def createTbl(
data,
settings=None,
_smote=False,
isBin=False,
bugThres=1,
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
# print("WHERE start")
tree = where2(m, m._rows) # Decision tree using where2
# print tree
# import pdb
# pdb.set_trace()
# print("WHERE end")
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)))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
return newTable(tbl, headerLabel, Rows)
def createTbl(data,
settings=None,
_smote=False,
isBin=False,
bugThres=1,
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
# print("WHERE start")
tree = where2(m, m._rows) # Decision tree using where2
# print tree
# import pdb
# pdb.set_trace()
# print("WHERE end")
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)))
j.__dict__.update({'cells': tmp})
Rows.append(j.cells)
return newTable(tbl, headerLabel, Rows)
def csv2py(self, filename, _smote=False, duplicate=False):
"Convert a csv file to a model file"
tbl = table(filename)
# if _smote:
# tbl = smote.SMOTE(
# tbl,
# atleast=50,
# atmost=101,
# bugIndx=1,
# resample=duplicate)
self.str2num(tbl)
tonum = lambda x: self.translate[x] if isinstance(x, str) else x
""" There's a bug in table.py that doesn't separate dependent and independent
Variable. The following, badly written, piece of code corrects for it...
"""
for indx, k in enumerate(tbl.indep):
for l in tbl.depen:
if k.name == l.name:
tbl.indep.pop(indx)
return self.data(indep=[i.name for i in tbl.indep],
less=[i.name for i in tbl.depen],
_rows=map(lambda x: [tonum(xx) for xx in x.cells],
tbl._rows))
def csv2py(self, filename, _smote=False, duplicate=False):
"Convert a csv file to a model file"
tbl = table(filename)
# if _smote:
# tbl = smote.SMOTE(
# tbl,
# atleast=50,
# atmost=101,
# bugIndx=1,
# resample=duplicate)
self.str2num(tbl)
tonum = lambda x: self.translate[x] if isinstance(x, str) else x
""" There's a bug in table.py that doesn't separate dependent and independent
Variable. The following, badly written, piece of code corrects for it...
"""
for indx, k in enumerate(tbl.indep):
for l in tbl.depen:
if k.name == l.name:
tbl.indep.pop(indx)
return self.data(indep=[i.name for i in tbl.indep],
less=[i.name for i in tbl.depen],
_rows=map(lambda x: [tonum(xx) for xx in x.cells],
tbl._rows))
