projects
/
picoclvr.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Update.
[picoclvr.git]
/
expr.py
diff --git
a/expr.py
b/expr.py
index
d3883d5
..
d07d09f
100755
(executable)
--- a/
expr.py
+++ b/
expr.py
@@
-1,6
+1,6
@@
#!/usr/bin/env python
#!/usr/bin/env python
-import math
+import math
, re
import torch, torchvision
import torch, torchvision
@@
-24,7
+24,7
@@
def random_expr(variables, budget):
else:
return str(torch.randint(10, (1,)).item())
else:
else:
return str(torch.randint(10, (1,)).item())
else:
- op = torch.randint(
4
, (1,)).item()
+ op = torch.randint(
3
, (1,)).item()
if op == 0:
e = random_expr(variables, budget - 2)
if ("+" in e or "-" in e or "*" in e) and (e[0] != "(" or e[-1] != ")"):
if op == 0:
e = random_expr(variables, budget - 2)
if ("+" in e or "-" in e or "*" in e) and (e[0] != "(" or e[-1] != ")"):
@@
-38,27
+38,43
@@
def random_expr(variables, budget):
if op == 1:
return e1 + "+" + e2
elif op == 2:
if op == 1:
return e1 + "+" + e2
elif op == 2:
- return e1 + "+" + e2
- elif op == 3:
return e1 + "*" + e2
def generate_program(nb_variables, length):
s = ""
variables = set()
return e1 + "*" + e2
def generate_program(nb_variables, length):
s = ""
variables = set()
+
+ # We take length itself half of the time, and uniform between 1
+ # and length otherwise. The actual length can be slightly greater
+
+ length = min(length, 1+torch.randint(length*2, (1,)).item())
while len(s) < length:
v = random_var(nb_variables=nb_variables)
s += v + "=" + random_expr(variables, budget=20) + ";"
variables.add(v)
while len(s) < length:
v = random_var(nb_variables=nb_variables)
s += v + "=" + random_expr(variables, budget=20) + ";"
variables.add(v)
+
return s, variables
return s, variables
+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):
def generate_sequences(nb, nb_variables=5, length=20):
+ assert nb_variables <= 26
sequences = []
sequences = []
+ result_max=99
for n in range(nb):
result = None
for n in range(nb):
result = None
- while result == None or max(result.values()) > 100:
- p, v = generate_program(nb_variables, length)
+ while result == None or max(result.values()) > result_max:
+ l = length
+ p, v = generate_program(nb_variables, l)
v = ", ".join(['"' + v + '": ' + v for v in v])
ldict = {}
exec(p + "result={" + v + "}", globals(), ldict)
v = ", ".join(['"' + v + '": ' + v for v in v])
ldict = {}
exec(p + "result={" + v + "}", globals(), ldict)
@@
-66,7
+82,7
@@
def generate_sequences(nb, nb_variables=5, length=20):
k = list(result.keys())
k.sort()
k = list(result.keys())
k.sort()
- sequences.append(p + " " + "
;".join([v + ":" + str(result[v])
for v in k]))
+ sequences.append(p + " " + "
".join([v + ":" + str(result[v]) + ";"
for v in k]))
return sequences
return sequences
@@
-75,8
+91,10
@@
if __name__ == "__main__":
import time
start_time = time.perf_counter()
import time
start_time = time.perf_counter()
- sequences = generate_sequences(1000)
+ sequences = generate_sequences(1000
, length=40
)
end_time = time.perf_counter()
for s in sequences[:10]:
print(s)
print(f"{len(sequences) / (end_time - start_time):.02f} samples per second")
end_time = time.perf_counter()
for s in sequences[:10]:
print(s)
print(f"{len(sequences) / (end_time - start_time):.02f} samples per second")
+
+ print(extract_results(sequences[:10]))