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 main(args):
"""
Takes the return value of the `commandlineArguments()` function as input and
trains/tests the model on regular expressions.
"""
#for dreaming
#parse use_ll_cutoff
use_ll_cutoff = args.pop('use_ll_cutoff')
if not use_ll_cutoff is False:
#if use_ll_cutoff is a list of strings, then train_ll_cutoff and train_ll_cutoff
#will be tuples of that string followed by the actual model
if len(use_ll_cutoff) == 1:
train_ll_cutoff = use_ll_cutoff[0] # make_cutoff_model(use_ll_cutoff[0], tasks))
test_ll_cutoff = use_ll_cutoff[0] # make_cutoff_model(use_ll_cutoff[0], tasks))
else:
assert len(use_ll_cutoff) == 2
train_ll_cutoff = use_ll_cutoff[0] #make_cutoff_model(use_ll_cutoff[0], tasks))
test_ll_cutoff = use_ll_cutoff[1] #make_cutoff_model(use_ll_cutoff[1], tasks))
else:
train_ll_cutoff = None
test_ll_cutoff = None
regexTasks = {"old": makeOldTasks,
"short": makeShortTasks,
"long": makeLongTasks,
"words": makeWordTasks,
"number": makeNumberTasks,
"handpicked": makeHandPickedTasks,
"new": makeNewTasks,
"newNumber": makeNewNumberTasks
}[args.pop("tasks")]
tasks = regexTasks() # TODO
eprint("Generated", len(tasks), "tasks")
maxTasks = args.pop("maxTasks")
if len(tasks) > maxTasks:
eprint("Unwilling to handle {} tasks, truncating..".format(len(tasks)))
seed = 42 # previously this was hardcoded and never changed
random.seed(seed)
random.shuffle(tasks)
del tasks[maxTasks:]
maxExamples = args.pop("maxExamples")
split = args.pop("split")
test, train = testTrainSplit(tasks, split)
eprint("Split tasks into %d/%d test/train" % (len(test), len(train)))
test = add_cutoff_values(test, test_ll_cutoff)
train = add_cutoff_values(train, train_ll_cutoff)
eprint("added cutoff values to tasks, train: ", train_ll_cutoff, ", test:", test_ll_cutoff )
if args.pop("use_str_const"):
assert args["primitives"] == "strConst" or args["primitives"] == "reduced"
ConstantInstantiateVisitor.SINGLE = \
ConstantInstantiateVisitor()
test = add_string_constants(test)
train = add_string_constants(train)
eprint("added string constants to test and train")
for task in test + train:
if len(task.examples) > maxExamples:
task.examples = task.examples[:maxExamples]
task.specialTask = ("regex", {"cutoff": task.ll_cutoff, "str_const": task.str_const})
task.examples = [(xs, [y for y in ys ])
for xs,ys in task.examples ]
task.maxParameters = 1
# from list stuff
primtype = args.pop("primitives")
prims = {"base": basePrimitives,
"alt1": altPrimitives,
"alt2": alt2Primitives,
"easyWords": easyWordsPrimitives,
"concat": concatPrimitives,
"reduced": reducedConcatPrimitives,
"strConst": strConstConcatPrimitives
}[primtype]
extractor = {
"learned": LearnedFeatureExtractor,
"json": MyJSONFeatureExtractor
}[args.pop("extractor")]
extractor.H = args.pop("hidden")
#stardecay = args.stardecay
#stardecay = args.pop('stardecay')
#decaystr = 'd' + str(stardecay)
import datetime
timestamp = datetime.datetime.now().isoformat()
outputDirectory = "experimentOutputs/regex/%s"%timestamp
os.system("mkdir -p %s"%outputDirectory)
args.update({
"featureExtractor": extractor,
"outputPrefix": "%s/regex"%(outputDirectory),
"evaluationTimeout": 0.005,
"topk_use_only_likelihood": True,
"maximumFrontier": 10,
"compressor": "ocaml"
})
####
# use the
#prim_list = prims(stardecay)
prim_list = prims()
specials = ["r_kleene", "r_plus", "r_maybe", "r_alt", "r_concat"]
n_base_prim = len(prim_list) - len(specials)
productions = [
(math.log(0.5 / float(n_base_prim)),
prim) if prim.name not in specials else (
math.log(0.10),
prim) for prim in prim_list]
baseGrammar = Grammar.fromProductions(productions, continuationType=tpregex)
#baseGrammar = Grammar.uniform(prims())
#for i in range(100):
# eprint(baseGrammar.sample(tpregex))
#eprint(baseGrammar)
#explore
test_stuff = args.pop("debug")
if test_stuff:
eprint(baseGrammar)
eprint("sampled programs from prior:")
for i in range(100): #100
eprint(baseGrammar.sample(test[0].request,maximumDepth=1000))
eprint("""half the probability mass is on higher-order primitives.
Therefore half of enumerated programs should have more than one node.
However, we do not observe this.
Instead we see a very small fraction of programs have more than one node.
So something seems to be wrong with grammar.sample.
Furthermore: observe the large print statement above.
This prints the candidates for sampleDistribution in grammar.sample.
the first element of each tuple is the probability passed into sampleDistribution.
Half of the probability mass should be on the functions, but instead they are equally
weighted with the constants. If you look at the grammar above, this is an error!!!!
""")
assert False
del args["likelihoodModel"]
explorationCompression(baseGrammar, train,
testingTasks = test,
**args)
def deepcoderProductions():
return [(0.0, prim) for prim in deepcoderPrimitives()]
# def flatten_program(p):
# string = p.show(False)
# num_inputs = string.count('lambda')
# string = string.replace('lambda', '')
# string = string.replace('(', '')
# string = string.replace(')', '')
# #remove '_fn' (optional)
# for i in range(num_inputs):
# string = string.replace('$' + str(num_inputs-i-1),'input_' + str(i))
# string = string.split(' ')
# string = list(filter(lambda x: x is not '', string))
# return string
if __name__ == "__main__":
#g = Grammar.uniform(deepcoderPrimitives())
g = Grammar.fromProductions(deepcoderProductions(), logVariable=.9)
request = arrow(tlist(tint), tint, tint)
p = g.sample(request)
print("request:", request)
print("program:")
print(prettyProgram(p))
print("flattened_program:")
flat = flatten_program(p)
print(flat)
#print("self.name", self.name)
return self.name
def __setstate__(self, state):
#for backwards compatibility:
if type(state) == dict:
pass #do nothing, i don't need to load them if they are old...
else:
p = Primitive.GLOBALS[state]
self.__init__(p.name, p.tp, p.value, p.constraint)
if __name__ == '__main__':
import time
CPrimitive("testCPrim", tint, lambda x: x, 17)
g = Grammar.fromProductions(RobustFillProductions())
print(len(g))
request = tprogram
p = g.sample(request)
print("request:", request)
print("program:")
print(prettyProgram(p))
s = 'abcdefg'
e = p.evaluate([])
#print("prog applied to", s)
#print(e(s))
print("flattened_program:")
flat = flatten_program(p)
print(flat)
t = time.time()
constraints = Constraint_prop().execute(p)
"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"))
#