def GetOperatorStats(self, RunPath_):
''' Get operator statistics. TODO: Generalize to MD. '''
operator_statistics = []
if self.JobType == 'CL' and self.Program == 'polyFTS':
number_columns = self.Nspecies * 2 + 4
datafile = open(os.path.join(RunPath_, 'operators.dat'), 'r')
for c in range(number_columns
)[::2]: #Skip step column and imaginary columns
try:
warmup, Data, nwarmup = stats.autoWarmupMSER(
datafile, c + 1)
except:
break
(nsamples, (min, max), Val, Valerr, kappa, unbiasedvar,
autocor) = stats.doStats(warmup, Data, False)
operator_statistics.append([Val, Valerr, nsamples])
elif self.JobType == 'SCFT' and self.Program == 'polyFTS':
number_columns = self.Nspecies + 2
data = np.loadtxt(os.path.join(RunPath_, 'operators.dat'))[-1]
for c in range(number_columns):
operator_statistics.append([data[c + 1], 0., 1])
return operator_statistics
runfile.close()
#call(["PolyFTSGPU.x","run.in"])
call('{} run.in > run.out'.format(FTS), shell=True)
# Data analysis:
# Partition 1
#datafile = open('model1_operators.dat','r')
datafile = open('operators.dat','r')
# ReP1
try:
warmup, Data, nwarmup = stats.autoWarmupMSER(datafile,3)
except:
print("Failed on ReP1")
break
(nsamples,(min,max),P1,P1err,kappa,unbiasedvar,autocor)=stats.doStats(warmup,Data,False)
datafile.seek(0)
# ImP1
try:
warmup, Data, nwarmup = stats.autoWarmupMSER(datafile,4)
except:
print("Failed on ImP1")
break
(nsamples,(min,max),imP1,imP1err,kappa,unbiasedvar,autocor)=stats.doStats(warmup,Data,False)
datafile.seek(0)
# mu1
try:
warmup, Data, nwarmup = stats.autoWarmupMSER(datafile,5)
except:
print("Failed on Re mu1")
break
def GetRgRee(traj,
DOP,
NP,
NAtomsPerChain=None,
plotDir='RgRee_plots',
RgDatName='RgTimeSeries',
ReeDatName='ReeTimeSeries',
RgStatOutName='RgReeStats',
Ext='.dat',
res0Id=0,
autowarmup=True,
nwarmup=100,
plot=False):
"""NAtomsPerChain: used if running CG system, if provided will assume there is one residue per chain
multiply coordinates by 10 if input traj was generated by lammps and unit is nonDim"""
ElementDictionary = {
"carbon": 12.01,
"hydrogen": 1.008,
"oxygen": 16.00,
"nitrogen": 14.001,
"virtual site": 1.0,
"sodium": 23.0,
"chloride": 35.5
}
if plot:
try:
os.mkdir(plotDir)
except:
pass
print('...Rg and Ree plots will be saved in {}...\n'.format(plotDir))
RgTimeseries = [range(traj.n_frames)]
Rgheader = "Frame "
RgSqStats = []
RgSqTimeseries = [range(traj.n_frames)]
RgSqheader = "Frame "
RgSqList = []
txtRg = ""
ReeTimeseries = [range(traj.n_frames)]
Reeheader = "Frame "
ReeSqStats = []
ReeSqTimeseries = [range(traj.n_frames)]
ReeSqheader = "Frame "
ReeSqList = []
#get indices of residues in all chains
MoleculeResidueList = []
BlockResName = []
if not NAtomsPerChain:
#number residues per chain = DOP (for AA systems)
for j in range(NP):
resId = range(res0Id + j * DOP, res0Id + (j + 1) * DOP)
MoleculeResidueList.append(resId)
resname = []
for res in traj.topology.residues:
if res.index in resId:
resname.append(res.name)
#check if diblock
if j == 0:
resname1 = resname[0]
resname2 = resname[-1]
i1 = np.where(np.array(resname) == resname1)[0]
i2 = np.where(np.array(resname) == resname2)[0]
if np.min(i1) == np.min(resId) and int(
np.min(i2) -
np.max(i1)) == 1 and np.max(i2) == np.max(resId):
block = True
BlockResName = [resname1, resname2]
RgSqList_b = [[], []]
RgSqStats_b = [[], []]
print(
'Detect diblock:\n block 1: {} {}-mer, block 2: {} {}-mer'
.format(resname1, len(i1), resname2, len(i2)))
else:
block = False
else:
#1 residue per chain (for CG system)
a0Id = [atom.index for atom in traj.topology.residue(res0Id).atoms]
a0Id = np.min(a0Id)
MoleculeResidueList
for i in range(NP):
atomId_per_chain = range(
a0Id + i * NAtomsPerChain,
a0Id + i * NAtomsPerChain + NAtomsPerChain)
resId_tmp = [
traj.topology.atom(aId).residue.index
for aId in atomId_per_chain
]
MoleculeResidueList.append(np.unique(resId_tmp))
block = False
for j, resId in enumerate(MoleculeResidueList):
resIdLow = np.min(resId)
resIdUp = np.max(resId)
atom_indices = traj.topology.select('resid {} to {}'.format(
resIdLow, resIdUp))
if block:
atom_indices_b = []
mass_list_b = []
for resname in BlockResName:
ii = traj.topology.select(
"resid {} to {} and resname '{}'".format(
resIdLow, resIdUp, resname))
atom_indices_b.append(ii)
tmp = []
for index in ii:
element = str(traj.topology.atom(index).element)
try:
mass = ElementDictionary[element]
except:
mass = 1.
tmp.append(mass)
tmp = np.array(tmp)
mass_list_b.append(tmp)
mass_list = []
for index in atom_indices:
element = str(traj.topology.atom(index).element)
try:
mass = ElementDictionary[element]
except:
mass = 1.
mass_list.append(mass)
mass_list = np.array(mass_list)
if j == 0:
print('Indices of atoms in chain {} \n{}'.format(
j + 1, atom_indices))
print('Mass of atoms in a chain {}'.format(mass_list))
print('Evaluate Rg and Ree of chain {}/{}'.format(
j + 1, len(MoleculeResidueList)))
'''=== Compute Rg ==='''
Rg = md.compute_rg(traj.atom_slice(atom_indices), masses=mass_list)
RgTimeseries.append(Rg.tolist())
Rgheader += 'Rg{} '.format(j + 1)
np.savetxt(RgDatName + Ext,
np.transpose(RgTimeseries),
fmt='%5.5f',
header=Rgheader)
RgSq = Rg**2.
RgSqTimeseries.append(RgSq.tolist())
Rgheader += 'Rg{}^2 '.format(j + 1)
np.savetxt('RgSqTimeSeries' + Ext,
np.transpose(RgSqTimeseries),
fmt='%5.5f',
header=RgSqheader)
#do stats on Rg^2
file = open('RgSqTimeSeries' + Ext, 'r')
if autowarmup:
warmup, Data, nwarmup = stats.autoWarmupMSER(file, j + 1)
#print ("Auto warmup detection with MSER-5 => ",nwarmup)
else:
warmup, Data = stats.extractData(file, j + 1, nwarmup)
(nsamples, (min, max), mean, semcc, kappa, unbiasedvar,
autocor) = stats.doStats(warmup, Data, False, False,
'_{0}_mol{1}'.format(file.name, j + 1))
Data = Data[::int(np.max([1., kappa]))] # get decorrelated samples
RgSqList.extend(Data)
lines = ""
lines += '\n==== Rg^2 for molecule {} ===='.format(j + 1)
lines += "\n - Mean = {} +/- {}".format(
mean, semcc)
lines += "\n - Equilibrated samples = {}".format(nsamples)
lines += "\n - Correlation time = {}".format(kappa)
lines += "\n - Effective # samples = {}".format(nsamples / kappa)
lines += "\n - Reduced-bias variance = {}".format(unbiasedvar)
# note that there is no unbiased estimator for the population standard deviation. We can use sqrt(var) as a indicative estimator.
lines += "\n - S.D. (unbiased, biased) = {} {}".format(
np.sqrt(unbiasedvar), np.std(Data, ddof=0)
) # ddof is correction to 1/N...using ddof=1 returns regular reduced-bias estimator
lines += "\n - Min, Max = {} {}\n".format(min, max)
txtRg += lines
Avg = mean
Std = np.sqrt(unbiasedvar)
Err = semcc
CorrTime = kappa
NUncorrSamples = nsamples / kappa
RgSqStats.append([Avg, Std, CorrTime, Err, NUncorrSamples])
''' Plot Rg '''
if plot:
plt.axvspan(0, nwarmup, alpha=0.5, color='#6495ED')
plt.plot(Rg, "k-")
plt.xlim(0)
plt.xlabel('timestep')
plt.ylabel('Radius-of-gryation')
plt.savefig("{}/Rg{}.png".format(plotDir, j + 1),
bbox_inches='tight')
plt.close()
''' Rg of blocks '''
if block:
Rg_b = []
for i, ai in enumerate(atom_indices_b):
Rg_tmp = md.compute_rg(traj.atom_slice(ai),
masses=mass_list_b[i])
Rg_b.append(Rg_tmp)
Rg_b = np.array(Rg_b)
RgSq_b = Rg_b**2.
for i, RgSq in enumerate(RgSq_b):
data = [range(0, len(RgSq))]
data.append(RgSq.tolist())
np.savetxt('tmp.dat', np.transpose(data), fmt='%5.5f')
#do stats on Rg^2
file = open('tmp.dat', 'r')
if autowarmup:
warmup, Data, nwarmup = stats.autoWarmupMSER(file, 1)
else:
warmup, Data = stats.extractData(file, 1, nwarmup)
(nsamples, (min, max), mean, semcc, kappa, unbiasedvar,
autocor) = stats.doStats(warmup, Data, False, False,
'_{0}_mol{1}'.format(file.name, 1))
Data = Data[::int(np.max([1., kappa
]))] # get decorrelated samples
RgSqList_b[i].extend(Data)
Avg = mean
Std = np.sqrt(unbiasedvar)
Err = semcc
CorrTime = kappa
NUncorrSamples = nsamples / kappa
RgSqStats_b[i].append(
[Avg, Std, CorrTime, Err, NUncorrSamples])
os.remove("tmp.dat")
'''=== Compute Ree ==='''
atom_pairs = [np.min(atom_indices), np.max(atom_indices)]
Ree = md.compute_distances(traj,
atom_pairs=[atom_pairs],
periodic=False,
opt=True)
Ree = Ree.tolist()
Ree = [a[0] for a in Ree]
ReeTimeseries.append(Ree)
Reeheader += 'Ree{} '.format(j + 1)
np.savetxt(ReeDatName + Ext,
np.transpose(ReeTimeseries),
fmt='%5.5f',
header=Reeheader)
ReeSq = np.array(Ree)**2.
ReeSqTimeseries.append(ReeSq.tolist())
Reeheader += 'Ree{}^2 '.format(j + 1)
np.savetxt('ReeSqTimeSeries' + Ext,
np.transpose(ReeSqTimeseries),
fmt='%5.5f',
header=ReeSqheader)
#do stats on Ree^2
file = open('ReeSqTimeSeries' + Ext, 'r')
if autowarmup:
warmup, Data, nwarmup = stats.autoWarmupMSER(file, j + 1)
#print ("Auto warmup detection with MSER-5 => ",nwarmup)
else:
warmup, Data = stats.extractData(file, j + 1, nwarmup)
(nsamples, (min, max), mean, semcc, kappa, unbiasedvar,
autocor) = stats.doStats(warmup, Data, False, False,
'_{0}_mol{1}'.format(file.name, j + 1))
Data = Data[::int(np.max([1., kappa]))]
ReeSqList.extend(Data)
lines = ""
lines += '\n==== Ree^2 for molecule {} ===='.format(j + 1)
lines += "\n - Mean = {} +/- {}".format(
mean, semcc)
lines += "\n - Equilibrated samples = {}".format(nsamples)
lines += "\n - Correlation time = {}".format(kappa)
lines += "\n - Effective # samples = {}".format(nsamples / kappa)
lines += "\n - Reduced-bias variance = {}".format(unbiasedvar)
# note that there is no unbiased estimator for the population standard deviation. We can use sqrt(var) as a indicative estimator.
lines += "\n - S.D. (unbiased, biased) = {} {}".format(
np.sqrt(unbiasedvar), np.std(Data, ddof=0)
) # ddof is correction to 1/N...using ddof=1 returns regular reduced-bias estimator
lines += "\n - Min, Max = {} {}\n".format(min, max)
txtRg += lines
Avg = mean
Std = np.sqrt(unbiasedvar)
Err = semcc
CorrTime = kappa
NUncorrSamples = nsamples / kappa
ReeSqStats.append([Avg, Std, CorrTime, Err, NUncorrSamples])
''' Plot Ree '''
if plot:
plt.axvspan(0, nwarmup, alpha=0.5, color='#6495ED')
plt.plot(Ree, "k-")
plt.xlim(0)
plt.xlabel('timestep')
plt.ylabel('End-to-end distance')
plt.savefig("{}/Ree{}.png".format(plotDir, j + 1),
bbox_inches='tight')
plt.close()
# get RMS Rg and Ree
RgSqList = np.array(RgSqList)
RgRMS = np.sqrt(np.mean(RgSqList))
RgSqErr = scipy.stats.sem(RgSqList)
RgRMSErr = 1. / 2. * RgSqErr / RgRMS # propagate SEM of Rg^2 to Rg
RgSqStd = np.std(RgSqList, ddof=1)
RgRMSStd = 1. / 2. * RgSqStd / RgRMS # propagate Std of Rg^2 to Rg
RgSqStats = np.array(RgSqStats)
RgRMSCorrTime = np.mean(RgSqStats[:, 2])
RgRMSCorrTimeErr = np.sqrt(np.var(RgSqStats[:, 2]) / len(RgSqStats[:, 2]))
RgRMSNUncorrSamples = np.mean(RgSqStats[:, 4])
#Rg of blocks
RgRMS_b = []
RgRMSErr_b = []
RgRMSStd_b = []
RgRMSCorrTime_b = []
RgRMSCorrTimeErr_b = []
RgRMSNUncorrSamples_b = []
if block:
for i, resname in enumerate(BlockResName):
RgSqList = np.array(RgSqList_b[i])
RgRMS_b.append(np.sqrt(np.mean(RgSqList)))
Err = scipy.stats.sem(RgSqList)
RgRMSErr_b.append(1. / 2. * Err / RgRMS_b[i])
Std = np.std(RgSqList, ddof=1)
RgRMSStd_b.append(1. / 2. * Std / RgRMS_b[i])
RgSqStats = np.array(RgSqStats_b[i])
RgRMSCorrTime_b.append(np.mean(RgSqStats[:, 2]))
RgRMSCorrTimeErr_b.append(
np.sqrt(np.var(RgSqStats[:, 2]) / len(RgSqStats[:, 2])))
RgRMSNUncorrSamples_b.append(np.mean(RgSqStats[:, 4]))
#Ree
ReeSqList = np.array(ReeSqList)
ReeRMS = np.sqrt(np.mean(ReeSqList))
ReeSqErr = scipy.stats.sem(ReeSqList)
ReeRMSErr = 1. / 2. * ReeSqErr / ReeRMS
ReeSqStd = np.std(ReeSqList, ddof=1)
ReeRMSStd = 1. / 2. * ReeSqStd / ReeRMS
ReeSqStats = np.array(ReeSqStats)
ReeRMSCorrTime = np.mean(ReeSqStats[:, 2])
ReeRMSCorrTimeErr = np.sqrt(
np.var(ReeSqStats[:, 2]) / len(ReeSqStats[:, 2]))
ReeRMSNUncorrSamples = np.mean(ReeSqStats[:, 4])
lines = ""
lines += '\n\n====================='
lines += '\n\nRMS of Rg is: {0:2.4f} +/- {1:2.5f}'.format(RgRMS, RgRMSErr)
lines += '\nRMS Rg correlation time: {0:5.4f} +/- {1:5.6f}'.format(
RgRMSCorrTime, RgRMSCorrTimeErr)
lines += '\n\nRMS of Ree is: {0:2.4f} +/- {1:2.5f}'.format(
ReeRMS, ReeRMSErr)
lines += '\nRMS Ree correlation time: {0:5.4f} +/- {1:5.6f}'.format(
ReeRMSCorrTime, ReeRMSCorrTimeErr)
if block:
for i, resname in enumerate(BlockResName):
lines += '\n\nRMS of Rg for block %i-%s is: %2.4f +/- %2.5f' % (
i + 1, resname, RgRMS_b[i], RgRMSErr_b[i])
lines += '\nRMS Rg correlation time: {0:5.4f} +/- {1:5.6f}'.format(
RgRMSCorrTime_b[i], RgRMSCorrTimeErr_b[i])
print(lines + '\n')
txtRg += lines
f = open(RgStatOutName + Ext, 'w')
f.write(txtRg)
return RgRMS, ReeRMS, RgRMSErr, ReeRMSErr, RgRMSCorrTime, RgRMSCorrTimeErr, RgRMSNUncorrSamples, ReeRMSCorrTime, ReeRMSCorrTimeErr, ReeRMSNUncorrSamples, RgRMSStd, ReeRMSStd, RgRMS_b, RgRMSErr_b, RgRMSStd_b, RgRMSCorrTime_b, RgRMSCorrTimeErr_b, RgRMSNUncorrSamples_b, BlockResName
def GetThermo(ThermoLog,
fi='lammps',
obs=None,
cols=None,
autowarmup=True,
nwarmup=100,
plot=False,
plotDir='Thermo_plots'):
""" fi: log file format, 'lammps' or 'openmm' """
if not obs == None and not cols == None:
Exception(
'Read data either by observable name or column index but not both!'
)
if plot:
try:
os.mkdir(plotDir)
except:
pass
print('...Thermo plots will be saved in {}...\n'.format(plotDir))
#conver log file:
if fi == 'openmm':
ThermoLog = log2txt.log2txt_openmm([ThermoLog])[0]
elif fi == 'lammps':
section = 'PRODUCTION RUNS'
ThermoLog = log2txt.log2txt_lammps([ThermoLog], section,
'production')[0]
print('new log file: {}'.format(ThermoLog))
txt = ""
obsID = []
Stats = []
#do stats
file = open(ThermoLog, 'r')
if not obs == None:
lines = file.readlines()
while not isinstance(cols, list):
for line in lines:
if line.startswith('#'):
obsNames = line.split()[1:]
print('obsNames {}'.format(obsNames))
cols = [
obsNames.index(val) for val in obsNames if val in obs
]
print('cols {}'.format(cols))
for i, col in enumerate(cols):
if autowarmup:
warmup, Data, nwarmup = stats.autoWarmupMSER(file, col)
print("Auto warmup detection with MSER-5 => ", nwarmup)
else:
warmup, Data = stats.extractData(file, col, nwarmup)
(nsamples, (min, max), mean, semcc, kappa, unbiasedvar,
autocor) = stats.doStats(warmup, Data, False, False,
'_{0}_mol{1}'.format(file.name, col))
try:
obsName = obsNames[col]
except:
obsName = 'col{}'.format(col)
lines = ""
lines += '\n==== {} ===='.format(obsName)
lines += "\n - Mean = {} +/- {}".format(
mean, semcc)
lines += "\n - Equilibrated samples = {}".format(nsamples)
lines += "\n - Correlation time = {}".format(kappa)
lines += "\n - Effective # samples = {}".format(nsamples / kappa)
lines += "\n - Reduced-bias variance = {}".format(unbiasedvar)
# note that there is no unbiased estimator for the population standard deviation. We can use sqrt(var) as a indicative estimator.
lines += "\n - S.D. (unbiased, biased) = {} {}".format(
np.sqrt(unbiasedvar), np.std(Data, ddof=0)
) # ddof is correction to 1/N...using ddof=1 returns regular reduced-bias estimator
lines += "\n - Min, Max = {} {}\n".format(min, max)
''' Plot '''
if plot:
plt.axvspan(0, nwarmup, alpha=0.5, color='#6495ED')
plt.plot(np.hstack((warmup, Data)))
plt.xlim(0)
plt.xlabel('timestep')
plt.ylabel(obsName)
plt.savefig("{}/{}.png".format(plotDir, obsName),
bbox_inches='tight')
plt.close()
print(lines)
txt += lines
Avg = mean
Std = np.sqrt(unbiasedvar)
Err = semcc
CorrTime = kappa
NUncorrSamples = nsamples / kappa
Stats.append([Avg, Std, CorrTime, Err, NUncorrSamples])
obsID.append(obsName)
return obsID, Stats
runfile.close()
call('{} run.in > run.out'.format(fts), shell=True)
# Data analysis:
# Partition 1
#datafile = open('model1_operators.dat','r')
datafile = open('operators.dat', 'r')
# ReP1
try:
warmup, Data, nwarmup = stats.autoWarmupMSER(datafile, 3)
except:
print("Failed on ReP1")
break
(nsamples, (min, max), P1, P1err, kappa, unbiasedvar,
autocor) = stats.doStats(warmup, Data, False)
datafile.seek(0)
# ImP1
try:
warmup, Data, nwarmup = stats.autoWarmupMSER(datafile, 4)
except:
print("Failed on ImP1")
break
(nsamples, (min, max), imP1, imP1err, kappa, unbiasedvar,
autocor) = stats.doStats(warmup, Data, False)
datafile.seek(0)
#mu and immu
mus = np.zeros(len(xs))
muerrs = np.zeros(len(xs))
immus = np.zeros(len(xs))