def hardSweep():
param=pd.read_pickle('/home/arya/out/vineet/param0.1_1.pd')
reload(Simulation)
s=0.01
X0=param['initHaps'].mean(0)
param['siteUnderSelection']=param['initHaps'].mean(0).argmin()
param['s']=s
param['numReplicates']=3
param['maxGeneration']=500
param['generationStep']=100
param['startGeneration']=0
X = Simulation.Simulation.forwardSimulationHardSweep(param)
def sig(x): return 1./(1+np.exp(-x))
if not param['startGeneration']:
x0=X0[param['siteUnderSelection']]
else:
x0=X[param['startGeneration']/param['generationStep'] -1,param['siteUnderSelection'],:].mean()
x0
c=np.log(1-x0)-np.log(x0)
z=sig(s*np.array(range(param['startGeneration'],param['maxGeneration']+1,param['generationStep'])[1:])/2. -c)
pd.DataFrame(np.append(X[:,3,:],z[:,None],axis=1)).plot()
y= np.array([[np.linalg.norm(X[t,:,r])**2 for t in range(X.shape[0])] for r in range(param['numReplicates'])]).T
y0=np.linalg.norm(X0)**2
theta=Estimate.watterson(np.tile(param['initHaps'],(10,1)));n=2000
theta=Estimate.watterson(param['initHaps']);n=200
a=[(y0 ,Z(X0[3], n, theta))]
for t in range(5):
a.append((y[t] ,Z(X[t,3,:], n, theta)))
pd.DataFrame(a)
times=range(param['startGeneration'],param['maxGeneration']+1,param['generationStep'])[1:]
times
x0_ = T.scalar("x0")
n_ = T.scalar("n")
theta_ = T.scalar("theta")
times_ = T.ivector("times")
S__=theano.shared(np.asarray(s, dtype = theano.config.floatX), 'S')
predall_, updatesRecurrence_ = theano.scan(lambda x_prev, s: (s*x_prev*x_prev+s*x_prev +2*x_prev)/(2*s*x_prev+2), outputs_info=x0_,non_sequences=S__,n_steps=times_[-1])
pred_=Z(predall_[times_-1],n_,theta_) #we only have target at some generations e.g. 10,20,...
Feedforward_ = theano.function(inputs=[x0_,times_,n_,theta_], outputs=pred_, updates=updatesRecurrence_)
Feedforward_(x0,times,n,theta)
x0
y
times
Z(X[:,3,:],n,theta)
theta,n
z
Z(z,2000,17)
pd.DataFrame(np.append(X[:,3,:],z[:,None],axis=1))
def HAFRNN():
x0=0.5
s=0.1
times=[1,10,20,30,40,50]
yhat=direct(x0, s, times)
param=pd.read_pickle('/home/arya/out/vineet/param0.1_1.pd')
X0=param['initHaps']
X=param['data']
idx=range(param['siteUnderSelection']-5,param['siteUnderSelection']+6)
X=X[:,idx,:]
X.shape
x0=param['initHaps'][param['siteUnderSelection']].mean()
XX0=np.tile(X0,(10,1))
theta =Estimate.watterson(XX0)
theta
idx,x0 ,theta
n=2000
theta/2
# y= np.array([[np.linalg.norm(X[t,:,r])**2 for t in range(5)] for r in range(3)]).T
# y
# x0_ = T.scalar("x0")
# n_ = T.scalar("n")
# theta_ = T.scalar("theta")
# times_ = T.ivector("times")
# S__=theano.shared(np.asarray(s, dtype = theano.config.floatX), 'S')
# predall_, updatesRecurrence_ = theano.scan(lambda x_prev, s: (s*x_prev*x_prev+s*x_prev +2*x_prev)/(2*s*x_prev+2), outputs_info=x0_,non_sequences=S__,n_steps=times_[-1])
# pred_=Z(predall_[times_-1],n_,theta_) #we only have target at some generations e.g. 10,20,...
# Feedforward_ = theano.function(inputs=[x0_,times_,n_,theta_], outputs=pred_, updates=updatesRecurrence_)
#
# times=param['times']
# theta=3; n=200
# S__.set_value(0)
# S__.get_value()
# Feedforward_(x0,times,n,theta)
# idx2=range(11)
# len(idx2)
# y
#
np.linalg.norm(X0.mean(0)[idx])**2
np.linalg.norm(XX0[:,idx].mean(0))**2
XX0.shape,Estimate.watterson(XX0[:,idx])
Estimate.watterson(XX0[:,idx])
idx=range(20,25);
import os
files=pd.Series(os.listdir('/home/arya/out/vineet/'))
idx_pd =files.map(lambda x: x[-3:]=='.pd')
idx_s= files.map(lambda x: 'param' in x)
idx=idx_pd & idx_s
print idx.sum()
res=[]
for f in files[idx]:
X0=pd.read_pickle('/home/arya/out/vineet/'+f)['initHaps']
XX0=np.tile(X0,(10,1))
res.append( (Z(nu=0.2, n=2000, theta=Estimate.watterson(XX0)), (Estimate.watterson(XX0)*(n-1))/(2*n),np.linalg.norm(XX0.mean(0))**2, XX0.mean(0).min()))
print
df=pd.DataFrame(res)
df[2].plot(kind='hist')
df[2].mean()
df[2].std()
df[3].describe()
n=2000
theta=17
theta=Estimate.watterson(XX0[:,idx])
theta*x0*((x0+1)/2. - 1./((1-x0)*n+1)) +theta*(1-x0)*((n+1)/(2.*n) - 1./((1-x0)*n+1))
n
((n-1)/2.)*17
np.linalg.norm(X0.mean(0))**2
print
def f(x): return Estimate.getEstimate(x=x, n=n, method='tajimaD', selectionPredictor=True),Estimate.getEstimate(x=x, n=n, method='H', selectionPredictor=True),Estimate.getEstimate(x=x, n=n, method='SFSelect', selectionPredictor=True, svm_model_sfselect=svm) for CHROM in CHROMS:
