def constructLikelihoodDiff(self, high_pickle_fn, low_pickle_fn):
"""
calculate difference of the conditional prob of whole data set given low and high class
"""
condi_dist_h = nb.loadCondiDistribution(high_pickle_fn)
condi_dist_l = nb.loadCondiDistribution(low_pickle_fn)
high_pdf = nb.buildPdf(condi_dist_h)
low_pdf = nb.buildPdf(condi_dist_l)
ener = self.all_set[:, 1:]
log_condi_predicted_high = nb.calculateConditionalProb(ener, high_pdf)
log_condi_predicted_low = nb.calculateConditionalProb(ener, low_pdf)
self.likelihood_diff = log_condi_predicted_low - log_condi_predicted_high
def calculateLikelihoodDiff():
h5_path = 'all_decoy.h5'
sub_path = 'noncentralized_path/low_decoy'
ener_matx = loadEnerMatx(h5_path, sub_path)
condi_dist_fn = 'low.dist'
low_pdf = nb.loadCondiDistribution(condi_dist_fn)
low_pdf = nb.buildPdf(low_pdf)
condi_dist_fn = 'high.dist'
high_pdf = nb.loadCondiDistribution(condi_dist_fn)
high_pdf = nb.buildPdf(high_pdf)
likelihood_low_diff = nb.getLikelihoodDiff(ener_matx, high_pdf, low_pdf)
sub_path = 'noncentralized_path/high_decoy'
ener_matx = loadEnerMatx(h5_path, sub_path)
likelihood_high_diff = nb.getLikelihoodDiff(ener_matx, high_pdf, low_pdf)
return likelihood_high_diff, likelihood_low_diff
return f[mcc_diff_path][()]
if __name__ == "__main__":
################################################################################
# print plain text file
# nb_ff = NB_ff('04ff_all_decoy.h5')
# nb_ff.printEner()
# nb_ff = NB_ff('08ff_all_decoy.h5')
# nb_ff.printEner()
# nb_ff = NB_ff('06ff_all_decoy.h5')
# nb_ff.printEner()
################################################################################
# build pdf
import sys
# matrix_fn = sys.argv[1]
matrix_fn = '08ff_high_decoy.mat'
# matrix_fn = '04ff_low_decoy.mat'
condi_dist_fn = matrix_fn.split('.')[0] + '.dist'
matrix = np.loadtxt(matrix_fn, delimiter=' ')
condi_dist = nb.getConditionalDist(matrix, dist_names)
nb.saveCondiDistribution(condi_dist, condi_dist_fn)
condi_dist = nb.loadCondiDistribution(condi_dist_fn)
print condi_dist
from lst_sub import getLst
import NB_classifier as nb
ener_rows_ifn = 'ener_row_name.txt'
ff = '08ff'
low_condi_dist_fn = ff + '_low_decoy.dist'
high_condi_dist_fn = ff + '_high_decoy.dist'
bayes_dist_ofn = ff + '_bayes.txt'
low_condi_dist = nb.loadCondiDistribution(low_condi_dist_fn)
high_condi_dist = nb.loadCondiDistribution(high_condi_dist_fn)
ener_rows = getLst(ener_rows_ifn)
def convertPdfName(dist_tuple):
"""conver the first letter of the distribution name to upper case
"""
name = dist_tuple[0]
name = name.upper()[0] + name[1:]
return (name, dist_tuple[1])
################################################################################
# converting
low_condi_dist = [convertPdfName(i) for i in low_condi_dist]
high_condi_dist = [convertPdfName(i) for i in high_condi_dist]
################################################################################
high_bayes_dists = [[ener_rows[i], high_condi_dist[i][0], high_condi_dist[i][1][0], high_condi_dist[i][1][1]]
for i in range(len(ener_rows))]
low_bayes_dists = [[ener_rows[i], low_condi_dist[i][0], low_condi_dist[i][1][0], low_condi_dist[i][1][1]]
for i in range(len(ener_rows))]