init_UV = 'random'
ARD = False
lambdaU, lambdaV = 0.1, 0.1
alphatau, betatau = 1., 1.
alpha0, beta0 = 1., 1.
hyperparams = {
'alphatau': alphatau,
'betatau': betatau,
'alpha0': alpha0,
'beta0': beta0,
'lambdaU': lambdaU,
'lambdaV': lambdaV
}
''' Load in data. '''
R, M = load_gdsc_ic50()
I, J = M.shape
''' Generate matrices M - one list of M's for each value of K. '''
M_attempts = 1000
all_Ms_training_and_test = [
compute_folds_attempts(I=I,
J=J,
no_folds=no_folds,
attempts=M_attempts,
M=M) for K in values_K
]
''' We now run the Gibbs sampler on each of the M's for each fraction. '''
all_performances = {metric: [] for metric in metrics}
average_performances = {metric: []
for metric in metrics} # averaged over repeats
for K, (Ms_train, Ms_test) in zip(values_K, all_Ms_training_and_test):
Methods for plotting the distribution of the drug sensitivity datasets.
'''
project_location = "/home/tab43/Documents/Projects/libraries/" # "/Users/thomasbrouwer/Documents/Projects/libraries/"
import sys
sys.path.append(project_location)
from BNMTF_ARD.data.drug_sensitivity.load_data import load_gdsc_ic50
from BNMTF_ARD.data.drug_sensitivity.load_data import load_ctrp_ec50
from BNMTF_ARD.data.drug_sensitivity.load_data import load_ccle_ic50
from BNMTF_ARD.data.drug_sensitivity.load_data import load_ccle_ec50
import itertools
import matplotlib.pyplot as plt
''' Load in the data. '''
R_gdsc, M_gdsc = load_gdsc_ic50()
R_ctrp, M_ctrp = load_ctrp_ec50()
R_ccle_ic, M_ccle_ic = load_ccle_ic50()
R_ccle_ec, M_ccle_ec = load_ccle_ec50()
def extract_values(R, M):
I, J = R.shape
return [
R[i, j] for i, j in itertools.product(range(I), range(J)) if M[i, j]
]
values_plotnames_bins = [
(extract_values(R_gdsc, M_gdsc), 'distribution_gdsc_ic50.pdf',
[v - 0.5 for v in range(0, 100 + 10, 5)]),
