print data[19]
print "Imputed:"
print imputer(data[19])
print
impdata = imputer(data)
for i in range(20, 25):
print data[i]
print impdata[i]
print
print "\n*** TREE-BASED IMPUTATION ***\n"
import orngTree
imputer = orange.ImputerConstructor_model()
imputer.learnerContinuous = imputer.learnerDiscrete = orngTree.TreeLearner(minSubset = 20)
imputer = imputer(data)
print "Example w/ missing values"
print data[19]
print "Imputed:"
print imputer(data[19])
print
impdata = imputer(data)
for i in range(20, 25):
print data[i]
print impdata[i]
print
def __call__(self, data, weight=None):
if not self.use_attributes is None:
new_domain = orange.Domain(self.use_attributes,
data.domain.classVar)
new_domain.addmetas(data.domain.getmetas())
data = orange.ExampleTable(new_domain, data)
if self.stepwise and self.stepwise_before:
use_attributes = stepwise(data,
add_sig=self.add_sig,
remove_sig=self.remove_sig)
new_domain = orange.Domain(use_attributes, data.domain.classVar)
new_domain.addmetas(data.domain.getmetas())
data = orange.ExampleTable(new_domain, data)
# continuization (replaces discrete with continuous attributes)
continuizer = orange.DomainContinuizer()
continuizer.multinomialTreatment = continuizer.FrequentIsBase
continuizer.zeroBased = True
domain0 = continuizer(data)
data = data.translate(domain0)
if self.stepwise and not self.stepwise_before:
use_attributes = stepwise(data,
weight,
add_sig=self.add_sig,
remove_sig=self.remove_sig)
new_domain = orange.Domain(use_attributes, data.domain.classVar)
new_domain.addmetas(data.domain.getmetas())
data = orange.ExampleTable(new_domain, data)
# missing values handling (impute missing)
imputer = orange.ImputerConstructor_model()
imputer.learnerContinuous = orange.MajorityLearner()
imputer.learnerDiscrete = orange.MajorityLearner()
imputer = imputer(data)
data = imputer(data)
# convertion to numpy
A, y, w = data.toNumpy() # weights ??
if A is None:
n = len(data)
m = 0
else:
n, m = numpy.shape(A)
if self.beta0 == True:
if A is None:
X = numpy.ones([len(data), 1])
else:
X = numpy.insert(A, 0, 1, axis=1) # adds a column of ones
else:
X = A
# set weights
W = numpy.identity(len(data))
if weight:
for di, d in enumerate(data):
W[di, di] = float(d[weight])
D = dot(
dot(numpy.linalg.pinv(dot(dot(X.T, W), X)), X.T), W
) # adds some robustness by computing the pseudo inverse; normal inverse could fail due to singularity of the X.T*W*X
beta = dot(D, y)
yEstimated = dot(X, beta) # estimation
# some desriptive statistisc
muY, sigmaY = numpy.mean(y), numpy.std(y)
muX, covX = numpy.mean(X, axis=0), numpy.cov(X, rowvar=0)
# model statistics
SST, SSR = numpy.sum((y - muY)**2), numpy.sum((yEstimated - muY)**2)
SSE, RSquare = SST - SSR, SSR / SST
R = numpy.sqrt(RSquare) # coefficient of determination
RAdjusted = 1 - (1 - RSquare) * (n - 1) / (n - m - 1)
F = (SSR / m) / (SST - SSR / (n - m - 1)) # F statistisc
df = m - 1
sigmaSquare = SSE / (n - m - 1)
# standard error of estimated coefficients
errCoeff = sqrt(sigmaSquare * inv(dot(X.T, X)).diagonal())
# t statistisc, significance
t = beta / errCoeff
df = n - 2
significance = []
for tt in t:
try:
significance.append(
statc.betai(df * 0.5, 0.5, df / (df + tt * tt)))
except:
significance.append(1.0)
# standardized coefficients
if m > 0:
stdCoeff = (sqrt(covX.diagonal()) / sigmaY) * beta
else:
stdCoeff = (sqrt(covX) / sigmaY) * beta
model = {
'descriptives': {
'meanX': muX,
'covX': covX,
'meanY': muY,
'sigmaY': sigmaY
},
'model': {
'estCoeff': beta,
'stdErrorEstimation': errCoeff
},
'model summary': {
'TotalVar': SST,
'ExplVar': SSE,
'ResVar': SSR,
'R': R,
'RAdjusted': RAdjusted,
'F': F,
't': t,
'sig': significance
}
}
return LinearRegression(statistics=model,
domain=data.domain,
name=self.name,
beta0=self.beta0,
imputer=imputer)