X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=expr.py;h=ca33daf9a6473468030e45c08d33bfe644aff451;hb=02c4828834319a5b7818bafb8821fce66b3a1bb1;hp=b453f235010a4c9a8f8e5ee1fd408da29db12c27;hpb=38d3035f027881bb2baffdaffc8cd666d3df5dba;p=picoclvr.git diff --git a/expr.py b/expr.py index b453f23..ca33daf 100755 --- a/expr.py +++ b/expr.py @@ -1,6 +1,6 @@ #!/usr/bin/env python -import math +import math, re import torch, torchvision @@ -48,17 +48,29 @@ def generate_program(nb_variables, length): variables = set() while len(s) < length: v = random_var(nb_variables=nb_variables) - s += v + "=" + random_expr(variables, budget=min(20, length - 3 - len(s))) + ";" + s += v + "=" + random_expr(variables, budget=20) + ";" variables.add(v) return s, variables -def generate_sequences(nb, nb_variables=5, length=20): +def extract_results(seq): + f = lambda a: (a[0], -1 if a[1] == "" else int(a[1])) + results = [ + dict([f(tuple(x.split(":"))) for x in re.findall("[A-Z]:[0-9]*", s)]) + for s in seq + ] + return results + + +def generate_sequences(nb, nb_variables=5, length=20, randomize_length=False): sequences = [] for n in range(nb): result = None while result == None or max(result.values()) > 100: - p, v = generate_program(nb_variables, length) + l = length + if l > 5 and randomize_length: + l = 5 + torch.randint(l - 5, (1,)).item() + p, v = generate_program(nb_variables, l) v = ", ".join(['"' + v + '": ' + v for v in v]) ldict = {} exec(p + "result={" + v + "}", globals(), ldict) @@ -80,3 +92,5 @@ if __name__ == "__main__": for s in sequences[:10]: print(s) print(f"{len(sequences) / (end_time - start_time):.02f} samples per second") + + print(extract_results(sequences[:10]))