def main():
from random import seed
from probability import genProbs
#### Unit test for training funciton
# Initiatializes seed for recurrent testing.
for _ in range(10):
dimen = (4, 3, 6, 5, 6)
classValues = 5
measures = MeasurementGenerator(dimen)
classes = ClassAssign(dimen, classValues)
conds = [list(genProbs(measures.range)) for _ in range(classValues)]
egain = [[2, 0, 0, 0, 1], [3, 4, 0, 2, 2], [2, 2, 5, 1, 1],
[2, 2, 3, 4, 1], [0, 1, -3, 2, 3]]
classifier = BayesClassifier(
None, conds, eGain=egain
) # Worries that supplying similar priors is affecting our results. Even though vFold updates.
y = train(classifier, 20, measures, classes, 6000, delta=.0005)
z = [y[i] - y[i - 1] for i in range(1, len(y))]
# Trying to figure out average negative error to see if this is floating point.
print(y)
print()
print(z)
q = [i for i in z if i < 0]
q = sum(q) / max(len(q), 1)
print(q)
print()
x = measures.genMeas(20)
p = classes.assign(x)
l = classifier.assign(x)
def test(classifier: BayesClassifier,
measures: Tuple[int],
tags: Tuple[int],
V=0) -> float:
## Training protocol for testing measurements. Shuffles measures and tags while retaining
# pairings and then classifies according to Bayes classifier. Returns expected gain
# of testing. If V is provided, performs V-fold testing on data of V partitions
# Shuffles tags and measures
K = classifier.range
e = classifier.eGain
measures, tags = shuffle(measures, tags)
# Sees if we are v-folding or just testing over a random measure.
if V:
normMatrix = vFold(measures, tags, V, classifier)
else:
results = classifier.assign(measures)
matrix = genConMatrix(tags, results, K)
normMatrix = normConMatrix(matrix)
return calcExpGain(normMatrix, e)
def biasCCP(classifier: BayesClassifier, delta: float) -> List[List[float]]:
# Destrucctively Updates CCP values in classifier. Classes are generated from classifier
# for all measurements d in M space. Each d|c is increased by delta towards classifier's selection
# and is normalized over class space. Returns conditional matrix. Not used in function but preserved
# for legacy update.
# Classifies for all d in measurement space M
M = classifier.spaceSize
K = classifier.range
bayesValues = classifier.assign(range(M))
conds = classifier.cond # Note, this alters the original classifier. Had to be done for speed and memory efficiency.
# Updates conditionals
for measure in range(M):
tag = bayesValues[measure]
conds[tag][measure] += delta
# Normalizes conditionals
for val in range(K):
sums = sum(conds[val])
conds[val] = [prb / sums for prb in conds[val]]
return conds
def vFold(meas: Tuple[int], tags: Tuple[int], V: int,
classifier: BayesClassifier) -> List[List[float]]:
# Performs a round of V-fold validation tests on measurements 'meas' and respective real classes 'tags'
# Performs V test using classifier. Returns a normalized confusion matrix of tests.
results = []
measFold = partition(meas, V)
tagsFold = partition(tags, V)
for v in range(V):
# Creates folds
# Assigns testing and training
trainTags = [tag for i in range(V) if i != v for tag in tagsFold[i]]
testMeas = measFold[v]
# Updates with new probability values
trainProb = calcClassProb(trainTags, classifier.range)
classifier.priorUpdate(trainProb)
results.append(classifier.assign(testMeas)) # Unfolds tuple
results = tuple(i for tpl in results for i in tpl)
matrix = genConMatrix(tags, results, classifier.range)
return results #normConMatrix(matrix)