def parse_and_augment_proof_step(self, proof_step, out=True):
''' this gets the data for the proof step, but also does the
randomization and the augmentation. There are a number of
strange choices in the augmentation, particularly with keeping
track of the distinct unconstrained variables but we'll leave
them as is for now. '''
prop = proof_step.prop
# figure out the unconstrained variables in prop, create
# the corresponding replacement rules and such.
# Eventually I'll distinguish the different non-target variables
# but that is a task for another day.
unconstrained_variables = prop.unconstrained_variables
uv_dict = {var:'UC' for var in unconstrained_variables}
target_index = np.random.choice(len(unconstrained_variables))
target_variable = unconstrained_variables[target_index]
uv_dict[target_variable] = 'TARGET_UC'
if out: self.out_tree = proof_step.unconstrained[target_index].copy()
# figure out the fit of prop to the proof step.
# now all the variables should be in fit or in uv_dict
fit = data_utils.prop_applies_to_statement(
proof_step.tree, prop, proof_step.context)
self.to_prove_trees = [hyp.tree.copy().replace(fit).replace_values(uv_dict)
for hyp in prop.hyps if hyp.type == 'e']
self.known_trees = [hyp.tree.copy()
for hyp in proof_step.context.hyps if hyp.type == 'e']
# now generate a random replacement dictionary
random_replacement_dict = self.config.lm.random_replacement_dict_f(f=proof_step.context.f)
self.random_replacement_dict = random_replacement_dict
# perform the replacements
if out: self.out_tree.replace_values(random_replacement_dict)
for tree in self.to_prove_trees:
tree.replace_values(random_replacement_dict)
for tree in self.known_trees:
tree.replace_values(random_replacement_dict)
# and get the graph structures
self.known_graph_structure = TreeInformation(self.known_trees,
start_symbol=None, intermediate_symbol='END_OF_HYP',
end_symbol='END_OF_SECTION')
self.to_prove_graph_structure = TreeInformation(self.to_prove_trees,
start_symbol=None, intermediate_symbol='END_OF_HYP',
end_symbol='END_OF_SECTION')
if out: self.out_graph_structure = TreeInformation([self.out_tree],
start_symbol='START_OUTPUT', intermediate_symbol=None,
end_symbol=None)
def parse_and_augment_proof_step(self, proof_step, out=True):
''' this gets the data for the proof step, but also does the
randomization and the augmentation. There are a number of
strange choices in the augmentation, particularly with keeping
track of the distinct unconstrained variables but we'll leave
them as is for now. '''
prop = proof_step.prop
# figure out the unconstrained variables in prop, create
# the corresponding replacement rules and such.
# Eventually I'll distinguish the different non-target variables
# but that is a task for another day.
unconstrained_variables = prop.unconstrained_variables
uv_dict = {var:'UC' for var in unconstrained_variables}
target_index = np.random.choice(len(unconstrained_variables))
target_variable = unconstrained_variables[target_index]
uv_dict[target_variable] = 'TARGET_UC'
if out: self.out_tree = proof_step.unconstrained[target_index].copy()
# figure out the fit of prop to the proof step.
# now all the variables should be in fit or in uv_dict
fit = data_utils.prop_applies_to_statement(
proof_step.tree, prop, proof_step.context)
self.to_prove_trees = [hyp.tree.copy().replace(fit).replace_values(uv_dict)
for hyp in prop.hyps if hyp.type == 'e']
self.known_trees = [hyp.tree.copy()
for hyp in proof_step.context.hyps if hyp.type == 'e']
# now generate a random replacement dictionary
random_replacement_dict = self.config.lm.random_replacement_dict_f(f=proof_step.context.f)
self.random_replacement_dict = random_replacement_dict
# perform the replacements
if out: self.out_tree.replace_values(random_replacement_dict)
for tree in self.to_prove_trees:
tree.replace_values(random_replacement_dict)
for tree in self.known_trees:
tree.replace_values(random_replacement_dict)
# and get the graph structures
self.known_graph_structure = TreeInformation(self.known_trees,
start_symbol=None, intermediate_symbol='END_OF_HYP',
end_symbol='END_OF_SECTION')
self.to_prove_graph_structure = TreeInformation(self.to_prove_trees,
start_symbol=None, intermediate_symbol='END_OF_HYP',
end_symbol='END_OF_SECTION')
if out: self.out_graph_structure = TreeInformation([self.out_tree],
start_symbol='START_OUTPUT', intermediate_symbol=None,
end_symbol=None)
def get_correct(context, t):
'''
gets the correct hypotheses from this context.
context is the un-standardized context
'''
prop = t.prop
fit = data.prop_applies_to_statement(t.tree, prop, context)
#print fit
assert fit is not None # the correct fit needs to work
for var, tree in zip(prop.unconstrained_variables, t.unconstrained):
fit[var] = tree
hyps = [h.tree.copy().replace(fit) for h in prop.hyps if h.type == 'e']
#print 'hyps', hyps
return hyps
def get_correct(context, t):
'''
gets the correct hypotheses from this context.
context is the un-standardized context
'''
prop = t.prop
fit = data.prop_applies_to_statement(t.tree, prop, context)
#print fit
assert fit is not None # the correct fit needs to work
for var, tree in zip(prop.unconstrained_variables, t.unconstrained):
fit[var] = tree
hyps = [h.tree.copy().replace(fit) for h in prop.hyps if h.type == 'e']
#print 'hyps', hyps
return hyps
def __init__(self, tree, context, prop, config, vs, args, gen_model,
allowed_constructors=None, beam_search_state=None,
return_replacement_dict=False, gt_step=None):
'''
init just builds the beam search state, and we'll use it for copying
inputs:
vs: a set of variable objects, for all the models we
are ensembling over
config: the config object
beam_search_state: a BeamSearchState to copy
'''
self.request = []
self.total_symbols = 0 if beam_search_state is None else beam_search_state.total_symbols
self.return_replacement_dict = return_replacement_dict if beam_search_state is None else beam_search_state.return_replacement_dict
# basic configuration stuff
self.random_replacement_dict = None if beam_search_state is None else beam_search_state.random_replacement_dict
self.args = args if beam_search_state is None else beam_search_state.args
self.gen_model = gen_model if beam_search_state is None else beam_search_state.gen_model
self.vs = vs if beam_search_state is None else beam_search_state.vs
self.config = config if beam_search_state is None else beam_search_state.config
self.lm = self.config.lm
self.tree = tree if beam_search_state is None else beam_search_state.tree
self.context = context if beam_search_state is None else beam_search_state.context
self.prop = prop if beam_search_state is None else beam_search_state.prop
self.value = 0 if beam_search_state is None else beam_search_state.value
self.complete = False if beam_search_state is None else beam_search_state.complete
self.gt_step = gt_step if beam_search_state is None else beam_search_state.gt_step
self.gt_string = None if beam_search_state is None else beam_search_state.gt_string
self.allowed_constructors = (self.get_all_allowed_symbols(allowed_constructors)
if beam_search_state is None
else beam_search_state.allowed_constructors)
# the current state (non-vector)
self.string = [] if beam_search_state is None else beam_search_state.string[:]
self.position_into_arity_stack = [0] if beam_search_state is None else beam_search_state.position_into_arity_stack[:]
self.parent_arity_stack = [-1] if beam_search_state is None else beam_search_state.parent_arity_stack[:]
self.complete = False if beam_search_state is None else beam_search_state.complete
self.next_symbol = None if beam_search_state is None else beam_search_state.next_symbol
# information about the current state vectors
self.h = None if beam_search_state is None else beam_search_state.h
self.parent_stack = [None] if beam_search_state is None else beam_search_state.parent_stack[:]
self.left_sibling_stack = [None] if beam_search_state is None else beam_search_state.left_sibling_stack[:]
self.logits = None if beam_search_state is None else beam_search_state.logits
self.logit_order = None if beam_search_state is None else beam_search_state.logit_order
self.parent_symbol_stack = None if beam_search_state is None else beam_search_state.parent_symbol_stack[:]
# the information for returning symbols
# this is immediately forgotten
self.returned_symbols = 0 # this state information dies when we copy.
self.exhausted = False
self.new_wff_added = not PERMIT_NEW_WFFS
self.new_set_added = not PERMIT_NEW_SETS
self.new_class_added = not PERMIT_NEW_CLASSES
self.next_vclass = None
# information about the current model
# this is kept until we move to the next unconstrained variable
self.current_models = None if beam_search_state is None else beam_search_state.current_models
self.disallowed_symbols = None if beam_search_state is None else beam_search_state.disallowed_symbols
#self.used_symbols = context.hyp_symbols.copy() if beam_search_state is None else beam_search_state.used_symbols.copy()
self.used_symbols = context.hyp_symbols if beam_search_state is None else beam_search_state.used_symbols.copy()
self.this_ua = None if beam_search_state is None else beam_search_state.this_ua
self.model_complete = True if beam_search_state is None else beam_search_state.model_complete
if beam_search_state is None:
self.fit = data_utils.prop_applies_to_statement(tree, prop, context)
self.fit_initial = self.fit.copy()
self.remaining_uas = [x.label for x in prop.hyps if x.type=='f' and x.label not in self.fit]
#print (self.remaining_uas)
np.random.shuffle(self.remaining_uas)
self.set_up_next_model()
if not self.complete:
self.determine_next_vclass()
else:
self.remaining_uas = beam_search_state.remaining_uas[:]
self.fit = beam_search_state.fit.copy()
self.fit_initial = beam_search_state.fit_initial.copy()
def __init__(self, tree, context, prop, config, vs,
allowed_constructors=None, beam_search_state=None,
return_replacement_dict=False):
'''
init just builds the beam search state, and we'll use it for copying
inputs:
vs: a set of variable objects, for all the models we
are ensembling over
config: the config object
beam_search_state: a BeamSearchState to copy
'''
self.total_symbols = 0 if beam_search_state is None else beam_search_state.total_symbols
self.return_replacement_dict = return_replacement_dict if beam_search_state is None else beam_search_state.return_replacement_dict
# basic configuration stuff
self.vs = vs if beam_search_state is None else beam_search_state.vs
self.config = config if beam_search_state is None else beam_search_state.config
self.lm = self.config.lm
self.tree = tree if beam_search_state is None else beam_search_state.tree
self.context = context if beam_search_state is None else beam_search_state.context
self.prop = prop if beam_search_state is None else beam_search_state.prop
self.value = 0 if beam_search_state is None else beam_search_state.value
self.complete = False if beam_search_state is None else beam_search_state.complete
self.allowed_constructors = (self.get_all_allowed_symbols(allowed_constructors)
if beam_search_state is None
else beam_search_state.allowed_constructors)
# the current state (non-vector)
self.string = [] if beam_search_state is None else beam_search_state.string[:]
self.position_into_arity_stack = [0] if beam_search_state is None else beam_search_state.position_into_arity_stack[:]
self.parent_arity_stack = [-1] if beam_search_state is None else beam_search_state.parent_arity_stack[:]
self.complete = False if beam_search_state is None else beam_search_state.complete
self.next_symbol = None if beam_search_state is None else beam_search_state.next_symbol
# information about the current state vectors
self.h = None if beam_search_state is None else beam_search_state.h
self.parent_stack = [None] if beam_search_state is None else beam_search_state.parent_stack[:]
self.left_sibling_stack = [None] if beam_search_state is None else beam_search_state.left_sibling_stack[:]
self.logits = None if beam_search_state is None else beam_search_state.logits
self.logit_order = None if beam_search_state is None else beam_search_state.logit_order
self.parent_symbol_stack = None if beam_search_state is None else beam_search_state.parent_symbol_stack[:]
# the information for returning symbols
# this is immediately forgotten
self.returned_symbols = 0 # this state information dies when we copy.
self.exhausted = False
self.new_wff_added = not PERMIT_NEW_WFFS
self.new_set_added = not PERMIT_NEW_SETS
self.new_class_added = not PERMIT_NEW_CLASSES
self.next_vclass = None
# information about the current model
# this is kept until we move to the next unconstrained variable
self.current_models = None if beam_search_state is None else beam_search_state.current_models
self.disallowed_symbols = None if beam_search_state is None else beam_search_state.disallowed_symbols
#self.used_symbols = context.hyp_symbols.copy() if beam_search_state is None else beam_search_state.used_symbols.copy()
self.used_symbols = context.hyp_symbols if beam_search_state is None else beam_search_state.used_symbols.copy()
self.this_ua = None if beam_search_state is None else beam_search_state.this_ua
self.model_complete = True if beam_search_state is None else beam_search_state.model_complete
if beam_search_state is None:
self.fit = data_utils.prop_applies_to_statement(tree, prop, context)
self.remaining_uas = [x.label for x in prop.hyps if x.type=='f' and x.label not in self.fit]
np.random.shuffle(self.remaining_uas)
self.set_up_next_model()
if not self.complete:
self.determine_next_vclass()
else:
self.remaining_uas = beam_search_state.remaining_uas[:]
self.fit = beam_search_state.fit.copy()
