def plotInfluential ( InferenceObject ):
"""Diagnostic plot for detecting influential observations
Determining influential observations follows a different logic for bootstrap
and for bayes inference. A block is labelled an influential observation if
the fit for a dataset without that point is significantly different from the
fit including that point. For BootstrapInference objects, this is quantified
using a normed distance of the maximum likelihood fit including the block and
withouth that block. This distance is normed in the following way: If the
maximum likelihood fit for the reduced dataset remains inside the 95% confidence
limits of the maximum likelihood fit for the full dataset, the influence
value is below 1. Thus, influence values large than 1 indicate a problem with
the data set. For BayesInference objects, the influence of a block is simply
quantified as the Kullbach-Leibler divergence of the posterior for the full
data set from the posterior for the reduced data set.
:Parameters:
*InferenceObject* :
Data set for which the influential observations are to be plotted
"""
maxinfl = N.argmax(InferenceObject.infl)
ind = range ( InferenceObject.data.shape[0] )
ind.pop(maxinfl)
# influencedDataset = psignidata.BootstrapInference( InferenceObject.data[ind,:],
# sample=False, **(InferenceObject.model))
# influencedDataset = psignidata.BayesInference ( InferenceObject.data[ind,:], **(InferenceObject.model) )
est = interface.mapestimate ( InferenceObject.data[ind,:], start=InferenceObject.estimate, **(InferenceObject.model) )[0]
x = N.mgrid[InferenceObject.data[:,0].min():InferenceObject.data[:,0].max():100j]
influencedPMF = interface.diagnostics ( x, est,
nafc = InferenceObject.model["nafc"],
sigmoid = InferenceObject.model["sigmoid"],
core = InferenceObject.model["core"] )
p.figure ( figsize=(6,8) )
# ax = p.axes ( (0.0,.5,.9,.5) )
ax = prepare_axes ( p.subplot ( 2,1,1 ) )
ax.set_ylabel ( r"$\Psi(x)$" )
if InferenceObject.__repr__().split()[1] in ["BayesInference","ASIRInference"]:
InferenceObject.drawposteriorexamples ( ax=ax )
plotPMF ( InferenceObject, ax=ax, showaxes=True, showdesc=False, color="b", linewidth=2 )
ax.plot ( [InferenceObject.data[maxinfl,0]], [InferenceObject.data[maxinfl,1].astype("d")/InferenceObject.data[maxinfl,2]],
'rx', markersize=20, markeredgewidth=5 )
# ax = plotPMF ( influencedDataset, ax=ax, showdesc=False, showaxes=True, color="r", markertype=([(0,0)],0), linewidth=2 )[-1]
ax.plot ( x, influencedPMF, color="r", linewidth=2 )
xl = list(ax.get_xlim ())
# ax = p.axes ( (0.0, 0., .9, .5) )
ax = p.subplot ( 2,1,2, sharex=ax )
if InferenceObject.__repr__().split()[1] == "BootstrapInference":
ax.plot ( [InferenceObject.data[:,0].min(),InferenceObject.data[:,0].max()], [1,1], 'k:' )
yname = "Influence"
else:
yname = "D_KL( full || reduced )"
ax.plot ( InferenceObject.data[:,0], InferenceObject.infl, 'bo' )
ax.set_xlim(xl)
drawaxes ( ax, ax.get_xticks(), "%g", ax.get_yticks(), "%g", r"stimulus intensity $x$", yname )
def test_old_doctest(self):
x = [float(2 * k) for k in xrange(6)]
k = [34, 32, 40, 48, 50, 48]
n = [50] * 6
d = [[xx, kk, nn] for xx, kk, nn in zip(x, k, n)]
prm = [2.75, 1.45, 0.015]
pred, di, D, thres, slope, Rpd, Rkd = interface.diagnostics(d, prm)
self.assertAlmostEqual(8.07484858608, D)
self.assertAlmostEqual(1.68932796526, di[0])
self.assertAlmostEqual(-0.19344675783032761, Rpd)
def test_old_doctest(self):
x = [float(2*k) for k in xrange(6)]
k = [34,32,40,48,50,48]
n = [50]*6
d = [[xx,kk,nn] for xx,kk,nn in zip(x,k,n)]
prm = [2.75, 1.45, 0.015]
pred,di,D,thres,slope,Rpd,Rkd = interface.diagnostics(d,prm)
self.assertAlmostEqual(8.07484858608, D)
self.assertAlmostEqual(1.68932796526, di[0])
self.assertAlmostEqual(-0.19344675783032761, Rpd)
def test_single_cut(self):
# this test was added to ensure the return type of swignifit
# is also an ndarray. Before it was a list. Unfortunately a list with
# one item cannot be cast to a float, but an ndarray with one item can
# this was a problem in the getThres() of the PsiInference class in
# psignidata.py
sfi_output = float(sfi.diagnostics(data, TestDiagnostics.prm,
cuts=[0.5])[3])
psipy_output = float(psipy.diagnostics(data, TestDiagnostics.prm,
cuts=[0.5])[3])
self.assertEqual(sfi_output, psipy_output)
def test_empty_data(self):
# if an empty sequence is passed we only obtain the threshold
result = interface.diagnostics([], TestDiagnostics.prm)
def sample ():
boots = interface.bootstrap ( d, priors=priors, nsamples=1500-2*k )
mape = interface.mapestimate ( d, priors=priors )
mcmc = interface.mcmc ( d, start=(4,2,.02), priors=priors, nsamples = 1500-2*k )
diag = interface.diagnostics ( d, (4,1,.02) )
return float(os.popen ( "ps -C python -o rss" ).readlines()[1])/1024
def test_cuts(self):
interface.diagnostics(data, TestDiagnostics.prm, cuts=[0.5, 0.75, 0.85])
def test_intensities_only(self):
predicted = interface.diagnostics(x, TestDiagnostics.prm)
def test_sigmoid(self):
interface.diagnostics(data, TestDiagnostics.prm, sigmoid='logistic')
def test_core(self):
interface.diagnostics(data, TestDiagnostics.prm, core='linear')
def test_nafc(self):
interface.diagnostics(data, TestDiagnostics.prm, nafc=23)
def test_nafc(self):
interface.diagnostics(data, TestDiagnostics.prm, nafc=23)
def test_basic(self):
interface.diagnostics(data, TestDiagnostics.prm)
def test_basic(self):
interface.diagnostics(data, TestDiagnostics.prm)
def test_empty_data(self):
# if an empty sequence is passed we only obtain the threshold
result = interface.diagnostics([], TestDiagnostics.prm)
def test_intensities_only(self):
predicted = interface.diagnostics(x, TestDiagnostics.prm)
def test_cuts(self):
interface.diagnostics(data,
TestDiagnostics.prm,
cuts=[0.5, 0.75, 0.85])
def test_core(self):
interface.diagnostics(data, TestDiagnostics.prm, core='linear')
def test_sigmoid(self):
interface.diagnostics(data, TestDiagnostics.prm, sigmoid='logistic')
