def __init__(
self,
pred=rforest,
_smoteit=True,
_n=-1,
_tuneit=False,
dataName=None,
reps=1,
extent=0.5,
fSelect=False,
Prune=False,
infoPrune=0.75):
self.pred = pred
self.extent = extent
self.fSelect = fSelect
self.Prune = Prune
self.infoPrune = infoPrune
self.dataName = dataName
self.out, self.out_pred = [], []
self._smoteit = _smoteit
self.train, self.test = self.categorize()
self.reps = reps
self._n = _n
self.tunedParams = None if not _tuneit else tuner(
self.pred, self.train[_n])
def __init__(
self,
pred=CART,
_smoteit=True,
_n=-1,
_tuneit=False,
dataName=None,
reps=1,
extent=0.5,
fSelect=False,
Prune=False,
infoPrune=0.75):
self.pred = pred
self.extent = extent
self.fSelect = fSelect
self.Prune = Prune
self.infoPrune = infoPrune
self.dataName = dataName
self.out, self.out_pred = [], []
self._smoteit = _smoteit
self.train, self.test = self.categorize()
self.reps = reps
self._n = _n
self.tunedParams = None if not _tuneit else tuner(
self.pred, self.train[_n])
def __init__(
self, pred=rforest, _smoteit=True, _n=-1
, _tuneit=False, dataName=None, reps=1):
self.pred = pred
self.dataName = dataName
self.out, self.out_pred = [self.dataName], []
self._smoteit = _smoteit
self.train, self.test = self.categorize()
self.reps = reps
self._n = _n
self.tunedParams = None if not _tuneit \
else tuner(self.pred, self.train[_n])
self.headers = createTbl(self.train[self._n], isBin=False
, bugThres=1).headers
def __init__(self, file='ant', tuned=True):
self.file = file
self.train = createTbl(data(dataName=self.file).train[-1], isBin=True)
self.test = createTbl(data(dataName=self.file).test[-1], isBin=True)
self.param = dEvol.tuner(rforest, data(dataName=self.file).train[-1]) if \
tuned else None
def __init__(self, file='ant'): self.file = file self.train = createTbl(data(dataName=self.file).train[-1], isBin=False) self.test = createTbl(data(dataName=self.file).test[-1], isBin=False) self.param = tuner(rforest, data(dataName=self.file).train[-1])
def main():
dir = '../Data'
from os import walk
dataName = [Name for _, Name, __ in walk(dir)][0]
numData = len(dataName) # Number of data
Prd = [CART] # , rforest] # , adaboost, logit, knn]
_smoteit = [True] # , False]
_tuneit = [False]
cd = {}
abcd = []
res = {}
for n in xrange(numData):
out11 = []
outA1 = []
out1 = []
outFar = []
outNear = []
outa = []
one, two = explore(dir)
data = [one[i] + two[i] for i in xrange(len(one))]
print('##', dataName[n])
for p in Prd:
train = [dat[0] for dat in withinClass(data[n])]
test = [dat[1] for dat in withinClass(data[n])]
reps = 10
abcd = [[], []]
for t in _tuneit:
tunedParams = None if not t else params
print('### Tuning') if t else print('### No Tuning')
for _smote in _smoteit:
# for _n in xrange(0):
_n = -1
# Training data
for _ in xrange(reps):
train_DF = createTbl(train[_n], isBin=True)
# set_trace()
# Testing data
test_df = createTbl(test[_n], isBin=True)
predRows = []
# Tune?
actual = Bugs(test_df)
before = p(train_DF, test_df,
tunings=tunedParams,
smoteit=True)
tunedParams = None if not t else tuner(p, train[_n])
for predicted, row in zip(before, test_df._rows):
tmp = row.cells
tmp[-2] = predicted
if predicted > 0:
predRows.append(tmp)
predTest = clone(test_df, rows=predRows)
# Find and apply contrast sets
# newTab = treatments(train = train[_n],
# test = test[_n],
# verbose = False,
# smoteit = False).main()
newTab_near = treatments2(train=train[_n], far=False, test=test[_n] # ).main()
, test_df=predTest).main() \
if predRows \
else treatments2(train=train[_n], test=test[_n]).main()
newTab_far = treatments2(train=train[_n], test=test[_n] # ).main()
, test_df=predTest).main() \
if predRows \
else treatments2(train=train[_n], test=test[_n]).main()
after_far = p(train_DF, newTab_far,
tunings=tunedParams,
smoteit=True)
after_near = p(train_DF, newTab_near,
tunings=tunedParams,
smoteit=True)
# print(showoff(dataName[n], before, after))
outa.append(_Abcd(before=actual, after=before))
# set_trace()
cliffsFar = cliffsdelta(Bugs(predTest), after_far)
cliffsNear = cliffsdelta(Bugs(predTest), after_near)
# print(cliffsDelta(Bugs(predTest), after))
# print('Gain = %1.2f' % float(\
# (sum(Bugs(predTest)) - sum(after)) / sum(Bugs(predTest)) * 100), r'%')
outFar.append(cliffsFar)
outNear.append(cliffsNear)
# out1.append(float((sum(before) - sum(after)) / sum(before) * 100))
# out1 = [o for o in out1 if np.isfinite(o)]
outNear.insert(0, dataName[n] + '_Far')
outFar.insert(0, dataName[n] + '_Near')
outa.insert(0, dataName[n])
out11.extend([outNear, outFar])
outA1.append(outa)
try:
print('```')
rdivDemo(out11, isLatex=False)
# rdivDemo(outA1, isLatex = False)
print('```')
except IndexError:
pass
