Update.

[picoclvr.git] / problems.py

diff --git a/problems.py b/problems.py
index 78bb64e..2c8602c 100755 (executable)
--- a/problems.py
+++ b/problems.py
@@ -21,8 +21,55 @@ class Problem:
 ####################
 
 
-class ProblemLevel0(Problem):
-    def __init__(self, nb_sentences=100, len_prompt=5, len_result=5):
+class ProblemTwoTargets(Problem):
+    def __init__(self, len_total=10, len_targets=3):
+        assert len_targets >= 3
+        assert len_total >= 3 * len_targets - 1
+        self.len_total = len_total
+        self.len_targets = len_targets
+
+    def generate_sequences(self, nb):
+        k = torch.arange(self.len_total)[None, :]
+        s = torch.randint(10, (nb, self.len_total))
+        l = torch.rand(nb, self.len_total)
+        l = l * (k <= self.len_total - self.len_targets).long()
+        k1 = l.argmax(dim=1, keepdim=True)
+        m = (k != k1).long() * (k != k1 + self.len_targets - 1).long()
+        s = s * m + 10 * (1 - m)
+        l = l * (
+            1
+            - (k + self.len_targets - 1 >= k1).long()
+            * (k < k1 + self.len_targets).long()
+        )
+        k2 = l.argmax(dim=1, keepdim=True)
+        m = (k != k2).long() * (k != k2 + self.len_targets - 1).long()
+        s = s * m + 11 * (1 - m)
+        a1 = s.gather(dim=1, index=k1 + 1 + torch.arange(self.len_targets - 2)[None, :])
+        a2 = s.gather(dim=1, index=k2 + 1 + torch.arange(self.len_targets - 2)[None, :])
+        sequences = torch.cat(
+            (
+                s,
+                torch.full((nb, 1), 12),
+                a1,
+                torch.full((nb, 1), 12),
+                a2,
+                torch.full((nb, 1), 12),
+            ),
+            1,
+        )
+        ar_mask = (sequences == 12).long()
+        ar_mask = (ar_mask.cumsum(1) - ar_mask).clamp(max=1)
+        return sequences, ar_mask
+
+    def seq2str(self, seq):
+        return "".join("0123456789-+|"[x.item()] for x in seq)
+
+
+####################
+
+
+class ProblemByHeart(Problem):
+    def __init__(self, nb_sentences=100, len_prompt=8, len_result=8):
         self.seq = torch.randint(10, (nb_sentences, len_prompt + 1 + len_result))
         self.seq[:, len_prompt] = 10
 
@@ -32,9 +79,15 @@ class ProblemLevel0(Problem):
         ar_mask = (ar_mask.cumsum(1) - ar_mask).clamp(max=1)
         return sequences, ar_mask
 
+    def seq2str(self, seq):
+        return "".join("0123456789|"[x.item()] for x in seq)
+
+
+####################
+
 
-class ProblemLevel1(Problem):
-    def __init__(self, nb_operators=100, len_source=5, len_result=8):
+class ProblemLearnOperator(Problem):
+    def __init__(self, nb_operators=100, len_source=6, len_result=9):
         self.len_source = len_source
         self.len_result = len_result
         self.len_nb_operator = int(math.log(nb_operators) / math.log(10)) + 1
@@ -51,7 +104,6 @@ class ProblemLevel1(Problem):
             // 10 ** torch.arange(self.len_nb_operator - 1, -1, -1)
         ) % 10
         marker1 = torch.full((nb, 1), 10)
-        # source = torch.randint(10, (nb, self.len_source))
         source = torch.rand(nb, 10).sort(dim=1).indices[:, : self.len_source]
         marker2 = torch.full((nb, 1), 11)
         result = operators.bmm(source[:, :, None]).squeeze(-1)
@@ -64,7 +116,10 @@ class ProblemLevel1(Problem):
         return "".join("0123456789|>"[x.item()] for x in seq)
 
 
-class ProblemLevel2(Problem):
+####################
+
+
+class ProblemGuessOperator(Problem):
     def __init__(self, len_source=5, len_result=8):
         self.len_source = len_source
         self.len_result = len_result
@@ -141,19 +196,8 @@ class ProblemAddition(Problem):
         return "".join(self.id2char[x.item()] for x in seq)
 
 
-# class ProblemUnion(Problem):
-# problems = [ProblemByheart()]
-# nb_common_codes = 100
-
-# def generate_sequences(nb_samples):
-# problem_indexes = torch.randint(len(problems), (nb_samples,))
-# nb_samples_per_problem = torch.one_hot(problem_indexes).sum(0)
-# print(f"{nb_samples_per_problem}")
-# all_seq = []
-# for nb, p in zip(nb_samples_per_problem, problems):
-# all_seq.append(p.generate_sequences(nb_samples_per_problem[nb]))
-# return all_seq
-
-# for strain, stest in zip(train_seq, test_seq):
-# s = torch.cat((strain, stest), 0)
-
+if __name__ == "__main__":
+    p = ProblemTwoTargets(12, 4)
+    s, m = p.generate_sequences(10)
+    for x in s:
+        print(p.seq2str(x))