def to_rule(self, table, cont_dists=None, disc_dists=None):
"""
@param cols list of attribute names
"""
if not self.rule:
domain = table.domain
attrnames = [attr.name for attr in domain]
cont_dists = cont_dists or dict(zip(attrnames, Orange.statistics.basic.Domain(table)))
disc_dists = disc_dists or dict(zip(attrnames, Orange.statistics.distribution.Domain(table)))
conds = []
for col, bound in zip(self.cols, zip(*self.bbox)):
attr = domain[col]
pos = domain.index(attr)
table_bound = cont_dists[attr.name]
minv, maxv = max(table_bound.min, bound[0]), min(table_bound.max, bound[1])
if maxv - minv > 0.9 * (table_bound.max-table_bound.min):
continue
conds.append(
orange.ValueFilter_continuous(
position=pos,
max=bound[1],
min=bound[0]
)
)
for disc_name, vidxs in self.discretes.iteritems():
attr = domain[disc_name]
disc_pos = domain.index(attr)
vals = [orange.Value(attr, attr.values[int(vidx)]) for vidx in vidxs if int(vidx) < len(attr.values)]
if not vals or len(vals) == len(disc_dists[attr.name]):
continue
conds.append(
orange.ValueFilter_discrete(
position = disc_pos,
values=vals
)
)
rule = SDRule(table, None, conditions=conds)
self.rule = rule
rule = self.rule
rule.quality = rule.score = self.error
rule.inf_state = self.inf_state
rule.c_range = self.c_range
return rule
if not isnumerical:
try:
val = float(val)
except:
val = quote_sql_str(val)
return '%s %s %s' % (attr, cmp, val)
#return '%s is not null and %s %s %s' % (attr, attr, cmp, val)
if __name__ == '__main__':
from learners.cn2sd.rule import SDRule
d = Orange.data.Table('iris')
rule = SDRule(d, d.domain.classVar.values[0])
rule = rule.cloneAndAddContCondition(d.domain[0], 4, 5)
print sdrule_to_clauses(rule)
exit()
import sys
import random
import time
import matplotlib
import matplotlib.pyplot as plt
sys.path.append('.')
from matplotlib.backends.backend_pdf import PdfPages
from collections import Counter