def compute(H, K):
Divergence.compute(H, K)
try:
if analytics.isValidPDF(H) and analytics.isValidPDF(K):
all_keys = dict(H.items() + K.items()).keys()
analytics.fill_gaps(H, all_keys)
analytics.fill_gaps(K, all_keys)
total = 0
for key in sorted(all_keys):
if H[key] != 0:
if K[key] == 0:
raise ValueError(
'KL Divergence is not defined for the input. Please see the definition of KL-Divergence'
)
else:
total += H[key] * math.log(H[key] / K[key], 2)
return total
else:
raise smp.InvalidProbabilityDensityException(
'Invalid probability density')
except ValueError:
logging.error(
'KL Divergence is not defined for the input. Please see the definition of KL-Divergence'
)
except smp.InvalidProbabilityDensityException:
logging.exception('Invalid probability density')
def compute(H, K, cdf=False):
H, K = Divergence.compute(H, K)
try:
if cdf:
if not (analytics.isValidCDF(H) and analytics.isValidCDF(K)):
raise smp.InvalidProbabilityDistributionException(
'Invalid cumulative distribution')
if not cdf:
if not (analytics.isValidPDF(H) and analytics.isValidPDF(K)):
raise smp.InvalidProbabilityDensityException(
'Invalid probability density')
#convert to cdf
H = analytics.pdfTocdf(H)
K = analytics.pdfTocdf(K)
all_keys = dict(H.items() + K.items()).keys()
analytics.fill_gaps(H, all_keys, cdf=True)
analytics.fill_gaps(K, all_keys, cdf=True)
max_diff = 0
#max_key=-1
for key in sorted(all_keys):
if math.fabs(H[key] - K[key]) > max_diff:
# max_key=key
max_diff = math.fabs(H[key] - K[key])
return max_diff #, max_key, H[max_key],K[max_key]
except smp.InvalidProbabilityDistributionException:
logging.exception('Invalid probability distribution')
except smp.InvalidProbabilityDensityException:
logging.exception('Invalid probability density')
def compute(H,K, cdf=False):
H,K=Divergence.compute(H, K)
try:
if cdf:
if not (analytics.isValidCDF(H) and analytics.isValidCDF(K)):
raise smp.InvalidProbabilityDistributionException('Invalid cumulative distribution')
if not cdf:
if not (analytics.isValidPDF(H) and analytics.isValidPDF(K)):
raise smp.InvalidProbabilityDensityException('Invalid probability density')
#convert to cdf
H=analytics.pdfTocdf(H)
K=analytics.pdfTocdf(K)
all_keys= dict(H.items()+K.items()).keys()
analytics.fill_gaps(H, all_keys,cdf=True)
analytics.fill_gaps(K, all_keys,cdf=True)
max_diff=0
#max_key=-1
for key in sorted(all_keys):
if math.fabs(H[key]-K[key])>max_diff:
# max_key=key
max_diff=math.fabs(H[key]-K[key])
return max_diff#, max_key, H[max_key],K[max_key]
except smp.InvalidProbabilityDistributionException:
logging.exception('Invalid probability distribution')
except smp.InvalidProbabilityDensityException:
logging.exception('Invalid probability density')
def distribution_save(H, K, file_name, cdf=False):
H,K=Divergence.compute(H, K)
try:
if cdf:
if not (analytics.isValidCDF(H) and analytics.isValidCDF(K)):
raise smp.InvalidProbabilityDistributionException('Invalid cumulative distribution')
if not cdf:
if not (analytics.isValidPDF(H) and analytics.isValidPDF(K)):
raise smp.InvalidProbabilityDensityException('Invalid probability density')
#convert to cdf
H=analytics.pdfTocdf(H)
K=analytics.pdfTocdf(K)
all_keys= dict(H.items()+K.items()).keys()
analytics.fill_gaps(H, all_keys, cdf=True)
analytics.fill_gaps(K, all_keys, cdf=True)
fileObject = open(file_name, 'w')
for key in sorted(all_keys):
fileObject.write(str(key)+' '+ str(K[key])+'\n')
# print("dict[%s] =" % key,K[key])
fileObject.close()
#==============================================================================
# plot_keys=[]
# plot_values=[]
# fileObject = open(file_name, 'w')
# for key in sorted(all_keys):
# plot_keys.append(key)
# plot_values.append(K[key])
#
# fileObject.write(str(key)+' '+ str(H[key])+'\n')
# print("dict[%s] =" % key,H[key])
# fileObject.close()
#
# plt.figure(1)
# plt.plot(plot_keys, plot_values, 'r-')
# plt.xscale('log')
# plt.yscale('log')
# plt.ylim([0,1])
# plt.ylabel('CDF')
# plt.xlabel('Degree')
# plt.savefig(file_name+ '_cdf.pdf')
# plt.clf()
#==============================================================================
except smp.InvalidProbabilityDistributionException:
logging.exception('Invalid probability distribution')
except smp.InvalidProbabilityDensityException:
logging.exception('Invalid probability density')
def compute(H, K):
Divergence.compute(H, K)
try:
if analytics.isValidPDF(H) and analytics.isValidPDF(K):
all_keys= dict(H.items()+K.items()).keys()
analytics.fill_gaps(H,all_keys)
analytics.fill_gaps(K,all_keys)
total=0
for key in sorted(all_keys):
if H[key] != 0:
if K[key] == 0:
raise ValueError('KL Divergence is not defined for the input. Please see the definition of KL-Divergence')
else:
total+=H[key]*math.log(H[key]/K[key],2)
return total
else:
raise smp.InvalidProbabilityDensityException('Invalid probability density')
except ValueError:
logging.error('KL Divergence is not defined for the input. Please see the definition of KL-Divergence')
except smp.InvalidProbabilityDensityException:
logging.exception('Invalid probability density')