def _test():
tbl_loc = explore(dir='../data.dat/Seigmund/', name='Apache')
tbl = csv2DF(tbl_loc)
# Define Tree settings
opt = Thing(min=1,
maxLvL=10,
infoPrune=0.5,
klass=-1,
prune=False,
debug=True,
verbose=True)
# Build a tree
tree = dtree(tbl, opt=opt)
# Show the tree
if opt.verbose: show(tree)
# ----- Debug? -----
if opt.debug: set_trace()
def dtree(tbl,
rows=None,
lvl=-1,
asIs=10**32,
up=None,
klass=-1,
branch=[],
f=None,
val=None,
opt=None):
if not opt:
opt = Thing(min=1,
maxLvL=10,
infoPrune=0.5,
klass=-1,
prune=True,
debug=True,
verbose=True)
here = Thing(t=tbl,
kids=[],
f=f,
val=val,
up=up,
lvl=lvl,
rows=rows,
modes={},
branch=branch)
features = fWeight(tbl)
if opt.prune and lvl < 0:
features = fWeight(tbl)[:int(len(features) * opt.infoPrune)]
name = features.pop(0)
remaining = tbl[features + [tbl.columns[opt.klass]]]
feature = tbl[name].values
klass = tbl[tbl.columns[opt.klass]].values
N = len(klass)
here.score = np.mean(klass)
splits = discretize(feature, klass)
LO, HI = min(feature), max(feature)
def pairs(lst):
while len(lst) > 1:
yield (lst.pop(0), lst[0])
cutoffs = [t for t in pairs(sorted(list(set(splits + [LO, HI]))))]
if lvl > (opt.maxLvL if opt.prune else int(len(features) * opt.infoPrune)):
return here
if asIs == 0:
return here
if len(features) < 1:
return here
def rows():
for span in cutoffs:
new = []
for f, row in zip(feature, remaining.values.tolist()):
if span[0] <= f < span[1]:
new.append(row)
elif f == span[1] == HI:
new.append(row)
yield pd.DataFrame(new, columns=remaining.columns), span
def ent(x):
C = Counter(x)
N = len(x)
return sum([-C[n] / N * np.log(C[n] / N) for n in C.keys()])
for child, span in rows():
n = child.shape[0]
toBe = ent(child[child.columns[opt.klass]])
if opt.min <= n < N:
here.kids += [
dtree(child,
lvl=lvl + 1,
asIs=toBe,
up=here,
branch=branch + [(name, span)],
f=name,
val=span,
opt=opt)
]
return here
def dtree2(tbl, rows=None, lvl=-1, asIs=10 ** 32, up=None, klass = -1, branch=[],
f=None, val=None, opt=None):
"""
Discrete independent variables
"""
if not opt:
opt = Thing(
min=1,
maxLvL=10,
infoPrune=1,
klass=-1,
prune=True,
debug=True,
verbose=True)
here = Thing(t=tbl, kids=[], f=f, val=val, up=up, lvl=lvl
, rows=rows, modes={}, branch=branch)
features = fWeight(tbl)
if opt.prune and lvl<0:
features = fWeight(tbl)[:int(len(features)*opt.infoPrune)]
name = features.pop(0)
remaining = tbl[features+[tbl.columns[opt.klass]]]
feature = tbl[name].values
klass = tbl[tbl.columns[opt.klass]].values
N = len(klass)
here.score = np.mean(klass)
splits = discretize(feature, klass, discrete=True)
LO, HI = min(feature), max(feature)
def pairs(lst):
while len(lst)>1:
yield (lst.pop(0), lst[0])
cutoffs = [LO, HI]
# set_trace()
if lvl>(opt.maxLvL if opt.prune else int(len(features)*opt.infoPrune)):
return here
if asIs == 0:
return here
if len(features)<1:
return here
def rows():
for span in cutoffs:
new=[]
for f, row in zip(feature, remaining.values.tolist()):
if f==span:
new.append(row)
yield pd.DataFrame(new,columns=remaining.columns), span
def ent(x):
C = Counter(x)
N = len(x)
return sum([-C[n]/N*np.log(C[n]/N) for n in C.keys()])
for child, span in rows():
# set_trace()
n = child.shape[0]
toBe = ent(child[child.columns[opt.klass]])
if opt.min<=n<N:
here.kids += [dtree2(child, lvl=lvl + 1, asIs=toBe, up=here
, branch= branch + [(name, span)]
, f=name, val=(span, span), opt=opt)]
return here
def dtree2(tbl,
rows=None,
lvl=-1,
asIs=10**32,
up=None,
klass=-5,
branch=[],
f=None,
val=None,
opt=None,
encode=True):
"""
Discrete independent variables
"""
if not opt:
opt = Thing(min=1,
maxLvL=10,
infoPrune=1,
klass=-1,
prune=True,
debug=True,
verbose=True)
features = fWeight(tbl)
# if encode==True:
# encode(tbl, features, opt=opt)
here = Thing(t=tbl,
kids=[],
f=f,
val=val,
up=up,
lvl=lvl,
rows=rows,
modes={},
branch=branch)
if opt.prune and lvl < 0:
features = fWeight(tbl)[:int(len(features) * opt.infoPrune)]
name = features.pop(0)
remaining = tbl[features + [tbl.columns[opt.klass]]]
feature = tbl[name].values
klass = tbl[tbl.columns[opt.klass:]].values
N = len(klass)
here.score = np.mean(klass, axis=0)
# splits = discretize(feature, klass, discrete=True)
LO, HI = min(feature), max(feature)
def pairs(lst):
while len(lst) > 1:
yield (lst.pop(0), lst[0])
cutoffs = [LO, HI]
# set_trace()
if lvl > (opt.maxLvL if opt.prune else int(len(features) * opt.infoPrune)):
return here
if asIs < 0.1:
return here
if len(features) < 1:
return here
def rows():
for span in cutoffs:
new = []
for f, row in zip(feature, remaining.values.tolist()):
if f == span:
new.append(row)
yield pd.DataFrame(new, columns=remaining.columns), span
ent = lambda x: sum([
-Counter[n] / len(x) * np.log(Counter[n] / len(x))
for n in Counter.keys()
])
sdv = lambda x: np.mean(np.var(x, axis=0))
for child, span in rows():
# set_trace()
n = child.shape[0]
toBe = sdv(child[child.columns[opt.klass]])
if opt.min <= n < N:
here.kids += [
dtree2(child,
lvl=lvl + 1,
asIs=toBe,
up=here,
branch=branch + [(name, span)],
f=name,
val=(span, span),
opt=opt,
encode=False)
]
return here
def _tree_builder(self,
tbl,
rows=None,
lvl=-1,
asIs=10**32,
up=None,
klass=-1,
branch=[],
f=None,
val=None,
opt=None):
here = Thing(t=tbl,
kids=[],
f=f,
val=val,
up=up,
lvl=lvl,
rows=rows,
modes={},
branch=branch)
features = fWeight(tbl)
if self.prune and lvl < 0:
features = fWeight(tbl)[:int(len(features) * self.infoPrune)]
name = features.pop(0)
remaining = tbl[features + [tbl.columns[self.klass]]]
feature = tbl[name].values
klass = tbl[tbl.columns[self.klass]].values
N = len(klass)
here.score = np.mean(klass)
splits = discretize(feature, klass)
lo, hi = min(feature), max(feature)
def _pairs(lst):
while len(lst) > 1:
yield (lst.pop(0), lst[0])
cutoffs = [t for t in _pairs(sorted(list(set(splits + [lo, hi]))))]
if lvl > (self.max_level if self.prune else int(
len(features) * self.infoPrune)):
return here
if asIs == 0:
return here
if len(features) < 1:
return here
def _rows():
for span in cutoffs:
new = []
for f, row in zip(feature, remaining.values.tolist()):
if span[0] <= f < span[1]:
new.append(row)
elif f == span[1] == hi:
new.append(row)
yield pd.DataFrame(new, columns=remaining.columns), span
def _entropy(x):
C = Counter(x)
N = len(x)
return sum([-C[n] / N * np.log(C[n] / N) for n in C.keys()])
for child, span in _rows():
n = child.shape[0]
toBe = _entropy(child[child.columns[self.klass]])
if self.min <= n < N:
here.kids += [
self._tree_builder(child,
lvl=lvl + 1,
asIs=toBe,
up=here,
branch=branch + [(name, span)],
f=name,
val=span,
opt=opt)
]
return here