fix_typo (#790)

Signed-off-by: unknown <lv.linlang@qq.com>

qlib/contrib/model/highfreq_gdbt_model.py

@@ -56,7 +56,7 @@ class HFLGBModel(ModelFT, LightGBMFInt):
 
     def hf_signal_test(self, dataset: DatasetH, threhold=0.2):
         """
-        Test the sigal in high frequency test set
+        Test the signal in high frequency test set
         """
         if self.model == None:
             raise ValueError("Model hasn't been trained yet")

qlib/contrib/model/pytorch_tabnet.py

@@ -446,7 +446,7 @@ class TabNet(nn.Module):
         Args:
             n_d: dimension of the features used to calculate the final results
             n_a: dimension of the features input to the attention transformer of the next step
-            n_shared: numbr of shared steps in feature transfomer(optional)
+            n_shared: numbr of shared steps in feature transformer(optional)
             n_ind: number of independent steps in feature transformer
             n_steps: number of steps of pass through tabbet
             relax coefficient:
@@ -479,7 +479,7 @@ class TabNet(nn.Module):
         out = torch.zeros(x.size(0), self.n_d).to(x.device)
         for step in self.steps:
             x_te, l = step(x, x_a, priors)
-            out += F.relu(x_te[:, : self.n_d])  # split the feautre from feat_transformer
+            out += F.relu(x_te[:, : self.n_d])  # split the feature from feat_transformer
             x_a = x_te[:, self.n_d :]
             sparse_loss.append(l)
         return self.fc(out), sum(sparse_loss)

qlib/contrib/model/pytorch_tra.py

@@ -232,7 +232,7 @@ class TRAModel(Model):
                     choice_all.append(pd.DataFrame(choice.detach().cpu().numpy(), index=index))
                 decay = self.rho ** (self.global_step // 100)  # decay every 100 steps
                 lamb = 0 if is_pretrain else self.lamb * decay
-                reg = prob.log().mul(P).sum(dim=1).mean()  # train router to predict OT assignment
+                reg = prob.log().mul(P).sum(dim=1).mean()  # train router to predict TO assignment
                 if self._writer is not None and not is_pretrain:
                     self._writer.add_scalar("training/router_loss", -reg.item(), self.global_step)
                     self._writer.add_scalar("training/reg_loss", loss.item(), self.global_step)
@@ -663,7 +663,7 @@ class TRA(nn.Module):
 
     """Temporal Routing Adaptor (TRA)
 
-    TRA takes historical prediction erros & latent representation as inputs,
+    TRA takes historical prediction errors & latent representation as inputs,
     then routes the input sample to a specific predictor for training & inference.
 
     Args:

qlib/contrib/model/pytorch_utils.py

@@ -33,5 +33,5 @@ def count_parameters(models_or_parameters, unit="m"):
     elif unit == "gb" or unit == "g":
         counts /= 2 ** 30
     elif unit is not None:
-        raise ValueError("Unknow unit: {:}".format(unit))
+        raise ValueError("Unknown unit: {:}".format(unit))
     return counts