refactor: apply bandit checks and fixes

pycytominer/annotate.py

@@ -99,9 +99,10 @@ def annotate(
 
  if not isinstance(external_metadata, pd.DataFrame):
  if external_metadata is not None:
- assert os.path.exists(
- external_metadata
- ), f"external metadata at {external_metadata} does not exist"
+ if not os.path.exists(external_metadata):
+ raise FileNotFoundError(
+ f"external metadata at {external_metadata} does not exist"
+ )
 
  external_metadata = pd.read_csv(external_metadata)
  else:

pycytominer/cyto_utils/collate.py

@@ -9,7 +9,7 @@ def run_check_errors(cmd):
  """Run a system command, and exit if an error occurred, otherwise continue"""
  if isinstance(cmd, str):
  cmd = cmd.split()
- output = subprocess.run(cmd, capture_output=True, text=True)
+ output = subprocess.run(cmd, capture_output=True, text=True) # noqa: S603
  if output.stderr != "":
  print_cmd = " ".join(map(str, cmd))
  sys.exit(
@@ -28,7 +28,7 @@ def collate(
  csv_dir="analysis",
  aws_remote=None,
  aggregate_only=False,
- tmp_dir="/tmp",
+ tmp_dir="/tmp", # noqa: S108
  overwrite=False,
  add_image_features=True,
  image_feature_categories=["Granularity", "Texture", "ImageQuality", "Threshold"],

pycytominer/cyto_utils/collate_cmd.py

@@ -46,7 +46,7 @@
  parser.add_argument(
  "--tmp-dir",
  dest="tmp_dir",
- default="/tmp",
+ default="/tmp", # noqa: S108
  help="The temporary directory to be used by cytominer-databases for output",
  )
  parser.add_argument(

pycytominer/feature_select.py

@@ -112,11 +112,13 @@ def feature_select(
 
  # Make sure the user provides a supported operation
  if isinstance(operation, list):
- assert all(
- x in all_ops for x in operation
- ), f"Some operation(s) {operation} not supported. Choose {all_ops}"
+ if not all(x in all_ops for x in operation):
+ raise ValueError(
+ f"Some operation(s) {operation} not supported. Choose {all_ops}"
+ )
  elif isinstance(operation, str):
- assert operation in all_ops, f"{operation} not supported. Choose {all_ops}"
+ if operation not in all_ops:
+ raise ValueError(f"{operation} not supported. Choose {all_ops}")
  operation = operation.split()
  else:
  return ValueError("Operation must be a list or string")

pycytominer/normalize.py

@@ -127,7 +127,8 @@ def normalize(
  method = method.lower()
 
  avail_methods = ["standardize", "robustize", "mad_robustize", "spherize"]
- assert method in avail_methods, f"operation must be one {avail_methods}"
+ if method not in avail_methods:
+ raise ValueError(f"operation must be one {avail_methods}")
 
  if method == "standardize":
  scaler = StandardScaler()

pycytominer/operations/correlation_threshold.py

@@ -42,7 +42,8 @@ def correlation_threshold(
  # Check that the input method is supported
  method = check_correlation_method(method)
 
- assert 0 <= threshold <= 1, "threshold variable must be between (0 and 1)"
+ if not 0 <= threshold <= 1:
+ raise ValueError("threshold variable must be between (0 and 1)")
 
  # Subset dataframe and calculate correlation matrix across subset features
  if samples != "all":

pycytominer/operations/noise_removal.py

@@ -49,17 +49,19 @@ def noise_removal(
 
  # If a metadata column name is specified, use that as the perturb groups
  if isinstance(noise_removal_perturb_groups, str):
- assert noise_removal_perturb_groups in population_df.columns, (
- 'f"{perturb} not found. Are you sure it is a ' "metadata column?"
- )
+ if noise_removal_perturb_groups not in population_df.columns:
+ raise ValueError(
+ 'f"{perturb} not found. Are you sure it is a ' "metadata column?"
+ )
  group_info = population_df[noise_removal_perturb_groups]
 
  # Otherwise, the user specifies a list of perturbs
  elif isinstance(noise_removal_perturb_groups, list):
- assert len(noise_removal_perturb_groups) == len(population_df), (
- f"The length of input list: {len(noise_removal_perturb_groups)} is not equivalent to your "
- f"data: {population_df.shape[0]}"
- )
+ if not len(noise_removal_perturb_groups) == len(population_df):
+ raise ValueError(
+ f"The length of input list: {len(noise_removal_perturb_groups)} is not equivalent to your "
+ f"data: {population_df.shape[0]}"
+ )
  group_info = noise_removal_perturb_groups
  else:
  raise TypeError(

pycytominer/operations/transform.py

@@ -205,9 +205,10 @@ def fit(self, X, y=None):
  self.W = self.W @ Vt
 
  # number of columns of self.W should be equal to that of X
- assert (
- self.W.shape[1] == X.shape[1]
- ), f"Error: W has {self.W.shape[1]} columns, X has {X.shape[1]} columns"
+ if not (self.W.shape[1] == X.shape[1]):
+ raise ValueError(
+ f"Error: W has {self.W.shape[1]} columns, X has {X.shape[1]} columns"
+ )
 
  if self.W.shape[1] != X.shape[1]:
  error_detail = (

pycytominer/operations/variance_threshold.py

@@ -42,8 +42,10 @@ def variance_threshold(
 
  """
 
- assert 0 <= freq_cut <= 1, "freq_cut variable must be between (0 and 1)"
- assert 0 <= unique_cut <= 1, "unique_cut variable must be between (0 and 1)"
+ if not 0 <= freq_cut <= 1:
+ raise ValueError("freq_cut variable must be between (0 and 1)")
+ if not 0 <= unique_cut <= 1:
+ raise ValueError("unique_cut variable must be between (0 and 1)")
 
  # Subset dataframe
  if samples != "all":

pyproject.toml

@@ -140,9 +140,9 @@ select = [
  "UP",
  # ruff
  "RUF",
- # The following checks are disabled, but we are working towards enabling them in the future.
  # flake8-bandit
- # "S",
+ "S",
+ # The following checks are disabled, but we are working towards enabling them in the future.
  # flake8-bugbear
  # "B",
  # isort
@@ -163,6 +163,7 @@ ignore = [
 # Ignore `E402` and `F401` (unusued imports) in all `__init__.py` files
 "__init__.py" = ["E402", "F401"]
 "tests/*" = ["S101"] # Ignore assert statements in tests
+"pycytominer/cyto_utils/*" = ["S101", "S608"] # Ignore assert statements in cyto_utils
 
 [tool.ruff.format]
 preview = true

tests/test_data/cytominer_database_example_data/shrink_SQ00014613.sqlite.py

@@ -32,7 +32,7 @@
  DELETE FROM {table}
  WHERE TableNumber NOT IN (SELECT TableNumber FROM Image)
  OR ObjectNumber > 1
- """
+ """ # noqa: S608
  )
 
  conn.commit()