def __init__(self,
root_models,
distances,
backend,
kernel=None,
seed=None):
self.model = root_models
# We define the joint Linear combination distance using all the distances for each individual models
self.distance = LinearCombination(root_models, distances)
if (kernel is None):
mapping, garbage_index = self._get_mapping()
models = []
for mdl, mdl_index in mapping:
models.append(mdl)
kernel = DefaultKernel(models)
self.kernel = kernel
self.backend = backend
self.rng = np.random.RandomState(seed)
self.logger = logging.getLogger(__name__)
self.accepted_parameters_manager = AcceptedParametersManager(
self.model)
self.simulation_counter = 0
def infer_parameters():
# define observation for true parameters mean=170, std=15
height_obs = [
160.82499176, 167.24266737, 185.71695756, 153.7045709, 163.40568812,
140.70658699, 169.59102084, 172.81041696, 187.38782738, 179.66358934,
176.63417241, 189.16082803, 181.98288443, 170.18565017, 183.78493886,
166.58387299, 161.9521899, 155.69213073, 156.17867343, 144.51580379,
170.29847515, 197.96767899, 153.36646527, 162.22710198, 158.70012047,
178.53470703, 170.77697743, 164.31392633, 165.88595994, 177.38083686,
146.67058471763457, 179.41946565658628, 238.02751620619537,
206.22458790620766, 220.89530574344568, 221.04082532837026,
142.25301427453394, 261.37656571434275, 171.63761180867033,
210.28121820385866, 237.29130237612236, 175.75558340169619,
224.54340549862235, 197.42448680731226, 165.88273684581381,
166.55094082844519, 229.54308602661584, 222.99844054358519,
185.30223966014586, 152.69149367593846, 206.94372818527413,
256.35498655339154, 165.43140916577741, 250.19273595481803,
148.87781549665536, 223.05547559193792, 230.03418198709608,
146.13611923127021, 138.24716809523139, 179.26755740864527,
141.21704876815426, 170.89587081800852, 222.96391329259626,
188.27229523693822, 202.67075179617672, 211.75963110985992,
217.45423324370509
]
# define prior
from abcpy.continuousmodels import Uniform
mu = Uniform([[150], [200]], )
sigma = Uniform([[5], [25]], )
# define the model
from abcpy.continuousmodels import Normal as Gaussian
height = Gaussian([mu, sigma], name='height')
# define statistics
from abcpy.statistics import Identity
statistics_calculator = Identity(degree=2, cross=False)
# define distance
from abcpy.distances import LogReg
distance_calculator = LogReg(statistics_calculator)
# define kernel
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([mu, sigma])
# define backend
# Note, the dummy backend does not parallelize the code!
from abcpy.backends import BackendDummy as Backend
backend = Backend()
# define sampling scheme
from abcpy.inferences import PMCABC
sampler = PMCABC([height], [distance_calculator], backend, kernel, seed=1)
# sample from scheme
T, n_sample, n_samples_per_param = 3, 250, 10
eps_arr = np.array([.75])
epsilon_percentile = 10
journal = sampler.sample([height_obs], T, eps_arr, n_sample,
n_samples_per_param, epsilon_percentile)
return journal
def __init__(self,
root_models,
distances,
backend,
kernel=None,
seed=None):
self.model = root_models
# We define the joint Linear combination distance using all the distances for each individual models
self.distance = LinearCombination(root_models, distances)
if (kernel is None):
mapping, garbage_index = self._get_mapping()
models = []
for mdl, mdl_index in mapping:
models.append(mdl)
kernel = DefaultKernel(models)
self.kernel = kernel
self.backend = backend
self.rng = np.random.RandomState(seed)
self.logger = logging.getLogger(__name__)
# these are usually big tables, so we broadcast them to have them once
# per executor instead of once per task
self.smooth_distances_bds = None
self.all_distances_bds = None
self.accepted_parameters_manager = AcceptedParametersManager(
self.model)
self.simulation_counter = 0
from Model import TIP4PGromacsOOOH as Water
# Define Graphical model
theta1 = Uniform([[.281] , [.53]],name='theta1')
theta2 = Uniform([[0.2] , [0.9]],name='theta2')
water = Water([theta1, theta2, 2500000])
# Define distance and statistics
statistics_calculator = Identity(degree = 1, cross = False)
distance_calculator = Abserror(statistics_calculator)
# Define kernel
from abcpy.backends import BackendMPI as Backend
backend = Backend()
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([theta1, theta2])
######### Inference for simulated data ###############
water_obs = [np.load('Data/obs_data.npy')]
sampler = APMCABC([water], [distance_calculator], backend, kernel, seed = 1)
steps, n_samples, n_samples_per_param, alpha, acceptance_cutoff, covFactor, full_output, journal_file =10, 100, 1, 0.1, 0.03, 2.0, 1, None
print('TIP4P: APMCABC Inferring for simulated data')
journal_apmcabc = sampler.sample([water_obs], steps, n_samples, n_samples_per_param, alpha, acceptance_cutoff, covFactor, full_output, journal_file)
print('TIP4P: APMCABC done for simulated data')
journal_apmcabc.save('Result/MD_GROMACS_APMCABC_obs.jrnl')
######### Inference for Experimental data 1 (Neutron Diffraction of Water) ###############
water_obs = [np.load('Data/exp_data.npy')]
import numpy as np
from abcpy.continuousmodels import Uniform
from Model import AshDispersal
u0 = Uniform([[100], [300]], name='u0')
l0 = Uniform([[30], [100]], name='l0')
AD = AshDispersal([u0, l0], name='AD')
from abcpy.backends import BackendDummy as Backend
backend = Backend(process_per_model=2)
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([u0, l0])
from Distance import DepositionDistance
distance_calculator = DepositionDistance()
print(distance_calculator.distance("test.h5", "test.h5"))
from abcpy.inferences import SABC
sampler = SABC([AD], [distance_calculator], backend, kernel, seed=1)
#steps, epsilon, n_samples, n_samples_per_param, beta, delta, v, ar_cutoff, resample, n_update, adaptcov, full_output = 3, [50], 50, 1, 2, 0.2, 0.3, 0.1, None, None, 1, 1
steps, epsilon, n_samples, n_samples_per_param, beta, delta, v, ar_cutoff, resample, n_update, adaptcov, full_output = 3, [
1
], 1, 1, 2, 0.2, 0.3, 0.1, None, None, 1, 1
print('SABC Inferring')
journal_sabc = sampler.sample("test.h5", steps, epsilon, n_samples,
n_samples_per_param, beta, delta, v, ar_cutoff,
resample, n_update, adaptcov, full_output)
print('SABC done')
def infer_parameters(backend,
scheme='rejection',
n_samples=250,
n_samples_per_param=10,
logging_level=logging.WARN):
"""Perform inference for this example.
Parameters
----------
backend
The parallelization backend
steps : integer, optional
Number of iterations in the sequential PMCABC algoritm ("generations"). The default value is 3
n_samples : integer, optional
Number of posterior samples to generate. The default value is 250.
n_samples_per_param : integer, optional
Number of data points in each simulated data set. The default value is 10.
Returns
-------
abcpy.output.Journal
A journal containing simulation results, metadata and optionally intermediate results.
"""
logging.basicConfig(level=logging_level)
# experimental setup
T = 50. # simulation time
dt = 0.025 # time step
I_amp = 0.32 # stimulus amplitude
r_soma = 40 # radius of soma
threshold = -55 # AP threshold
# input stimulus
stimulus_dict = constant_stimulus(I_amp=I_amp,
T=T,
dt=dt,
t_stim_on=10,
t_stim_off=40,
r_soma=r_soma)
I = stimulus_dict["I"]
#I_stim = stimulus_dict["I_stim"]
# true parameters
gbar_K_true = 36
gbar_Na_true = 120
gbar_K_std = 5
gbar_Na_std = 5
# define priors
gbar_K = Normal([[gbar_K_true], [gbar_K_std]], name='gbar_K')
gbar_Na = Normal([[gbar_Na_true], [gbar_Na_std]], name='gbar_Na')
# define the model
hh_simulator = HHSimulator([gbar_K, gbar_Na], I, T, dt)
# observed data
obs_data = hh_simulator.forward_simulate([gbar_K_true, gbar_Na_true])
# define statistics
statistics_calculator = Identity()
# Learn the optimal summary statistics using Semiautomatic summary selection
statistics_learning = Semiautomatic([hh_simulator],
statistics_calculator,
backend,
n_samples=1000,
n_samples_per_param=1,
seed=42)
new_statistics_calculator = statistics_learning.get_statistics()
# define distance
distance_calculator = Euclidean(new_statistics_calculator)
# define kernel
kernel = DefaultKernel([gbar_K, gbar_Na])
# define sampling scheme
if scheme == 'rejection':
sampler = RejectionABC([hh_simulator], [distance_calculator],
backend,
seed=42)
# sample from scheme
epsilon = 2.
journal = sampler.sample([obs_data], n_samples, n_samples_per_param,
epsilon)
elif scheme == 'smc':
sampler = SMCABC([hh_simulator], [distance_calculator],
backend,
kernel,
seed=42)
# sample from scheme
steps = 3
journal = sampler.sample([obs_data], steps, n_samples,
n_samples_per_param)
elif scheme == 'pmc':
sampler = PMCABC([hh_simulator], [distance_calculator],
backend,
kernel,
seed=42)
# sample from scheme
steps = 3
eps_arr = np.array([2.])
epsilon_percentile = 10
journal = sampler.sample([obs_data], steps, eps_arr, n_samples,
n_samples_per_param, epsilon_percentile)
return journal
def infer_parameters(steps=2, n_sample=50, n_samples_per_param=1, logging_level=logging.WARN):
"""Perform inference for this example.
Parameters
----------
steps : integer, optional
Number of iterations in the sequential PMCABC algorithm ("generations"). The default value is 3
n_samples : integer, optional
Number of posterior samples to generate. The default value is 250.
n_samples_per_param : integer, optional
Number of data points in each simulated data set. The default value is 10.
Returns
-------
abcpy.output.Journal
A journal containing simulation results, metadata and optionally intermediate results.
"""
logging.basicConfig(level=logging_level)
# define backend
# Note, the dummy backend does not parallelize the code!
from abcpy.backends import BackendDummy as Backend
backend = Backend()
# define observation for true parameters mean=170, std=15
height_obs = [160.82499176, 167.24266737, 185.71695756, 153.7045709, 163.40568812, 140.70658699, 169.59102084,
172.81041696, 187.38782738, 179.66358934, 176.63417241, 189.16082803, 181.98288443, 170.18565017,
183.78493886, 166.58387299, 161.9521899, 155.69213073, 156.17867343, 144.51580379, 170.29847515,
197.96767899, 153.36646527, 162.22710198, 158.70012047, 178.53470703, 170.77697743, 164.31392633,
165.88595994, 177.38083686, 146.67058471763457, 179.41946565658628, 238.02751620619537,
206.22458790620766, 220.89530574344568, 221.04082532837026, 142.25301427453394, 261.37656571434275,
171.63761180867033, 210.28121820385866, 237.29130237612236, 175.75558340169619, 224.54340549862235,
197.42448680731226, 165.88273684581381, 166.55094082844519, 229.54308602661584, 222.99844054358519,
185.30223966014586, 152.69149367593846, 206.94372818527413, 256.35498655339154, 165.43140916577741,
250.19273595481803, 148.87781549665536, 223.05547559193792, 230.03418198709608, 146.13611923127021,
138.24716809523139, 179.26755740864527, 141.21704876815426, 170.89587081800852, 222.96391329259626,
188.27229523693822, 202.67075179617672, 211.75963110985992, 217.45423324370509]
# define prior
from abcpy.continuousmodels import Uniform
mu = Uniform([[150], [200]], name="mu")
sigma = Uniform([[5], [25]], name="sigma")
# define the model
from abcpy.continuousmodels import Normal
height = Normal([mu, sigma], )
# 1) generate simulations from prior
from abcpy.inferences import DrawFromPrior
draw_from_prior = DrawFromPrior([height], backend=backend)
# notice the use of the `.sample_par_sim_pairs` method rather than `.sample` to obtain data suitably formatted
# for the summary statistics learning routines
parameters, simulations = draw_from_prior.sample_par_sim_pairs(100, n_samples_per_param=1)
# if you want to use the test loss to do early stopping in the training:
parameters_val, simulations_val = draw_from_prior.sample_par_sim_pairs(100, n_samples_per_param=1)
# discard the mid dimension (n_samples_per_param, as the StatisticsLearning classes use that =1)
simulations = simulations.reshape(simulations.shape[0], simulations.shape[2])
simulations_val = simulations_val.reshape(simulations_val.shape[0], simulations_val.shape[2])
# 2) now train the NNs with the different methods with the generated data
from abcpy.statistics import Identity
identity = Identity() # to apply before computing the statistics
logging.info("semiNN")
from abcpy.statisticslearning import SemiautomaticNN, TripletDistanceLearning
semiNN = SemiautomaticNN([height], identity, backend=backend, parameters=parameters,
simulations=simulations, parameters_val=parameters_val, simulations_val=simulations_val,
early_stopping=True, # early stopping
seed=1, n_epochs=10, scale_samples=False, use_tqdm=False)
logging.info("triplet")
triplet = TripletDistanceLearning([height], identity, backend=backend, parameters=parameters,
simulations=simulations, parameters_val=parameters_val,
simulations_val=simulations_val,
early_stopping=True, # early stopping
seed=1, n_epochs=10, scale_samples=True, use_tqdm=False)
# 3) save and re-load NNs:
# get the statistics from the already fit StatisticsLearning object 'semiNN':
learned_seminn_stat = semiNN.get_statistics()
learned_triplet_stat = triplet.get_statistics()
# this has a save net method:
learned_seminn_stat.save_net("seminn_net.pth")
# if you used `scale_samples=True` in learning the NNs, need to provide a path where pickle stores the scaler too:
learned_triplet_stat.save_net("triplet_net.pth", path_to_scaler="scaler.pkl")
# to reload: need to use the Neural Embedding statistics fromFile; this needs to know which kind of NN it is using;
# need therefore to pass either the input/output size (it data size and number parameters) or the network class if
# that was specified explicitly in the StatisticsLearning class. Check the docstring for NeuralEmbedding.fromFile
# for more details.
from abcpy.statistics import NeuralEmbedding
learned_seminn_stat_loaded = NeuralEmbedding.fromFile("seminn_net.pth", input_size=1, output_size=2)
learned_triplet_stat_loaded = NeuralEmbedding.fromFile("triplet_net.pth", input_size=1, output_size=2,
path_to_scaler="scaler.pkl")
# 4) you can optionally rescale the different summary statistics be their standard deviation on a reference dataset
# of simulations. To do this, it is enough to pass at initialization the reference dataset, and the rescaling will
# be applied every time the statistics is computed on some simulation or observation.
learned_triplet_stat_loaded = NeuralEmbedding.fromFile("triplet_net.pth", input_size=1, output_size=2,
path_to_scaler="scaler.pkl",
reference_simulations=simulations_val)
# 5) perform inference
# define distance
from abcpy.distances import Euclidean
distance_calculator = Euclidean(learned_seminn_stat_loaded)
# define kernel
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([mu, sigma])
# define sampling scheme
from abcpy.inferences import PMCABC
sampler = PMCABC([height], [distance_calculator], backend, kernel, seed=1)
eps_arr = np.array([500]) # starting value of epsilon; the smaller, the slower the algorithm.
# at each iteration, take as epsilon the epsilon_percentile of the distances obtained by simulations at previous
# iteration from the observation
epsilon_percentile = 10
journal = sampler.sample([height_obs], steps, eps_arr, n_sample, n_samples_per_param, epsilon_percentile)
return journal
pT = Uniform([[0.1], [10.0]], name='pT')
pF = Uniform([[0.1e-3], [9.0e-3]], name='pF')
aT = Uniform([[0], [10]], name='aT')
v_z_AP = Uniform([[1.0e-3], [9.0e-3]], name='v_z_AP')
v_z_NAP = Uniform([[1.0e-4], [9.0e-4]], name='v_z_NAP')
PD = PlateletDeposition([noAP, noNAP, SR_x, pAd, pAg, pT, pF, aT, v_z_AP, v_z_NAP], name='PD')
# XObserved = np.array([0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 2.11600000e+05, 5.96585366e+03,
# 2.00000000e+01, 3.90572997e+03, 1.59328549e+01, 1.38943902e+05, 0.00000000e+00,
# 6.00000000e+01, 3.42727305e+03, 2.80052570e+01, 8.57585366e+04, 0.00000000e+00,
# 1.20000000e+02, 2.33523014e+03, 7.57715388e+01, 4.25231707e+04, 0.00000000e+00,
# 3.00000000e+02, 1.74166329e+02, 2.46413793e+03, 5.15975610e+03, 0.00000000e+00])
# obsdata = [np.array(XObserved).reshape(1, -1)]
# # Define kernel and join the defined kernels
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([pAd, pAg, pT, pF, aT, v_z_AP, v_z_NAP])
# Define Distance functions
from abcpy.distances import Euclidean
from statistic import Multiply
L = np.load('Data/L_all_3_cross.npz')['L']
stat_mult = Multiply(L=L, degree=3, cross=True)
dist_calc_mult = Euclidean(stat_mult)
# SABC - Multiply##
from abcpy.inferences import SABC
print('Inference using Classifier Loss')
sampler = SABC([PD], [dist_calc_mult], backend, kernel, seed=1)
steps, epsilon, n_samples, n_samples_per_param, ar_cutoff, full_output, journal_file = 20, 10e20, 511, 1, 0.001, 1, None
print('SABC Inferring')
def infer_parameters(steps=3,
n_sample=250,
n_samples_per_param=10,
logging_level=logging.WARN):
"""Perform inference for this example.
Parameters
----------
steps : integer, optional
Number of iterations in the sequential PMCABC algoritm ("generations"). The default value is 3
n_samples : integer, optional
Number of posterior samples to generate. The default value is 250.
n_samples_per_param : integer, optional
Number of data points in each simulated data set. The default value is 10.
Returns
-------
abcpy.output.Journal
A journal containing simulation results, metadata and optionally intermediate results.
"""
logging.basicConfig(level=logging_level)
# define observation for true parameters mean=170, std=15
height_obs = [
160.82499176, 167.24266737, 185.71695756, 153.7045709, 163.40568812,
140.70658699, 169.59102084, 172.81041696, 187.38782738, 179.66358934,
176.63417241, 189.16082803, 181.98288443, 170.18565017, 183.78493886,
166.58387299, 161.9521899, 155.69213073, 156.17867343, 144.51580379,
170.29847515, 197.96767899, 153.36646527, 162.22710198, 158.70012047,
178.53470703, 170.77697743, 164.31392633, 165.88595994, 177.38083686,
146.67058471763457, 179.41946565658628, 238.02751620619537,
206.22458790620766, 220.89530574344568, 221.04082532837026,
142.25301427453394, 261.37656571434275, 171.63761180867033,
210.28121820385866, 237.29130237612236, 175.75558340169619,
224.54340549862235, 197.42448680731226, 165.88273684581381,
166.55094082844519, 229.54308602661584, 222.99844054358519,
185.30223966014586, 152.69149367593846, 206.94372818527413,
256.35498655339154, 165.43140916577741, 250.19273595481803,
148.87781549665536, 223.05547559193792, 230.03418198709608,
146.13611923127021, 138.24716809523139, 179.26755740864527,
141.21704876815426, 170.89587081800852, 222.96391329259626,
188.27229523693822, 202.67075179617672, 211.75963110985992,
217.45423324370509
]
# define prior
from abcpy.continuousmodels import Uniform
mu = Uniform([[150], [200]], name='mu')
sigma = Uniform([[5], [25]], name='sigma')
# define the model
from abcpy.continuousmodels import Normal
height = Normal([mu, sigma], name='height')
# define statistics
from abcpy.statistics import Identity
statistics_calculator = Identity(degree=2, cross=False)
# define distance
from abcpy.distances import LogReg
distance_calculator = LogReg(statistics_calculator, seed=42)
# define kernel
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([mu, sigma])
# define backend
# Note, the dummy backend does not parallelize the code!
from abcpy.backends import BackendDummy as Backend
backend = Backend()
# define sampling scheme
from abcpy.inferences import PMCABC
sampler = PMCABC([height], [distance_calculator], backend, kernel, seed=1)
eps_arr = np.array([.75])
epsilon_percentile = 10
journal = sampler.sample([height_obs], steps, eps_arr, n_sample,
n_samples_per_param, epsilon_percentile)
return journal
def infer_parameters():
# The data corresponding to model_1 defined below
grades_obs = [
3.872486707973337, 4.6735380808674405, 3.9703538990858376,
4.11021272048805, 4.211048655421368, 4.154817956586653,
4.0046893064392695, 4.01891381384729, 4.123804757702919,
4.014941267301294, 3.888174595940634, 4.185275142948246,
4.55148774469135, 3.8954427675259016, 4.229264035335705,
3.839949451328312, 4.039402553532825, 4.128077814241238,
4.361488645531874, 4.086279074446419, 4.370801602256129,
3.7431697332475466, 4.459454162392378, 3.8873973643008255,
4.302566721487124, 4.05556051626865, 4.128817316703757,
3.8673704442215984, 4.2174459453805015, 4.202280254493361,
4.072851400451234, 3.795173229398952, 4.310702877332585,
4.376886328810306, 4.183704734748868, 4.332192463368128,
3.9071312388426587, 4.311681374107893, 3.55187913252144,
3.318878360783221, 4.187850500877817, 4.207923106081567,
4.190462065625179, 4.2341474252986036, 4.110228694304768,
4.1589891480847765, 4.0345604687633045, 4.090635481715123,
3.1384654393449294, 4.20375641386518, 4.150452690356067,
4.015304457401275, 3.9635442007388195, 4.075915739179875,
3.5702080541929284, 4.722333310410388, 3.9087618197155227,
4.3990088006390735, 3.968501165774181, 4.047603645360087,
4.109184340976979, 4.132424805281853, 4.444358334346812,
4.097211737683927, 4.288553086265748, 3.8668863066511303,
3.8837108501541007
]
# The prior information changing the class size and social background, depending on school location
from abcpy.continuousmodels import Uniform, Normal
school_location = Uniform([[0.2], [0.3]], )
# The average class size of a certain school
class_size = Normal([[school_location], [0.1]], )
# The social background of a student
background = Normal([[school_location], [0.1]], )
# The grade a student would receive without any bias
grade_without_additional_effects = Normal([[4.5], [0.25]], )
# The grade a student of a certain school receives
final_grade = grade_without_additional_effects - class_size - background
# The data corresponding to model_2 defined below
scholarship_obs = [
2.7179657436207805, 2.124647285937229, 3.07193407853297,
2.335024761813643, 2.871893855192, 3.4332002458233837,
3.649996835818173, 3.50292335102711, 2.815638168018455,
2.3581613289315992, 2.2794821846395568, 2.8725835459926503,
3.5588573782815685, 2.26053126526137, 1.8998143530749971,
2.101110815311782, 2.3482974964831573, 2.2707679029919206,
2.4624550491079225, 2.867017757972507, 3.204249152084959,
2.4489542437714213, 1.875415915801106, 2.5604889644872433,
3.891985093269989, 2.7233633223405205, 2.2861070389383533,
2.9758813233490082, 3.1183403287267755, 2.911814060853062,
2.60896794303205, 3.5717098647480316, 3.3355752461779824,
1.99172284546858, 2.339937680892163, 2.9835630207301636,
2.1684912355975774, 3.014847335983034, 2.7844122961916202,
2.752119871525148, 2.1567428931391635, 2.5803629307680644,
2.7326646074552103, 2.559237193255186, 3.13478196958166,
2.388760269933492, 3.2822443541491815, 2.0114405441787437,
3.0380056368041073, 2.4889680313769724, 2.821660164621084,
3.343985964873723, 3.1866861970287808, 4.4535037154856045,
3.0026333138006027, 2.0675706089352612, 2.3835301730913185,
2.584208398359566, 3.288077633446465, 2.6955853384148183,
2.918315169739928, 3.2464814419322985, 2.1601516779909433,
3.231003347780546, 1.0893224045062178, 0.8032302688764734,
2.868438615047827
]
# A quantity that determines whether a student will receive a scholarship
scholarship_without_additional_effects = Normal([[2], [0.5]], )
# A quantity determining whether a student receives a scholarship, including his social background
final_scholarship = scholarship_without_additional_effects + 3 * background
# Define a summary statistics for final grade and final scholarship
from abcpy.statistics import Identity
statistics_calculator_final_grade = Identity(degree=2, cross=False)
statistics_calculator_final_scholarship = Identity(degree=3, cross=False)
# Define a distance measure for final grade and final scholarship
from abcpy.approx_lhd import SynLikelihood
approx_lhd_final_grade = SynLikelihood(statistics_calculator_final_grade)
approx_lhd_final_scholarship = SynLikelihood(
statistics_calculator_final_scholarship)
# Define a backend
from abcpy.backends import BackendDummy as Backend
backend = Backend()
# Define a perturbation kernel
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([school_location, class_size, grade_without_additional_effects, \
background, scholarship_without_additional_effects])
# Define sampling parameters
T, n_sample, n_samples_per_param = 3, 250, 10
# Define sampler
from abcpy.inferences import PMC
sampler = PMC([final_grade, final_scholarship], \
[approx_lhd_final_grade, approx_lhd_final_scholarship], backend, kernel)
# Sample
journal = sampler.sample([grades_obs, scholarship_obs], T, n_sample,
n_samples_per_param)
np.save('Result/obs_data_' + str(ind), result)
# Define backend
from abcpy.backends import BackendMPI as Backend
backend = Backend()
# Define Statistics
from abcpy.statistics import Identity
statistics_calculator = Identity(degree=1, cross=False)
# Define distance
from KLdistance import KLdistance
distance_calculator = KLdistance(statistics_calculator)
# Define kernel
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([sigma, epsilon])
## APMCABC ##
from abcpy.inferences import APMCABC
sampler = APMCABC([relentropy], [distance_calculator], backend, kernel, seed=1)
steps, n_samples, n_samples_per_param, alpha, acceptance_cutoff, covFactor, full_output, journal_file = 10, 1000, 1, 0.1, 0.03, 2.0, 1, None
# Import Simulated Dataset
relentropy_obs = [np.load('Result/obs_data.npy')]
print('APMCABC Inferring Heliuma Potential')
journal_apmcabc = sampler.sample([relentropy_obs], steps, n_samples,
n_samples_per_param, alpha, acceptance_cutoff,
covFactor, full_output, journal_file)
journal_apmcabc.save('Result/APMCABCHelium.jrnl')
# print(statistics_calculator.statistics(resultfakeobs1))
# print(statistics_calculator.statistics(resultfakeobs2))
# Define distance
from abcpy.distances import Euclidean
distance_calculator = Euclidean(statistics_calculator)
# print('# Check whether the distance works')
# print(distance_calculator.distance(resultfakeobs1, resultfakeobs1))
# print(distance_calculator.distance(resultfakeobs1, resultfakeobs2))
#
# Define kernel
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([
B_0, activation_energy, energy_tissue, energy_food, energy_synthesis,
half_saturation_coeff, max_ingestion_rate, mass_birth, mass_cocoon,
mass_maximum, mass_sexual_maturity, growth_constant, max_reproduction_rate,
speed
])
## SABC ##
from abcpy.inferences import SABC
sampler = SABC([EarthWorm], [distance_calculator], backend, kernel, seed=1)
steps, epsilon, n_samples, n_samples_per_param, ar_cutoff, full_output, journal_file = 10, 10000, 500, 1, 0.001, 1, None
print('SABC Inferring')
# We use resultfakeobs1 as our observed dataset
journal_sabc = sampler.sample([resultfakeobs1],
steps=steps,
epsilon=epsilon,
n_samples=n_samples,
#print(statistics_calculator.statistics(resultfakeobs1))
#print(statistics_calculator.statistics(obs_data))
# Define distance
from Distance import WeightedEuclidean
wt = list(1000 * np.ones(11)) + list(0 * np.ones(11))
for ind in range(60):
wt = wt + list((1 / 30) * np.ones(11))
distance_calculator = WeightedEuclidean(statistics_calculator,
weight=np.array(wt))
#print('# Check whether the distance works')
#print(distance_calculator.distance(obs_data, resultfakeobs1))
if sample:
# Define kernel
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([H, Am, AE, PM, I])
if algorithm == 'sabc':
## SABC ##
from abcpy.inferences import SABC
sampler = SABC([Bass], [distance_calculator], backend, kernel, seed=1)
steps, epsilon, n_samples, n_samples_per_param, ar_cutoff, full_output, journal_file = 10, 10e20, 111, 1, 0.001, 1, None
print('SABC Inferring')
# We use resultfakeobs1 as our observed dataset
journal_sabc = sampler.sample(observations=[obs_data],
steps=steps,
epsilon=epsilon,
n_samples=n_samples,
n_samples_per_param=n_samples_per_param,
beta=2,
delta=0.2,
np.array([[0, 0, 0, 172200, 4808], [20, 1689, 26.8, 155100, 1683],
[60, 2004, 29.9, 149400, 0], [120, 1968, 31.3, 140700, 0],
[300, 1946, 36.6, 125801, 0]])
]
# Example to Generate Data to check it's correct
#PDtry = PlateletDeposition([110.0, 14.6, 0.6, 1.7e-3, 6.0], name = 'PD')
#resultfakeobs1 = PDtry.forward_simulate([110.0, 14.6, 0.6, 1.7e-3, 6.0], 1)
# Define backend
from abcpy.backends import BackendDummy as Backend
backend = Backend()
# Define kernel and join the defined kernels
from abcpy.perturbationkernel import DefaultKernel
kernel = DefaultKernel([pAd, pAg, pT, pF, aT])
# Define Statistics
from Statistics import DepositionStatistics
statistics_calculator = DepositionStatistics(degree=1, cross=False)
# Define distance
from Distance import DepositionDistance
distance_calculator = DepositionDistance(statistics_calculator)
print(distance_calculator.distance(data_obs, data_obs_1))
print('Hello')
## SABC ##
from abcpy.inferences import SABC