def _check_bayesfit_batch_process(branch):
# Generate dataset
data_batch = np.array([[0.0010, 45.0000, 90.0000],
[0.0015, 50.0000, 90.0000],
[0.0020, 44.0000, 90.0000],
[0.0025, 44.0000, 90.0000],
[0.0030, 52.0000, 90.0000],
[0.0035, 53.0000, 90.0000],
[0.0040, 62.0000, 90.0000],
[0.0045, 64.0000, 90.0000],
[0.0050, 76.0000, 90.0000],
[0.0060, 79.0000, 90.0000],
[0.0070, 88.0000, 90.0000],
[0.0080, 90.0000, 90.0000],
[0.0100, 90.0000, 90.0000]])
# Create batch data object
data = dict()
data['data01'] = data_batch
data['data02'] = data_batch
# Choose branch that defines sigmoid fit
if branch == 0:
param_free = [True, True, False, False]
elif branch == 1:
param_free = [True, True, True, False]
elif branch == 2:
param_free = [True, True, True, True]
# Use BayesFit to fit function
metrics, options = bf.fitmodel(data,
batch=True,
param_free=param_free,
density=20)
# Update success flag
success = 1
return success
def _check_bayesfit_psyfunctions(branch):
# Generate dataset
data = np.array([[0.0010, 45.0000, 90.0000], [0.0015, 50.0000, 90.0000],
[0.0020, 44.0000, 90.0000], [0.0025, 44.0000, 90.0000],
[0.0030, 52.0000, 90.0000], [0.0035, 53.0000, 90.0000],
[0.0040, 62.0000, 90.0000], [0.0045, 64.0000, 90.0000],
[0.0050, 76.0000, 90.0000], [0.0060, 79.0000, 90.0000],
[0.0070, 88.0000, 90.0000], [0.0080, 90.0000, 90.0000],
[0.0100, 90.0000, 90.0000]])
# Choose branch that defines sigmoid fit
if branch == 0:
sigmoid_type = 'logistic'
elif branch == 1:
sigmoid_type = 'weibull'
elif branch == 2:
sigmoid_type = 'gumbel'
elif branch == 3:
sigmoid_type = 'quick'
elif branch == 4:
sigmoid_type = 'log-quick'
elif branch == 5:
sigmoid_type = 'hyperbolic'
elif branch == 6:
sigmoid_type = 'norm'
# Use BayesFit to fit function
metrics, options = bf.fitmodel(data,
sigmoid_type=sigmoid_type,
logspace=False)
# Update success flag
success = 1
return success
def _check_plot_cdf():
# Generate dataset
x = [0.1, 0.21, 0.33, 0.44, 0.55, 0.66, 0.78, 0.9]
y = [0.48, 0.47, 0.53, 0.55, 0.73, 0.83, 0.97, 0.96]
N = [100, 100, 100, 100, 100, 100, 100, 100]
data = np.array([x, y, N]).T
# Use BayesFit to fit function
trace, metrics, options = bf.fitmodel(data)
# Generate cdf plot
bf.plot_cdf(data, metrics, options)
# Update success flag
success = 1
return success
def _check_geweke_plot():
# Generate dataset
x = [0.1, 0.21, 0.33, 0.44, 0.55, 0.66, 0.78, 0.9]
y = [0.48, 0.47, 0.53, 0.55, 0.73, 0.83, 0.97, 0.96]
N = [100, 100, 100, 100, 100, 100, 100, 100]
data = np.array([x, y, N]).T
# Use BayesFit to fit function
trace, metrics, options = bf.fitmodel(data)
# Generate geweke plot
bf.geweke_plot(trace=trace['alpha'], intervals=10, length=300)
# Update success flag
success = 1
return success
def _check_bayesfit_priors():
# Generate dataset
data = np.array([[0.0010, 45.0000, 90.0000], [0.0015, 50.0000, 90.0000],
[0.0020, 44.0000, 90.0000], [0.0025, 44.0000, 90.0000],
[0.0030, 52.0000, 90.0000], [0.0035, 53.0000, 90.0000],
[0.0040, 62.0000, 90.0000], [0.0045, 64.0000, 90.0000],
[0.0050, 76.0000, 90.0000], [0.0060, 79.0000, 90.0000],
[0.0070, 88.0000, 90.0000], [0.0080, 90.0000, 90.0000],
[0.0100, 90.0000, 90.0000]])
priors = ['Norm(0.005,0.001)', 'Norm(3,0.75)', None, None]
metrics, options = bf.fitmodel(data,
priors=priors,
sigmoid_type='weibull',
logspace=False)
# Update success flag
success = 1
return success
def _check_bayesfit_param_constraints(branch):
# Generate dataset
x = [0.1, 0.21, 0.33, 0.44, 0.55, 0.66, 0.78, 0.9]
y = [0.48, 0.47, 0.53, 0.55, 0.73, 0.83, 0.97, 0.96]
N = [100, 100, 100, 100, 100, 100, 100, 100]
data = np.array([x, y, N]).T
# Choose branch that defines sigmoid fit
if branch == 0:
param_constraints = [True, True, False, False]
elif branch == 1:
param_constraints = [True, True, True, False]
elif branch == 2:
param_constraints = [True, True, True, True]
# Use BayesFit to fit function
trace, metrics, options = bf.fitmodel(data,
param_constraints=param_constraints)
# Update success flag
success = 1
return success
def _check_plot_marginals():
# Generate dataset
data = np.array([[0.0010, 45.0000, 90.0000],
[0.0015, 50.0000, 90.0000],
[0.0020, 44.0000, 90.0000],
[0.0025, 44.0000, 90.0000],
[0.0030, 52.0000, 90.0000],
[0.0035, 53.0000, 90.0000],
[0.0040, 62.0000, 90.0000],
[0.0045, 64.0000, 90.0000],
[0.0050, 76.0000, 90.0000],
[0.0060, 79.0000, 90.0000],
[0.0070, 88.0000, 90.0000],
[0.0080, 90.0000, 90.0000],
[0.0100, 90.0000, 90.0000]]);
# Use BayesFit to fit function
metrics, options = bf.fitmodel(data, sigmoid_type = 'norm')
# Generate geweke plot
bf.plot_marginals(metrics)
# Update success flag
success = 1
return success
def _check_bayesfit_psyfunctions(branch):
# Generate dataset
x = [0.1, 0.21, 0.33, 0.44, 0.55, 0.66, 0.78, 0.9]
y = [0.48, 0.47, 0.53, 0.55, 0.73, 0.83, 0.97, 0.96]
N = [100, 100, 100, 100, 100, 100, 100, 100]
data = np.array([x, y, N]).T
# Choose branch that defines sigmoid fit
if branch == 0:
sigmoid_type = 'logistic'
elif branch == 1:
sigmoid_type = 'weibull'
elif branch == 2:
sigmoid_type = 'gumbel'
elif branch == 3:
sigmoid_type = 'quick'
elif branch == 4:
sigmoid_type = 'log-quick'
elif branch == 5:
sigmoid_type = 'hyperbolic'
# Use BayesFit to fit function
trace, metrics, options = bf.fitmodel(data, sigmoid_type=sigmoid_type)
# Update success flag
success = 1
return success
import numpy as np
import bayesfit as bf
#################################################################
# GENERATE DATAFRAME OF RESPONSES USING MOCS / MLE
#################################################################
data = np.array([[0.0010, 45.0000, 90.0000], [0.0015, 50.0000, 90.0000],
[0.0020, 44.0000, 90.0000], [0.0025, 44.0000, 90.0000],
[0.0030, 52.0000, 90.0000], [0.0035, 53.0000, 90.0000],
[0.0040, 62.0000, 90.0000], [0.0045, 64.0000, 90.0000],
[0.0050, 76.0000, 90.0000], [0.0060, 79.0000, 90.0000],
[0.0070, 88.0000, 90.0000], [0.0080, 90.0000, 90.0000],
[0.0100, 90.0000, 90.0000]])
metrics, options = bf.fitmodel(data, sigmoid_type='logistic')
#################################################################
# GENERATE DATAFRAME OF RESPONSES USING STAIRCASE / MLE
#################################################################
data_stairs = np.array([[0.0010, 3.0000, 7.0000], [0.0015, 11.0000, 20.0000],
[0.0020, 17.0000, 35.0000], [0.0025, 7.0000, 15.0000],
[0.0030, 26.0000, 45.0000], [0.0035, 45.0000, 78.0000],
[0.0040, 55.0000, 80.0000], [0.0045, 64.0000, 90.0000],
[0.0050, 75.0000, 89.0000], [0.0060, 44.0000, 51.0000],
[0.0070, 19.0000, 20.0000], [0.0080, 7.0000, 7.0000],
[0.0100, 2.0000, 2.0000]])
metrics, options = bf.fitmodel(data_stairs, sigmoid_type='norm')
#################################################################
