X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=expr.py;h=818360b16f4ac008b15dd9db049981f7f9f7c677;hb=363ce48d64d1a036b86d29564bf6ad367126c2b1;hp=b453f235010a4c9a8f8e5ee1fd408da29db12c27;hpb=38d3035f027881bb2baffdaffc8cd666d3df5dba;p=picoclvr.git

diff --git a/expr.py b/expr.py
index b453f23..818360b 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 +48,30 @@ 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):
+    assert nb_variables <= 26
     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)
@@ -66,7 +79,7 @@ def generate_sequences(nb, nb_variables=5, length=20):
 
         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
 
@@ -75,8 +88,10 @@ if __name__ == "__main__":
     import time
 
     start_time = time.perf_counter()
-    sequences = generate_sequences(1000)
+    sequences = generate_sequences(1000, length=30)
     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]))