repeats = 10
iterations = 1000
init_UV = 'random'
I, J, K = 622,138,25
minimum_TN = 0.1
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
nmf = nmf_icm(R,M,K,priors)
nmf.initialise(init_UV)
nmf.run(iterations,minimum_TN=minimum_TN)
# Extract the performances and timestamps across all iterations
sys.path.append(project_location) from BNMTF.code.nmtf_np import NMTF from BNMTF.drug_sensitivity.experiments_gdsc.load_data import load_gdsc import matplotlib.pyplot as plt ########## standardised = False #standardised Sanger or unstandardised iterations = 1000 I, J, K, L = 622,138,5, 5 init_S = 'exponential' init_FG = 'kmeans' expo_prior = 1/10. # Load in data (_,X_min,M,_,_,_,_) = load_gdsc(standardised=standardised) # Run the algorithm nmtf = NMTF(X_min,M,K,L) nmtf.initialise(init_S,init_FG,expo_prior) nmtf.run(iterations) # Print the performances across iterations (MSE) print "all_performances = %s" % nmtf.all_performances['MSE'] # Plot the performances (MSE) plt.plot(nmtf.all_performances['MSE'])
standardised = False
train_config = {
'iterations' : 1000,
'init_UV' : 'exponential',
'expo_prior' : 0.1
}
K_range = range(2,10+1,2)
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 = MatrixCrossValidation(
method=NMF,
X=X_min,
M=M,
K=no_folds,
parameter_search=parameter_search,
train_config=train_config,
file_performance=output_file
)
nested_crossval.run()
standardised = False
train_config = {
'iterations': 1000,
'init_UV': 'exponential',
'expo_prior': 0.1
}
K_range = range(2, 10 + 1, 2)
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 = MatrixCrossValidation(method=NMF,
X=X_min,
M=M,
K=no_folds,
parameter_search=parameter_search,
train_config=train_config,
file_performance=output_file)
nested_crossval.run()
