fix some typo in doc/comments (microsoft#1389)

* fix typo in docstrings

* fix typo

* fix typo

* fix black lint

* fix black lint

Author: qianyun210603

qlib/contrib/model/pytorch_adarnn.py

@@ -56,7 +56,7 @@ def __init__(
         n_splits=2,
         GPU=0,
         seed=None,
-        **kwargs
+        **_
     ):
         # Set logger.
         self.logger = get_module_logger("ADARNN")
@@ -81,7 +81,7 @@ def __init__(
         self.optimizer = optimizer.lower()
         self.loss = loss
         self.n_splits = n_splits
-        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
+        self.device = torch.device("cuda:%d" % GPU if torch.cuda.is_available() and GPU >= 0 else "cpu")
         self.seed = seed
 
         self.logger.info(
@@ -213,7 +213,8 @@ def train_AdaRNN(self, train_loader_list, epoch, dist_old=None, weight_mat=None)
             weight_mat = self.transform_type(out_weight_list)
             return weight_mat, None
 
-    def calc_all_metrics(self, pred):
+    @staticmethod
+    def calc_all_metrics(pred):
         """pred is a pandas dataframe that has two attributes: score (pred) and label (real)"""
         res = {}
         ic = pred.groupby(level="datetime").apply(lambda x: x.label.corr(x.score))
@@ -259,8 +260,6 @@ def fit(
 
         save_path = get_or_create_path(save_path)
         stop_steps = 0
-        best_score = -np.inf
-        best_epoch = 0
         evals_result["train"] = []
         evals_result["valid"] = []
 
@@ -400,7 +399,7 @@ def __init__(
         self.model_type = model_type
         self.trans_loss = trans_loss
         self.len_seq = len_seq
-        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
+        self.device = torch.device("cuda:%d" % GPU if torch.cuda.is_available() and GPU >= 0 else "cpu")
         in_size = self.n_input
 
         features = nn.ModuleList()
@@ -499,7 +498,8 @@ def process_gate_weight(self, out, index):
         res = self.softmax(weight).squeeze()
         return res
 
-    def get_features(self, output_list):
+    @staticmethod
+    def get_features(output_list):
         fea_list_src, fea_list_tar = [], []
         for fea in output_list:
             fea_list_src.append(fea[0 : fea.size(0) // 2])
@@ -561,7 +561,7 @@ def __init__(self, loss_type="cosine", input_dim=512, GPU=0):
         """
         self.loss_type = loss_type
         self.input_dim = input_dim
-        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
+        self.device = torch.device("cuda:%d" % GPU if torch.cuda.is_available() and GPU >= 0 else "cpu")
 
     def compute(self, X, Y):
         """Compute adaptation loss
@@ -676,7 +676,8 @@ def __init__(self, kernel_type="linear", kernel_mul=2.0, kernel_num=5):
         self.fix_sigma = None
         self.kernel_type = kernel_type
 
-    def guassian_kernel(self, source, target, kernel_mul=2.0, kernel_num=5, fix_sigma=None):
+    @staticmethod
+    def guassian_kernel(source, target, kernel_mul=2.0, kernel_num=5, fix_sigma=None):
         n_samples = int(source.size()[0]) + int(target.size()[0])
         total = torch.cat([source, target], dim=0)
         total0 = total.unsqueeze(0).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))
@@ -691,7 +692,8 @@ def guassian_kernel(self, source, target, kernel_mul=2.0, kernel_num=5, fix_sigm
         kernel_val = [torch.exp(-L2_distance / bandwidth_temp) for bandwidth_temp in bandwidth_list]
         return sum(kernel_val)
 
-    def linear_mmd(self, X, Y):
+    @staticmethod
+    def linear_mmd(X, Y):
         delta = X.mean(axis=0) - Y.mean(axis=0)
         loss = delta.dot(delta.T)
         return loss

qlib/contrib/strategy/signal_strategy.py

@@ -428,7 +428,7 @@ def get_risk_data(self, date):
         specific_risk = load_dataset(root + "/" + self.specific_risk_path, index_col=[0])
 
         if not factor_exp.index.equals(specific_risk.index):
-            # NOTE: for stocks missing specific_risk, we always assume it have the highest volatility
+            # NOTE: for stocks missing specific_risk, we always assume it has the highest volatility
             specific_risk = specific_risk.reindex(factor_exp.index, fill_value=specific_risk.max())
 
         universe = factor_exp.index.tolist()

qlib/model/riskmodel/structured.py

@@ -18,7 +18,7 @@ class StructuredCovEstimator(RiskModel):
     `B` is the regression coefficients matrix for all observations (row) on
     all factors (columns), and `U` is the residual matrix with shape like `X`.
 
-    Therefore the structured covariance can be estimated by
+    Therefore, the structured covariance can be estimated by
         cov(X.T) = F @ cov(B.T) @ F.T + diag(var(U))
 
     In finance domain, there are mainly three methods to design `F` [1][2]:

qlib/workflow/__init__.py

@@ -155,7 +155,7 @@ def search_records(self, experiment_ids, **kwargs):
 
         The arguments of this function are not set to be rigid, and they will be different with different implementation of
         ``ExpManager`` in ``Qlib``. ``Qlib`` now provides an implementation of ``ExpManager`` with mlflow, and here is the
-        example code of the this method with the ``MLflowExpManager``:
+        example code of the method with the ``MLflowExpManager``:
 
         .. code-block:: Python
 

qlib/workflow/record_temp.py

@@ -30,7 +30,8 @@ class RecordTemp:
     """
 
     artifact_path = None
-    depend_cls = None  # the depend class of the record; the record will depend on the results generated by `depend_cls`
+    depend_cls = None  # the dependant class of the record; the record will depend on the results generated by
+    # `depend_cls`
 
     @classmethod
     def get_path(cls, path=None):
@@ -119,7 +120,7 @@ def check(self, include_self: bool = False, parents: bool = True):
         Check if the records is properly generated and saved.
         It is useful in following examples
 
-        - checking if the depended files complete before generating new things.
+        - checking if the dependant files complete before generating new things.
         - checking if the final files is completed
 
         Parameters
@@ -186,7 +187,7 @@ def generate_label(dataset):
         return raw_label
 
     def generate(self, **kwargs):
-        # generate prediciton
+        # generate prediction
         pred = self.model.predict(self.dataset)
         if isinstance(pred, pd.Series):
             pred = pred.to_frame("score")
@@ -285,7 +286,8 @@ def list(self):
 
 class SigAnaRecord(ACRecordTemp):
     """
-    This is the Signal Analysis Record class that generates the analysis results such as IC and IR. This class inherits the ``RecordTemp`` class.
+    This is the Signal Analysis Record class that generates the analysis results such as IC and IR.
+    This class inherits the ``RecordTemp`` class.
     """
 
     artifact_path = "sig_analysis"
@@ -382,7 +384,7 @@ def __init__(
         indicator_analysis_freq : str|List[str]
             indicator analysis freq of report
         indicator_analysis_method : str, optional, default by None
-            the candidated values include 'mean', 'amount_weighted', 'value_weighted'
+            the candidate values include 'mean', 'amount_weighted', 'value_weighted'
         """
         super().__init__(recorder=recorder, skip_existing=skip_existing, **kwargs)
 
@@ -456,9 +458,9 @@ def _generate(self, **kwargs):
         pred = self.load("pred.pkl")
 
         # replace the "<PRED>" with prediction saved before
-        placehorder_value = {"<PRED>": pred}
+        placeholder_value = {"<PRED>": pred}
         for k in "executor_config", "strategy_config":
-            setattr(self, k, fill_placeholder(getattr(self, k), placehorder_value))
+            setattr(self, k, fill_placeholder(getattr(self, k), placeholder_value))
 
         # if the backtesting time range is not set, it will automatically extract time range from the prediction file
         dt_values = pred.index.get_level_values("datetime")

scripts/data_collector/pit/README.md

@@ -19,7 +19,7 @@ cd qlib/scripts/data_collector/pit/
 python collector.py download_data --source_dir ~/.qlib/stock_data/source/pit --start 2000-01-01 --end 2020-01-01 --interval quarterly
 ```
 
-Downloading all data from the stock is very time consuming. If you just want run a quick test on a few stocks,  you can run the command below
+Downloading all data from the stock is very time-consuming. If you just want to run a quick test on a few stocks,  you can run the command below
 ```bash
 python collector.py download_data --source_dir ~/.qlib/stock_data/source/pit --start 2000-01-01 --end 2020-01-01 --interval quarterly --symbol_regex "^(600519|000725).*"
 ```