#Number of bootstrap samples
boot_samples = 5000
z_dist_boot = np.zeros(200)
z_dist_ideal_boot = np.zeros(200)
z_dist_min_boot = np.zeros(200)
Nsample = boot_samples
L0,L1 = df.get_limits(Nsample, size, rank)
#Actually run the methods and save their outputs
for obs_num in xrange(L0,L1):
boot_phi = np.random.choice(sampled_data,size=num_obs,replace=True)
z_dist_max, ideal_chisq_stop, min_chisq = lucy_replicator(50000,boot_phi)
z_dist_ideal_chisq = lucy_replicator(ideal_chisq_stop,boot_phi)[0]
z_dist_min_chisq = lucy_replicator(min_chisq,boot_phi)[0]
z_dist_boot = z_dist_boot+z_dist_max
z_dist_ideal_boot = z_dist_ideal_boot+z_dist_ideal_chisq
z_dist_min_boot = z_dist_min_boot+z_dist_min_chisq
def lucy_replicator(iters,phi):
#Initialize arrays that will hold goodness-of-fit information
#ks_zdist_psi = np.zeros(iters+1)
#cr_val_zdist_psi = np.zeros(iters+1)
#ks_phitilde_c = np.zeros(iters+1)
#cr_val_phi_tilde_c = np.zeros(iters+1)
chisq_psi_zdist = np.zeros(iters+1)
chisq_c_phitilde = np.zeros(iters+1)
#Use the same initial guess as in Lucy (1974)
initial_guess = (np.sqrt(2)/np.pi)/(1+zm**4)
#initial_guess=np.ones(200)
#Turn our observed data into a histogram
phi_tilde = np.histogram(phi,bins=bins,density=True)[0]
#Run the first iteration of the RLD algorithm
z_dist = df.integral_calc(initial_guess,lucy_conditional_dists,phi_tilde)
z_dist = z_dist/sum(z_dist)/.025
#Calculate the phi^r term, which we call c
c = np.dot(z_dist,lucy_conditional_dists)
c=c/sum(c)/.025
#Perform the KS tests, saving p values and test statistics
#ks_zdist_psi[0] = ks_test(z_dist,norm_vals,num_obs)[0]
#cr_val_zdist_psi[0] = ks_test(z_dist,norm_vals,num_obs)[1]
#ks_phitilde_c[0] = ks_test(phi_tilde,c,num_obs)[0]
#cr_val_phi_tilde_c[0] = ks_test(phi_tilde,c,num_obs)[1]
#Perform the chi-squared test
expected_psi = np.round(num_obs*norm_vals*.025)
observed_zdist = np.round(num_obs*z_dist*.025)
expected_c = np.round(num_obs*c*.025)
obs_phi = np.round(num_obs*phi_tilde*.025)
chisq_psi_zdist[0] = chisquare(observed_zdist,expected_psi)[0]
chisq_c_phitilde[0] = chisquare(obs_phi,expected_c)[0]
for i in range(0,iters):
#Run the RLD algorithm
z_dist = df.integral_calc(z_dist,lucy_conditional_dists,phi_tilde)
z_dist = z_dist/sum(z_dist)/.025
#Calculate the phi^r term, which we call c
c = np.dot(z_dist,lucy_conditional_dists)
c=c/sum(c)/.025
#Perform the KS tests, saving p values and test statistics
#ks_zdist_psi[i+1] = ks_test(z_dist,norm_vals,num_obs)[0]
#cr_val_zdist_psi[i+1] = ks_test(z_dist,norm_vals,num_obs)[1]
#ks_phitilde_c[i+1] = ks_test(phi_tilde,c,num_obs)[0]
#cr_val_phi_tilde_c[i+1] = ks_test(phi_tilde,c,num_obs)[1]
#Perform the chi-squared test
#expected_psi = (num_obs*norm_vals*.025)
observed_zdist = (num_obs*z_dist*.025)
expected_c = (num_obs*c*.025)
obs_phi = np.round(num_obs*phi_tilde*.025)
chisq_psi_zdist[i+1] = chisquare(observed_zdist,expected_psi)[0]
chisq_c_phitilde[i+1] = chisquare(obs_phi,expected_c)[0]
#Find the best iteration number to stop at, according the Lucy (1974)
ideal_chisq_stop = np.max(np.where(chisq_c_phitilde>233)[0])
#ideal_ks_stop = np.max(np.where(ks_phitilde_c > cr_val_phi_tilde_c[0]))
#Find best iteration number to stop at, in terms of "distance" between estimate and truth
min_chisq = np.argmin(chisq_psi_zdist)
#min_ks = np.argmin(ks_zdist_psi)
return z_dist, ideal_chisq_stop, min_chisq
#Load the finished SOMz
A = load('SOMz_finished_cut.npy')
finished_SOMz = A.item()
######################
num_bins=200
bins = linspace(0,2,201)
zm = .5*(bins[:-1]+bins[1:])
bins[num_bins] = 2.001
bins[num_bins] = 2.001
Nsample = len(Mean_test)
L0,L1 = df.get_limits(Nsample, size, rank)
#Set the initial guess and number of iterations
initial_guess = eval(params.initial_guess)
iters = params.single_iters
####################
#Initialize empty lists
base_point_dist = []
base_pdf_dist = []
matias_point_dist =[]
matias_pdf_dist =[]
rossi_point_local_dist =[]
rossi_pdf_local_dist =[]
rossi_point_global_dist =[]
rossi_pdf_global_dist = []
