def samplingRMSDmixing(RMSDfile, numSamples = 100):
import random
RMSDs = libRMSD.readRMSDfromCSV(RMSDfile, WithRemovedLimit=10)
if len(RMSDs.keys()) < numSamples:
return (RMSDs)
else:
samplesList = random.sample(RMSDs.keys(), numSamples)
# create the new samplesRMSD
samplesRMSD = {}
for key in samplesList:
samplesRMSD[key] = RMSDs[key]
return (samplesRMSD)
def samplingRMSDtoCluster(RMSDfile, numSamples = 100):
import random
RMSDs = libRMSD.readRMSDfromCSV(RMSDfile, WithRemovedLimit=10)
samplesRMSD = {}
totalSamplesPerCluster = int(numSamples / MAX_ANGSTROM)
for value in range(MAX_ANGSTROM):
filterRMSD = filterDict(RMSDs, minValue=value, maxValue=value+1)
if len(filterRMSD.keys()) > totalSamplesPerCluster:
samplesList = random.sample(filterRMSD.keys(), totalSamplesPerCluster)
# create the new samplesRMSD
randomRMSD = {}
for key in samplesList:
randomRMSD[key] = filterRMSD[key]
filterRMSD = randomRMSD
#print(filterRMSD)
samplesRMSD.update(filterRMSD)
return (samplesRMSD)