def createTbl(data,
settings=None,
_smote=False,
isBin=False,
bugThres=2,
duplicate=False):
"""
kwargs:
_smote = True/False : SMOTE input data (or not)
_isBin = True/False : Reduce bugs to defects/no defects
_bugThres = int : Threshold for marking stuff as defective,
default = 1. Not defective => Bugs < 1
"""
makeaModel = makeAmodel.makeAModel()
_r = []
for t in data:
m = makeaModel.csv2py(t, _smote=_smote, duplicate=duplicate)
_r += m._rows
m._rows = _r
prepare(m, settings=None) # Initialize all parameters for where2 to run
tree = where2(m, m._rows) # Decision tree using where2
tbl = table(t)
headerLabel = '=klass'
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = j.cells
if isBin:
tmp[-1] = 0 if tmp[-1] < bugThres else 1
tmp.append('_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
return newTable(tbl, headerLabel, Rows)
def createTbl(
data, settings=None, _smote=False, isBin=False, bugThres=2, duplicate=False):
"""
kwargs:
_smote = True/False : SMOTE input data (or not)
_isBin = True/False : Reduce bugs to defects/no defects
_bugThres = int : Threshold for marking stuff as defective,
default = 1. Not defective => Bugs < 1
"""
makeaModel = makeAmodel.makeAModel()
_r = []
for t in data:
m = makeaModel.csv2py(t, _smote=_smote, duplicate=duplicate)
_r += m._rows
m._rows = _r
prepare(m, settings=None) # Initialize all parameters for where2 to run
tree = where2(m, m._rows) # Decision tree using where2
tbl = table(t)
headerLabel = '=klass'
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = j.cells
if isBin:
tmp[-1] = 0 if tmp[-1] < bugThres else 1
tmp.append('_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
return newTable(tbl, headerLabel, Rows)
def tdivPrec(where=None, dtree=None, train=None, test=None):
rseed(1)
makeaModel = makeAModel()
# pdb.set_trace()
"""
Training
"""
_r = []
for t in train:
m = makeaModel.csv2py(t)
_r += m._rows
m._rows = _r
prepare(m, settings=where) # Initialize all parameters for where2 to run
tree = where2(m, m._rows) # Decision tree using where2
tbl = table(t)
headerLabel = '=klass'
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = (j.cells)
tmp.append('_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
tbl2 = newTable(tbl, headerLabel, Rows)
"""
Testing
"""
_r = []
for tt in test:
mTst = makeaModel.csv2py(tt)
_r += mTst._rows
mTst._rows = _r
prepare(mTst,
settings=where) # Initialize all parameters for where2 to run
tree = where2(mTst, mTst._rows) # Decision tree using where2
tbl = table(tt)
headerLabel = '=klass'
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = (j.cells)
tmp.append('_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
tbl3 = newTable(tbl, headerLabel, Rows)
temp = []
def sort(lst):
return [i[0] for i in sorted(enumerate(lst), key = lambda x:x[1])], \
[i[1] for i in sorted(enumerate(lst), key = lambda x:x[1])]
def thresh(val1, val2):
indx, sorted = sort()
def isdefective(case, test=False):
def createDF(data):
makeaModel = makeAModel()
_r = []
for t in data:
m = makeaModel.csv2py(t)
_r += m._rows
m._rows = _r
prepare(m)
tree = where2(m, m._rows)
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = (j.cells)
tmp.append('Class_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
return pd.DataFrame(Rows, columns=get_headers(data) + ['klass'])
def createDF(data):
makeaModel = makeAModel()
_r = []
for t in data:
m = makeaModel.csv2py(t)
_r += m._rows
m._rows = _r
prepare(m)
tree = where2(m, m._rows)
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = (j.cells)
tmp.append('Class_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
return pd.DataFrame(Rows, columns = get_headers(data) + ['klass'])
def createTbl(data):
makeaModel = makeAModel()
_r = []
for t in data:
m = makeaModel.csv2py(t)
_r += m._rows
m._rows = _r
prepare(m, settings=None) # Initialize all parameters for where2 to run
tree = where2(m, m._rows) # Decision tree using where2
tbl = table(t)
headerLabel = '=klass'
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = (j.cells)
tmp.append('_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
return newTable(tbl, headerLabel, Rows)
def createTbl(data):
makeaModel = makeAModel()
_r = []
for t in data:
m = makeaModel.csv2py(t)
_r += m._rows
m._rows = _r
prepare(m, settings = None) # Initialize all parameters for where2 to run
tree = where2(m, m._rows) # Decision tree using where2
tbl = table(t)
headerLabel = '=klass'
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = (j.cells)
tmp.append('_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
return newTable(tbl, headerLabel, Rows)
def tdivPrec(where = None , dtree = None, train = None, test = None):
rseed(1)
makeaModel = makeAModel()
# pdb.set_trace()
"""
Training
"""
_r = []
for t in train:
m = makeaModel.csv2py(t)
_r += m._rows
m._rows = _r
prepare(m, settings = where) # Initialize all parameters for where2 to run
tree = where2(m, m._rows) # Decision tree using where2
tbl = table(t)
headerLabel = '=klass'
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = (j.cells)
tmp.append('_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
tbl2 = newTable(tbl, headerLabel, Rows)
"""
Testing
"""
_r = []
for tt in test:
mTst = makeaModel.csv2py(tt)
_r += mTst._rows
mTst._rows = _r
prepare(mTst, settings = where) # Initialize all parameters for where2 to run
tree = where2(mTst, mTst._rows) # Decision tree using where2
tbl = table(tt)
headerLabel = '=klass'
Rows = []
for k, _ in leaves(tree): # for k, _ in leaves(tree):
for j in k.val:
tmp = (j.cells)
tmp.append('_' + str(id(k) % 1000))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
tbl3 = newTable(tbl, headerLabel, Rows)
temp = []
def sort(lst):
return [i[0] for i in sorted(enumerate(lst), key = lambda x:x[1])], \
[i[1] for i in sorted(enumerate(lst), key = lambda x:x[1])]
def thresh(val1, val2):
indx, sorted = sort()
def isdefective(case, test = False):
if not test:
return 'Defect' if case.cells[-2] > 0 else 'No Defect'
else:
bugs = [r.cells[-2] for r in case.rows];
meanBugs = np.mean(bugs);
medianBugs = np.median(bugs);
rangeBugs = (sorted(bugs)[0] + sorted(bugs)[-1]) / 2;
temp.append(meanBugs);
return 'Defect' if meanBugs > 1.5 else 'No Defect'
testCase = tbl3._rows
# print testCase
testDefective = []
defectivClust = []
t = discreteNums(tbl2, map(lambda x: x.cells, tbl2._rows))
myTree = tdiv(t, opt = dtree)
# showTdiv(myTree)
testCase = tbl3._rows
# # print testCase
for tC in testCase:
loc = drop(tC, myTree)
# if len(loc.kids)==0:
testDefective.append(isdefective(tC))
defectivClust.append(isdefective(loc, test = True))
#
saveImg(temp, 10)
# contrastSet = getContrastSet(loc, myTree)
# print 'Contrast Set:', contrastSet
return [testDefective, defectivClust]