X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=expr.py;h=e073dcae327368c1edcda745f712ce75a5113d8e;hb=046c2b8633a415e533ec14cb72d77845f0c3e85f;hp=baee50275248c8c4a4f234ba8dc1f8f96eabe48b;hpb=495c959114942d07808788e27d9fcaa951a7d21e;p=picoclvr.git

diff --git a/expr.py b/expr.py
index baee502..e073dca 100755
--- a/expr.py
+++ b/expr.py
@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 
-import math
+import math, re
 
 import torch, torchvision
 
@@ -53,6 +53,15 @@ def generate_program(nb_variables, length):
     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, randomize_length=False):
     sequences = []
     for n in range(nb):
@@ -60,7 +69,7 @@ def generate_sequences(nb, nb_variables=5, length=20, randomize_length=False):
         while result == None or max(result.values()) > 100:
             l = length
             if l > 5 and randomize_length:
-                l = 5 + torch.randint(l-5, (1,)).item()
+                l = 5 + torch.randint(l - 5, (1,)).item()
             p, v = generate_program(nb_variables, l)
             v = ", ".join(['"' + v + '": ' + v for v in v])
             ldict = {}
@@ -69,7 +78,7 @@ def generate_sequences(nb, nb_variables=5, length=20, randomize_length=False):
 
         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
 
@@ -78,8 +87,10 @@ if __name__ == "__main__":
     import time
 
     start_time = time.perf_counter()
-    sequences = generate_sequences(1000, randomize_length=True)
+    sequences = generate_sequences(1000)
     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]))