Merge remote-tracking branch 'origin/celltype_annotation_automl' into…

… celltype_annotation_automl

dance/transforms/filter.py

@@ -274,6 +274,20 @@ def __init__(
 @register_preprocessor("filter", "cell")
 @add_mod_and_transform
 class FilterCellsCommonMod(BaseTransform):
+    """Initialize the FilterCellsCommonMod class.
+
+    Parameters
+    ----------
+    mod1 : str
+        Name of the first modality in the single-cell dataset.
+    mod2 : str
+        Name of the second modality in the single-cell dataset.
+    sol : Optional[str], default=None
+        Name of the optional solution dataset containing cell labels or annotations.
+    **kwargs : dict
+        Additional keyword arguments passed to the base transformation class.
+
+    """
 
     def __init__(self, mod1: str, mod2: str, sol: Optional[str] = None, **kwargs):
         super().__init__(**kwargs)

dance/utils/wrappers.py

@@ -95,6 +95,8 @@ def wrapped_func(*args):
 
 
 def add_mod_and_transform(cls):
+    """A decorator that modifies a class to add functionality for working with specific
+    modalities (`mod`) in a `mudata` object."""
     original_init = cls.__init__
     original_call = cls.__call__
     cls.add_mod_and_transform = "add_mod_and_transform"
@@ -107,6 +109,16 @@ def new_init(self, *args, **kwargs):
 
     @functools.wraps(original_call)
     def new_call(self, data: Data, *args, **kwargs):
+        """
+        Parameters
+        ----------
+        data : Data
+            The input data object containing the `mudata` with multiple modalities.
+        Returns
+        -------
+        Any
+            The result of the original_call method.
+        """
         if hasattr(self, 'mod') and self.mod is not None:
             md_data = data.data
             ad_data = Data(data=transform_mod_to_anndata(md_data, self.mod))

examples/get_result_web.py

@@ -16,22 +16,23 @@
 
 def check_identical_strings(string_list):
     if not string_list:
-        raise ValueError("列表为空")
+        raise ValueError("The list is empty")
 
     arr = np.array(string_list)
     if not np.all(arr == arr[0]):
-        raise ValueError("发现不同的字符串")
+        raise ValueError("Different strings found")
 
     return string_list[0]
 
-
     # if not string_list:
-    #     raise ValueError("列表为空")
+    #     raise ValueError("The list is empty")
     # first_string = string_list[0]
     # for s in string_list[1:]:
     #     if s != first_string:
-    #         raise ValueError(f"发现不同的字符串: '{first_string}' 和 '{s}'")
+    #         raise ValueError(f"Different strings found: '{first_string}' and '{s}'")
     # return first_string
+
+
 def get_sweep_url(step_csv: pd.DataFrame, single=True):
     ids = step_csv["id"]
     sweep_urls = []
@@ -57,7 +58,7 @@ def spilt_web(url: str):
     if match:
         entity = match.group(1)
         project = match.group(2)
-        pattern = r'/sweeps/([^/?]+)'  # 正则表达式模式
+        pattern = r'/sweeps/([^/?]+)'  # Regular expression pattern
         match = re.search(pattern, url)
         if match:
             sweep_id = match.group(1)
@@ -161,8 +162,8 @@ def write_ans(tissue):
             step3_urls = []
             for i in range(3):
                 file_csv = f"{file_path}/results/params/{i}_best_test_acc.csv"
-                if not os.path.exists(file_csv):  #no parameter
-                    print(f"文件 {file_csv} 不存在，跳过。")
+                if not os.path.exists(file_csv):  # no parameter
+                    print(f"File {file_csv} does not exist, skipping.")
                     continue
                 step3_urls.append(get_sweep_url(pd.read_csv(file_csv)))
             step3_str = ",".join(step3_urls)