X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=expr.py;h=685efd3b9319c87abe0e5c76e9c84e731904c10b;hb=5332c56acd44d7049f3fbb33a8643482e0c71f4d;hp=f294d6874451c0ff6101d4a299c9b44c76595dd7;hpb=a8f039a9b491b1b4b47f6b9f8123c7261e758661;p=picoclvr.git

diff --git a/expr.py b/expr.py
index f294d68..685efd3 100755
--- a/expr.py
+++ b/expr.py
@@ -1,5 +1,10 @@
 #!/usr/bin/env python
 
+# Any copyright is dedicated to the Public Domain.
+# https://creativecommons.org/publicdomain/zero/1.0/
+
+# Written by Francois Fleuret <francois@fleuret.org>
+
 import math, re
 
 import torch, torchvision
@@ -16,56 +21,46 @@ def random_var(nb_variables=None, variables=None):
         return l[torch.randint(len(l), (1,)).item()]
 
 
-def random_expr(variables, budget):
+def random_expr(variables, operand_max, budget):
     if budget <= 5:
         op = torch.randint(2, (1,)).item()
         if op == 0 and len(variables) > 0:
             return random_var(variables=variables)
         else:
-            return str(torch.randint(10, (1,)).item())
+            return str(torch.randint(operand_max + 1, (1,)).item())
     else:
         op = torch.randint(3, (1,)).item()
         if op == 0:
-            e = random_expr(variables, budget - 2)
+            e = random_expr(variables, operand_max, budget - 2)
             if ("+" in e or "-" in e or "*" in e) and (e[0] != "(" or e[-1] != ")"):
                 return "(" + e + ")"
             else:
                 return e
         else:
             b = 2 + torch.randint(budget - 5, (1,)).item()
-            e1 = random_expr(variables, b)
-            e2 = random_expr(variables, budget - b - 1)
+            e1 = random_expr(variables, operand_max, b)
+            e2 = random_expr(variables, operand_max, budget - b - 1)
             if op == 1:
                 return e1 + "+" + e2
             elif op == 2:
                 return e1 + "*" + e2
 
 
-def generate_program(nb_variables, length):
+def generate_program(nb_variables, operand_max, length):
     s = ""
     variables = set()
 
     while len(s) < length:
         v = random_var(nb_variables=nb_variables)
-        s += v + "=" + random_expr(variables, budget=20) + ";"
+        s += v + "=" + random_expr(variables, operand_max, budget=20) + ";"
         variables.add(v)
 
     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, operand_max=9, result_max=99):
     assert nb_variables <= 26
     sequences = []
-    result_max = 99
 
     for n in range(nb):
         # We take length itself half of the time, and uniform between
@@ -75,7 +70,7 @@ def generate_sequences(nb, nb_variables=5, length=20):
         l = min(length, 1 + torch.randint(length * 2, (1,)).item())
         result = None
         while result == None or max(result.values()) > result_max:
-            p, v = generate_program(nb_variables, l)
+            p, v = generate_program(nb_variables, operand_max, l)
             v = ", ".join(['"' + v + '": ' + v for v in v])
             ldict = {}
             exec(p + "result={" + v + "}", globals(), ldict)
@@ -88,6 +83,15 @@ def generate_sequences(nb, nb_variables=5, length=20):
     return sequences
 
 
+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
+
+
 if __name__ == "__main__":
     import time