def main(self, name='Apache', reps=20):
out_xtrees = ['xtrees']
out_HOW = ['HOW']
out_cart = ['CART']
out_basln = ['Base']
out_baslnFss = ['Base+FSS']
for _ in xrange(reps):
data = self.explorer(name)
for d in data:
if name == d[0].strip().split('/')[-2]:
# set_trace()
train = [d[0] + d[1][1]]
test = [d[0] + d[1][0]]
# set_trace()
train_df = formatData(createTbl(train, _smote=False, isBin=False))
test_df = formatData(createTbl(test, _smote=False, isBin=False))
actual = test_df[test_df.columns[-2]].astype('float32').tolist()
before = predictor(train=train_df, test=test_df).rforest()
"Apply Different Planners"
xTrees = xtrees(train=train,
test=test,
bin=False,
majority=True).main()
cart = xtrees(train=train,
test=test,
bin=False,
majority=False).main()
how = HOW(name)
baseln = strawman(
train=train,
test=test).main(
config=True)
baselnFss = strawman(
train=train,
test=test,
prune=True).main(config=True)
after = lambda newTab: predictor(
train=train_df,
test=formatData(newTab)).rforest()
frac = lambda aft: sum(aft) / sum(before)
# set_trace()
out_xtrees.append(frac(after(xTrees)))
out_cart.append(frac(after(cart)))
out_HOW.extend(how)
out_basln.append(frac(after(baseln)))
out_baslnFss.append(frac(after(baselnFss)))
return [out_xtrees, out_cart, out_HOW, out_basln, out_baslnFss]
def main(self, name='Apache', reps=20):
out_xtrees = ['xtrees']
out_HOW = ['HOW']
out_cart = ['CART']
out_basln = ['Base']
out_baslnFss = ['Base+FSS']
for _ in xrange(reps):
data = self.explorer(name)
for d in data:
if name == d[0].strip().split('/')[-2]:
# set_trace()
train = [d[0] + d[1][1]]
test = [d[0] + d[1][0]]
# set_trace()
train_df = formatData(
createTbl(train, _smote=False, isBin=False))
test_df = formatData(
createTbl(test, _smote=False, isBin=False))
actual = test_df[test_df.columns[-2]].astype(
'float32').tolist()
before = predictor(train=train_df, test=test_df).rforest()
"Apply Different Planners"
xTrees = xtrees(train=train,
test=test,
bin=False,
majority=True).main()
cart = xtrees(train=train,
test=test,
bin=False,
majority=False).main()
how = HOW(name)
baseln = strawman(train=train, test=test).main(config=True)
baselnFss = strawman(train=train, test=test,
prune=True).main(config=True)
after = lambda newTab: predictor(
train=train_df, test=formatData(newTab)).rforest()
frac = lambda aft: sum(aft) / sum(before)
# set_trace()
out_xtrees.append(frac(after(xTrees)))
out_cart.append(frac(after(cart)))
out_HOW.extend(how)
out_basln.append(frac(after(baseln)))
out_baslnFss.append(frac(after(baselnFss)))
return [out_xtrees, out_cart, out_HOW, out_basln, out_baslnFss]
def main(self, name='Apache', reps=20):
rseed(1)
for planner in ['DTREE', 'CD+FS', 'CD', 'BIC']:
out = [planner]
after = lambda newTab: predictor(
train=train_df,
test=formatData(newTab)).rforest()
frac = lambda aft: (1 - sum(aft) / sum(before))
data = self.explorer(name)
for d in data:
if name == d[0].strip().split('/')[-2]:
# set_trace()
train = [d[0] + d[1][1]]
test = [d[0] + d[1][0]]
# set_trace()
train_df = formatData(createTbl(train, _smote=False, isBin=False))
test_df = formatData(createTbl(test, _smote=False, isBin=False))
valid = [
isValid(
new.cells, name=name) for new in createTbl(
test,
_smote=False,
isBin=False)._rows]
actual = test_df[test_df.columns[-2]].astype('float32').tolist()
before = predictor(train=train_df, test=test_df).rforest()
for _ in xrange(reps):
newTab = None # Just so I am sure, there isn't any residue.
"Apply Different Planners"
if planner == 'xtrees':
newTab = xtrees(train=train,
test=test,
bin=False,
majority=True,
name=name).main()
if planner == 'DTREE':
newTab = xtrees(train=train,
test=test,
bin=False,
majority=False,
name=name).main()
valid = [isValid(new.cells, name=name) for new in newTab._rows]
# set_trace()
if planner == 'BIC':
newTab = HOW(name)
valid = [isValid(new.cells, name=name) for new in newTab._rows]
# set_trace()
if planner == 'CD':
newTab = strawman(name=name,
train=train,
test=test).main(mode="config")
valid = [isValid(new.cells, name=name) for new in newTab._rows]
# set_trace()
if planner == 'CD+FS':
newTab = strawman(name=name,
train=train,
test=test,
prune=True).main(mode="config")
valid = [isValid(new.cells, name=name) for new in newTab._rows]
# set_trace()
try:
out.append(frac(after(newTab)))
except:
set_trace()
yield out
def deltas(self, name, planner):
predRows = []
delta = []
data = self.explorer(name)
rows = lambda newTab: map(lambda r: r.cells[:-2], newTab._rows)
for d in data:
if name == d[0].strip().split('/')[-2]:
train = [d[0] + '/' + d[1][1]]
test = [d[0] + '/' + d[1][0]]
train_DF = createTbl(train, isBin=False)
test_df = createTbl(test, isBin=False)
self.headers = train_DF.headers
write2file(rows(test_df), fname='before_cpm') # save file
"""
Apply Learner
"""
if planner == 'xtrees':
newTab = xtrees(train=train,
test=test,
bin=False,
majority=True,
name=name).main(justDeltas=True)
delta.append(
[d for d in self.delta1(newTab, train_DF.headers, norm=len(predRows))])
return np.array(
np.sum(delta[0], axis=0), dtype='float') / np.size(newTab, axis=0)
if planner == 'DTREE':
newTab = xtrees(train=train,
test=test,
bin=False,
majority=False,
name=name).main(justDeltas=True)
delta.append(
[d for d in self.delta1(newTab, train_DF.headers, norm=len(predRows))])
return np.array(
np.sum(delta[0], axis=0), dtype='float') / np.size(newTab, axis=0)
if planner == 'BIC':
newTab = HOW(name, justDeltas=True)
delta.append(
[d for d in self.delta1(newTab, train_DF.headers, norm=len(predRows))])
return np.array(
np.sum(delta[0], axis=0), dtype='float') / np.size(newTab, axis=0)
if planner == 'CD':
newTab = strawman(name=name,
train=train,
test=test).main(mode="config", justDeltas=True)
delta.append(
[d for d in self.delta1(newTab, train_DF.headers, norm=len(predRows))])
return np.array(
np.sum(delta[0], axis=0), dtype='float') / np.size(newTab, axis=0)
if planner == 'CD+FS':
newTab = strawman(name=name,
train=train,
test=test,
prune=True).main(mode="config", justDeltas=True)
delta.append(
[d for d in self.delta1(newTab, train_DF.headers, norm=len(predRows))])
return np.array(
np.sum(delta[0], axis=0), dtype='float') / np.size(newTab, axis=0)