init_FG = 'kmeans'
minimum_TN = 0.1
metrics = ['MSE', 'R^2', 'Rp']
# Load in data
R = numpy.loadtxt(input_folder + "R.txt")
# Seed all of the methods the same
numpy.random.seed(3)
# Generate matrices M - one list of M's for each fraction
M_attempts = 100
all_Ms = [[
try_generate_M(I, J, fraction, M_attempts) for r in range(0, repeats)
] for fraction in fractions_unknown]
all_Ms_test = [[calc_inverse_M(M) for M in Ms] for Ms in all_Ms]
# Make sure each M has no empty rows or columns
def check_empty_rows_columns(M, fraction):
sums_columns = M.sum(axis=0)
sums_rows = M.sum(axis=1)
for i, c in enumerate(sums_rows):
assert c != 0, "Fully unobserved row in M, row %s. Fraction %s." % (
i, fraction)
for j, c in enumerate(sums_columns):
assert c != 0, "Fully unobserved column in M, column %s. Fraction %s." % (
j, fraction)
fraction_unknown = 0.1
attempts_M = 100
alpha, beta = 100., 1. #1., 1.
tau = alpha / beta
lambdaF = numpy.ones((I,true_K))
lambdaS = numpy.ones((true_K,true_L))
lambdaG = numpy.ones((J,true_L))
classifier = bnmtf_gibbs_optimised
initFG = 'kmeans'
initS = 'random'
# Generate data
(_,_,_,_,_,R) = generate_dataset(I,J,true_K,true_L,lambdaF,lambdaS,lambdaG,tau)
M = try_generate_M(I,J,fraction_unknown,attempts_M)
# Run the line search. The priors lambdaF,S,G need to be a single value (recall K,L is unknown)
priors = { 'alpha':alpha, 'beta':beta, 'lambdaF':lambdaF[0,0], 'lambdaS':lambdaS[0,0], 'lambdaG':lambdaG[0,0] }
grid_search = GridSearch(classifier,values_K,values_L,R,M,priors,initS,initFG,iterations,restarts)
grid_search.search(burn_in,thinning)
# Plot the performances of all three metrics
for metric in ['loglikelihood', 'BIC', 'AIC','MSE']:
# Make three lists of indices X,Y,Z (K,L,metric)
values = numpy.array(grid_search.all_values(metric)).flatten()
list_values_K = numpy.array([values_K for l in range(0,len(values_L))]).T.flatten()
list_values_L = numpy.array([values_L for k in range(0,len(values_K))]).flatten()
# Set up a regular grid of interpolation points
Ki, Li = (numpy.linspace(min(list_values_K), max(list_values_K), 100),
}
init_S = 'random'
init_FG = 'kmeans'
minimum_TN = 0.1
metrics = ['MSE', 'R^2', 'Rp']
# Load in data
R_true = numpy.loadtxt(input_folder + "R_true.txt")
# For each noise ratio, generate mask matrices for each attempt
M_attempts = 100
all_Ms = [[
try_generate_M(I, J, fraction_unknown, M_attempts)
for r in range(0, repeats)
] for noise in noise_ratios]
all_Ms_test = [[calc_inverse_M(M) for M in Ms] for Ms in all_Ms]
# Make sure each M has no empty rows or columns
def check_empty_rows_columns(M, fraction):
sums_columns = M.sum(axis=0)
sums_rows = M.sum(axis=1)
for i, c in enumerate(sums_rows):
assert c != 0, "Fully unobserved row in M, row %s. Fraction %s." % (
i, fraction)
for j, c in enumerate(sums_columns):
assert c != 0, "Fully unobserved column in M, column %s. Fraction %s." % (
j, fraction)
