for i in range(data_size):
# how many in this set
set_size = weighted_sample( range(1,10+1), probs=[7187, 1484, 593, 334, 297, 165, 151, 86, 105, 112] )
# get the objects in the current set
s = set(sample_sets_of_objects(set_size, all_objects))
# sample according to the target
if random() < ALPHA: r = WORDS[len(s)-1]
else: r = weighted_sample( WORDS )
# and append the sampled utterance
data.append(FunctionData(input=[s], output=r)) # convert to "FunctionData" and store
return data
# compute a string describing the behavior of this knower-level
def get_knower_pattern(ne):
out = ''
resp = [ ne(set(sample_sets_of_objects(n, all_objects))) for n in xrange(1, 10)]
return ''.join([str(word_to_number[x]) if (x is not None and x is not 'undef') else 'U' for x in resp])
# ============================================================================================================
# All objects -- not very exciting
#here this is really just a dummy -- one type of object, which is replicated in sample_sets_of_objects
all_objects = make_all_objects(shape=['duck'])
# all possible data sets on 10 objects
all_possible_data = [ ('', set(sample_sets_of_objects(n, all_objects))) for n in xrange(1,10) ]
# And finally, add the primitives
for s in SHAPES:
grammar.add_rule('BOOL', 'is_shape_', ['x', q(s)], FEATURE_WEIGHT)
for c in COLORS:
grammar.add_rule('BOOL', 'is_color_', ['x', q(c)], FEATURE_WEIGHT)
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Data
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
from LOTlib.DataAndObjects import FunctionData, make_all_objects
from LOTlib.Miscellaneous import sample_one
all_objects = make_all_objects(shape=SHAPES, color=COLORS)
# Generator for data
# Just import some defaults
from LOTlib.Examples.NAND.TargetConcepts import TargetConcepts
def make_data(N=20, f=TargetConcepts[0]):
data = []
for _ in xrange(N):
o = sample_one(all_objects)
data.append(FunctionData(input=[o], output=f(o), alpha=0.90))
return data
from LOTlib.DataAndObjects import FunctionData, make_all_objects
from LOTlib.Miscellaneous import sample_one
from Grammar import SHAPES, COLORS
# ------------------------------------------------------------------
# Set up the objects
# ------------------------------------------------------------------
all_objects = make_all_objects( shape=SHAPES, color=COLORS )
# ------------------------------------------------------------------
# Generator for data
# ------------------------------------------------------------------
# Just import some defaults
from LOTlib.Examples.NAND.TargetConcepts import TargetConcepts
def make_data(N=20, f=TargetConcepts[0]):
data = []
for _ in xrange(N):
o = sample_one(all_objects)
data.append(FunctionData(input=[o], output=f(o), alpha=0.90))
return data
# get the objects in the current set
s = set(sample_sets_of_objects(set_size, all_objects))
# sample according to the target
if random() < alpha:
r = WORDS[len(s) - 1]
else:
r = weighted_sample(WORDS)
# and append the sampled utterance
data.append(FunctionData(input=[s], output=r, alpha=alpha))
return data
# here this is really just a dummy -- one type of object, which is replicated in sample_sets_of_objects
all_objects = make_all_objects(shape=["duck"])
# all possible data sets on 10 objects
all_possible_data = [("", set(sample_sets_of_objects(n, all_objects))) for n in xrange(1, 10)]
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Grammar
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
from LOTlib.Grammar import Grammar
from LOTlib.Miscellaneous import q
# The priors here are somewhat hierarchical by type in generation, tuned to be a little more efficient
# (but the actual RR prior does not care about these probabilities)
grammar = Grammar()
with open('HypothesisSpace.pkl', 'r') as f:
hypotheses = list(pickle.load(f))
print "# Loaded hypotheses: ", len(hypotheses)
'''
# For now, we'll just sample from the prior
hypotheses = set([RationalRulesLOTHypothesis(grammar=grammar, maxnodes=100) for _ in xrange(20)])
for h in hypotheses:
print h
from LOTlib.DataAndObjects import make_all_objects
objects = make_all_objects(size=['miniature', 'intermediate', 'colossal'],
color=['cinnabar', 'viridian', 'cerulean'],
shape=['rhombus', 'pentagon', 'dodecahedron'])
data = make_data(dataset=['A', 'B'])
L = [[h.compute_likelihood(dp) for h in hypotheses] for dp in data]
# Store the likelihoods for visualization
with open('Viz/Likelihoods_' + MODEL + '.csv', 'w') as f:
lines = []
for l in L:
lines.extend('\n'.join([str(x) for x in l]))
lines.extend('\n')
f.writelines(lines)
# We'll use this to simulate the humans
def human(objs, attr=['color'], value=['cinnabar'], n=200, groups=1):
nyes = []
# Decide which rules to use
which_rules = [r for r in grammar if r.nt not in ['START']]
counts, sig2idx, prior_offset = create_counts(grammar, hypotheses, which_rules=which_rules)
print "# Computed counts for each hypothesis & nonterminal"
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Load the human data
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
from LOTlib.DataAndObjects import make_all_objects
objects = make_all_objects(size=['small', 'medium', 'large'],
color=['red', 'green', 'blue'],
shape=['square', 'triangle', 'circle'])
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# The data that learners observed
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
data = [FunctionData(input=[Obj(size='small', color='green', shape='square')], output=True, alpha=0.99),
FunctionData(input=[Obj(size='large', color='red', shape='triangle')], output=False, alpha=0.99)]
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Human data, we'll simulate on all objects
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
NYes = []
NNo = []
range(1, 10 + 1),
probs=[7187, 1484, 593, 334, 297, 165, 151, 86, 105, 112])
# get the objects in the current set
s = set(sample_sets_of_objects(set_size, all_objects))
# sample according to the target
if random() < alpha: r = WORDS[len(s) - 1]
else: r = weighted_sample(WORDS)
# and append the sampled utterance
data.append(FunctionData(input=[s], output=r, alpha=alpha))
return data
#here this is really just a dummy -- one type of object, which is replicated in sample_sets_of_objects
all_objects = make_all_objects(shape=['duck'])
# all possible data sets on 10 objects
all_possible_data = [('', set(sample_sets_of_objects(n, all_objects)))
for n in xrange(1, 10)]
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Grammar
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
from LOTlib.Grammar import Grammar
from LOTlib.Miscellaneous import q
# The priors here are somewhat hierarchical by type in generation, tuned to be a little more efficient
# (but the actual RR prior does not care about these probabilities)
from LOTlib.GrammarInference.Precompute import create_counts
trees = [h.value for h in hypotheses]
nt2counts, sig2idx, prior_offset = create_counts(grammar, trees, log=None)
print "# Computed counts for each hypothesis & nonterminal"
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Load the human data
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
from LOTlib.DataAndObjects import make_all_objects
objects = make_all_objects(size=['small', 'medium', 'large'],
color=['red', 'green', 'blue'],
shape=['square', 'triangle', 'circle'])
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# The data that learners observed
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
data = [FunctionData(input=[Obj(size='small', color='green', shape='square')], output=True, alpha=0.99),
FunctionData(input=[Obj(size='large', color='red', shape='triangle')], output=False, alpha=0.99)]
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Human data, we'll simulate on all objects
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
NYes = []
NNo = []
print "# Loaded hypotheses: ", len(hypotheses)
'''
# For now, we'll just sample from the prior
hypotheses = set([
RationalRulesLOTHypothesis(grammar=grammar, maxnodes=100)
for _ in xrange(20)
])
for h in hypotheses:
print h
from LOTlib.DataAndObjects import make_all_objects
objects = make_all_objects(size=['miniature', 'intermediate', 'colossal'],
color=['cinnabar', 'viridian', 'cerulean'],
shape=['rhombus', 'pentagon', 'dodecahedron'])
data = make_data(dataset=['A', 'B'])
L = [[h.compute_likelihood(dp) for h in hypotheses] for dp in data]
# Store the likelihoods for visualization
with open('Viz/Likelihoods_' + MODEL + '.csv', 'w') as f:
lines = []
for l in L:
lines.extend('\n'.join([str(x) for x in l]))
lines.extend('\n')
f.writelines(lines)
# We'll use this to simulate the humans
def human(objs, attr=['color'], value=['cinnabar'], n=200, groups=1):
nyes = []