X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=expr.py;h=f294d6874451c0ff6101d4a299c9b44c76595dd7;hb=a8f039a9b491b1b4b47f6b9f8123c7261e758661;hp=e539fcbb8ec58c17a33dd4686669546a17713df9;hpb=233f57347c9560aec2f3cbaf001a8efa56a0243b;p=picoclvr.git

diff --git a/expr.py b/expr.py
index e539fcb..f294d68 100755
--- a/expr.py
+++ b/expr.py
@@ -44,10 +44,12 @@ def random_expr(variables, budget):
 def generate_program(nb_variables, length):
     s = ""
     variables = set()
+
     while len(s) < length:
         v = random_var(nb_variables=nb_variables)
         s += v + "=" + random_expr(variables, budget=20) + ";"
         variables.add(v)
+
     return s, variables
 
 
@@ -60,15 +62,19 @@ def extract_results(seq):
     return results
 
 
-def generate_sequences(nb, nb_variables=5, length=20, randomize_length=False):
+def generate_sequences(nb, nb_variables=5, length=20):
     assert nb_variables <= 26
     sequences = []
+    result_max = 99
+
     for n in range(nb):
+        # We take length itself half of the time, and uniform between
+        # 1 and length otherwise. The actual length can be slightly
+        # greater
+
+        l = min(length, 1 + torch.randint(length * 2, (1,)).item())
         result = None
-        while result == None or max(result.values()) > 100:
-            l = length
-            if l > 5 and randomize_length:
-                l = 5 + torch.randint(l - 5, (1,)).item()
+        while result == None or max(result.values()) > result_max:
             p, v = generate_program(nb_variables, l)
             v = ", ".join(['"' + v + '": ' + v for v in v])
             ldict = {}
@@ -86,7 +92,7 @@ if __name__ == "__main__":
     import time
 
     start_time = time.perf_counter()
-    sequences = generate_sequences(1000, length=30)
+    sequences = generate_sequences(1000, length=40)
     end_time = time.perf_counter()
     for s in sequences[:10]:
         print(s)