EqualWidth = namedtuple("EqualWidth", ["k"])
Remove = namedtuple("Remove", [])
Custom = namedtuple("Custom", ["points"])
METHODS = [(Default, ), (Leave, ), (MDL, ), (EqualFreq, ), (EqualWidth, ),
(Remove, ), (Custom, )]
_dispatch = {
Default:
lambda m, data, var: _dispatch[type(m.method)](m.method, data, var),
Leave:
lambda m, data, var: var,
MDL:
lambda m, data, var: disc.EntropyMDL()(data, var),
EqualFreq:
lambda m, data, var: disc.EqualFreq(m.k)(data, var),
EqualWidth:
lambda m, data, var: disc.EqualWidth(m.k)(data, var),
Remove:
lambda m, data, var: None,
Custom:
lambda m, data, var: disc.Discretizer.create_discretized_var(
var, m.points)
}
# Variable discretization state
DState = namedtuple(
"DState",
[
"method", # discretization method
"points", # induced cut points
()),
MethodDesc(Methods.Keep,
"Keep numeric", "keep",
"Keep the variable as is",
lambda data, var: var,
()),
MethodDesc(Methods.MDL,
"Entropy vs. MDL", "entropy",
"Split values until MDL exceeds the entropy (Fayyad-Irani)\n"
"(requires discrete class variable)",
_mdl_discretization,
()),
MethodDesc(Methods.EqualFreq,
"Equal frequency, intervals: ", "equal freq, k={}",
"Create bins with same number of instances",
lambda data, var, k: disc.EqualFreq(k)(data, var),
("freq_spin", )),
MethodDesc(Methods.EqualWidth,
"Equal width, intervals: ", "equal width, k={}",
"Create bins of the same width",
lambda data, var, k: disc.EqualWidth(k)(data, var),
("width_spin", )),
MethodDesc(Methods.Remove,
"Remove", "remove",
"Remove variable",
lambda *_: None,
()),
MethodDesc(Methods.Binning,
"Natural binning, desired bins: ", "binning, desired={}",
"Create bins with nice thresholds; "
"try matching desired number of bins",