def test_all_values():
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
gridsearch = GridSearch(classifier, values_K, values_L, R, M, priors,
initS, initFG, iterations)
gridsearch.all_performances = {
'BIC': [[10, 9, 8], [11, 12, 13], [17, 16, 15], [13, 13, 13]],
'AIC': [[8, 8, 8], [7, 7, 7], [10, 11, 15], [6, 6, 6]],
'loglikelihood': [[10, 12, 13], [17, 18, 29], [5, 4, 3], [3, 2, 1]]
}
assert numpy.array_equal(
gridsearch.all_values('BIC'),
[[10, 9, 8], [11, 12, 13], [17, 16, 15], [13, 13, 13]])
assert numpy.array_equal(gridsearch.all_values('AIC'),
[[8, 8, 8], [7, 7, 7], [10, 11, 15], [6, 6, 6]])
assert numpy.array_equal(
gridsearch.all_values('loglikelihood'),
[[10, 12, 13], [17, 18, 29], [5, 4, 3], [3, 2, 1]])
with pytest.raises(AssertionError) as error:
gridsearch.all_values('FAIL')
assert str(error.value) == "Unrecognised metric name: FAIL."
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 = 'random'
iterations = 1
gridsearch = GridSearch(classifier, values_K, values_L, R, M, priors,
initS, initFG, iterations)
gridsearch.search()
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
gridsearch = GridSearch(classifier, values_K, values_L, R, M, priors,
initS, initFG, iterations)
assert gridsearch.I == I
assert gridsearch.J == J
assert numpy.array_equal(gridsearch.values_K, values_K)
assert numpy.array_equal(gridsearch.values_L, values_L)
assert numpy.array_equal(gridsearch.R, R)
assert numpy.array_equal(gridsearch.M, M)
assert gridsearch.priors == priors
assert gridsearch.iterations == iterations
assert gridsearch.initS == initS
assert gridsearch.initFG == initFG
assert gridsearch.all_performances['BIC'].shape == (4, 3)
assert gridsearch.all_performances['AIC'].shape == (4, 3)
assert gridsearch.all_performances['loglikelihood'].shape == (4, 3)
# 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 lambdaF,S,G need to be a single value (recall K,L is unknown)
priors = {
'alpha': alpha,
'beta': beta,
'lambdaF': lambdaF[0, 0] / 10,
'lambdaS': lambdaS[0, 0] / 10,
'lambdaG': lambdaG[0, 0] / 10
}
grid_search = GridSearch(classifier, values_K, values_L, R, M, priors, initS,
initFG, iterations, restarts)
grid_search.search()
# Plot the performances of all three metrics
metrics = ['loglikelihood', 'BIC', 'AIC', 'MSE']
for metric in metrics:
# 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),
numpy.linspace(min(list_values_L), max(list_values_L), 100))
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),
numpy.linspace(min(list_values_L), max(list_values_L), 100))
Ki, Li = numpy.meshgrid(Ki, Li)
# Interpolate