def manualLogoTask(name,
expression,
proto=False,
needToTrain=False,
supervise=False,
lambdaCalculus=False):
p = Program.parse(expression) if lambdaCalculus else parseLogo(expression)
from dreamcoder.domains.logo.logoPrimitives import primitives
from dreamcoder.grammar import Grammar
g = Grammar.uniform(primitives, continuationType=turtle)
gp = Grammar.uniform(primitives)
try:
l = g.logLikelihood(arrow(turtle, turtle), p)
lp = gp.logLikelihood(arrow(turtle, turtle), p)
assert l >= lp
eprint(name, -l, "nats")
except:
eprint("WARNING: could not calculate likelihood of manual logo", p)
attempts = 0
while True:
[output, highresolution] = drawLogo(p,
p,
resolution=[28, 128],
cost=True)
if output == "timeout" or highresolution == "timeout":
attempts += 1
else:
break
if attempts > 0:
eprint(
f"WARNING: Took {attempts} attempts to render task {name} within timeout"
)
cost = output[1]
output = output[0]
assert highresolution[1] == cost
highresolution = highresolution[0]
shape = list(map(int, output))
highresolution = list(map(float, highresolution))
t = Task(name, arrow(turtle, turtle), [(([0]), shape)])
t.mustTrain = needToTrain
t.proto = proto
t.specialTask = ("LOGO", {"proto": proto})
t.specialTask[1]["cost"] = cost * 1.05
t.highresolution = highresolution
if supervise:
t.supervisedSolution = p
return t
def main(args):
"""
Takes the return value of the `commandlineArguments()` function as input and
trains/tests the model on manipulating sequences of numbers.
"""
random.seed(args.pop("random_seed"))
tasks = make_list_bootstrap_tasks()
print(tasks)
maxTasks = args.pop("maxTasks")
if maxTasks and len(tasks) > maxTasks:
eprint("Unwilling to handle {} tasks, truncating..".format(len(tasks)))
random.shuffle(tasks)
del tasks[maxTasks:]
baseGrammar = Grammar.uniform(McCarthyPrimitives())
extractor = {
"learned": LearnedFeatureExtractor,
}[args.pop("extractor")]
extractor.H = args.pop("hidden")
timestamp = datetime.datetime.now().isoformat()
outputDirectory = "experimentOutputs/list/%s" % timestamp
os.system("mkdir -p %s" % outputDirectory)
args.update({
"featureExtractor": extractor,
"outputPrefix": "%s/list" % outputDirectory,
"evaluationTimeout": 0.0005,
})
eprint("Got {} list tasks".format(len(tasks)))
split = args.pop("split")
if split:
train_some = defaultdict(list)
for t in tasks:
# necessary = train_necessary(t)
# if not necessary:
# continue
# if necessary == "some":
# train_some[t.name.split()[0]].append(t)
# else:
t.mustTrain = True
# for k in sorted(train_some):
# ts = train_some[k]
# random.shuffle(ts)
# ts.pop().mustTrain = True
test, train = testTrainSplit(tasks, split)
eprint("Alotted {} tasks for training and {} for testing".format(
len(train), len(test)))
else:
train = tasks
test = []
explorationCompression(baseGrammar, train, testingTasks=test, **args)
def demoLogoTasks():
import scipy.misc
import numpy as np
g0 = Grammar.uniform(primitives, continuationType=turtle)
eprint("dreaming into /tmp/dreams_0...")
N = 1000
programs = [
p for _ in range(N)
for p in [g0.sample(arrow(turtle, turtle), maximumDepth=20)]
if p is not None
]
os.system("mkdir -p /tmp/dreams_0")
for n, p in enumerate(programs):
with open(f"/tmp/dreams_0/{n}.dream", "w") as handle:
handle.write(str(p))
drawLogo(*programs,
pretty=True,
smoothPretty=False,
resolution=512,
filenames=[
f"/tmp/dreams_0/{n}_pretty.png" for n in range(len(programs))
],
timeout=1)
if len(sys.argv) > 1:
tasks = makeTasks(sys.argv[1:], proto=False)
else:
tasks = makeTasks(['all'], proto=False)
montageTasks(tasks, columns=16, testTrain=True)
for n, t in enumerate(tasks):
a = t.highresolution
w = int(len(a)**0.5)
scipy.misc.imsave('/tmp/logo%d.png' % n,
np.array([a[i:i + w] for i in range(0, len(a), w)]))
logo_safe_name = t.name.replace("=", "_").replace(' ', '_').replace(
'/', '_').replace("-", "_") + ".png"
#os.system(f"convert /tmp/logo{n}.png -morphology Dilate Octagon /tmp/{logo_safe_name}")
os.system(
f"convert /tmp/logo{n}.png -channel RGB -negate /tmp/{logo_safe_name}"
)
eprint(len(tasks), "tasks")
eprint(sum(t.mustTrain for t in tasks), "need to be trained on")
for t in dSLDemo():
a = t.highresolution
w = int(len(a)**0.5)
scipy.misc.imsave('/tmp/logoDemo%s.png' % t.name,
np.array([a[i:i + w] for i in range(0, len(a), w)]))
os.system(
f"convert /tmp/logoDemo{t.name}.png -morphology Dilate Octagon /tmp/logoDemo{t.name}_dilated.png"
)
tasks = [t for t in tasks if t.mustTrain]
random.shuffle(tasks)
montageTasks(tasks[:16 * 3], "subset", columns=16)
montageTasks(rotationalSymmetryDemo(), "rotational")
def __init__(self):
args = commandlineArguments(enumerationTimeout=200,
activation='tanh',
iterations=1,
recognitionTimeout=3600,
a=3,
maximumFrontier=5,
topK=2,
pseudoCounts=30.0,
helmholtzRatio=0.5,
structurePenalty=1.,
CPUs=min(numberOfCPUs(), 8),
extras=list_options)
args['noConsolidation'] = True
args.pop("random_seed")
args['contextual'] = True
args['biasOptimal'] = True
args['auxiliaryLoss'] = True
args['activation'] = "relu"
args['useDSL'] = False
extractor = {
"learned": LearnedFeatureExtractor,
}[args.pop("extractor")]
extractor.H = args.pop("hidden")
timestamp = datetime.datetime.now().isoformat()
outputDirectory = "tmp/%s" % timestamp
os.system("mkdir -p %s" % outputDirectory)
args.update({
"featureExtractor": extractor,
"outputPrefix": "%s/hint" % outputDirectory,
"evaluationTimeout": 0.0005,
})
args.pop("maxTasks")
args.pop("split")
self.primitives = McCarthyPrimitives()
baseGrammar = Grammar.uniform(self.primitives)
self.grammar = baseGrammar
self.train_args = args
self.semantics = [Semantics(i) for i in range(len(SYMBOLS))]
self.allFrontiers = None
self.helmholtzFrontiers = None
def update_grammar(self):
programs = [
Invented(smt.program.prog) for smt in self.semantics
if smt.learnable and smt.solved and smt.program is not None
and smt.program.arity > 0 and '#' not in str(smt.program)
]
# if '#' in the program, the program uses a invented primitive, it is very likely to have a high computation cost.
# Therefore we don't add this program into primitives, since it might slow the enumeration a lot.
# it might be resolved by increasing the enumeration time
new_grammar = Grammar.uniform(self.primitives + programs)
# self.train_args['enumerationTimeout'] += 100 * len(programs)
if new_grammar != self.grammar:
self.grammar = new_grammar
self.helmholtzFrontiers = None
self.allFrontiers = None
print(
"Update grammar with invented programs and set frontiers to none."
)
def memorizeInduce(g, frontiers, **kwargs):
existingInventions = {p.uncurry()
for p in g.primitives }
programs = {f.bestPosterior.program for f in frontiers if not f.empty}
newInventions = programs - existingInventions
newGrammar = Grammar.uniform([p for p in g.primitives] + \
[Invented(ni) for ni in newInventions])
# rewrite in terms of new primitives
def substitute(p):
nonlocal newInventions
if p in newInventions: return Invented(p).uncurry()
return p
newFrontiers = [Frontier([FrontierEntry(program=np,
logPrior=newGrammar.logLikelihood(f.task.request, np),
logLikelihood=e.logLikelihood)
for e in f
for np in [substitute(e.program)] ],
task=f.task)
for f in frontiers ]
return newGrammar, newFrontiers
('mapping', [
'(map _ $x)',
'(mapi _ $x)',
'(flatten $x)',
'(map _ (zip (droplast 1 $x) (drop 1 $x)))',
'(map _ (drop 1 $x))'
], lambda e: e == '$l')
])
## features computed in 'predict()' in bin/list_routines_misc.py
Primitive.GLOBALS.clear()
Grammar.uniform(list_routines_misc.primitives())
pre_features = {
'program_length': lambda _, __, ___, p: Program.parse(p).size(),
'depth': lambda _, __, ___, p: Program.parse(p).depth(),
'apps': lambda _, __, ___, p: list_routines_misc.count_applications(Program.parse(p))
}
## miscellaneous features
misc_features = {}
concept_examples = {'model': {}, 'dataset': {}}
for purpose, num in [('model', 100), ('dataset', 150)]:
concepts = os.listdir('analysis/concept_examples/{}'.format(purpose))
for concept in map(lambda n: 'c{:03}'.format(n), range(1, num+1)):
# Primitive("map", arrow(arrow(t0, t1), tlist(t0), tlist(t1)), _map),
# Primitive("index", arrow(tint,tlist(t0),t0),None),
# Primitive("length", arrow(tlist(t0),tint),None),
primitiveRecursion1,
#primitiveRecursion2,
Primitive("gt?", arrow(tint, tint, tbool), _gt),
Primitive("if", arrow(tbool, t0, t0, t0), _if),
Primitive("eq?", arrow(tint, tint, tbool), _eq),
Primitive("+", arrow(tint, tint, tint), _addition),
Primitive("-", arrow(tint, tint, tint), _subtraction),
] + [Primitive(str(j), tint, j) for j in range(2)]
if __name__ == "__main__":
bootstrapTarget()
g = Grammar.uniform(McCarthyPrimitives())
# with open("/home/ellisk/om/ec/experimentOutputs/list_aic=1.0_arity=3_ET=1800_expandFrontier=2.0_it=4_likelihoodModel=all-or-nothing_MF=5_baseline=False_pc=10.0_L=1.0_K=5_rec=False.pickle", "rb") as handle:
# b = pickle.load(handle).grammars[-1]
# print b
p = Program.parse(
"(lambda (lambda (lambda (if (empty? $0) empty (cons (+ (car $1) (car $0)) ($2 (cdr $1) (cdr $0)))))))")
t = arrow(tlist(tint), tlist(tint), tlist(tint)) # ,tlist(tbool))
print(g.logLikelihood(arrow(t, t), p))
assert False
print(b.logLikelihood(arrow(t, t), p))
# p = Program.parse("""(lambda (lambda
# (unfold 0
# (lambda (+ (index $0 $2) (index $0 $1)))
# (lambda (1+ $0))
def main(args):
"""
Takes the return value of the `commandlineArguments()` function as input and
trains/tests the model on manipulating sequences of numbers.
"""
random.seed(args.pop("random_seed"))
tasks = make_list_bootstrap_tasks()
print(tasks)
maxTasks = args.pop("maxTasks")
if maxTasks and len(tasks) > maxTasks:
eprint("Unwilling to handle {} tasks, truncating..".format(len(tasks)))
random.shuffle(tasks)
del tasks[maxTasks:]
primitives = McCarthyPrimitives()
from dreamcoder.program import Program, Invented
# plus = Program.parse("(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 $1 (incr ($2 $1 (decr0 $0))))))))))")
# plus = Invented(plus)
# primitives.append(plus)
# minus = Program.parse("(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 $1 ($2 (decr0 $1) (decr0 $0)))))))))")
# minus = Invented(minus)
# primitives.append(minus)
# times = Program.parse("(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 0 (#(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 $1 (incr ($2 $1 (decr0 $0)))))))))) $1 ($2 (decr0 $0) $1)))))))))")
# times = Invented(times)
# primitives.append(times)
baseGrammar = Grammar.uniform(primitives)
baseGrammar = Grammar(
0.0, [(5.0 if p.name.startswith('fix') else 0.0, p.infer(), p)
for p in primitives])
extractor = {
"learned": LearnedFeatureExtractor,
}[args.pop("extractor")]
extractor.H = args.pop("hidden")
timestamp = datetime.datetime.now().isoformat()
outputDirectory = "experimentOutputs/list/%s" % timestamp
os.system("mkdir -p %s" % outputDirectory)
args.update({
"featureExtractor": extractor,
"outputPrefix": "%s/list" % outputDirectory,
"evaluationTimeout": 0.0005,
})
eprint("Got {} list tasks".format(len(tasks)))
split = args.pop("split")
if split:
train_some = defaultdict(list)
for t in tasks:
# necessary = train_necessary(t)
# if not necessary:
# continue
# if necessary == "some":
# train_some[t.name.split()[0]].append(t)
# else:
t.mustTrain = True
# for k in sorted(train_some):
# ts = train_some[k]
# random.shuffle(ts)
# ts.pop().mustTrain = True
test, train = testTrainSplit(tasks, split)
eprint("Alotted {} tasks for training and {} for testing".format(
len(train), len(test)))
else:
train = tasks
test = []
result = explorationCompression(baseGrammar,
train,
testingTasks=test,
**args)
print([x.bestPosterior for x in result.taskSolutions.values()])
for char, name in disallowed
] + [
Primitive("r_dot", tpregex, emp_dot_no_letter(corpus)),
Primitive("r_d", tpregex, emp_d(corpus)),
Primitive("r_s", tpregex, pregex.s),
Primitive("r_kleene", arrow(tpregex, tpregex), _kleene),
#Primitive("r_plus", arrow(tpregex, tpregex), _plus),
#Primitive("r_maybe", arrow(tpregex, tpregex), _maybe),
Primitive("r_alt", arrow(tpregex, tpregex, tpregex), _alt),
Primitive("r_concat", arrow(tpregex, tpregex, tpregex), _concat),
]
if __name__ == '__main__':
concatPrimitives()
from dreamcoder.program import Program
p = Program.parse(
"(lambda (r_kleene (lambda (r_maybe (lambda (string_x $0)) $0)) $0))")
print(p)
print(p.runWithArguments([pregex.String("")]))
prims = concatPrimitives()
g = Grammar.uniform(prims)
for i in range(100):
prog = g.sample(arrow(tpregex, tpregex))
preg = prog.runWithArguments([pregex.String("")])
print("preg:", preg.__repr__())
print("sample:", preg.sample())
bootstrapTarget()
equationPrimitives = [
# real,
f0,
f1,
fpi,
real_power,
real_subtraction,
real_addition,
real_division,
real_multiplication
] + [
Program.parse(n)
for n in ["map", "fold", "empty", "cons", "car", "cdr", "zip"]
]
baseGrammar = Grammar.uniform(equationPrimitives)
eprint("Got %d equation discovery tasks..." % len(tasks))
explorationCompression(baseGrammar,
tasks,
outputPrefix="experimentOutputs/scientificLaws",
evaluationTimeout=0.1,
testingTasks=[],
**commandlineArguments(
compressor="ocaml",
featureExtractor=DummyFeatureExtractor,
iterations=10,
CPUs=numberOfCPUs(),
structurePenalty=0.5,
helmholtzRatio=0.5,
def main(args):
"""
Takes the return value of the `commandlineArguments()` function as input and
trains/tests the model on LOGO tasks.
"""
# The below legacy global statement is required since prefix_dreams is used by LogoFeatureCNN.
# TODO(lcary): use argument passing instead of global variables.
global prefix_dreams
# The below global statement is required since primitives is modified within main().
# TODO(lcary): use a function call to retrieve and declare primitives instead.
global primitives
visualizeCheckpoint = args.pop("visualize")
if visualizeCheckpoint is not None:
with open(visualizeCheckpoint, 'rb') as handle:
primitives = pickle.load(handle).grammars[-1].primitives
visualizePrimitives(primitives)
sys.exit(0)
dreamCheckpoint = args.pop("dreamCheckpoint")
dreamDirectory = args.pop("dreamDirectory")
proto = args.pop("proto")
if dreamCheckpoint is not None:
#outputDreams(dreamCheckpoint, dreamDirectory)
enumerateDreams(dreamCheckpoint, dreamDirectory)
sys.exit(0)
animateCheckpoint = args.pop("animate")
if animateCheckpoint is not None:
animateSolutions(loadPickle(animateCheckpoint).allFrontiers)
sys.exit(0)
target = args.pop("target")
red = args.pop("reduce")
save = args.pop("save")
prefix = args.pop("prefix")
prefix_dreams = prefix + "/dreams/" + ('_'.join(target)) + "/"
prefix_pickles = prefix + "/logo." + ('.'.join(target))
if not os.path.exists(prefix_dreams):
os.makedirs(prefix_dreams)
tasks = makeTasks(target, proto)
eprint("Generated", len(tasks), "tasks")
costMatters = args.pop("cost")
for t in tasks:
t.specialTask[1]["costMatters"] = costMatters
# disgusting hack - include whether cost matters in the dummy input
if costMatters: t.examples = [(([1]), t.examples[0][1])]
os.chdir("prototypical-networks")
subprocess.Popen(["python", "./protonet_server.py"])
time.sleep(3)
os.chdir("..")
test, train = testTrainSplit(tasks, args.pop("split"))
eprint("Split tasks into %d/%d test/train" % (len(test), len(train)))
try:
if test: montageTasks(test, "test_")
montageTasks(train, "train_")
except:
eprint(
"WARNING: couldn't generate montage. Do you have an old version of scipy?"
)
if red is not []:
for reducing in red:
try:
with open(reducing, 'r') as f:
prods = json.load(f)
for e in prods:
e = Program.parse(e)
if e.isInvented:
primitives.append(e)
except EOFError:
eprint("Couldn't grab frontier from " + reducing)
except IOError:
eprint("Couldn't grab frontier from " + reducing)
except json.decoder.JSONDecodeError:
eprint("Couldn't grab frontier from " + reducing)
primitives = list(OrderedDict((x, True) for x in primitives).keys())
baseGrammar = Grammar.uniform(primitives, continuationType=turtle)
eprint(baseGrammar)
timestamp = datetime.datetime.now().isoformat()
outputDirectory = "experimentOutputs/logo/%s" % timestamp
os.system("mkdir -p %s" % outputDirectory)
generator = ecIterator(baseGrammar,
train,
testingTasks=test,
outputPrefix="%s/logo" % outputDirectory,
evaluationTimeout=0.01,
**args)
r = None
for result in generator:
iteration = len(result.learningCurve)
dreamDirectory = "%s/dreams_%d" % (outputDirectory, iteration)
os.system("mkdir -p %s" % dreamDirectory)
eprint("Dreaming into directory", dreamDirectory)
dreamFromGrammar(result.grammars[-1], dreamDirectory)
r = result
needsExport = [
str(z) for _, _, z in r.grammars[-1].productions if z.isInvented
]
if save is not None:
with open(save, 'w') as f:
json.dump(needsExport, f)
response = json.loads(result.decode("utf-8"))
for b, entry in enumerate(response):
frontiers.append(
Frontier([
FrontierEntry(program=Program.parse(p),
logPrior=entry["ll"],
logLikelihood=0.)
for p in entry["programs"]
],
task=Task(str(b), request, [])))
eprint("Total number of Helmholtz frontiers:", len(frontiers))
return frontiers
return get
if __name__ == "__main__":
g = Grammar.uniform([k1, k0, addition, subtraction, multiplication])
frontiers = helmholtzEnumeration(g, arrow(tint, tint), [[0], [1], [2]],
10.)
eprint("average frontier size", mean(len(f.entries) for f in frontiers))
f = DummyFeatureExtractor([])
r = RecognitionModel(f, g, hidden=[], contextual=True)
r.trainBiasOptimal(frontiers, frontiers, steps=70)
g = r.grammarOfTask(frontiers[0].task).untorch()
frontiers = helmholtzEnumeration(g, arrow(tint, tint), [[0], [1], [2]],
10.)
for f in frontiers:
eprint(f.summarizeFull())
eprint("average frontier size", mean(len(f.entries) for f in frontiers))
# from dreamcoder.domains.draw.makeDrawTasks import drawDrawings from dreamcoder.domains.draw.drawPrimitives import primitives, taxes, tartist, tangle, tscale, tdist # from dreamcoder.dreamcoder import ecIterator from dreamcoder.grammar import Grammar # from dreamcoder.program import Program # from dreamcoder.recognition import variable, maybe_cuda from dreamcoder.task import Task from dreamcoder.type import arrow # from dreamcoder.utilities import eprint, testTrainSplit, loadPickle g0 = Grammar.uniform(primitives) def dreamFromGrammar(g=g0, directory = "", N=50): # request = taxes # arrow9turtle turtle) just for logl. request = arrow(taxes, taxes) # arrow9turtle turtle) just for logl. programs = [ p for _ in range(N) for p in [g.sample(request, maximumDepth=20)] if p is not None] return programs # drawDrawings(*programs, filenames)
helmholtzRatio=0.5,
activation="tanh",
maximumFrontier=5,
a=3,
topK=2,
pseudoCounts=30.0,
extras=rational_options)
primitives = [
real,
# f1,
real_division,
real_addition,
real_multiplication
]
baseGrammar = Grammar.uniform(primitives)
random.seed(42)
tasks = makeTasks()
smooth = arguments.pop('smooth')
for t in tasks:
t.features = drawFunction(200, 10., t.f)
delattr(t, 'f')
if smooth:
t.likelihoodThreshold = None
eprint("Got %d tasks..." % len(tasks))
test, train = testTrainSplit(tasks, 100)
random.shuffle(test)
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser(description="")
parser.add_argument("--domain", '-d', default="text")
parser.add_argument("--taskLikelihood", default=False, action='store_true')
parser.add_argument("--sampleLikelihood",
default=False,
action='store_true')
parser.add_argument("--test", type=str, default=False)
parser.add_argument("--timeout", type=float, default=600)
arguments = parser.parse_args()
if arguments.domain == "text":
tasks = makeTasks()
g = Grammar.uniform(text_primitives.primitives +
[p for p in bootstrapTarget()])
input_vocabularies = [
list(printable[:-4]) + ['EOE'],
list(printable[:-4])
]
test = loadPBETasks("PBE_Strings_Track")[0]
fe = Text.LearnedFeatureExtractor(tasks=tasks, testingTasks=test)
BATCHSIZE = 16
elif arguments.domain == "regex":
g = Grammar.uniform(reducedConcatPrimitives(),
continuationType=tpregex)
tasks = makeNewTasks()
fe = Regex.LearnedFeatureExtractor(tasks)
def make_grammar(g):
Primitive.GLOBALS.clear()
return Grammar.uniform(g())
def main(args):
"""
Takes the return value of the `commandlineArguments()` function as input and
trains/tests the model on manipulating sequences of numbers.
"""
random.seed(args.pop("random_seed"))
dataset = args.pop("dataset")
tasks = {
"Lucas-old":
lambda: retrieveJSONTasks("data/list_tasks.json") + sortBootstrap(),
"bootstrap":
make_list_bootstrap_tasks,
"sorting":
sortBootstrap,
"Lucas-depth1":
lambda: retrieveJSONTasks("data/list_tasks2.json")[:105],
"Lucas-depth2":
lambda: retrieveJSONTasks("data/list_tasks2.json")[:4928],
"Lucas-depth3":
lambda: retrieveJSONTasks("data/list_tasks2.json"),
}[dataset]()
maxTasks = args.pop("maxTasks")
if maxTasks and len(tasks) > maxTasks:
necessaryTasks = [] # maxTasks will not consider these
if dataset.startswith("Lucas2.0") and dataset != "Lucas2.0-depth1":
necessaryTasks = tasks[:105]
eprint("Unwilling to handle {} tasks, truncating..".format(len(tasks)))
random.shuffle(tasks)
del tasks[maxTasks:]
tasks = necessaryTasks + tasks
if dataset.startswith("Lucas"):
# extra tasks for filter
tasks.extend([
Task("remove empty lists",
arrow(tlist(tlist(tbool)), tlist(tlist(tbool))),
[((ls, ), list(filter(lambda l: len(l) > 0, ls)))
for _ in range(15) for ls in [[[
random.random() < 0.5
for _ in range(random.randint(0, 3))
] for _ in range(4)]]]),
Task("keep squares", arrow(tlist(tint), tlist(tint)), [
((xs, ), list(filter(lambda x: int(math.sqrt(x))**2 == x, xs)))
for _ in range(15) for xs in [[
random.choice([0, 1, 4, 9, 16, 25])
if random.random() < 0.5 else random.randint(0, 9)
for _ in range(7)
]]
]),
Task("keep primes", arrow(tlist(tint), tlist(tint)), [
((xs, ),
list(
filter(
lambda x: x in
{2, 3, 5, 7, 11, 13, 17, 19, 23, 29, 31, 37}, xs)))
for _ in range(15) for xs in [[
random.choice([2, 3, 5, 7, 11, 13, 17, 19, 23, 29, 31, 37])
if random.random() < 0.5 else random.randint(0, 9)
for _ in range(7)
]]
]),
])
for i in range(4):
tasks.extend([
Task("keep eq %s" % i, arrow(tlist(tint), tlist(tint)),
[((xs, ), list(filter(lambda x: x == i, xs)))
for _ in range(15)
for xs in [[random.randint(0, 6) for _ in range(5)]]]),
Task("remove eq %s" % i, arrow(tlist(tint), tlist(tint)),
[((xs, ), list(filter(lambda x: x != i, xs)))
for _ in range(15)
for xs in [[random.randint(0, 6) for _ in range(5)]]]),
Task("keep gt %s" % i, arrow(tlist(tint), tlist(tint)),
[((xs, ), list(filter(lambda x: x > i, xs)))
for _ in range(15)
for xs in [[random.randint(0, 6) for _ in range(5)]]]),
Task("remove gt %s" % i, arrow(tlist(tint), tlist(tint)),
[((xs, ), list(filter(lambda x: not x > i, xs)))
for _ in range(15)
for xs in [[random.randint(0, 6) for _ in range(5)]]])
])
def isIdentityTask(t):
return all(len(xs) == 1 and xs[0] == y for xs, y in t.examples)
eprint("Removed", sum(isIdentityTask(t) for t in tasks),
"tasks that were just the identity function")
tasks = [t for t in tasks if not isIdentityTask(t)]
prims = {
"base": basePrimitives,
"McCarthy": McCarthyPrimitives,
"common": bootstrapTarget_extra,
"noLength": no_length,
"rich": primitives
}[args.pop("primitives")]()
haveLength = not args.pop("noLength")
haveMap = not args.pop("noMap")
haveUnfold = not args.pop("noUnfold")
eprint(f"Including map as a primitive? {haveMap}")
eprint(f"Including length as a primitive? {haveLength}")
eprint(f"Including unfold as a primitive? {haveUnfold}")
baseGrammar = Grammar.uniform([p
for p in prims
if (p.name != "map" or haveMap) and \
(p.name != "unfold" or haveUnfold) and \
(p.name != "length" or haveLength)])
extractor = {
"learned": LearnedFeatureExtractor,
}[args.pop("extractor")]
extractor.H = args.pop("hidden")
timestamp = datetime.datetime.now().isoformat()
outputDirectory = "experimentOutputs/list/%s" % timestamp
os.system("mkdir -p %s" % outputDirectory)
args.update({
"featureExtractor": extractor,
"outputPrefix": "%s/list" % outputDirectory,
"evaluationTimeout": 0.0005,
})
eprint("Got {} list tasks".format(len(tasks)))
split = args.pop("split")
if split:
train_some = defaultdict(list)
for t in tasks:
necessary = train_necessary(t)
if not necessary:
continue
if necessary == "some":
train_some[t.name.split()[0]].append(t)
else:
t.mustTrain = True
for k in sorted(train_some):
ts = train_some[k]
random.shuffle(ts)
ts.pop().mustTrain = True
test, train = testTrainSplit(tasks, split)
if True:
test = [t for t in test if t.name not in EASYLISTTASKS]
eprint("Alotted {} tasks for training and {} for testing".format(
len(train), len(test)))
else:
train = tasks
test = []
explorationCompression(baseGrammar, train, testingTasks=test, **args)
def update_grammar(self):
programs = [
Invented(smt.program.prog_ori) for smt in self.semantics
if smt.solved and smt.program.arity > 0
]
self.grammar = Grammar.uniform(McCarthyPrimitives() + programs)
