def plotBinomials(dataMatrix,nVals,p):
nTrials = nVals.size # rows are the trials
# same the mean and variances...
means = np.zeros(nTrials)
varReal = np.zeros(nTrials)
varDist = np.zeros(nTrials)
for i,n in enumerate(nVals):
means[i],varReal[i],varDist[i] =\
plotSingleHist(n,p,dataMatrix[i,:],outDir)
# plot the means and variances
fig = pPlotUtil.figure()
plt.subplot(1,2,1)
plt.title("Mean of g(xBar)-g(mu) approaches 0",fontsize=fontsize)
expMean = 0
plt.plot(nVals,means,'ko',label="Actual Mean")
plt.axhline(expMean,color='b',linestyle='--',
label="Expected Mean: {:.2g}".format(expMean))
plt.ylim(-min(means),max(means)*1.1)
plt.xlabel("Value of n for binomial",fontsize=fontsize)
plt.ylabel("Value of g(xBar)-g(mu)",fontsize=fontsize)
plt.legend(fontsize=fontsize)
pPlotUtil.tickAxisFont()
plt.subplot(1,2,2)
plt.semilogy(nVals,varReal,'ko',label="Actual Variance")
plt.semilogy(nVals,varDist,'b--',label="Expected Variance")
plt.title("Variance of g(xBar)-g(mu)\n approaches expected",
fontsize=fontsize)
plt.xlabel("Value of n for binomial",fontsize=fontsize)
plt.ylabel("Value of g(xBar) variance",fontsize=fontsize)
pPlotUtil.tickAxisFont()
plt.legend(fontsize=fontsize)
pPlotUtil.savefig(fig,outDir + "MeanVar")
def plotSingleHist(n,p,xTrials,outDir):
# coverage is just a plotting artifact
fig = pPlotUtil.figure()
# mu: expected value of Binomial(n,p)
# effectie variance
dist,distMean,distVar,normalStd,normalDist,xVals,nBins = \
getDeltaModelDistr(n,p,xTrials)
normV = normHist(dist,nBins,\
label=("Actual Distr: Mean={:.4f},Stdev={:.4f}").\
format(distMean,np.sqrt(distVar)))
rawPDF = normalDist.pdf(xVals)
plt.plot(xVals,rawPDF,'r--',linewidth=5.0,
label="Theorertical Distr: Stdev={:.4f}".\
format(normalStd))
plt.title("Histogram for g(xBar)-g(mu) for n={:d},p={:.2f}".\
format(int(n),p),fontsize=g_title)
plt.xlabel("(g(Xbar)-g(mu)) ~ Normal(0,[g'(x)*sigma]^2/n)",
fontsize=g_label)
plt.ylabel("Proportion",fontsize=g_label)
plt.legend(frameon=False)
pPlotUtil.tickAxisFont()
catArr = list(rawPDF) + list(normV)
plt.ylim([0,max(catArr)*1.2])
plt.xlim([-max(nBins),max(nBins)])
pPlotUtil.tickAxisFont()
pPlotUtil.savefig(fig,outDir + "trial_n{:d}".format(int(n)))
#return the statistics for plotting
return distMean,distVar,normalStd**2
def plotSingleHist(n, p, xTrials, outDir):
# coverage is just a plotting artifact
fig = pPlotUtil.figure()
# mu: expected value of Binomial(n,p)
# effectie variance
dist,distMean,distVar,normalStd,normalDist,xVals,nBins = \
getDeltaModelDistr(n,p,xTrials)
normV = normHist(dist,nBins,\
label=("Actual Distr: Mean={:.4f},Stdev={:.4f}").\
format(distMean,np.sqrt(distVar)))
rawPDF = normalDist.pdf(xVals)
plt.plot(xVals,rawPDF,'r--',linewidth=5.0,
label="Theorertical Distr: Stdev={:.4f}".\
format(normalStd))
plt.title("Histogram for g(xBar)-g(mu) for n={:d},p={:.2f}".\
format(int(n),p),fontsize=g_title)
plt.xlabel("(g(Xbar)-g(mu)) ~ Normal(0,[g'(x)*sigma]^2/n)",
fontsize=g_label)
plt.ylabel("Proportion", fontsize=g_label)
plt.legend(frameon=False)
pPlotUtil.tickAxisFont()
catArr = list(rawPDF) + list(normV)
plt.ylim([0, max(catArr) * 1.2])
plt.xlim([-max(nBins), max(nBins)])
pPlotUtil.tickAxisFont()
pPlotUtil.savefig(fig, outDir + "trial_n{:d}".format(int(n)))
#return the statistics for plotting
return distMean, distVar, normalStd**2
def plotBinomials(dataMatrix, nVals, p):
nTrials = nVals.size # rows are the trials
# same the mean and variances...
means = np.zeros(nTrials)
varReal = np.zeros(nTrials)
varDist = np.zeros(nTrials)
for i, n in enumerate(nVals):
means[i],varReal[i],varDist[i] =\
plotSingleHist(n,p,dataMatrix[i,:],outDir)
# plot the means and variances
fig = pPlotUtil.figure()
plt.subplot(1, 2, 1)
plt.title("Mean of g(xBar)-g(mu) approaches 0", fontsize=fontsize)
expMean = 0
plt.plot(nVals, means, 'ko', label="Actual Mean")
plt.axhline(expMean,
color='b',
linestyle='--',
label="Expected Mean: {:.2g}".format(expMean))
plt.ylim(-min(means), max(means) * 1.1)
plt.xlabel("Value of n for binomial", fontsize=fontsize)
plt.ylabel("Value of g(xBar)-g(mu)", fontsize=fontsize)
plt.legend(fontsize=fontsize)
pPlotUtil.tickAxisFont()
plt.subplot(1, 2, 2)
plt.semilogy(nVals, varReal, 'ko', label="Actual Variance")
plt.semilogy(nVals, varDist, 'b--', label="Expected Variance")
plt.title("Variance of g(xBar)-g(mu)\n approaches expected",
fontsize=fontsize)
plt.xlabel("Value of n for binomial", fontsize=fontsize)
plt.ylabel("Value of g(xBar) variance", fontsize=fontsize)
pPlotUtil.tickAxisFont()
plt.legend(fontsize=fontsize)
pPlotUtil.savefig(fig, outDir + "MeanVar")
def plotScoreHistograms(scores,fontSize,edgecolor='none'):
meanScore = np.mean(scores)
stdevScore = np.std(scores)
step = 1
bins = np.arange(min(scores)-step,max(scores)+step,1)
plt.hist(scores, bins,normed=True,label="Distr. "+
"mean:{:.3g}, var: {:.3g})".format(meanScore,stdevScore**2),
alpha=0.25,edgecolor=edgecolor)
plt.xlabel("Optimal alignment score for sequence",fontsize=fontSize)
plt.ylabel("Occurence of score",fontsize=fontSize)
pPlotUtil.tickAxisFont()
return meanScore,stdevScore,bins
