From: François Fleuret <francois@fleuret.org>
Date: Tue, 4 Jul 2023 13:56:03 +0000 (+0200)
Subject: Update.
X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=commitdiff_plain;h=38d3035f027881bb2baffdaffc8cd666d3df5dba;p=culture.git

Update.
---

diff --git a/expr.py b/expr.py
index 8a89945..b453f23 100755
--- a/expr.py
+++ b/expr.py
@@ -7,71 +7,76 @@ import torch, torchvision
 from torch import nn
 from torch.nn import functional as F
 
+
 def random_var(nb_variables=None, variables=None):
     if variables is None:
-        return chr(ord('A') + torch.randint(nb_variables, (1,)).item())
+        return chr(ord("A") + torch.randint(nb_variables, (1,)).item())
     else:
         l = list(variables)
         return l[torch.randint(len(l), (1,)).item()]
 
+
 def random_expr(variables, budget):
     if budget <= 5:
-        op=torch.randint(2, (1,)).item()
+        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())
     else:
-        op=torch.randint(4, (1,)).item()
+        op = torch.randint(4, (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]!=")"):
-                return "("+e+")"
+            e = random_expr(variables, 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)
+            b = 2 + torch.randint(budget - 5, (1,)).item()
+            e1 = random_expr(variables, b)
+            e2 = random_expr(variables, budget - b - 1)
             if op == 1:
-                return e1+"+"+e2
+                return e1 + "+" + e2
             elif op == 2:
-                return e1+"+"+e2
+                return e1 + "+" + e2
             elif op == 3:
-                return e1+"*"+e2
+                return e1 + "*" + e2
+
 
 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 = min(20,length-3-len(s)))+";"
+        s += v + "=" + random_expr(variables, budget=min(20, length - 3 - len(s))) + ";"
         variables.add(v)
     return s, variables
 
-def generate_sequences(nb, nb_variables = 5, length=20):
-    sequences=[]
+
+def generate_sequences(nb, nb_variables=5, length=20):
+    sequences = []
     for n in range(nb):
         result = None
-        while result==None or max(result.values())>100:
-            p,v=generate_program(nb_variables, length)
-            v=", ".join([ "\""+v+"\": "+v for v in v ])
-            ldict={}
-            exec(p+"result={"+v+"}",globals(),ldict)
-            result=ldict["result"]
-
-        k=list(result.keys())
+        while result == None or max(result.values()) > 100:
+            p, v = generate_program(nb_variables, length)
+            v = ", ".join(['"' + v + '": ' + v for v in v])
+            ldict = {}
+            exec(p + "result={" + v + "}", globals(), ldict)
+            result = ldict["result"]
+
+        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
 
+
 if __name__ == "__main__":
     import time
+
     start_time = time.perf_counter()
-    sequences=generate_sequences(1000)
+    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")
-
diff --git a/main.py b/main.py
index 319e94b..b774fce 100755
--- a/main.py
+++ b/main.py
@@ -32,7 +32,10 @@ parser = argparse.ArgumentParser(
 )
 
 parser.add_argument(
-    "--task", type=str, default="picoclvr", help="picoclvr, mnist, maze, snake, stack, expr"
+    "--task",
+    type=str,
+    default="picoclvr",
+    help="picoclvr, mnist, maze, snake, stack, expr",
 )
 
 parser.add_argument("--log_filename", type=str, default="train.log", help=" ")
@@ -223,7 +226,6 @@ def masked_inplace_autoregression(
     progress_bar_desc="autoregression",
     device=torch.device("cpu"),
 ):
-
     batches = zip(input.split(batch_size), ar_mask.split(batch_size))
 
     if progress_bar_desc is not None:
@@ -1018,11 +1020,32 @@ class TaskExpr(Task):
 
         train_sequences = expr.generate_sequences(nb_train_samples)
         test_sequences = expr.generate_sequences(nb_test_samples)
-        self.char2id = dict([ (c,n) for n,c in enumerate(set("".join(train_sequences + test_sequences))) ])
-        self.id2char = dict([ (n,c) for n,c in self.char2id.items() ])
+        self.char2id = dict(
+            [
+                (c, n)
+                for n, c in enumerate(set("".join(train_sequences + test_sequences)))
+            ]
+        )
+        self.id2char = dict([(n, c) for n, c in self.char2id.items()])
         len_max = max([len(x) for x in train_sequences + test_sequences])
-        self.train_input = torch.cat([torch.tensor([char2id(c) for c in s + " "*(len_max-len(s))] for s in train_sequences)], 0)
-        self.test_input = torch.cat([torch.tensor([char2id(c) for c in s + " "*(len_max-len(s))] for s in test_sequences)], 0)
+        self.train_input = torch.cat(
+            [
+                torch.tensor(
+                    [char2id(c) for c in s + " " * (len_max - len(s))]
+                    for s in train_sequences
+                )
+            ],
+            0,
+        )
+        self.test_input = torch.cat(
+            [
+                torch.tensor(
+                    [char2id(c) for c in s + " " * (len_max - len(s))]
+                    for s in test_sequences
+                )
+            ],
+            0,
+        )
         self.nb_codes = max(self.train_input.max(), self.test_input.max()) + 1
 
     def batches(self, split="train", nb_to_use=-1, desc=None):