def remove_vars(literal):
"""
This removes all variables by putting XXX at the front of the string, so it
cannot be unified anymore.
"""
return tuple('XXX' + ele if is_variable(ele) else
remove_vars(ele) if isinstance(ele, tuple) else ele
for ele in literal)
def generalize_literal(literal, gensym):
"""
This takes a literal and returns the most general version of it possible.
i.e., a version that has all the values replaced with new veriables.
"""
return (literal[0], ) + tuple(ele if is_variable(ele) else
# '?gen%s' % hash(ele)
gensym() for ele in literal[1:])
def successors(self, node):
h = node.state
(constraints, c_length, p_uncovered, n_uncovered, pset, nset,
gensym) = node.extra
# remove literals
for literal in h:
removable = True
for ele in literal[1:]:
if not is_variable(ele):
removable = False
break
if (count_occurances(ele, h) > 1):
removable = False
break
if removable:
new_h = frozenset(x for x in h if x != literal)
new_pset, new_nset = test_coverage(new_h, constraints,
p_uncovered, n_uncovered)
new_p_uncovered = [p for p in p_uncovered if p not in new_pset]
new_n_uncovered = [n for n in n_uncovered if n not in new_nset]
new_c_length = c_length - 1
# new_c_length = clause_length(new_h)
score = self.score(
len(pset) - len(new_p_uncovered),
len(nset) - len(new_n_uncovered), len(pset), len(nset),
new_c_length)
yield Node(new_h,
node, ('remove literal', literal),
-1 * score,
extra=(constraints, new_c_length, new_p_uncovered,
new_n_uncovered, pset, nset, gensym))
# replace constants with variables.
for literal in h:
for new_l in get_variablizations(literal, gensym):
new_h = frozenset([x if x != literal else new_l for x in h])
new_pset, new_nset = test_coverage(new_h, constraints,
p_uncovered, n_uncovered)
new_p_uncovered = [p for p in p_uncovered if p not in new_pset]
new_n_uncovered = [n for n in n_uncovered if n not in new_nset]
new_c_length = c_length - 1
# new_c_length = clause_length(new_h)
score = self.score(
len(pset) - len(new_p_uncovered),
len(nset) - len(new_n_uncovered), len(pset), len(nset),
new_c_length)
yield Node(new_h,
node, ('variablize', literal, new_l),
-1 * score,
extra=(constraints, new_c_length, new_p_uncovered,
new_n_uncovered, pset, nset, gensym))
def count_elements(x, var_counts):
"""
Counts the number of constants and keeps track of variable occurnaces.
"""
c = 0
if isinstance(x, tuple):
c = sum([count_elements(ele, var_counts) for ele in x])
elif is_variable(x):
if x not in var_counts:
var_counts[x] = 0
var_counts[x] += 1
else:
c = 1
return c
def get_variablizations(literal):
"""
Takes a literal and returns all possible variablizations of it. Currently,
this replaces constants only. Also, it replaces them with a variable that
is generated based on the hash of the constant, so that similar constants
map to the same variable.
"""
if isinstance(literal, tuple):
head = literal[0]
possible_bodies = [[e] + list(get_variablizations(e))
for e in literal[1:]]
for body in product(*possible_bodies):
yield (head, ) + tuple(body)
elif not is_variable(literal):
yield '?gen%i' % hash(literal)
def gen_generalizations(self, node):
h = node.state
(constraints, c_length, p_covered, p_uncovered, n_covered, n_uncovered,
gensym) = node.extra
# remove literals
for literal in h:
removable = True
for ele in literal[1:]:
if not is_variable(ele):
removable = False
break
if (count_occurances(ele, h) > 1):
removable = False
break
if removable:
new_h = frozenset(x for x in h if x != literal)
new_pc_subset, new_nc_subset = test_coverage(
new_h, constraints, p_uncovered, n_uncovered)
new_p_covered = p_covered + new_pc_subset
new_n_covered = n_covered + new_nc_subset
new_p_uncovered = [
p for p in p_uncovered if p not in new_pc_subset
]
new_n_uncovered = [
n for n in n_uncovered if n not in new_nc_subset
]
new_c_length = c_length - 1
score = self.score(len(new_p_covered), len(new_p_uncovered),
len(new_n_covered), len(new_n_uncovered),
new_c_length)
yield Node(new_h,
None,
None,
-1 * score,
extra=(constraints, new_c_length, new_p_covered,
new_p_uncovered, new_n_covered,
new_n_uncovered, gensym))
# replace constants with variables.
for literal in h:
for new_l in get_variablizations(literal, gensym):
new_h = frozenset([x if x != literal else new_l for x in h])
new_pc_subset, new_nc_subset = test_coverage(
new_h, constraints, p_uncovered, n_uncovered)
new_p_covered = p_covered + new_pc_subset
new_n_covered = n_covered + new_nc_subset
new_p_uncovered = [
p for p in p_uncovered if p not in new_pc_subset
]
new_n_uncovered = [
n for n in n_uncovered if n not in new_nc_subset
]
new_c_length = c_length - 1
score = self.score(len(new_p_covered), len(new_p_uncovered),
len(new_n_covered), len(new_n_uncovered),
new_c_length)
yield Node(new_h,
None,
None,
-1 * score,
extra=(constraints, new_c_length, new_p_covered,
new_p_uncovered, new_n_covered,
new_n_uncovered, gensym))