def getErr(i=96, s=0.01):
sim = Simulation.Simulation.load(
s=s,
nu0=0.005,
experimentID=i,
ModelName="TimeSeries",
numReplicates=10,
step=10,
startGeneration=0,
maxGeneration=50,
)
bot = pd.read_pickle(home + "out/BottleneckedNeutrals.NotNormalized.df")[i].loc[[0, 10, 20, 30, 40, 50]]
td = Estimate.Estimate.getEstimate(sim.X, n=200, method="tajimaD", removeFixedSites=True, normalizeTajimaD=False)
td.index = sim.getTrueGenerationTimes()
ctd = td.apply(lambda x: ((x - bot).diff().iloc[1:]))
ctd[leaveOneOut(ctd)] = None
ctd = ctd.apply(regularize)
t = sim.getTrueGenerationTimes()
nu = sig(s * t / 2 + logit(0.1))
a = Estimate.Estimate.getEstimate(sim.X0, n=200, method="pi")
b = -Estimate.Estimate.getEstimate(sim.X0, n=200, method="watterson") / (1.0 / np.arange(1, 201)).sum()
f = pd.Series(b * np.log(1 - nu) - a * nu ** 2, index=t).diff().iloc[1:]
# ctd.mean(1).plot(color='b',legend=False);f.plot(linewidth=3,color='k');
# ctds.mean(1).plot(ax=plt.gca(),color='r',legend=False);
return ((ctd.mean(1).sum() - f.mean())) / neurtrality(i, s)
def fit(self,y=None,pos=1,verbose=0):
timesIDX=y.abs().sum(1)!=0
self.y= y[timesIDX]
self.times= self.Times[np.where(timesIDX.values)[0]]
obj0=self.getZeroObj()
if self.initSviaLineSearch:
self.setInitYslackViaLineSearch()
self.setInitSviaLineSearch()
self.reset()
start_time=time.time()
for i in range(self.maxIter):
obj=self.Objective_(self.y,self.lr_s, self.lr_nu, self.lr_theta, self.times, (self.final_momentum , self.initial_momentum)[i<5],self.n, self.theta)
if verbose>1:
print obj ,self.S__.get_value(), self.Yslack__.get_value(),sig(self.c__.get_value())
if verbose:
print obj ,self.S__.get_value(), self.Yslack__.get_value(),sig(self.c__.get_value())
negLogLikelihoodRatio=np.log(obj0)-np.log(self.Loss_(self.y,self.Feedforward_(self.times,self.n,self.theta)))
s=np.asscalar(self.S__.get_value())
if s<1e-6:
negLogLikelihoodRatio=0
s=0
self.sol=pd.Series({'s':s,'LR':negLogLikelihoodRatio,'Time':time.time()-start_time,'pos':pos,'nu0':sig(self.c__.get_value()),'slack':np.asscalar(self.Yslack__.get_value()),'obj':float(obj), 'obj0':float(obj0), 'times': self.times, 'y':self.y, 'theta':self.theta, 'n':self.n, 'smoothTimes': np.tile(np.arange(self.times[0][0] , self.times[-1][0]+1),(self.sim.numReplicates,1)).T})
return self.sol
def load2(iii=96, s=0.01):
sim = Simulation.Simulation.load(
s=s,
nu0=0.005,
experimentID=iii,
ModelName="TimeSeries",
numReplicates=10,
step=10,
startGeneration=0,
maxGeneration=50,
)
simn = Simulation.Simulation.load(
s=0,
nu0=0.005,
experimentID=iii,
ModelName="TimeSeries",
numReplicates=10,
step=10,
startGeneration=0,
maxGeneration=50,
)
bot = pd.read_pickle(home + "out/BottleneckedNeutrals.NotNormalized.df")[iii].loc[[0, 10, 20, 30, 40, 50]]
td = Estimate.Estimate.getEstimate(
sim.X, n=200, method="tajimaD", removeFixedSites=True, normalizeTajimaD=False
).mean(1)
td.index = sim.getTrueGenerationTimes()
tdn = Estimate.Estimate.getEstimate(
simn.X, n=200, method="tajimaD", removeFixedSites=True, normalizeTajimaD=False
).mean(1)
tdn.index = simn.getTrueGenerationTimes()
ctd = [td - bot, regularize2(td - bot), regularize3(td - bot)]
ctdn = [tdn - bot, regularize2(tdn - bot), regularize3(tdn - bot)]
t = sim.getTrueGenerationTimes()
nu = sig(s * t / 2 + logit(0.005))
a = Estimate.Estimate.getEstimate(sim.X0, n=200, method="pi")
b = -Estimate.Estimate.getEstimate(sim.X0, n=200, method="watterson") / (1.0 / np.arange(1, 201)).sum()
D0 = Estimate.Estimate.getEstimate(sim.X0, n=200, method="tajimaD", normalizeTajimaD=False)
Dt = pd.Series(b * np.log(1 - nu) - a * nu ** 2, index=t)
return map(lambda x: x, ctd), map(lambda x: x, ctdn), Dt
def fit(self,winidx,windowIndex=None,filterAfterDrop=True,linesearchTheta=False,YslackLineSearch=False):
if windowIndex is None:
y=self.sim.getAverageHAF(self.sim.winIdx[winidx])
else:
y=self.sim.getAverageHAF(windowIndex)
self.times= self.Times
if filterAfterDrop:
self.lastGenerationIndex = self.sim.filterTimeSamplesWithHighNegDer(y)
else:
self.lastGenerationIndex=(np.ones(self.numReplicates)*self.times.shape[0]).astype(int)-1
self.y=y.values
self.reset()
if YslackLineSearch: self.setInitYslackViaSettingInitObservation()
self.setInitSviaLineSearch()
start_time=time.time()
if self.verbose>2:
print 'y:\n{},times:\n{}\nn:{},\ttheta:{}\tlastGenIDX:{}\tRepIDX:{}'.format(self.y,self.times,self.n,self.Theta__.get_value(),self.lastGenerationIndex,self.replicateIndex)
self.obj=float(self.Loss_(self.y,self.times,self.n,self.lastGenerationIndex,self.replicateIndex))
if self.verbose>1: print 'Before\nIter,\tobj,\ts,\ttheta,\tYslack,\tnu\n','{}\t{:.3f}\t{:.3f}\t{:.3f}\t{:.3f}\t{}'.format(0,self.obj ,float(self.S__.get_value()),float(self.Theta__.get_value()) ,float(self.Yslack__.get_value()),sig(self.c__.get_value()))
for i in range(self.maxIter):
self.saveState()
self.obj=self.Objective_(self.y, self.lr_s, self.lr_nu, self.lr_Yslack, self.lr_theta, self.times, (self.final_momentum , self.initial_momentum)[i<5],self.n, self.lastGenerationIndex,self.replicateIndex)
if self.verbose>1: print '{}\t{:.3f}\t{:.3f}\t{:.3f}\t{:.3f}\t{}'.format(i+1,float(self.obj) ,float(self.S__.get_value()),float(self.Theta__.get_value()) ,float(self.Yslack__.get_value()),sig(self.c__.get_value()))
if self.obj>self.obj__prev:
self.undoStep()
break
s, nu0, slack,theta= np.asscalar(self.S__.get_value()), sig(self.c__.get_value()),np.asscalar(self.Yslack__.get_value()),np.asscalar(self.Theta__.get_value())
obj=self.Loss_(self.y,self.times,self.n,self.lastGenerationIndex,self.replicateIndex)
obj0=self.getZeroObj()
negLogLikelihoodRatio=np.log(obj0)-np.log(obj)
if s<0:
negLogLikelihoodRatio=0
s=0
# if negLogLikelihoodRatio<0: negLogLikelihoodRatio=0
self.sol=pd.Series({'s':s,'LR':negLogLikelihoodRatio,'Time':time.time()-start_time,'pos':self.sim.winMidPos[winidx],'nu0':nu0,'slack':slack,'obj':float(obj), 'obj0':float(obj0), 'lastTimes': self.lastGenerationIndex, 'y':self.y, 'theta':theta, 'n':self.n, 'winidx':winidx, 'SLR': np.exp(negLogLikelihoodRatio)*s, 'watterson':Estimate.watterson(self.sim.H0.iloc[:,self.sim.winIdx[winidx]]),'method':'HAF'})
return self.sol
