def buildPdf(condi_dist_fn, sub_path):
h5_path = 'all_decoy.h5'
ener_matx = loadEnerMatx(h5_path, sub_path)
condi_dist = nb.getConditionalDist(ener_matx, dist_names)
nb.saveCondiDistribution(condi_dist, condi_dist_fn)
print condi_dist
def calculateAuc():
high_mcc_diff = h5py.File('/ddnB/work/jaydy/dat/output/linr_out/08ff_all_decoy.h5')['/gaussian_nb/high/high_mcc_diff'][()]
low_mcc_diff = h5py.File('/ddnB/work/jaydy/dat/output/linr_out/08ff_all_decoy.h5')['/gaussian_nb/low/low_mcc_diff'][()]
import NB_classifier as nb
TPRs, FPRs = nb.constructRoc(low_mcc_diff[:, 1], high_mcc_diff[:, 1])
import numpy as np
auc = np.trapz(TPRs, x=FPRs)
print "AUC\t: ", auc
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))]
print(arr)
#do ml prediction here
decision = t.predict(arr, gnb_clf)
#print("MLsays:")
f = 1
ok = 0
if (f == 1):
print(decision)
cv2.imshow('res2', res2)
#return ok
cv2.waitKey(0)
#cv2.destroyAllWindows()
#train dataset
t = ml.Gaussian_Naive_Bayes()
X, Y = t.select_data("satellitePixel.csv")
X_train, X_test, y_train, y_test = t.split_data(X, Y)
gnb_clf = t.train_classifier(X_train, y_train)
t.get_accuracy_score(gnb_clf, X_test, y_test)
isok = 0
#take pics in loop
print(
"\nAquiring images and detecting pollution like from a real-time feed:\n")
for m in range(1, 37):
z = "E:/18.Win.Sem/Satellite/pic" + str(m) + ".jpg"
print("Image number - " + str(m))
#isok=isok+pollution(z)
pollution(z)
#print("Accuracy till now:")
#print(isok/m)
sr = Series
# condi_dist_h = nb.loadCondiDistribution('08ff_high_bk.dist')
# h = np.loadtxt('08ff_high_bk.mat', delimiter=' ')
# condi_dist_h = nb.loadCondiDistribution('06ff_high_decoy.dist')
# h = np.loadtxt('06ff_high_decoy.mat', delimiter=' ')
h5_path = 'all_decoy.h5'
sub_path = 'noncentralized_path/low_decoy'
condi_dist_fn = 'low.dist'
f = h5py.File(h5_path)
dset = f[sub_path][()]
ener_matx = dset[:, 1:]
condi_dist_h = nb.loadCondiDistribution(condi_dist_fn)
h = ener_matx
total_samples = 1000
high_pdf = nb.buildPdf(condi_dist_h)
for i in range(h.shape[1]):
high0_pdf, fitting_para = high_pdf[i]
print high0_pdf, fitting_para
h0 = h[:,i]
max_val = h0.max()
min_val = h0.min()
def weightDiff(likelihood_diff_high, likelihood_diff_low, weights):
likelihood_diff_low = np.dot(likelihood_diff_low, weights)
likelihood_diff_high = np.dot(likelihood_diff_high, weights)
return likelihood_diff_high, likelihood_diff_low
if __name__ == '__main__':
condi_dist_fn = 'low.dist'
sub_path = 'noncentralized_path/low_decoy'
buildPdf(condi_dist_fn, sub_path)
condi_dist_fn = 'high.dist'
sub_path = 'noncentralized_path/high_decoy'
buildPdf(condi_dist_fn, sub_path)
likelihood_diff_high, likelihood_diff_low = calculateLikelihoodDiff()
weights_fn = '/work/jaydy/working/nb_ff_running/even_weight.txt'
weights = np.loadtxt(weights_fn)
likelihood_diff_high, likelihood_diff_low = weightDiff(likelihood_diff_high, likelihood_diff_low, weights)
TPRs, FPRs = nb.constructRoc(likelihood_diff_high, likelihood_diff_low)
auc = np.trapz(TPRs, x=FPRs)
print "AUC\t: ", auc
