def load(self, model):
self.idx = model['idx']
self.solved = model['solved']
self.likelihood = model['likelihood']
self.total_examples = model['total_examples']
self.arity = model['arity']
self.program = None if model['program'] is None else ProgramWrapper(
Program.parse(model['program']))
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 get():
results = [p.get() for p in promises]
frontiers = []
with timing("(Helmholtz enumeration) Decoded json into frontiers"):
for request, result in zip(requests, results):
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
def expression(e, environment):
for n, v in enumerate(environment):
if e == v: return Index(n)
if isinstance(e, int): return Program.parse(str(e))
mapping = {
"1a": _ua,
"1d": _ul,
"1l": _ul,
"0a": _za,
"0d": _zl,
"0l": _zl,
"/a": _da,
"/l": _dl,
"/d": _dl,
"*a": _ma,
"*l": _ml,
"*d": _ml,
"+a": _aa,
"+d": _al,
"+l": _al,
"-a": _sa,
"-d": _sl,
"-l": _sl,
"+": _addition,
"infinity": _infinity,
"epsilonAngle": _ea,
"epsilonDistance": _el,
"epsilonLength": _el
}
if e == float('inf'): return _infinity
for name, value in mapping.items():
if e == Symbol(name): return value
assert isinstance(e, list), "not a list %s" % e
for name, value in mapping.items():
if e[0] == Symbol(name):
f = value
for argument in e[1:]:
f = Application(f, expression(argument, environment))
return f
assert False
def parseLogo(s):
_ua = Program.parse("logo_UA")
_ul = Program.parse("logo_UL")
_za = Program.parse("logo_ZA")
_zl = Program.parse("logo_ZL")
_da = Program.parse("logo_DIVA")
_ma = Program.parse("logo_MULA")
_dl = Program.parse("logo_DIVL")
_ml = Program.parse("logo_MULL")
_aa = Program.parse("logo_ADDA")
_sa = Program.parse("logo_SUBA")
_al = None #Program.parse("logo_ADDL")
_sl = None #Program.parse("logo_SUBL")
_pu = None #Program.parse("logo_PU")
_pd = None #Program.parse("logo_PD")
_p = Program.parse("logo_PT")
_move = Program.parse("logo_FWRT")
_embed = Program.parse("logo_GETSET")
_addition = Program.parse("+")
_infinity = Program.parse("logo_IFTY")
_ea = Program.parse("logo_epsA")
_el = Program.parse("logo_epsL")
_loop = Program.parse("logo_forLoop")
from sexpdata import loads, Symbol
s = loads(s)
def command(k, environment, continuation):
assert isinstance(k, list)
if k[0] == Symbol("move"):
return Application(
Application(Application(_move, expression(k[1], environment)),
expression(k[2], environment)), continuation)
if k[0] == Symbol("for") or k[0] == Symbol("loop"):
v = k[1]
b = expression(k[2], environment)
newEnvironment = [None, v] + environment
body = block(k[3:], newEnvironment, Index(0))
return Application(
Application(Application(_loop, b),
Abstraction(Abstraction(body))), continuation)
if k[0] == Symbol("embed"):
body = block(k[1:], [None] + environment, Index(0))
return Application(Application(_embed, Abstraction(body)),
continuation)
if k[0] == Symbol("p"):
body = block(k[1:], [None] + environment, Index(0))
return Application(Application(_p, Abstraction(body)),
continuation)
assert False
def expression(e, environment):
for n, v in enumerate(environment):
if e == v: return Index(n)
if isinstance(e, int): return Program.parse(str(e))
mapping = {
"1a": _ua,
"1d": _ul,
"1l": _ul,
"0a": _za,
"0d": _zl,
"0l": _zl,
"/a": _da,
"/l": _dl,
"/d": _dl,
"*a": _ma,
"*l": _ml,
"*d": _ml,
"+a": _aa,
"+d": _al,
"+l": _al,
"-a": _sa,
"-d": _sl,
"-l": _sl,
"+": _addition,
"infinity": _infinity,
"epsilonAngle": _ea,
"epsilonDistance": _el,
"epsilonLength": _el
}
if e == float('inf'): return _infinity
for name, value in mapping.items():
if e == Symbol(name): return value
assert isinstance(e, list), "not a list %s" % e
for name, value in mapping.items():
if e[0] == Symbol(name):
f = value
for argument in e[1:]:
f = Application(f, expression(argument, environment))
return f
assert False
def block(b, environment, continuation):
if len(b) == 0: return continuation
return command(b[0], environment,
block(b[1:], environment, continuation))
try:
return Abstraction(command(s, [], Index(0)))
except:
return Abstraction(block(s, [], Index(0)))
'(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)):
with open('analysis/concept_examples/{}/{}'.format(
purpose,
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))
# (lambda (eq? $0 (length $1))))))
# """)
p = Program.parse("""(lambda (lambda
(map (lambda (+ (index $0 $2) (index $0 $1))) (range (length $0)) )))""")
# .replace("unfold", "#(lambda (lambda (lambda (lambda (fix1 $0 (lambda (lambda (#(lambda (lambda (lambda (if $0 empty (cons $1 $2))))) ($1 ($3 $0)) ($4 $0) ($5 $0)))))))))").\
# replace("length", "#(lambda (fix1 $0 (lambda (lambda (if (empty? $0) 0 (+ ($1 (cdr $0)) 1))))))").\
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())
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)
def visualizePrimitives(primitives, export='/tmp/logo_primitives.png'):
from itertools import product
from dreamcoder.program import Index, Abstraction, Application
from dreamcoder.utilities import montageMatrix, makeNiceArray
from dreamcoder.type import tint
import scipy.misc
from dreamcoder.domains.logo.makeLogoTasks import parseLogo
angles = [
Program.parse(a) for a in [
"logo_ZA",
"logo_epsA",
"(logo_MULA logo_epsA 2)",
"(logo_DIVA logo_UA 4)",
"(logo_DIVA logo_UA 5)",
"(logo_DIVA logo_UA 7)",
"(logo_DIVA logo_UA 9)",
]
]
specialAngles = {
"#(lambda (lambda (logo_forLoop logo_IFTY (lambda (lambda (logo_FWRT (logo_MULL logo_UL 3) (logo_MULA $2 4) $0))) $1)))":
[Program.parse("(logo_MULA logo_epsA 4)")] +
[Program.parse("(logo_DIVA logo_UA %d)" % n) for n in [7, 9]]
}
numbers = [Program.parse(n) for n in ["1", "2", "5", "7", "logo_IFTY"]]
specialNumbers = {
"#(lambda (#(lambda (lambda (lambda (lambda (logo_forLoop $2 (lambda (lambda (logo_FWRT $5 (logo_DIVA logo_UA $3) $0))) $0))))) (logo_MULL logo_UL $0) 4 4))":
[Program.parse(str(n)) for n in [1, 2, 3]]
}
distances = [
Program.parse(l) for l in [
"logo_ZL", "logo_epsL", "(logo_MULL logo_epsL 2)",
"(logo_DIVL logo_UL 2)", "logo_UL"
]
]
subprograms = [
parseLogo(sp) for sp in [
"(move 1d 0a)",
"(loop i infinity (move (*l epsilonLength 4) (*a epsilonAngle 2)))",
"(loop i infinity (move (*l epsilonLength 5) (/a epsilonAngle 2)))",
"(loop i 4 (move 1d (/a 1a 4)))"
]
]
entireArguments = {
"#(lambda (lambda (#(#(lambda (lambda (lambda (logo_forLoop $2 (lambda (lambda (logo_FWRT $2 $3 $0))))))) logo_IFTY) (logo_MULA (#(logo_DIVA logo_UA) $1) $0) (#(logo_MULL logo_UL) 3))))":
[[Program.parse(str(x)) for x in xs]
for xs in [("3", "1", "$0"), ("4", "1",
"$0"), ("5", "1",
"$0"), ("5", "3",
"$0"), ("7", "3", "$0")]
]
}
specialDistances = {
"#(lambda (lambda (logo_forLoop 7 (lambda (lambda (#(lambda (lambda (lambda (#(lambda (lambda (lambda (logo_forLoop $2 (lambda (lambda (logo_FWRT $2 $3 $0))))))) 7 $1 $2 $0)))) $3 logo_epsA $0))) $0)))":
[Program.parse("(logo_MULL logo_epsL %d)" % n) for n in range(5)]
}
matrix = []
for p in primitives:
if not p.isInvented: continue
t = p.tp
eprint(p, ":", p.tp)
if t.returns() != turtle:
eprint("\t(does not return a turtle)")
continue
def argumentChoices(t):
if t == turtle:
return [Index(0)]
elif t == arrow(turtle, turtle):
return subprograms
elif t == tint:
return specialNumbers.get(str(p), numbers)
elif t == tangle:
return specialAngles.get(str(p), angles)
elif t == tlength:
return specialDistances.get(str(p), distances)
else:
return []
ts = []
for arguments in entireArguments.get(
str(p),
product(*[argumentChoices(t) for t in t.functionArguments()])):
eprint(arguments)
pp = p
for a in arguments:
pp = Application(pp, a)
pp = Abstraction(pp)
i = np.reshape(np.array(drawLogo(pp, resolution=128)), (128, 128))
if i is not None:
ts.append(i)
if ts == []: continue
matrix.append(ts)
if len(ts) < 6: ts = [ts]
else: ts = makeNiceArray(ts)
r = montageMatrix(ts)
fn = "/tmp/logo_primitive_%d.png" % len(matrix)
eprint("\tExported to", fn)
scipy.misc.imsave(fn, r)
matrix = montageMatrix(matrix)
scipy.misc.imsave(export, matrix)
"non",
"l",
"erase",
"m",
"comes",
"up",
"comparison",
"during",
"'s value is the largest inclusive, which is strictly less than maximum element in numbers from 1 to the element in `a` which'",
"'s value is the biggest (inclusive), which is strictly less than maximum element of range from 1 to the element in `a` which'",
"'s value is the highest, which is strictly less than maximum element among sequence of digits of the element in `a` which'"]
if __name__ == "__main__":
#g = Grammar.uniform(deepcoderPrimitives())
g = Grammar.fromProductions(algolispProductions(), logVariable=.9)
#p=Program.parse("(lambda (fn_call filter (list_add_symbol (lambda1_call == (list_add_symbol 1 (list_init_symbol (fn_call mod ( list_add_symbol 2 (list_init_symbol arg1)) ))) ) (list_init_symbol $0)) )")
p=Program.parse("(lambda (fn_call filter (list_add_symbol (lambda1_call eq (list_add_symbol (symbol_constant 1) (list_init_symbol (fn_call mod ( list_add_symbol (symbol_constant 2) (list_init_symbol (symbol_constant arg1))) ))) ) (list_init_symbol (symbol_constant $0)))))")
print(p)
#tree = p.evaluate(["a"])
tree = p.evaluate([])
print(tree("a"))
#
import sys
sys.setrecursionlimit(int(1e4))
sys.path.insert(0, "./semantics/dreamcoder")
from dreamcoder.domains.hint.hintPrimitives import McCarthyPrimitives
_ = McCarthyPrimitives()
from dreamcoder.program import Program
from semantics.semantics import ProgramWrapper
# Plus
pg = Program.parse(
"(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 $1 ($2 (incr $1) (decr0 $0)))))))))"
)
pg = ProgramWrapper(pg)
print(pg(1, 2))
# pg = Program.parse("(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 $1 ($2 $0 (decr0 $1)))))))))")
pg = Program.parse(
"(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 $1 (incr ($2 $1 (decr0 $0))))))))))"
)
pg = ProgramWrapper(pg)
print(pg(1, 1))
# Minus
# pg = Program.parse("(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 $1 ($2 (decr0 $1) (decr0 $0)))))))))")
pg = Program.parse(
"(lambda (lambda (fix2 $1 $0 (lambda (lambda (lambda (if0 $0 $1 ($2 $0 (decr0 $1)))))))))"
)
pg = ProgramWrapper(pg)
print(pg(0, 2))
makeTask("c^2 = a^2 + b^2", arrow(tpositive, tpositive, tpositive),
lambda a, b: a * a + b * b)
]
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,
def rustInduce(g0,
frontiers,
_=None,
topK=1,
pseudoCounts=1.0,
aic=1.0,
structurePenalty=0.001,
a=0,
CPUs=1,
iteration=-1,
topk_use_only_likelihood=False,
vs=False):
def finite_logp(l):
return l if l != float("-inf") else -1000
message = {
"strategy": {
"version-spaces": {
"top_i": 50
}
} if vs else {
"fragment-grammars": {}
},
"params": {
"structure_penalty": structurePenalty,
"pseudocounts": int(pseudoCounts + 0.5),
"topk": topK,
"topk_use_only_likelihood": topk_use_only_likelihood,
"aic": aic if aic != float("inf") else None,
"arity": a,
},
"primitives": [{
"name": p.name,
"tp": str(t),
"logp": finite_logp(l)
} for l, t, p in g0.productions if p.isPrimitive],
"inventions": [
{
"expression": str(p.body),
"logp": finite_logp(l)
} # -inf=-100
for l, t, p in g0.productions if p.isInvented
],
"variable_logprob":
finite_logp(g0.logVariable),
"frontiers": [{
"task_tp":
str(f.task.request),
"solutions": [{
"expression": str(e.program),
"logprior": finite_logp(e.logPrior),
"loglikelihood": e.logLikelihood,
} for e in f],
} for f in frontiers],
}
eprint("running rust compressor")
messageJson = json.dumps(message)
with open("jsonDebug", "w") as f:
f.write(messageJson)
# check which version of python we are using
# if >=3.6 do:
if sys.version_info[1] >= 6:
p = subprocess.Popen(['./rust_compressor/rust_compressor'],
encoding='utf-8',
stdin=subprocess.PIPE,
stdout=subprocess.PIPE)
elif sys.version_info[1] == 5:
p = subprocess.Popen(['./rust_compressor/rust_compressor'],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE)
messageJson = bytearray(messageJson, encoding='utf-8')
# convert messageJson string to bytes
else:
eprint("must be python 3.5 or 3.6")
assert False
p.stdin.write(messageJson)
p.stdin.flush()
p.stdin.close()
if p.returncode is not None:
raise ValueError("rust compressor failed")
if sys.version_info[1] >= 6:
resp = json.load(p.stdout)
elif sys.version_info[1] == 5:
import codecs
resp = json.load(codecs.getreader('utf-8')(p.stdout))
productions = [(x["logp"], p) for p, x in
zip((p for (_, _, p) in g0.productions if p.isPrimitive), resp["primitives"])] + \
[(i["logp"], Invented(Program.parse(i["expression"])))
for i in resp["inventions"]]
productions = [(l if l is not None else float("-inf"), p)
for l, p in productions]
g = Grammar.fromProductions(productions,
resp["variable_logprob"],
continuationType=g0.continuationType)
newFrontiers = [
Frontier([
FrontierEntry(Program.parse(s["expression"]),
logPrior=s["logprior"],
logLikelihood=s["loglikelihood"])
for s in r["solutions"]
], f.task) for f, r in zip(frontiers, resp["frontiers"])
]
return g, newFrontiers
def parse_program(expression):
return Program.parse(expression)
def ocamlInduce(g,
frontiers,
_=None,
topK=1,
pseudoCounts=1.0,
aic=1.0,
structurePenalty=0.001,
a=0,
CPUs=1,
bs=1000000,
topI=300):
# This is a dirty hack!
# Memory consumption increases with the number of CPUs
# And early on we have a lot of stuff to compress
# If this is the first iteration, only use a fraction of the available CPUs
topK = 5
topI = 600
if all(not p.isInvented for p in g.primitives):
if a > 3:
CPUs = max(1, int(CPUs / 6))
else:
CPUs = max(1, int(CPUs / 3))
else:
CPUs = max(1, int(CPUs / 2))
CPUs = 2
# X X X FIXME X X X
# for unknown reasons doing compression all in one go works correctly and doing it with Python and the outer loop causes problems
iterations = 99 # maximum number of components to add at once
while True:
g0 = g
originalFrontiers = frontiers
t2f = {f.task: f for f in frontiers}
frontiers = [f for f in frontiers if not f.empty]
message = {
"arity": a,
"topK": topK,
"pseudoCounts": float(pseudoCounts),
"aic": aic,
"bs": bs,
"topI": topI,
"structurePenalty": float(structurePenalty),
"CPUs": CPUs,
"DSL": g.json(),
"iterations": iterations,
"frontiers": [f.json() for f in frontiers]
}
message = json.dumps(message)
if True:
timestamp = datetime.datetime.now().isoformat()
os.system("mkdir -p compressionMessages")
fn = "compressionMessages/%s" % timestamp
with open(fn, "w") as f:
f.write(message)
eprint("Compression message saved to:", fn)
try:
# Get relative path
compressor_file = os.path.join(get_root_dir(), 'compression')
process = subprocess.Popen(compressor_file,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE)
response, error = process.communicate(
bytes(message, encoding="utf-8"))
response = json.loads(response.decode("utf-8"))
except OSError as exc:
raise exc
g = response["DSL"]
g = Grammar(g["logVariable"],
[(l, p.infer(), p) for production in g["productions"]
for l in [production["logProbability"]]
for p in [Program.parse(production["expression"])]],
continuationType=g0.continuationType)
frontiers = {
original.task: Frontier([
FrontierEntry(p,
logLikelihood=e["logLikelihood"],
logPrior=g.logLikelihood(original.task.request,
p))
for e in new["programs"]
for p in [Program.parse(e["program"])]
],
task=original.task)
for original, new in zip(frontiers, response["frontiers"])
}
frontiers = [
frontiers.get(f.task, t2f[f.task]) for f in originalFrontiers
]
if iterations == 1 and len(g) > len(g0):
eprint("Grammar changed - running another round of consolidation.")
continue
else:
eprint("Finished consolidation.")
return g, frontiers
Primitive("logo_DIVA", arrow(tangle, tint, tangle), ""),
Primitive("logo_MULA", arrow(tangle, tint, tangle), ""),
Primitive("logo_DIVL", arrow(tlength, tint, tlength), ""),
Primitive("logo_MULL", arrow(tlength, tint, tlength), ""),
Primitive("logo_ADDA", arrow(tangle, tangle, tangle), ""),
Primitive("logo_SUBA", arrow(tangle, tangle, tangle), ""),
# Primitive("logo_ADDL", arrow(tlength,tlength,tlength), ""),
# Primitive("logo_SUBL", arrow(tlength,tlength,tlength), ""),
# Primitive("logo_PU", arrow(turtle,turtle), ""),
# Primitive("logo_PD", arrow(turtle,turtle), ""),
Primitive("logo_PT", arrow(arrow(turtle, turtle), arrow(turtle, turtle)),
None),
Primitive("logo_FWRT", arrow(tlength, tangle, turtle, turtle), ""),
Primitive("logo_GETSET", arrow(arrow(turtle, turtle), turtle, turtle), "")
] + [
Primitive("logo_IFTY", tint, ""),
Primitive("logo_epsA", tangle, ""),
Primitive("logo_epsL", tlength, ""),
Primitive(
"logo_forLoop", arrow(tint, arrow(tint, turtle, turtle), turtle,
turtle),
"ERROR: python has no way of expressing this hence you shouldn't eval on this"
),
] + [Primitive(str(j), tint, j) for j in range(10)]
if __name__ == "__main__":
expr_s = "(lambda (logo_forLoop 3 (lambda (lambda (logo_GET (lambda (logo_FWRT (logo_S2L (logo_I2S 1)) (logo_S2A (logo_I2S 0)) (logo_SET $0 (logo_FWRT (logo_S2L eps) (logo_DIVA (logo_S2A (logo_I2S 2)) (logo_I2S 3)) ($1)))))))) ($0)))"
x = Program.parse(expr_s)
print(x)