standardised = False
train_config = {
'iterations' : 2000,
'init_UV' : 'exponential',
'expo_prior' : 0.1
}
K_range = [6,8,10,12,14]
no_folds = 10
output_file = "./results.txt"
files_nested_performances = ["./fold_%s.txt" % fold for fold in range(1,no_folds+1)]
# Construct the parameter search
parameter_search = [{'K':K} for K in K_range]
# Load in the Sanger dataset
(_,X_min,M,_,_,_,_) = load_gdsc(standardised=standardised,sep=',')
# Run the cross-validation framework
random.seed(42)
numpy.random.seed(9000)
nested_crossval = MatrixNestedCrossValidation(
method=NMF,
X=X_min,
M=M,
K=no_folds,
P=5,
parameter_search=parameter_search,
train_config=train_config,
file_performance=output_file,
files_nested_performances=files_nested_performances
)
standardised = False #standardised Sanger or unstandardised
repeats = 10
iterations = 500
init_UV = 'random'
I, J, K = 622,138,25
alpha, beta = 1., 1. #1., 1.
lambdaU = numpy.ones((I,K))/10.
lambdaV = numpy.ones((J,K))/10.
priors = { 'alpha':alpha, 'beta':beta, 'lambdaU':lambdaU, 'lambdaV':lambdaV }
# Load in data
(_,R,M,_,_,_,_) = load_gdsc(standardised=standardised)
# Run the VB algorithm, <repeats> times
times_repeats = []
performances_repeats = []
for i in range(0,repeats):
# Set all the seeds
numpy.random.seed(0)
# Run the classifier
BNMF = bnmf_vb_optimised(R,M,K,priors)
BNMF.initialise(init_UV)
BNMF.run(iterations)
# Extract the performances and timestamps across all iterations
'init_FG': 'kmeans',
'init_S': 'exponential',
'expo_prior': 0.1
}
P = 5
no_folds = 10
output_file = "./results.txt"
files_nested_performances = [
"./fold_%s.txt" % fold for fold in range(1, no_folds + 1)
]
# Construct the parameter search
parameter_search = [{'K': K, 'L': L} for (K, L) in [(6, 6), (8, 8), (10, 10)]]
# Load in the Sanger dataset
(_, X_min, M, _, _, _, _) = load_gdsc(standardised=standardised)
# Run the cross-validation framework
#random.seed(42)
#numpy.random.seed(9000)
nested_crossval = MatrixNestedCrossValidation(
method=NMTF,
X=X_min,
M=M,
K=no_folds,
P=5,
parameter_search=parameter_search,
train_config=train_config,
file_performance=output_file,
files_nested_performances=files_nested_performances)
nested_crossval.run()
