self, par_names=None, prior_info_csv_file=None, fig_filename='pairwise_correlation.png',
figure_size=(10, 10)):
""" creates pairwise correlation between parameters specified by ids
:param par_names: (list) names of parameter to display
:param prior_info_csv_file: (string) filename where parameter prior ranges are located
(Note: '!' will be replaced with '\n')
:param fig_filename: (string) filename to save the figure as
:param figure_size: (tuple) figure size
"""
# read information about prior distributions
dict_of_priors = None
if prior_info_csv_file is not None:
dict_of_priors = self.get_dict_of_priors(prior_info_csv_file=prior_info_csv_file)
# if parameter names are not specified, include all parameters
if par_names is None:
par_names = self.get_all_parameter_names()
# find the info of parameters to include in the analysis
info_of_param_info_to_include = []
# for each parameter, read sampled parameter values and create the histogram
for par_name in par_names:
# get parameter values
par_values = self.dictOfParamValues[par_name]
# get info
title, multiplier, x_range, decimal, form = self.get_title_multiplier_x_range_decimal_format(
par_name=par_name, dict_of_priors=dict_of_priors)
# adjust parameter values
par_values = [v*multiplier for v in par_values]
# append the info for this parameter
info_of_param_info_to_include.append(
ParamInfo(name=par_name,
label=title.replace('!', '\n'),
values=par_values, value_range=x_range))
# plot pairwise
# set default properties of the figure
plt.rc('font', size=6) # fontsize of texts
plt.rc('axes', titlesize=6) # fontsize of the figure title
plt.rc('axes', titleweight='semibold') # fontweight of the figure title
# plot each panel
n = len(info_of_param_info_to_include)
if n == 0:
raise ValueError('Values of parameters are not provided. '
'Make sure the calibration algorithm exports the parameter values.')
f, axarr = plt.subplots(nrows=n, ncols=n, figsize=figure_size)
for i in range(n):
for j in range(n):
# get the current axis
ax = axarr[i, j]
if j == 0:
ax.set_ylabel(info_of_param_info_to_include[i].label)
if i == n-1:
ax.set_xlabel(info_of_param_info_to_include[j].label)
if i == j:
# plot histogram
Fig.add_histogram_to_ax(
ax=ax,
data=info_of_param_info_to_include[i].values,
x_range=info_of_param_info_to_include[i].range
)
ax.set_yticklabels([])
ax.set_yticks([])
else:
ax.scatter(info_of_param_info_to_include[j].values,
info_of_param_info_to_include[i].values,
alpha=0.5, s=2)
ax.set_xlim(info_of_param_info_to_include[j].range)
ax.set_ylim(info_of_param_info_to_include[i].range)
# correlation line
b, m = polyfit(info_of_param_info_to_include[j].values,
info_of_param_info_to_include[i].values, 1)
ax.plot(info_of_param_info_to_include[j].values,
b + m * info_of_param_info_to_include[j].values, '-', c='black')
corr, p = pearsonr(info_of_param_info_to_include[j].values,
info_of_param_info_to_include[i].values)
ax.text(0.95, 0.95, '{0:.2f}'.format(corr), transform=ax.transAxes, fontsize=6,
va='top', ha='right')
f.align_ylabels(axarr[:, 0])
f.tight_layout()
output_figure(plt=f, filename=fig_filename, dpi=300)
def plot_pairwise(self,
ids=None,
csv_file_name_prior=None,
fig_filename='pairwise_correlation.png',
figure_size=(10, 10)):
""" creates pairwise corrolation between parameters specified by ids
:param ids: (list) list of parameter ids
:param csv_file_name_prior: (string) filename where parameter prior ranges are located
:param fig_filename: (string) filename to save the figure as
:param figure_size: (tuple) figure size
"""
# read prior distributions
priors = None
if csv_file_name_prior is not None:
priors = IO.read_csv_rows(file_name=csv_file_name_prior,
if_ignore_first_row=True,
delimiter=',',
if_convert_float=True)
# find the names of parameters to include in the analysis
info_of_params_to_include = []
par_id = 0
for key, par_values in self.dictOfParams.items():
# skip these columns
if key in ['Simulation Replication', 'Random Seed']:
continue
# check if the histogram should be created for this parameter
if_show = False
if ids is None:
if_show = True
elif par_id in ids:
if_show = True
# create the histogram
if if_show:
# find prior range
x_range = None
if priors is not None:
try:
x_range = [
float(priors[par_id][Column.LB.value]),
float(priors[par_id][Column.UB.value])
]
except:
print(
'Could not convert string to float to find the prior distribution of parameter:',
par_id)
else:
x_range = None
# find title
if priors[par_id][Column.TITLE.value] in ('', None):
label = priors[par_id][Column.NAME.value]
else:
label = priors[par_id][Column.TITLE.value]
# find multiplier
if priors[par_id][Column.MULTIPLIER.value] in ('', None):
multiplier = 1
else:
multiplier = float(priors[par_id][Column.MULTIPLIER.value])
x_range = [x * multiplier for x in x_range]
par_values = [v * multiplier for v in par_values]
# append the info for this parameter
info_of_params_to_include.append(
ParamInfo(idx=par_id,
name=key,
label=label.replace('!', '\n'),
values=par_values,
range=x_range))
# move to the next parameter
par_id += 1
# plot pairwise
# set default properties of the figure
plt.rc('font', size=6) # fontsize of texts
plt.rc('axes', titlesize=6) # fontsize of the figure title
plt.rc('axes',
titleweight='semibold') # fontweight of the figure title
# plot each panel
n = len(info_of_params_to_include)
f, axarr = plt.subplots(nrows=n, ncols=n, figsize=figure_size)
for i in range(n):
for j in range(n):
# get the current axis
ax = axarr[i, j]
if j == 0:
ax.set_ylabel(info_of_params_to_include[i].label)
if i == n - 1:
ax.set_xlabel(info_of_params_to_include[j].label)
if i == j:
# plot histogram
Fig.add_histogram_to_ax(
ax=ax,
data=info_of_params_to_include[i].values,
x_range=info_of_params_to_include[i].range)
ax.set_yticklabels([])
ax.set_yticks([])
else:
ax.scatter(info_of_params_to_include[j].values,
info_of_params_to_include[i].values,
alpha=0.5,
s=2)
ax.set_xlim(info_of_params_to_include[j].range)
ax.set_ylim(info_of_params_to_include[i].range)
# correlation line
b, m = polyfit(info_of_params_to_include[j].values,
info_of_params_to_include[i].values, 1)
ax.plot(info_of_params_to_include[j].values,
b + m * info_of_params_to_include[j].values,
'-',
c='black')
corr, p = pearsonr(info_of_params_to_include[j].values,
info_of_params_to_include[i].values)
ax.text(0.95,
0.95,
'{0:.2f}'.format(corr),
transform=ax.transAxes,
fontsize=6,
va='top',
ha='right')
f.align_ylabels(axarr[:, 0])
f.tight_layout()
f.savefig(fig_filename, bbox_inches='tight', dpi=300)
cohort_size=Sets.SIM_POP_SIZE,
time_steps=Sets.TIME_STEPS)
# plot the sample paths
Path.plot_sample_paths(sample_paths=calibrated_model.multiCohorts.
multiCohortOutcomes.survivalCurves,
title='Survival Curves',
x_label='Time-Step (Year)',
y_label='Number Survived',
transparency=0.5)
# plot the histogram of mean survival time
Hist.plot_histogram(
data=calibrated_model.multiCohorts.multiCohortOutcomes.meanSurvivalTimes,
title='Histogram of Mean Survival Time',
x_label='Mean Survival Time (Year)',
y_label='Count',
bin_width=0.25,
x_range=[2.5, 21.5])
# create the histogram of the resampled mortality probabilities
Hist.plot_histogram(data=calibrated_model.resampledMortalityProb,
title='Histogram of Resampled Mortality Probabilities',
x_label='Mortality Probability',
y_label='Counts',
x_range=[Sets.PRIOR_L, Sets.PRIOR_U])
# Estimate of mortality probability and the posterior interval
print(
'Estimate of mortality probability ({:.{prec}%} credible interval):'.
format(1 - Sets.ALPHA, prec=0),