diff --git a/docs/conf.py b/docs/conf.py
index 6e52b0e34..a7147a964 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -54,9 +54,9 @@ master_doc = "index"
 
 
 # General information about the project.
-project = u"QLib"
-copyright = u"Microsoft"
-author = u"Microsoft"
+project = "QLib"
+copyright = "Microsoft"
+author = "Microsoft"
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -174,7 +174,7 @@ latex_elements = {
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, "qlib.tex", u"QLib Documentation", u"Microsoft", "manual"),
+    (master_doc, "qlib.tex", "QLib Documentation", "Microsoft", "manual"),
 ]
 
 
@@ -182,7 +182,7 @@ latex_documents = [
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [(master_doc, "qlib", u"QLib Documentation", [author], 1)]
+man_pages = [(master_doc, "qlib", "QLib Documentation", [author], 1)]
 
 
 # -- Options for Texinfo output -------------------------------------------
@@ -194,7 +194,7 @@ texinfo_documents = [
     (
         master_doc,
         "QLib",
-        u"QLib Documentation",
+        "QLib Documentation",
         author,
         "QLib",
         "One line description of project.",
diff --git a/examples/benchmarks/TRA/src/model.py b/examples/benchmarks/TRA/src/model.py
index f6ee69af3..cff94388e 100644
--- a/examples/benchmarks/TRA/src/model.py
+++ b/examples/benchmarks/TRA/src/model.py
@@ -130,7 +130,7 @@ class TRAModel(Model):
 
             if prob is not None:
                 P = sinkhorn(-L, epsilon=0.01)  # sample assignment matrix
-                lamb = self.lamb * (self.rho ** self.global_step)
+                lamb = self.lamb * (self.rho**self.global_step)
                 reg = prob.log().mul(P).sum(dim=-1).mean()
                 loss = loss - lamb * reg
 
@@ -547,7 +547,7 @@ def evaluate(pred):
     score = pred.score
     label = pred.label
     diff = score - label
-    MSE = (diff ** 2).mean()
+    MSE = (diff**2).mean()
     MAE = (diff.abs()).mean()
     IC = score.corr(label)
     return {"MSE": MSE, "MAE": MAE, "IC": IC}
diff --git a/examples/orderbook_data/example.py b/examples/orderbook_data/example.py
index 3daa0a1ee..f8bd84ea7 100644
--- a/examples/orderbook_data/example.py
+++ b/examples/orderbook_data/example.py
@@ -21,7 +21,7 @@ class TestClass(unittest.TestCase):
         provider_uri = "~/.qlib/qlib_data/yahoo_cn_1min"
         qlib.init(
             provider_uri=provider_uri,
-            mem_cache_size_limit=1024 ** 3 * 2,
+            mem_cache_size_limit=1024**3 * 2,
             mem_cache_type="sizeof",
             kernels=1,
             expression_provider={"class": "LocalExpressionProvider", "kwargs": {"time2idx": False}},
diff --git a/qlib/contrib/data/processor.py b/qlib/contrib/data/processor.py
index e8ea38870..875e9b531 100644
--- a/qlib/contrib/data/processor.py
+++ b/qlib/contrib/data/processor.py
@@ -59,10 +59,10 @@ class ConfigSectionProcessor(Processor):
 
         # Features
         cols = df_focus.columns[df_focus.columns.str.contains("^KLEN|^KLOW|^KUP")]
-        df_focus[cols] = df_focus[cols].apply(lambda x: x ** 0.25).groupby(level="datetime").apply(_feature_norm)
+        df_focus[cols] = df_focus[cols].apply(lambda x: x**0.25).groupby(level="datetime").apply(_feature_norm)
 
         cols = df_focus.columns[df_focus.columns.str.contains("^KLOW2|^KUP2")]
-        df_focus[cols] = df_focus[cols].apply(lambda x: x ** 0.5).groupby(level="datetime").apply(_feature_norm)
+        df_focus[cols] = df_focus[cols].apply(lambda x: x**0.5).groupby(level="datetime").apply(_feature_norm)
 
         _cols = [
             "KMID",
diff --git a/qlib/contrib/model/double_ensemble.py b/qlib/contrib/model/double_ensemble.py
index 9ce005507..228997ba8 100644
--- a/qlib/contrib/model/double_ensemble.py
+++ b/qlib/contrib/model/double_ensemble.py
@@ -160,7 +160,7 @@ class DEnsembleModel(Model, FeatureInt):
         h_avg = h.groupby("bins")["h_value"].mean()
         weights = pd.Series(np.zeros(N, dtype=float))
         for i_b, b in enumerate(h_avg.index):
-            weights[h["bins"] == b] = 1.0 / (self.decay ** k_th * h_avg[i_b] + 0.1)
+            weights[h["bins"] == b] = 1.0 / (self.decay**k_th * h_avg[i_b] + 0.1)
         return weights
 
     def feature_selection(self, df_train, loss_values):
diff --git a/qlib/contrib/model/pytorch_adarnn.py b/qlib/contrib/model/pytorch_adarnn.py
index b5700def6..bda115d83 100644
--- a/qlib/contrib/model/pytorch_adarnn.py
+++ b/qlib/contrib/model/pytorch_adarnn.py
@@ -682,9 +682,9 @@ class MMD_loss(nn.Module):
         if fix_sigma:
             bandwidth = fix_sigma
         else:
-            bandwidth = torch.sum(L2_distance.data) / (n_samples ** 2 - n_samples)
+            bandwidth = torch.sum(L2_distance.data) / (n_samples**2 - n_samples)
         bandwidth /= kernel_mul ** (kernel_num // 2)
-        bandwidth_list = [bandwidth * (kernel_mul ** i) for i in range(kernel_num)]
+        bandwidth_list = [bandwidth * (kernel_mul**i) for i in range(kernel_num)]
         kernel_val = [torch.exp(-L2_distance / bandwidth_temp) for bandwidth_temp in bandwidth_list]
         return sum(kernel_val)
 
diff --git a/qlib/contrib/model/pytorch_tra.py b/qlib/contrib/model/pytorch_tra.py
index 81c9ba145..5c7484c32 100644
--- a/qlib/contrib/model/pytorch_tra.py
+++ b/qlib/contrib/model/pytorch_tra.py
@@ -742,7 +742,7 @@ def evaluate(pred):
     score = pred.score
     label = pred.label
     diff = score - label
-    MSE = (diff ** 2).mean()
+    MSE = (diff**2).mean()
     MAE = (diff.abs()).mean()
     IC = score.corr(label, method="spearman")
     return {"MSE": MSE, "MAE": MAE, "IC": IC}
diff --git a/qlib/contrib/model/pytorch_utils.py b/qlib/contrib/model/pytorch_utils.py
index 224809dc2..eb35c383b 100644
--- a/qlib/contrib/model/pytorch_utils.py
+++ b/qlib/contrib/model/pytorch_utils.py
@@ -27,11 +27,11 @@ def count_parameters(models_or_parameters, unit="m"):
         counts = sum(v.numel() for v in models_or_parameters)
     unit = unit.lower()
     if unit in ("kb", "k"):
-        counts /= 2 ** 10
+        counts /= 2**10
     elif unit in ("mb", "m"):
-        counts /= 2 ** 20
+        counts /= 2**20
     elif unit in ("gb", "g"):
-        counts /= 2 ** 30
+        counts /= 2**30
     elif unit is not None:
         raise ValueError("Unknown unit: {:}".format(unit))
     return counts
diff --git a/qlib/contrib/model/tcn.py b/qlib/contrib/model/tcn.py
index aa61bd44a..173404b2b 100644
--- a/qlib/contrib/model/tcn.py
+++ b/qlib/contrib/model/tcn.py
@@ -55,7 +55,7 @@ class TemporalConvNet(nn.Module):
         layers = []
         num_levels = len(num_channels)
         for i in range(num_levels):
-            dilation_size = 2 ** i
+            dilation_size = 2**i
             in_channels = num_inputs if i == 0 else num_channels[i - 1]
             out_channels = num_channels[i]
             layers += [
diff --git a/qlib/contrib/strategy/optimizer/enhanced_indexing.py b/qlib/contrib/strategy/optimizer/enhanced_indexing.py
index 9da609005..7e42856a2 100644
--- a/qlib/contrib/strategy/optimizer/enhanced_indexing.py
+++ b/qlib/contrib/strategy/optimizer/enhanced_indexing.py
@@ -125,7 +125,7 @@ class EnhancedIndexingOptimizer(BaseOptimizer):
 
         # objective
         ret = d @ r  # excess return
-        risk = cp.quad_form(v, cov_b) + var_u @ (d ** 2)  # tracking error
+        risk = cp.quad_form(v, cov_b) + var_u @ (d**2)  # tracking error
         obj = cp.Maximize(ret - self.lamb * risk)
 
         # weight bounds
diff --git a/qlib/contrib/strategy/signal_strategy.py b/qlib/contrib/strategy/signal_strategy.py
index b0826b1ba..9d2b8124f 100644
--- a/qlib/contrib/strategy/signal_strategy.py
+++ b/qlib/contrib/strategy/signal_strategy.py
@@ -482,7 +482,7 @@ class EnhancedIndexingStrategy(WeightStrategyBase):
             r=score,
             F=factor_exp,
             cov_b=factor_cov,
-            var_u=specific_risk ** 2,
+            var_u=specific_risk**2,
             w0=cur_weight,
             wb=bench_weight,
             mfh=mask_force_hold,
diff --git a/qlib/model/riskmodel/poet.py b/qlib/model/riskmodel/poet.py
index 840384555..8946b2ac5 100644
--- a/qlib/model/riskmodel/poet.py
+++ b/qlib/model/riskmodel/poet.py
@@ -63,7 +63,7 @@ class POETCovEstimator(RiskModel):
         lamb = rate * self.thresh
         SuPCA = uhat.dot(uhat.T) / n
         SuDiag = np.diag(np.diag(SuPCA))
-        R = np.linalg.inv(SuDiag ** 0.5).dot(SuPCA).dot(np.linalg.inv(SuDiag ** 0.5))
+        R = np.linalg.inv(SuDiag**0.5).dot(SuPCA).dot(np.linalg.inv(SuDiag**0.5))
 
         if self.thresh_method == self.THRESH_HARD:
             M = R * (np.abs(R) > lamb)
@@ -78,7 +78,7 @@ class POETCovEstimator(RiskModel):
             M = M1 + M2 + M3
 
         Rthresh = M - np.diag(np.diag(M)) + np.eye(p)
-        SigmaU = (SuDiag ** 0.5).dot(Rthresh).dot(SuDiag ** 0.5)
+        SigmaU = (SuDiag**0.5).dot(Rthresh).dot(SuDiag**0.5)
         SigmaY = SigmaU + Lowrank
 
         return SigmaY
diff --git a/qlib/model/riskmodel/shrink.py b/qlib/model/riskmodel/shrink.py
index 3cb2620d1..b2594f707 100644
--- a/qlib/model/riskmodel/shrink.py
+++ b/qlib/model/riskmodel/shrink.py
@@ -174,7 +174,7 @@ class ShrinkCovEstimator(RiskModel):
             alpha = A / B
         where `n`, `p` are the dim of observations and variables respectively.
         """
-        trS2 = np.sum(S ** 2)
+        trS2 = np.sum(S**2)
         tr2S = np.trace(S) ** 2
 
         n, p = X.shape
@@ -192,8 +192,8 @@ class ShrinkCovEstimator(RiskModel):
         """
         t, n = X.shape
 
-        y = X ** 2
-        phi = np.sum(y.T.dot(y) / t - S ** 2)
+        y = X**2
+        phi = np.sum(y.T.dot(y) / t - S**2)
 
         gamma = np.linalg.norm(S - F, "fro") ** 2
 
@@ -213,11 +213,11 @@ class ShrinkCovEstimator(RiskModel):
         sqrt_var = np.sqrt(var)
         r_bar = (np.sum(S / np.outer(sqrt_var, sqrt_var)) - n) / (n * (n - 1))
 
-        y = X ** 2
-        phi_mat = y.T.dot(y) / t - S ** 2
+        y = X**2
+        phi_mat = y.T.dot(y) / t - S**2
         phi = np.sum(phi_mat)
 
-        theta_mat = (X ** 3).T.dot(X) / t - var[:, None] * S
+        theta_mat = (X**3).T.dot(X) / t - var[:, None] * S
         np.fill_diagonal(theta_mat, 0)
         rho = np.sum(np.diag(phi_mat)) + r_bar * np.sum(np.outer(1 / sqrt_var, sqrt_var) * theta_mat)
 
@@ -239,16 +239,16 @@ class ShrinkCovEstimator(RiskModel):
         cov_mkt = np.asarray(X.T.dot(X_mkt) / len(X))
         var_mkt = np.asarray(X_mkt.dot(X_mkt) / len(X))
 
-        y = X ** 2
-        phi = np.sum(y.T.dot(y)) / t - np.sum(S ** 2)
+        y = X**2
+        phi = np.sum(y.T.dot(y)) / t - np.sum(S**2)
 
-        rdiag = np.sum(y ** 2) / t - np.sum(np.diag(S) ** 2)
+        rdiag = np.sum(y**2) / t - np.sum(np.diag(S) ** 2)
         z = X * X_mkt[:, None]
         v1 = y.T.dot(z) / t - cov_mkt[:, None] * S
         roff1 = np.sum(v1 * cov_mkt[:, None].T) / var_mkt - np.sum(np.diag(v1) * cov_mkt) / var_mkt
         v3 = z.T.dot(z) / t - var_mkt * S
         roff3 = (
-            np.sum(v3 * np.outer(cov_mkt, cov_mkt)) / var_mkt ** 2 - np.sum(np.diag(v3) * cov_mkt ** 2) / var_mkt ** 2
+            np.sum(v3 * np.outer(cov_mkt, cov_mkt)) / var_mkt**2 - np.sum(np.diag(v3) * cov_mkt**2) / var_mkt**2
         )
         roff = 2 * roff1 - roff3
         rho = rdiag + roff
diff --git a/qlib/workflow/record_temp.py b/qlib/workflow/record_temp.py
index b78e421b1..e16121ffa 100644
--- a/qlib/workflow/record_temp.py
+++ b/qlib/workflow/record_temp.py
@@ -321,9 +321,9 @@ class SigAnaRecord(ACRecordTemp):
             metrics.update(
                 {
                     "Long-Short Ann Return": long_short_r.mean() * self.ann_scaler,
-                    "Long-Short Ann Sharpe": long_short_r.mean() / long_short_r.std() * self.ann_scaler ** 0.5,
+                    "Long-Short Ann Sharpe": long_short_r.mean() / long_short_r.std() * self.ann_scaler**0.5,
                     "Long-Avg Ann Return": long_avg_r.mean() * self.ann_scaler,
-                    "Long-Avg Ann Sharpe": long_avg_r.mean() / long_avg_r.std() * self.ann_scaler ** 0.5,
+                    "Long-Avg Ann Sharpe": long_avg_r.mean() / long_avg_r.std() * self.ann_scaler**0.5,
                 }
             )
             objects.update(