def argueWithoutSample(sample, conclusion):
"""
Builds an argument for conclusion (assumed to be passed in as a string, NOT a full conclusion
(so no parameters can be attached to the conclusion, currently...), but this may change), after
removing the given sample from the dataset.
"""
#first let's check that we need to remove samples
arg = engine.buildArgument(conclusions.Conclusion(conclusion))
name = "can argue for '" + conclusion + "' without sample " + str(sample)
if arg.getSingleConfidence().isStrongly(True):
return SimResult(-arg.getSingleConfidence(), name,
"good argument for '" + conclusion + "' before removing any samples",
arg)
savedSamples = samples.sampleList[:]
samples.sampleList.remove(sample)
arg = engine.buildArgument(conclusions.Conclusion(conclusion))
samples.sampleList = savedSamples
return SimResult(arg.getSingleConfidence(), name,
(arg.getSingleConfidence().isTrue() and 'valid' or 'invalid') +
" argument for " + conclusion + " without " + str(sample), arg)
def centralAgreement(sample):
"""
Checks whether we can remove samples at the edges to get a reasonably large group with
a single central tendency.
Should pay attention to whether removed samples have similar ages to each other or not
Also, this should be run once and the results saved, instead of being run again for every
single sample...
"""
#first let's check that we need to remove samples
arg = engine.buildArgument(conclusions.Conclusion("no process"))
name = "removal of youngest and oldest samples allows argument for 'no process'"
if arg.getSingleConfidence().isStrongly(True):
return SimResult(-arg.getSingleConfidence(), name,
"good argument for 'no process' before removing any samples",
arg)
savedSamples = samples.sampleList[:]
samples.sampleList.sort(cmp = lambda x, y: cmp(x[__getAge()], y[__getAge()]))
while len(samples.sampleList) > 0:
mean = calculations.calcMean(__getAge())
younger = mean - samples.sampleList[0][__getAge()]
older = samples.sampleList[-1][__getAge()] - mean
if younger > older:
del samples.sampleList[0]
else:
del samples.sampleList[-1]
arg = engine.buildArgument(conclusions.Conclusion("no process"))
if arg.getSingleConfidence().isStrongly(True):
break
if sample in samples.sampleList:
res = SimResult(confidence.Confidence(confidence.Applic.cf, confidence.Validity.sound), name,
str(sample) + " does not need to be removed to have good argument for 'no process'",
arg)
samples.sampleList = savedSamples
return res
reduction = len(samples.sampleList) / float(len(savedSamples))
#removed = len(savedSamples) - len(samples.sampleList)
samples.sampleList = savedSamples
conf = __getConfidence((.2, .35, .6, .8, .9), reduction, confidence.Validity.prob)
#print reduction, conf
#oldest n samples appear to be outliers
return SimResult(conf, name, "removed " + str(100 - (reduction * 100)) +
"% of samples before finding a good argument for 'no process'", arg)
def run(self, env):
"""
So this is different because we don't call some function and then do something with the
result. Instead, we need to call the engine and construct a new, complete argument for the
conclusion listed in name.
"""
self._useEnv(env)
self.argument = engine.buildArgument(conclusions.Conclusion(self.name, self.useParams))
self.confidence = self.argument.getSingleConfidence()
def quantizedInheritance():
"""
Checks whether we can remove only a small percentage of samples from the oldest end of the
sample set and, in so doing, get a successful "no process" argument.
"""
#first let's check that we need to remove samples
arg = engine.buildArgument(conclusions.Conclusion("no process"))
name = "removal of groups of older samples allows argument for 'no process'"
if arg.getSingleConfidence().isProbably(True):
return SimResult(-arg.getSingleConfidence(), name,
"good argument for 'no process' before removing any samples",
arg)
savedSamples = samples.sampleList[:]
samples.sampleList.sort(cmp = lambda x, y: cmp(x[__getAge()], y[__getAge()]))
while len(samples.sampleList) > 0:
curMax = samples.sampleList[-1][__getAge()] - \
samples.sampleList[-1][__getAge() + ' uncertainty']
#delete in chunks, not one at a time
samples.sampleList = [sample for sample in samples.sampleList if sample[__getAge()] < curMax]
arg = engine.buildArgument(conclusions.Conclusion("no process"))
if arg.getSingleConfidence().isProbably(True):
break
reduction = len(samples.sampleList) / float(len(savedSamples))
#removed = len(savedSamples) - len(samples.sampleList)
samples.sampleList = savedSamples
conf = __getConfidence((.1, .2, .4, .65, .80), reduction, confidence.Validity.accept)
#oldest n samples appear to be outliers
return SimResult(conf, name, "removed " + str(100 - (reduction * 100)) +
"% of samples before finding a good argument for 'no process'", arg)
