def test_init():
I,J = 10,9
values_K = [1,2,4,5]
values_L = [5,4,3]
R = 2*numpy.ones((I,J))
M = numpy.ones((I,J))
priors = { 'alpha':3, 'beta':4, 'lambdaF':5, 'lambdaS':6, 'lambdaG':7 }
initFG = 'exp'
initS = 'random'
iterations = 11
greedysearch = GreedySearch(classifier,values_K,values_L,R,M,priors,initS,initFG,iterations)
assert greedysearch.I == I
assert greedysearch.J == J
assert numpy.array_equal(greedysearch.values_K, values_K)
assert numpy.array_equal(greedysearch.values_L, values_L)
assert numpy.array_equal(greedysearch.R, R)
assert numpy.array_equal(greedysearch.M, M)
assert greedysearch.priors == priors
assert greedysearch.iterations == iterations
assert greedysearch.initS == initS
assert greedysearch.initFG == initFG
assert greedysearch.all_performances['BIC'] == []
assert greedysearch.all_performances['AIC'] == []
assert greedysearch.all_performances['loglikelihood'] == []
def test_search():
# Check whether we get no exceptions...
I,J = 10,9
values_K = [1,2,4,5]
values_L = [5,4,3]
R = 2*numpy.ones((I,J))
R[0,0] = 1
M = numpy.ones((I,J))
priors = { 'alpha':3, 'beta':4, 'lambdaF':5, 'lambdaS':6, 'lambdaG':7 }
initFG = 'exp'
initS = 'exp'
iterations = 1
search_metric = 'BIC'
numpy.random.seed(0)
random.seed(0)
greedysearch = GreedySearch(classifier,values_K,values_L,R,M,priors,initS,initFG,iterations)
greedysearch.search(search_metric)
with pytest.raises(AssertionError) as error:
greedysearch.all_values('FAIL')
assert str(error.value) == "Unrecognised metric name: FAIL."
# We go from: (1,5) -> (1,4) -> (1,3), and try 6 locations
assert len(greedysearch.all_values('BIC')) == 6
def test_best_value():
I, J = 10, 9
values_K = [1, 2, 4, 5]
values_L = [5, 4, 3]
R = 2 * numpy.ones((I, J))
M = numpy.ones((I, J))
priors = {'alpha': 3, 'beta': 4, 'lambdaF': 5, 'lambdaS': 6, 'lambdaG': 7}
initFG = 'exp'
initS = 'random'
iterations = 11
greedysearch = GreedySearch(classifier, values_K, values_L, R, M, priors,
initS, initFG, iterations)
greedysearch.all_performances = {
'BIC': [(1, 2, 10.), (2, 2, 20.), (2, 3, 30.), (2, 4, 5.),
(5, 3, 20.)],
'AIC': [(1, 2, 10.), (2, 2, 20.), (2, 3, 4.), (2, 4, 25.),
(5, 3, 20.)],
'loglikelihood': [(1, 2, 10.), (2, 2, 8.), (2, 3, 30.), (2, 4, 40.),
(5, 3, 20.)]
}
assert greedysearch.best_value('BIC') == (2, 4)
assert greedysearch.best_value('AIC') == (2, 3)
assert greedysearch.best_value('loglikelihood') == (2, 2)
with pytest.raises(AssertionError) as error:
greedysearch.all_values('FAIL')
assert str(error.value) == "Unrecognised metric name: FAIL."
# Generate data
(_, _, _, _, _, R) = generate_dataset(I, J, true_K, true_L, lambdaF, lambdaS,
lambdaG, tau)
M = numpy.ones((I, J))
#M = try_generate_M(I,J,fraction_unknown,attempts_M)
# Run the line search. The priors lambdaU and lambdaV need to be a single value (recall K is unknown)
priors = {
'alpha': alpha,
'beta': beta,
'lambdaF': lambdaF[0, 0] / 10,
'lambdaS': lambdaS[0, 0] / 10,
'lambdaG': lambdaG[0, 0] / 10
}
greedy_search = GreedySearch(classifier, values_K, values_L, R, M, priors,
initS, initFG, iterations, restarts)
greedy_search.search(search_metric)
# Plot the performances of all three metrics
metrics = ['loglikelihood', 'BIC', 'AIC', 'MSE', 'ELBO']
for metric in metrics:
# Make three lists of indices X,Y,Z (K,L,metric)
KLvalues = numpy.array(greedy_search.all_values(metric))
(list_values_K, list_values_L, values) = zip(*KLvalues)
# Set up a regular grid of interpolation points
Ki, Li = (numpy.linspace(min(list_values_K), max(list_values_K), 100),
numpy.linspace(min(list_values_L), max(list_values_L), 100))
Ki, Li = numpy.meshgrid(Ki, Li)
# Interpolate
lambdaS = numpy.ones((true_K,true_L))
lambdaG = numpy.ones((J,true_L))
classifier = bnmtf_gibbs_optimised
initFG = 'kmeans'
initS = 'random'
search_metric = 'AIC'
# 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 lambdaU and lambdaV need to be a single value (recall K is unknown)
priors = { 'alpha':alpha, 'beta':beta, 'lambdaF':lambdaF[0,0], 'lambdaS':lambdaS[0,0], 'lambdaG':lambdaG[0,0] }
greedy_search = GreedySearch(classifier,values_K,values_L,R,M,priors,initS,initFG,iterations,restarts)
greedy_search.search(search_metric,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)
KLvalues = numpy.array(greedy_search.all_values(metric))
(list_values_K,list_values_L,values) = zip(*KLvalues)
# Set up a regular grid of interpolation points
Ki, Li = (numpy.linspace(min(list_values_K), max(list_values_K), 100),
numpy.linspace(min(list_values_L), max(list_values_L), 100))
Ki, Li = numpy.meshgrid(Ki, Li)
# Interpolate
rbf = scipy.interpolate.Rbf(list_values_K, list_values_L, values, function='linear')