Merge pull request #348 from MannLabs/liniting_rule_B

liniting_rule_B

.secrets.baseline

@@ -139,6 +139,16 @@
     }
   ],
   "results": {
+    ".github/workflows/create_release.yml": [
+      {
+        "type": "Secret Keyword",
+        "filename": ".github/workflows/create_release.yml",
+        "hashed_secret": "3e26d6750975d678acb8fa35a0f69237881576b0",
+        "is_verified": false,
+        "line_number": 15,
+        "is_secret": false
+      }
+    ],
     "docs/workflow_mq.html": [
       {
         "type": "Base64 High Entropy String",
@@ -150,5 +160,5 @@
       }
     ]
   },
-  "generated_at": "2024-09-18T09:54:14Z"
+  "generated_at": "2024-10-08T15:30:41Z"
 }

README.md

@@ -148,6 +148,13 @@ You can run the checks yourself using:
 pre-commit run --all-files
 ```
 
+##### The `detect-secrets` hook fails
+This is because you added some code that was identified as a potential secret.
+1. Run `detect-secrets scan --exclude-files testfiles --exclude-lines '"(hash|id|image/\w+)":.*' > .secrets.baseline`
+(check `.pre-commit-config.yaml` for the exact parameters)
+2. Run `detect-secrets audit .secrets.baseline` and check if the detected 'secret' is actually a secret
+3. Commit the latest version of `.secrets.baseline`
+
 
 
 ---

alphastats/DataSet.py

@@ -328,7 +328,7 @@ def plot_volcano(
         perm: int = 100,
         fdr: float = 0.05,
         # compare_preprocessing_modes: bool = False, # TODO reimplement
-        color_list: list = [],
+        color_list: list = None,
     ):
         """Plot Volcano Plot
 
@@ -360,6 +360,8 @@ def plot_volcano(
         #     return results
         #
         # else:
+        if color_list is None:
+            color_list = []
         volcano_plot = VolcanoPlot(
             mat=self.mat,
             rawinput=self.rawinput,

alphastats/gui/AlphaPeptStats.py

@@ -29,9 +29,7 @@
 _this_directory = os.path.dirname(_this_file)
 icon = os.path.join(_this_directory, "alphapeptstats_logo.png")
 
-header_html = img_center + "<img src='data:image/png;base64,{}'>".format(
-    img_to_bytes(icon)
-)
+header_html = img_center + f"<img src='data:image/png;base64,{img_to_bytes(icon)}'>"
 
 st.markdown(
     header_html,

alphastats/gui/utils/ollama_utils.py

@@ -356,7 +356,7 @@ def display_chat_history(self):
         -------
         None
         """
-        for i, message in enumerate(self.messages):
+        for message in self.messages:
             role = message["role"].capitalize()
             content = message["content"]
 

alphastats/gui/utils/openai_utils.py

@@ -155,7 +155,7 @@ def send_message_save_thread(
         plots = None
     messages = client.beta.threads.messages.list(thread_id=thread_id)
     st.session_state[storing_variable] = []
-    for num, message in enumerate(messages.data[::-1]):
+    for message in messages.data[::-1]:
         role = message.role
         if message.content:
             content = message.content[0].text.value

alphastats/loader/MaxQuantLoader.py

@@ -15,11 +15,7 @@ def __init__(
         intensity_column: Union[str, list] = "LFQ intensity [sample]",
         index_column: str = "Protein IDs",
         gene_names_column: str = "Gene names",
-        filter_columns: list = [
-            "Only identified by site",
-            "Reverse",
-            "Potential contaminant",
-        ],
+        filter_columns: list = None,
         confidence_column: str = "Q-value",
         evidence_file=None,
         sep: str = "\t",
@@ -36,6 +32,12 @@ def __init__(
             sep (str, optional): separation of the input file. Defaults to "\t".
         """
 
+        if filter_columns is None:
+            filter_columns = [
+                "Only identified by site",
+                "Reverse",
+                "Potential contaminant",
+            ]
         super().__init__(file, intensity_column, index_column, sep)
         self.filter_columns = filter_columns + self.filter_columns
         self.confidence_column = confidence_column

alphastats/multicova/multicova.py

@@ -105,19 +105,21 @@ def workflow_permutation_tvals(df, c1, c2, s0=1, n_perm=2, parallelize=False):
     res_perm = list()
     for i in np.arange(0, len(all_c_rand)):
         if parallelize:
-            res_i = df.swifter.progress_bar(False).apply(
+            res_i = df.swifter.progress_bar(
+                False
+            ).apply(
                 lambda row: perform_ttest(
-                    row[all_c_rand[i][0 : len(c1)]],
-                    row[all_c_rand[i][len(c1) : len(c1) + len(c2)]],
+                    row[all_c_rand[i][0 : len(c1)]],  # noqa: B023
+                    row[all_c_rand[i][len(c1) : len(c1) + len(c2)]],  # noqa: B023
                     s0=s0,
                 ),
                 axis=1,
             )
         else:
             res_i = df.apply(
                 lambda row: perform_ttest(
-                    row[all_c_rand[i][0 : len(c1)]],
-                    row[all_c_rand[i][len(c1) : len(c1) + len(c2)]],
+                    row[all_c_rand[i][0 : len(c1)]],  # noqa: B023
+                    row[all_c_rand[i][len(c1) : len(c1) + len(c2)]],  # noqa: B023
                     s0=s0,
                 ),
                 axis=1,
@@ -312,13 +314,17 @@ def get_fdr_line(
     n_x,
     n_y,
     plot=False,
-    fc_s=np.arange(0, 6, 0.01),
-    s_s=np.arange(0.005, 6, 0.005),
+    fc_s=None,
+    s_s=None,
 ):
     """
     Function to get the fdr line for a volcano plot as specified tval_s0
     limit, s0, n_x and n_y.
     """
+    if fc_s is None:
+        fc_s = np.arange(0, 6, 0.01)
+    if s_s is None:
+        s_s = np.arange(0.005, 6, 0.005)
     pvals = np.ones(len(fc_s))
     svals = np.zeros(len(fc_s))
     for i in np.arange(0, len(fc_s)):
@@ -490,17 +496,22 @@ def regression_workflow_permutation(y, X_rand, s0):
     return res_rand
 
 
-def get_fdr_line_regression(
+def get_fdr_line_regression(  # TODO: unused
     t_limits,
     s0,
     X,
     plot=False,
-    fc_s=np.arange(0, 6, 0.01),
-    s_s=np.arange(0.005, 6, 0.005),
+    fc_s=None,
+    s_s=None,
 ):
     """
     Function to get the fdr line for a volcano plot as specified tval_s0 limit, s0, n_x and n_y.
     """
+    if fc_s is None:
+        fc_s = np.arange(0, 6, 0.01)
+    if fc_s is None:
+        s_s = np.arange(0.005, 6, 0.005)
+
     # pvals = [list(np.ones(len(fc_s)))] * X.shape[1]
     pvals = [list(np.ones(len(fc_s))) for i in range(0, X.shape[1])]
     # print(pvals)
@@ -565,7 +576,8 @@ def perform_ttest_getMaxS_regression(fc, s, s0, X):
 
 def generate_perms(n, n_rand, seed=42):
     """
-    Generate n_rand permutations of indeces ranging from 0 to n.
+    Generate n_rand permutations of indices ranging from 0 to n.
+    # TODO: replace with something from a library
     """
     np.random.seed(seed)
     idx_v = np.arange(0, n)
@@ -574,18 +586,16 @@ def generate_perms(n, n_rand, seed=42):
     n_rand_max = math.factorial(n) - 1
     if n_rand_max <= n_rand:
         print(
-            "{} random permutations cannot be created. The maximum of n_rand={} is used instead.".format(
-                n_rand, n_rand_max
-            )
+            f"{n_rand} random permutations cannot be created. The maximum of n_rand={n_rand_max} is used instead."
         )
         n_rand = n_rand_max
     while n_rand_i < n_rand:
         rand_i = list(np.random.permutation(idx_v))
         if np.all(rand_i == idx_v):
-            next
+            continue
         else:
             if rand_i in rand_v:
-                next
+                continue
             else:
                 rand_v.append(rand_i)
                 n_rand_i = len(rand_v)

alphastats/plots/VolcanoPlot.py

@@ -56,8 +56,10 @@ def __init__(
         plot=True,
         perm=100,
         fdr=0.05,
-        color_list=[],
+        color_list=None,
     ):
+        if color_list is None:
+            color_list = []
         self.mat: pd.DataFrame = mat
         self.rawinput = rawinput
         self.metadata: pd.DataFrame = metadata

alphastats/utils.py

@@ -57,8 +57,8 @@ def check_internetconnection():
     try:
         connection.request("HEAD", "/")
         return True
-    except Exception:
-        raise ConnectionError("No internet connection available.")
+    except Exception as e:
+        raise ConnectionError("No internet connection available.") from e
     finally:
         connection.close()
 

pyproject.toml

@@ -7,18 +7,19 @@ extend-exclude = [".bumpversion.cfg", ".secrets.baseline"]
 #    "E",
 #    # Pyflakes
 #    "F",
-#    # pyupgrade
-#    "UP",
+    # pyupgrade
+    "UP",
 #    # flake8-bugbear
-#    "B",
+    "B",
 #    # flake8-simplify
     "SIM",
     # isort
     "I",
  ]
 
-# ignore = [
+ignore = [
 #    "E501",  # Line too long  (ruff wraps code, but not docstrings)
-#    "B028",  #  No explicit `stacklevel` keyword argument found (for warnings)
+    "B028",  #  No explicit `stacklevel` keyword argument found (for warnings)
 #    "B905"  # This causes problems in numba code: `zip()` without an explicit `strict=` parameter
-# ]
+     "B019" # Use of `functools.lru_cache` or `functools.cache` on methods can lead to memory leaks  TODO: revisit
+]

setup.py

@@ -11,7 +11,7 @@
 
 
 def get_long_description():
-    with open("README.md", "r") as readme_file:
+    with open("README.md") as readme_file:
         long_description = readme_file.read()
     return long_description
 

tests/test_DataSet.py

@@ -31,13 +31,6 @@ class BaseTestDataSet:
     # this is wrapped in a nested class so it doesnt get called separatly when testing
     # plus to avoid multiple inheritance
     class BaseTest(unittest.TestCase):
-        @contextmanager
-        def assertNotRaises(self, exc_type):
-            try:
-                yield None
-            except exc_type:
-                raise self.failureException("{} raised".format(exc_type.__name__))
-
         def __init__(self, *args, **kwargs):
             super().__init__(*args, **kwargs)
 
@@ -49,8 +42,8 @@ def __init__(self, *args, **kwargs):
             self.comparison_column = None
 
         def test_check_loader_no_error(self):
-            with self.assertNotRaises(ValueError):
-                self.obj._check_loader(loader=self.loader)
+            self.obj._check_loader(loader=self.loader)
+            # nothing raised -> ok
 
         def test_check_loader_error_invalid_column(self):
             #  invalid index column

tests/test_loaders.py

@@ -24,13 +24,6 @@ class BaseTestLoader:
     # this is wrapped in a nested class so it doesnt get called separatly when testing
     # plus to avoid multiple inheritance
     class BaseTest(unittest.TestCase):
-        @contextmanager
-        def assertNotRaises(self, exc_type):
-            try:
-                yield None
-            except exc_type:
-                raise self.failureException("{} raised".format(exc_type.__name__))
-
         def test_dataformat(self):
             # check if loaded data is pandas dataframe
             self.assertIsInstance(self.obj.rawinput, pd.DataFrame)
@@ -46,8 +39,9 @@ def test_check_if_columns_are_present_error(self):
         def test_check_if_columns_are_present_no_error(self):
             # check if columns are present
             # check if error gets raised when column is not present
-            with self.assertNotRaises(KeyError):
-                self.obj._check_if_columns_are_present()
+            self.obj._check_if_columns_are_present()
+
+            # nothing raised -> ok
 
         @patch("logging.Logger.warning")
         def test_check_if_indexcolumn_is_unique_warning(self, mock):