fix_pylint_for_CI (microsoft#1119)

* fix_pylint_for_CI

* reformat_with_black

* fix_pylint_C3001

* fix_flake8_error

.github/workflows/test.yml

@@ -72,7 +72,7 @@ jobs:
       run: |
         pip install --upgrade pip
         pip install pylint
-        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0201,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' qlib --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500"
+        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' qlib --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500"
 
     # The following flake8 error codes were ignored:
       # E501 line too long

qlib/contrib/data/dataset.py

@@ -63,11 +63,20 @@ def _get_date_parse_fn(target):
         get_date_parse_fn(20120101)('2017-01-01') => 20170101
     """
     if isinstance(target, int):
-        _fn = lambda x: int(str(x).replace("-", "")[:8])  # 20200201
+
+        def _fn(x):
+            return int(str(x).replace("-", "")[:8])  # 20200201
+
     elif isinstance(target, str) and len(target) == 8:
-        _fn = lambda x: str(x).replace("-", "")[:8]  # '20200201'
+
+        def _fn(x):
+            return str(x).replace("-", "")[:8]  # '20200201'
+
     else:
-        _fn = lambda x: x  # '2021-01-01'
+
+        def _fn(x):
+            return x  # '2021-01-01'
+
     return _fn
 
 

qlib/contrib/data/handler.py

@@ -255,7 +255,10 @@ def parse_config_to_fields(config):
             exclude = config["rolling"].get("exclude", [])
             # `exclude` in dataset config unnecessary filed
             # `include` in dataset config necessary field
-            use = lambda x: x not in exclude and (include is None or x in include)
+
+            def use(x):
+                return x not in exclude and (include is None or x in include)
+
             if use("ROC"):
                 fields += ["Ref($close, %d)/$close" % d for d in windows]
                 names += ["ROC%d" % d for d in windows]

qlib/contrib/eva/alpha.py

@@ -48,7 +48,9 @@ def calc_long_short_prec(
 
     group = df.groupby(level=date_col)
 
-    N = lambda x: int(len(x) * quantile)
+    def N(x):
+        return int(len(x) * quantile)
+
     # find the top/low quantile of prediction and treat them as long and short target
     long = group.apply(lambda x: x.nlargest(N(x), columns="pred").label).reset_index(level=0, drop=True)
     short = group.apply(lambda x: x.nsmallest(N(x), columns="pred").label).reset_index(level=0, drop=True)
@@ -98,7 +100,10 @@ def calc_long_short_return(
     if dropna:
         df.dropna(inplace=True)
     group = df.groupby(level=date_col)
-    N = lambda x: int(len(x) * quantile)
+
+    def N(x):
+        return int(len(x) * quantile)
+
     r_long = group.apply(lambda x: x.nlargest(N(x), columns="pred").label.mean())
     r_short = group.apply(lambda x: x.nsmallest(N(x), columns="pred").label.mean())
     r_avg = group.label.mean()

qlib/contrib/meta/data_selection/dataset.py

@@ -290,7 +290,7 @@ def _prepare_meta_ipt(self, task):
         ic_df = self.internal_data.data_ic_df
 
         segs = task["dataset"]["kwargs"]["segments"]
-        end = max([segs[k][1] for k in ("train", "valid") if k in segs])
+        end = max(segs[k][1] for k in ("train", "valid") if k in segs)
         ic_df_avail = ic_df.loc[:end, pd.IndexSlice[:, :end]]
 
         # meta data set focus on the **information** instead of preprocess

qlib/contrib/model/highfreq_gdbt_model.py

@@ -92,7 +92,10 @@ def _prepare_data(self, dataset: DatasetH):
             # Convert label into alpha
             df_train["label"][l_name] = df_train["label"][l_name] - df_train["label"][l_name].mean(level=0)
             df_valid["label"][l_name] = df_valid["label"][l_name] - df_valid["label"][l_name].mean(level=0)
-            mapping_fn = lambda x: 0 if x < 0 else 1
+
+            def mapping_fn(x):
+                return 0 if x < 0 else 1
+
             df_train["label_c"] = df_train["label"][l_name].apply(mapping_fn)
             df_valid["label_c"] = df_valid["label"][l_name].apply(mapping_fn)
             x_train, y_train = df_train["feature"], df_train["label_c"].values

qlib/contrib/model/pytorch_hist.py

@@ -292,7 +292,9 @@ def fit(
             pretrained_model.load_state_dict(torch.load(self.model_path))
 
         model_dict = self.HIST_model.state_dict()
-        pretrained_dict = {k: v for k, v in pretrained_model.state_dict().items() if k in model_dict}
+        pretrained_dict = {
+            k: v for k, v in pretrained_model.state_dict().items() if k in model_dict  # pylint: disable=E1135
+        }
         model_dict.update(pretrained_dict)
         self.HIST_model.load_state_dict(model_dict)
         self.logger.info("Loading pretrained model Done...")

qlib/contrib/model/pytorch_tra.py

@@ -167,8 +167,8 @@ def _init_model(self):
             for param in self.tra.predictors.parameters():
                 param.requires_grad_(False)
 
-        self.logger.info("# model params: %d" % sum([p.numel() for p in self.model.parameters() if p.requires_grad]))
-        self.logger.info("# tra params: %d" % sum([p.numel() for p in self.tra.parameters() if p.requires_grad]))
+        self.logger.info("# model params: %d" % sum(p.numel() for p in self.model.parameters() if p.requires_grad))
+        self.logger.info("# tra params: %d" % sum(p.numel() for p in self.tra.parameters() if p.requires_grad))
 
         self.optimizer = optim.Adam(list(self.model.parameters()) + list(self.tra.parameters()), lr=self.lr)
 

qlib/data/dataset/__init__.py

@@ -438,7 +438,7 @@ def build_index(data: pd.DataFrame) -> Tuple[pd.DataFrame, dict]:
 
     @property
     def empty(self):
-        return self.__len__() == 0
+        return len(self) == 0
 
     def _get_indices(self, row: int, col: int) -> np.array:
         """

qlib/rl/utils/data_queue.py

@@ -145,7 +145,7 @@ def __del__(self):
     def __iter__(self):
         if not self._activated:
             raise ValueError(
-                "Need to call activate() to launch a daemon worker " "to produce data into data queue before using it."
+                "Need to call activate() to launch a daemon worker to produce data into data queue before using it."
             )
         return self._consumer()
 

qlib/workflow/task/collect.py

@@ -169,7 +169,10 @@ def __init__(
         self.experiment = experiment
         self.artifacts_path = artifacts_path
         if rec_key_func is None:
-            rec_key_func = lambda rec: rec.info["id"]
+
+            def rec_key_func(rec):
+                return rec.info["id"]
+
         if artifacts_key is None:
             artifacts_key = list(self.artifacts_path.keys())
         self.rec_key_func = rec_key_func