def testAdmixInvalidProportion(self):
"""
Test requirement that admix prop is 0 <= p <= 1
"""
m = fp.MetaPopVec(64, [100, 100])
rng = fp.GSLrng(101)
with self.assertRaises(RuntimeError):
demog.admix_pops(rng, m, 0, 1, -0.1, 100)
#Population size
N=1000
#We'll evolve for 10N generations.
#nlist is a list of population sizes over time.
#len(nlist) is the length of the simulation
#We use numpy arrays for speed and optimised RAM
#use. Note the dtype=np.uint32, which means 32-bit
#unsigned integer. Failure to use this type will
#cause a run-time error.
nlist = np.array([N]*10*N,dtype=np.uint32)
# In[6]:
#Initalize a random number generator with seed value of 101
rng = fp.GSLrng(101)
# In[7]:
#Simulate 40 replicate populations. This uses C++11 threads behind the scenes:
pops = fp.evolve_regions(rng, #The random number generator
40, #The number of pops to simulate = number of threads to use.
N, #Initial population size for each of the 40 demes
nlist[0:], #List of population sizes over time.
0.005, #Neutral mutation rate (per gamete, per generation)
0.01, #Deleterious mutation rate (per gamete, per generation)
0.005, #Recombination rate (per diploid, per generation)
nregions, #Defined above
sregions, #Defined above
recregions)#Defined above
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], "m:e:H:S:O:N:t:s:r:F:n:")
except getopt.GetoptError as err:
# print help information and exit:
print(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
N = 1000 # pop size
e = 0.25 # s.d. of effect sizes
S = 1 # V(S)
H = None # desired b-sense H^2
mu_del_ttl = None # Mutation rate (per gamete, per generation) to alleles affecting trait value
r = 0.5 # rec. rate b/w loci (per diploid, per gen)
Opt = 0.0 # Value of optimum after 10N gens
ofile = None
seed = 0
t = None
nsam = 100
for o, a in opts:
if o == '-m':
mu_del_ttl = float(a)
elif o == '-e':
e = float(a)
elif o == '-H':
H = float(a)
elif o == '-S':
S = float(a)
elif o == '-O':
Opt = float(a)
elif o == '-N':
N = int(a)
elif o == '-s':
seed = int(a)
elif o == '-r':
r = float(a)
elif o == '-F':
ofile = a
elif o == '-t':
t = int(a)
elif o == '-n':
nsam = int(a)
if H is None:
usage()
sys.exit(2)
if mu_del_ttl is None:
usage()
sys.exit(2)
if ofile is None:
usage()
sys.exit(2)
if t is None:
t = 0.1 * float(N)
#Constants:
NLOCI = 10
NREPS = 64
##The next 2 are the 'sizes' of each locus in scaled params. Roughly 100kb in 'humans' in terms of pi.
theta = 100.0
rho = 100.0
#Can start working now:
REP = 0
out = pd.HDFStore(ofile, "w", complevel=6, complib='zlib')
little_r_per_locus = rho / (4.0 * float(N))
mu_n_region = theta / (4.0 * float(N))
rnge = fp.GSLrng(seed)
rngs = fp.GSLrng(seed)
nlist = np.array([N] * (10 * N), dtype=np.uint32)
fitness = qtm.MlocusAdditiveTrait()
sregions = [fp.GaussianS(0, 1, 1, e, 1.0)] * NLOCI
for BATCH in range(16): #16*64=1024
x = fp.MlocusPopVec(NREPS, N, NLOCI)
sampler = fp.PopSampler(len(x), nsam, rngs)
qtm.evolve_qtraits_mloc_sample_fitness(
rnge,
x,
sampler,
fitness,
nlist,
[mu_n_region] * NLOCI,
[mu_del_ttl / float(NLOCI)] * NLOCI,
sregions,
[little_r_per_locus] * NLOCI,
[0.5] * (NLOCI - 1), #loci unlinked
sample=t,
VS=S)
samples = sampler.get()
get_summstats_parallel(samples, REP, out)
sampler = fp.PopSampler(nsam, rngs)
qtm.evolve_qtraits_mloc_sample_fitnes(
rnge,
x,
sampler,
fitness,
nlist,
[mu_n_region] * NLOCI,
[mu_del_ttl / float(NLOCI)] * NLOCI,
sregions,
[little_r_per_locus] * NLOCI,
[0.5] * (NLOCI - 1), #loci unlinked
sample=t,
VS=S,
optimum=Opt)
samples = sampler.get()
get_summstats_parallel(samples, REP, out)
REP += NREPS
out.close()
nregions = []
rregions = [fp.Region(0, 1, 1)]
reference_mu = 1e-3
recrate = 0.5
N = 1000
simlen = 10 * N
Nlist = np.array([N] * (simlen), dtype=np.uint32)
#grid of VS values. 1 is our reference value
relative_mu = [0.25, 0.5, 1.0, 5.0, 10.0]
reference_sigma = math.sqrt(0.05)
reference_vm = 2.0 * reference_mu * (math.pow(reference_sigma, 2.0))
reference_vg = 4 * reference_mu * 1.0
rng = fp.GSLrng(1525152)
#plot VG, ebar, tbar,max_expl over time
fig = plt.figure(figsize=(10, 10))
tbar = plt.subplot2grid((3, 2), (1, 0), rowspan=1, colspan=2)
VG = plt.subplot2grid((3, 2), (0, 0), rowspan=1, colspan=2)
sfs = plt.subplot2grid((3, 2), (2, 0), rowspan=1, colspan=2)
#hdf5 files to save the output for further plotting...
popstats_output = pd.HDFStore('popstats_vary_mu_VMconstant.h5',
'w',
complevel=6,
complib='zlib')
sfs_output = pd.HDFStore('sfs_vary_mu_VMconstant.h5',
'w',
complevel=6,
#The next three lines process and compile our custom fitness module:
import pyximport
pyximport.install()
import test_fwdpy_extensions.test_custom_fitness as tfp
#import fwdpy and numpy as usual
import fwdpy as fp
import numpy as np
rng = fp.GSLrng(101)
rngs = fp.GSLrng(202)
p = fp.SpopVec(3, 1000)
s = fp.NothingSampler(len(p))
n = np.array([1000] * 1000, dtype=np.uint32)
nr = [fp.Region(0, 1, 1)]
sr = [fp.ExpS(0, 1, 1, 0.1)]
#Now, let's do some evolution with our 'custom' fitness functions:
fitness = tfp.AdditiveFitnessTesting()
fp.evolve_regions_sampler_fitness(rng, p, s, fitness, n, 0.001, 0.001, 0.001,
nr, sr, nr, 1)
fitness = tfp.AaOnlyTesting()
fp.evolve_regions_sampler_fitness(rng, p, s, fitness, n, 0.001, 0.001, 0.001,
nr, sr, nr, 1)
fitness = tfp.GBRFitness()
fp.evolve_regions_sampler_fitness(rng, p, s, fitness, n, 0.001, 0.001, 0.001,
nr, sr, nr, 1)
def main():
try:
opts, args = getopt.getopt(sys.argv[1:],"m:e:H:S:O:N:s:r:",["traj="])
except getopt.GetoptError as err:
# print help information and exit:
print(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
N=1000 # pop size
e = 0.25 # s.d. of effect sizes
S = 1 # V(S)
H = None # desired b-sense H^2
mu_del_ttl = None # Mutation rate (per gamete, per generation) to alleles affecting trait value
r = 0.5 # rec. rate b/w loci (per diploid, per gen)
Opt = 0.0 # Value of optimum after 10N gens
trajFile=None
seed = 0
for o,a in opts:
if o == '-m':
mu_del_ttl = float(a)
elif o == '-e':
e = float(a)
elif o == '-H':
H = float(a)
elif o == '-S':
S = float(a)
elif o == '-O':
Opt = float(a)
elif o == '-N':
N=int(a)
elif o == '-s':
seed = int(a)
elif o == '-r':
r = float(a)
elif o == '--traj':
trajFile=a
if H is None:
usage()
sys.exit(2)
if mu_del_ttl is None:
usage()
sys.exit(2)
if trajFile is None:
usage()
sys.exit(2)
#Constants:
NLOCI=10
NREPS=64
##The next 2 are the 'sizes' of each locus in scaled params. Roughly 100kb in 'humans' in terms of pi.
theta=100.0
rho=100.0
#Can start working now:
REP=0
out=pd.HDFStore(trajFile,"w",complevel=6,complib='zlib')
little_r_per_locus = rho/(4.0*float(N))
mu_n_region=theta/(4.0*float(N))
rnge=fp.GSLrng(seed)
nlist=np.array([N]*(10*N),dtype=np.uint32)
fitness = qtm.MlocusAdditiveTrait()
sregions=[fp.GaussianS(0,1,1,e,1.0)]*NLOCI
for BATCH in range(16): #16*64=1024
x = fp.MlocusPopVec(NREPS,N,NLOCI)
sampler=fp.FreqSampler(len(x))
qtm.evolve_qtraits_mloc_sample_fitness(rnge,x,sampler,fitness,nlist,
[mu_n_region]*NLOCI,
[mu_del_ttl/float(NLOCI)]*NLOCI,
sregions,
[little_r_per_locus]*NLOCI,
[0.5]*(NLOCI-1),#loci unlinked
sample=1,VS=S)
traj1=sampler.get()
sampler=fp.FreqSampler(len(x))
qtm.evolve_qtraits_mloc_sample_fitness(rnge,x,sampler,fitness,nlist,
[mu_n_region]*NLOCI,
[mu_del_ttl/float(NLOCI)]*NLOCI,
sregions,
[little_r_per_locus]*NLOCI,
[0.5]*(NLOCI-1),#loci unlinked
sample=1,VS=S,optimum=Opt)
traj2=sampler.get()
m=fp.tidy_trajectories(fp.merge_trajectories(traj1,traj2))
for i in m:
temp=pd.DataFrame(i)
temp['rep']=[REP]*len(temp.index)
out.append('traj',temp)
REP+=1
out.close()
def main():
try:
opts, args = getopt.getopt(sys.argv[1:],"m:e:H:S:O:N:s:r:",["fixed=","ages=","traj="])
except getopt.GetoptError as err:
# print help information and exit:
print(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
#set up default params
N=1000 # pop size
e = 0.25 # s.d. of effect sizes
S = 1 # V(S)
H = None # desired b-sense H^2
m = None # Mutation rate (per gamete, per generation) to alleles affecting trait value
r = 0.5 # rec. rate (per diploid, per gen)
Opt = 0.0 # Value of optimum after 10N gens
fixationsFile=None
lostFile=None
trajFile=None
seed = 0
for o,a in opts:
if o == '-m':
m = float(a)
elif o == '-e':
e = float(a)
elif o == '-H':
H = float(a)
elif o == '-S':
S = float(a)
elif o == '-O':
Opt = float(a)
elif o == '-N':
N=int(a)
elif o == '-s':
seed = int(a)
elif o == '-r':
r = float(a)
elif o == '--fixed':
fixationsFile=a
elif o == '--ages':
lostFile=a
elif o == '--traj':
trajFile=a
if H is None:
usage()
sys.exit(2)
if m is None:
usage()
sys.exit(2)
if fixationsFile is None or lostFile is None or trajFile is None:
usage()
sys.exit(2)
rng = fp.GSLrng(seed)
hdf_fixed = pd.HDFStore(fixationsFile,'w',complevel=6,complib='zlib')
hdf_fixed.open()
hdf_lost = pd.HDFStore(lostFile,'w',complevel=6,complib='zlib')
hdf_lost.open()
hdf_traj = pd.HDFStore(trajFile,'w',complevel=6,complib='zlib')
hdf_traj.open()
sigE = get_sigE_additive(m,S,H)
nregions = []
recregions = [fp.Region(0,1,1)]
sregions = [fp.GaussianS(0,1,1,e)]
#population size over time -- constant & we re-use this over and over
nlist = np.array([N]*(10*N),dtype=np.uint32)
REPLICATE=0
#16 batches of 64 runs = 1024 replicates
for i in range(16):
#set up populations
pops=fp.SpopVec(64,N)
#Evolve to equilibrium
sampler = fp.FreqSampler(len(pops))
qt.evolve_regions_qtrait_sampler(rng,
pops,
sampler,
nlist[0:],
0,
m,
r,
nregions,sregions,recregions,
sigmaE=sigE,
sample=1,
VS=S) ##Do not track popstats during "burn-in"
traj1=sampler.get()
sampler = fp.FreqSampler(len(pops))
#evolve for another 10N generations at new optimum
qt.evolve_regions_qtrait_sampler(rng,pops,sampler,
nlist[0:],
0,
m,
r,
nregions,sregions,recregions,
sigmaE=sigE,
VS=S,optimum=Opt,sample=1)
traj2=sampler.get()
AGES=[]
FIXATIONS=[]
#merge trajectories and get allele ages (parallelized via open MP)
traj1=fp.merge_trajectories(traj1,traj2)
ages = fp.allele_ages(traj1)
REPTEMP=REPLICATE
for ai in range(len(ages)):
dfi=pd.DataFrame(ages[ai])
dfi['rep']=[REPTEMP]*len(dfi.index)
FIXATIONS.append(dfi[dfi['max_freq']==1.0])
AGES.append(dfi[dfi['max_freq']<1.0])
REPTEMP+=1
# for j in range(len(pops)):
# #Merge all trajectories for this replicate
# df = pd.concat([pd.DataFrame(traj1[j]),
# pd.DataFrame(traj2[j])])
# for name,group in df.groupby(['pos','esize']):
# if group.freq.max() < 1: #mutation did not reach fixation...
# if group.generation.max()-group.generation.min()>1: #... and it lived > 1 generation ...
# AGES.append({'rep':REPLICATE,
# 'esize':name[1],
# 'origin':group.generation.min(),
# 'final_g':group.generation.max(),
# 'max_q':group.freq.max(),
# 'last_q':group.freq.iloc[-1]})
# else: #mutation did reach fixation!
# FIXATIONS.append({'rep':REPLICATE,
# 'esize':name[1],
# 'origin':group.generation.min(),
# 'final_g':group.generation.max()})
# REPLICATE+=1
##Add more info into the trajectories
for t in traj1:
LD=[]
for i in t:
I=int(0)
for j in i[1]:
x=copy.deepcopy(i[0])
x['freq']=j
x['generation']=i[0]['origin']+I
I+=1
LD.append(x)
d=pd.DataFrame(LD)
d['rep']=[REPLICATE]*len(d.index)
REPLICATE+=1
hdf_traj.append('trajectories',d)
hdf_fixed.append('fixations',pd.concat(FIXATIONS))
hdf_lost.append('allele_ages',pd.concat(AGES))
hdf_fixed.close()
hdf_lost.close()
hdf_traj.close()
def testSplitOutOfRange(self):
m = fp.MetaPopVec(64, [100])
rng = fp.GSLrng(101)
with self.assertRaises(IndexError):
demog.split_pops(rng, m, 2, 50)
def testAdmixOutOfRange(self):
m = fp.MetaPopVec(64, [100, 100])
rng = fp.GSLrng(101)
with self.assertRaises(IndexError):
demog.admix_pops(rng, m, 0, 2, 0.1, 100)
import fwdpy as fp
import fwdpy.qtrait_mloc as qtm
import fwdpy.fitness as fpw
import numpy as np
import pandas as pd
#import matplotlib
#import matplotlib.pyplot as plt
import copy,sys
N=1000
NLOCI=10
NREPS=20
rnge=fp.GSLrng(100)
nlist=np.array([N]*(15*N),dtype=np.uint32)
theta_neutral_per_locus=0.0
rho_per_locus=100.0
little_r_per_locus=rho_per_locus/(4.0*float(N))
mu_n_region=theta_neutral_per_locus/(4.0*float(N))
mu_del_ttl=1e-3
#sigmas=[0.1]*NLOCI
hdf=pd.HDFStore("cumVA.h5",'w')
fmodel = fpw.MlocusAdditive()
sregions = []
for i in range(NLOCI):
sregions.append(fp.GaussianS(i,i+1,1,0.1))
REPLICATE=0
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], "m:e:H:S:O:N:t:s:F:r:n:d:", [
"theta=", "rho=", "trait=", "sampler=", "nsam=", "cores=",
"batches=", "nstub=", "sstub=", "nloci=", "fixations=", "t2=",
"g2="
]) #,"neutral="])
except getopt.GetoptError as err:
# print help information and exit:
print(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
#set up default params
N = 1000 # pop size
t = None # 0.1N
t2 = None
e = 0.25 # s.d. of effect sizes
S = 1 # V(S)
H = 1.0 # desired b-sense H^2
m = None # Mutation rate (per gamete, per generation) to alleles affecting trait value
r = 0.5 #Recombination rate between locis
Opt = 0.0 # Value of optimum after 10N gens
ofile = None
seed = 0
NLOCI = 10 #The total number of loci to simulate
#NeutralLocus = 5 #The index of the locus where no causal mutations will occur
theta = 100 # mutational size of region where neutral mutations occur
rho = 100 # recombination size of region where neutral mutations occur
traitString = "additive"
samplerString = None
ncores = 64
nbatches = 16
dominance = 1.0
ssize = None
fixationsFileName = None
G2 = None
nstub = None
sstub = None
for o, a in opts:
if o == '-m':
m = float(a)
elif o == '-e':
e = float(a)
elif o == '-H':
H = float(a)
elif o == '-S':
S = float(a)
elif o == '-O':
Opt = float(a)
elif o == '-N':
N = int(a)
elif o == '-t':
t = int(a)
t2 = t
elif o == '-s':
seed = int(a)
elif o == '-F':
ofile = a
elif o == '-r':
r = float(a)
elif o == '--nsam':
ssize = int(a)
elif o == '--theta':
theta = float(a)
elif o == '--rho':
rho = float(a)
elif o == '--trait':
traitString = a
if a not in valid_trait_models:
print("Error: invalid trait model")
usage()
sys.exit(0)
elif o == '--sampler':
samplerString = a
if a not in valid_sampler_names:
print("Error: invalid sampler name")
usage()
sys.exit(0)
elif o == '--cores':
ncores = int(a)
if ncores < 1:
print("--ncores must be > 0")
usage()
sys.exit(0)
elif o == '--batches':
nbatches = int(a)
if nbatches < 1:
print("--nbatches myst be > 0")
usage()
sys.exit(0)
elif o == '--nloci':
NLOCI = int(a)
if NLOCI < 2:
rpint("--nloci must be > 1")
usage()
sys.exit(0)
elif o == "--fixations":
fixationsFileName = a
elif o == "--t2":
t2 = int(a)
elif o == "--g2":
G2 = int(a)
elif o == "--nstub":
nstub = a
elif o == '--sstub':
sstub = a
#elif o == "--neutral":
# if a != "None":
# NeutralLocus=int(a)
# else:
# NeutralLocus=a
if samplerString is None:
print("Error: sampler must be defined")
usage()
sys.exit(0)
if t is None:
print("Error: sampling interval must be defined")
usage()
sys.exit(0)
if t2 is None:
t2 = t
if m is None:
usage()
sys.exit(2)
if ofile is None:
usage()
sys.exit(2)
if G2 is None:
G2 = 10 * N
#Can start working now:
REP = 0
out = pd.HDFStore(ofile, "w", complevel=6, complib='zlib')
if fixationsFileName is not None:
if os.path.exists(fixationsFileName):
os.remove(fixationsFileName)
little_r_per_locus = rho / (4.0 * float(N))
mu_n_region = theta / (4.0 * float(N))
rnge = fp.GSLrng(seed)
rngs = fp.GSLrng(seed)
nlist = np.array([N] * (10 * N), dtype=np.uint32)
fitness = get_trait_model(traitString)
sregions = [fp.GaussianS(0, 1, 1, e, dominance)] * NLOCI
neutral_mut_rates = [mu_n_region] * NLOCI
causal_mut_rates = [m / float(NLOCI)] * NLOCI
#if NeutralLocus is not None:
# causal_mut_rates[NeutralLocus]=0.0
for BATCH in range(nbatches):
x = fp.MlocusPopVec(ncores, N, NLOCI)
nstub_t = None
sstub_t = None
if nstub is not None:
nstub_t = nstub + b'.pre_shift.batch' + str(BATCH)
if sstub is not None:
sstub_t = sstub + b'.pre_shift.batch' + str(BATCH)
sampler = get_sampler(samplerString, len(x), Opt, ssize, rngs, nstub_t,
sstub_t)
qtm.evolve_qtraits_mloc_sample_fitness(
rnge,
x,
sampler,
fitness,
nlist,
neutral_mut_rates,
causal_mut_rates,
sregions,
[little_r_per_locus] * NLOCI,
[r] * (NLOCI - 1), #loci unlinked
sample=t,
VS=S)
write_output(sampler, out, NLOCI, REP)
if nstub is not None:
nstub_t = nstub + b'.post_shift.batch' + str(BATCH)
if sstub is not None:
sstub_t = sstub + b'.post_shift.batch' + str(BATCH)
sampler = get_sampler(samplerString, len(x), Opt, ssize, rngs, nstub_t,
sstub_t)
qtm.evolve_qtraits_mloc_sample_fitness(
rnge,
x,
sampler,
fitness,
nlist[:G2],
neutral_mut_rates,
causal_mut_rates,
sregions,
[little_r_per_locus] * NLOCI,
[r] * (NLOCI - 1), #loci unlinked
sample=t2,
VS=S,
optimum=Opt)
write_output(sampler, out, NLOCI, REP)
if fixationsFileName is not None:
write_fixations(x, fixationsFileName, REP)
REP += len(x)
if fixationsFileName is not None:
con = sqlite3.connect(fixationsFileName)
con.execute("create index gen on fixations (generation)")
con.execute("create index gen_rep on fixations (generation,rep)")
con.close()
out.close()
import unittest
import fwdpy
import numpy as np
nregions = [fwdpy.Region(0, 1, 1), fwdpy.Region(2, 3, 1)]
sregions = [fwdpy.ExpS(1, 2, 1, -0.1), fwdpy.ExpS(1, 2, 0.01, 0.001)]
rregions = [fwdpy.Region(0, 3, 1)]
rng = fwdpy.GSLrng(100)
N = 1000
NGENS = 100
popsizes = np.array([N], dtype=np.uint32)
popsizes = np.tile(popsizes, NGENS)
pops = fwdpy.evolve_regions(rng, 1, N, popsizes[0:], 0.001, 0.0001, 0.001,
nregions, sregions, rregions)
#The sum of the gamete counts must be 2*(deme size):
#mpops = fwdpy.evolve_regions_split(rng,pops,popsizes[0:],popsizes[0:],0.001,0.0001,0.001,nregions,sregions,rregions,[0]*2)
class test_singlepop_views(unittest.TestCase):
def testNumGametes(self):
gams = fwdpy.view_gametes(pops[0])
nsingle = 0
for i in gams:
nsingle += i['n']
self.assertEqual(nsingle, 2000)
def testDipsize(self):
dips_single = fwdpy.view_diploids(pops[0], [0, 1, 2])
self.assertEqual(len(dips_single), 3)
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], "m:e:H:S:O:N:t:s:F:r:",
["cores=", "batches="])
except getopt.GetoptError as err:
# print help information and exit:
print(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
#set up default params
N = 1000 # pop size
t = None # 0.1N
e = 0.25 # s.d. of effect sizes
S = 1 # V(S)
H = None # desired b-sense H^2
m = None # Mutation rate (per gamete, per generation) to alleles affecting trait value
r = 0.5 # rec. rate (per diploid, per gen)
Opt = 0.0 # Value of optimum after 10N gens
ofile = None
seed = 0
ncores = 64
nbatches = 16
for o, a in opts:
if o == '-m':
m = float(a)
elif o == '-e':
e = float(a)
elif o == '-H':
H = float(a)
elif o == '-S':
S = float(a)
elif o == '-O':
Opt = float(a)
elif o == '-N':
N = int(a)
elif o == '-t':
t = int(a)
elif o == '-s':
seed = int(a)
elif o == '-F':
ofile = a
elif o == '-r':
r = float(a)
elif o == '--cores':
ncores = int(a)
elif o == '--batches':
nbatches = int(a)
if t is None:
t = int(0.1 * float(N))
if H is None:
usage()
sys.exit(2)
if m is None:
usage()
sys.exit(2)
if ofile is None:
usage()
sys.exit(2)
rng = fp.GSLrng(seed)
hdf = pd.HDFStore(ofile, 'w', complevel=6, complib='zlib')
hdf.open()
sigE = get_sigE_additive(m, S, H)
nregions = []
recregions = [fp.Region(0, 1, 1)]
sregions = [fp.GaussianS(0, 1, 1, e)]
#population size over time -- constant & we re-use this over and over
nlist = np.array([N] * (10 * N), dtype=np.uint32)
#16 batches of 64 runs = 1024 replicates
fitness = qt.SpopAdditiveTrait()
REPLICATE = 0
for i in range(nbatches):
pops = fp.SpopVec(ncores, N)
sampler = fp.QtraitStatsSampler(len(pops), 0.0)
#Evolve to equilibrium, tracking along the way
qt.evolve_regions_qtrait_sampler_fitness(rng,
pops,
sampler,
fitness,
nlist[0:],
0,
m,
r,
nregions,
sregions,
recregions,
sigmaE=sigE,
sample=t,
VS=S,
optimum=0)
stats = sampler.get()
RTEMP = REPLICATE
for si in stats:
ti = pd.DataFrame(si)
ti['rep'] = [RTEMP] * len(ti.index)
RTEMP += 1
hdf.append('popstats', ti)
#simulate another 10*N generations, sampling stats every 't' generations
sampler = fp.QtraitStatsSampler(len(pops), Opt)
qt.evolve_regions_qtrait_sampler_fitness(rng,
pops,
sampler,
fitness,
nlist[0:],
0,
m,
r,
nregions,
sregions,
recregions,
sigmaE=sigE,
sample=t,
VS=S,
optimum=Opt)
stats = sampler.get()
for si in stats:
ti = pd.DataFrame(si)
ti['rep'] = [REPLICATE] * len(ti.index)
hdf.append('popstats', ti)
REPLICATE += 1
hdf.close()
def main():
parser=make_parser()
args=parser.parse_args(sys.argv[1:])
if args.verbose:
print (args)
##Figure out sigma_E from params
sigE = get_sigE_additive(args.mutrate,args.VS,args.H2)
trait = get_trait_model(args.trait)
nlist = np.array([args.popsize]*(10*args.popsize),dtype=np.uint32)
rng=fp.GSLrng(args.seed)
mu_neutral = 0.0
nregions=[]
sregions=[fp.GaussianS(0,1,1,args.sigmu,args.dominance)]
recregions=[fp.Region(0,1,1)]
if args.sampler == 'stats':
output=pd.HDFStore(args.outfile,'w',complevel=6,complib='zlib')
output.close()
REPID=0
for BATCH in range(args.nbatches):
pops=fp.SpopVec(args.ncores,args.popsize)
sampler=get_sampler_type(args.sampler,args.trait,len(pops),0.0)
qt.evolve_regions_qtrait_sampler_fitness(rng,pops,sampler,trait,
nlist,
0.0,
args.mutrate,
args.recrate,
nregions,
sregions,
recregions,
args.tsample,
sigE,
optimum=0.0,
VS=args.VS)
if args.sampler != 'freq':
if args.sampler == 'freq':
dummy=write_output(sampler,args,REPID,BATCH,'w')
elif args.sampler == 'stats':
dummy=write_output(sampler,args,REPID,BATCH,'a')
else:
dummy=write_output(sampler,args,REPID,BATCH,'a')
sampler=get_sampler_type(args.sampler,args.trait,len(pops),args.optimum)
qt.evolve_regions_qtrait_sampler_fitness(rng,pops,sampler,trait,
nlist,
0.0,
args.mutrate,
args.recrate,
nregions,
sregions,
recregions,
args.tsample,
sigE,
optimum=args.optimum,
VS=args.VS)
if args.sampler == 'freq':
#Append this time!
REPID=write_output(sampler,args,REPID,BATCH,'w')
elif args.sampler == 'stats':
REPID=write_output(sampler,args,REPID,BATCH,'a')
else:
REPID=write_output(sampler,args,REPID,BATCH,'a')
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], "m:e:H:S:O:N:t:s:F:r:n:",
["theta=", "rho="])
except getopt.GetoptError as err:
# print help information and exit:
print(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
#set up default params
N = 1000 # pop size
t = None # 0.1N
e = 0.25 # s.d. of effect sizes
S = 1 # V(S)
H = None # desired b-sense H^2
m = None # Mutation rate (per gamete, per generation) to alleles affecting trait value
r = 0.5 # rec. rate (per diploid, per gen)
Opt = 0.0 # Value of optimum after 10N gens
ofile = None
seed = 0
ssize = 50 #sample size
theta = 100 # mutational size of region where neutral mutations occur
rho = 100 # recombination size of region where neutral mutations occur
for o, a in opts:
if o == '-m':
m = float(a)
elif o == '-e':
e = float(a)
elif o == '-H':
H = float(a)
elif o == '-S':
S = float(a)
elif o == '-O':
Opt = float(a)
elif o == '-N':
N = int(a)
elif o == '-t':
t = int(a)
elif o == '-s':
seed = int(a)
elif o == '-F':
ofile = a
elif o == '-r':
r = float(a)
elif o == '-n':
ssize = int(a)
elif o == '--theta':
theta = float(a)
elif o == '--rho':
rho = float(a)
if t is None:
t = 0
if H is None:
usage()
sys.exit(2)
if m is None:
usage()
sys.exit(2)
if ofile is None:
usage()
sys.exit(2)
##Figure out sigma_E from params
sigE = get_sigE_additive(m, S, H)
rng = fp.GSLrng(seed)
rng2 = fp.GSLrng(seed * 100)
PIK = gzip.open(ofile, "wb")
#16 batches of 64 runs = 1024 replicates
mun = theta / float(4 * N)
littler = rho / float(4 * N)
nreg = make_neutral_region()
recstuff = make_buried_rec_region(littler)
sreg = make_Gaussian_sregion(recstuff['beg'], recstuff['end'], sigma=e)
rrg = recstuff['region']
nlist = np.array([N] * (10 * N), dtype=np.uint32)
for i in range(16):
#Evolve to equilibrium
pops = qt.evolve_regions_qtrait(
rng,
64,
N,
nlist[0:],
mun,
m,
r,
nreg,
sreg,
rrg,
sigmaE=sigE,
f=0.,
VS=S,
optimum=0) ##Do not track popstats during "burn-in"
#simulate another 2*N generations, sampling stats every 't' generations
sampler = fp.PopSampler(len(pops), ssize, rng2)
qt.evolve_regions_qtrait_sampler(rng,
pops,
sampler,
nlist[0:],
mun,
m,
r,
nreg,
sreg,
rrg,
sigmaE=sigE,
sample=t,
VS=S,
optimum=Opt)
samples = sampler.get()
print samples
for j in samples:
pickle.dump(j, PIK)
PIK.close()
def run_batch(argtuple):
args, repid, batch = argtuple
print("seed for batch = ", args.seed)
nstub = "neutral.mu" + str(args.mu) + ".opt" + str(args.opt)
sstub = "selected.mu" + str(args.mu) + ".opt" + str(args.opt)
rnge = fp.GSLrng(args.seed)
NANC = 7310
locus_boundaries = [(float(i + i * 11), float(i + i * 11 + 11))
for i in range(args.nloci)]
nregions = [
fp.Region(j[0], j[1], args.theta / (4. * float(NANC)), coupled=True)
for i, j in zip(range(args.nloci), locus_boundaries)
]
recregions = [
fp.Region(j[0], j[1], args.rho / (4. * float(NANC)), coupled=True)
for i, j in zip(range(args.nloci), locus_boundaries)
]
sregions = [
fp.GaussianS(j[0] + 5., j[0] + 6., args.mu, args.sigmu, coupled=False)
for i, j in zip(range(args.nloci), locus_boundaries)
]
f = qtm.MlocusAdditiveTrait()
nlist = np.array(get_nlist1(), dtype=np.uint32)
pops = fp.MlocusPopVec(args.ncores, nlist[0], args.nloci)
sampler = fp.NothingSampler(len(pops))
d = datetime.datetime.now()
print("starting batch, ", batch, "at ", d.now())
qtm.evolve_qtraits_mloc_regions_sample_fitness(rnge, pops, sampler, f,
nlist[0:], nregions,
sregions, recregions,
[0.5] * (args.nloci - 1), 0,
0, 0.)
d = datetime.datetime.now()
print(d.now())
nlist = np.array(get_nlist2(), dtype=np.uint32)
qtm.evolve_qtraits_mloc_regions_sample_fitness(rnge, pops, sampler, f,
nlist[0:], nregions,
sregions, recregions,
[0.5] * (args.nloci - 1), 0,
args.opt)
d = datetime.datetime.now()
print(d.now())
if args.statfile is not None:
sched = lsp.scheduler_init(args.TBB)
for pi in pops:
#Apply the sampler 1 population at a time.
#This saves a fair bit of RAM.
neutralFile = nstub + '.rep' + str(repid) + '.gz'
selectedFile = sstub + '.rep' + str(repid) + '.gz'
BIGsampler = fp.PopSampler(1,
6000,
rnge,
False,
neutralFile,
selectedFile,
recordSamples=True,
boundaries=locus_boundaries)
fp.apply_sampler_single(pi, BIGsampler)
if args.statfile is not None:
for di in BIGsampler:
process_samples((di, args.statfile, locus_boundaries, repid))
repid += 1
pops.clear()
pops = None
