Merge pull request #49 from MannLabs/48-basic-linting

48 basic linting

.pre-commit-config.yaml

@@ -11,4 +11,4 @@ repos:
   rev: v0.4.0
   hooks:
     - id: ruff-format
-#    - id: ruff
+    - id: ruff

alpharaw/__init__.py

@@ -6,14 +6,14 @@
 
 
 def register_readers():
-    from .ms_data_base import ms_reader_provider
-    from .legacy_msdata import mgf
-    from .mzml import MzMLReader
-    from .wrappers import alphapept_wrapper
+    from .ms_data_base import ms_reader_provider  # noqa: F401  # TODO remove import side effect
+    from .legacy_msdata import mgf  # noqa: F401  # TODO remove import side effect
+    from .mzml import MzMLReader  # noqa: F401  # TODO remove import side effect
+    from .wrappers import alphapept_wrapper  # noqa: F401  # TODO remove import side effect
 
     try:
-        from .sciex import SciexWiffData
-        from .thermo import ThermoRawData
+        from .sciex import SciexWiffData  # noqa: F401  # TODO remove import side effect
+        from .thermo import ThermoRawData  # noqa: F401  # TODO remove import side effect
     except (RuntimeError, ImportError):
         print("[WARN] pythonnet is not installed")
 

alpharaw/cli.py

@@ -3,13 +3,13 @@
 
 import alpharaw
 from alpharaw.ms_data_base import ms_reader_provider
-from alpharaw.legacy_msdata import mgf
-from alpharaw.mzml import MzMLReader
-from alpharaw.wrappers import alphapept_wrapper
+from alpharaw.legacy_msdata import mgf  # noqa: F401  # TODO remove import side effect
+from alpharaw.mzml import MzMLReader  # noqa: F401  # TODO remove import side effect
+from alpharaw.wrappers import alphapept_wrapper  # noqa: F401  # TODO remove import side effect
 
 try:
-    from alpharaw.sciex import SciexWiffData
-    from alpharaw.thermo import ThermoRawData
+    from alpharaw.sciex import SciexWiffData  # noqa: F401 # TODO remove import side effect
+    from alpharaw.thermo import ThermoRawData  # noqa: F401 # TODO remove import side effect
 except (RuntimeError, ImportError):
     print("[WARN] pythonnet is not installed")
 
@@ -51,7 +51,7 @@ def run(ctx, **kwargs):
     type=str,
     default="thermo_raw",
     show_default=True,
-    help=f"Only `thermo_raw`, `sciex_wiff` is supported currently.",
+    help="Only `thermo_raw`, `sciex_wiff` is supported currently.",
 )
 @click.option(
     "--raw",

alpharaw/dia/normal_dia.py

@@ -1,4 +1,3 @@
-import pandas as pd
 import numpy as np
 import typing
 

alpharaw/feature/chem.py

@@ -7,12 +7,6 @@
 # Some legacy chemistry functions
 # Maybe replacd with alphabase?
 
-from numba.typed import Dict
-from numba import types, njit
-import numpy as np
-from numba import int32, float32, float64, njit, types
-from numba.experimental import jitclass
-from numba.typed import Dict
 
 averagine_aa = Dict.empty(key_type=types.unicode_type, value_type=types.float64)
 

alpharaw/feature/finding.py

@@ -1,6 +1,5 @@
 import pandas as pd
 import numpy as np
-import numba
 
 from alpharaw.feature.chem import averagine_aa, isotopes, maximum_offset
 from alpharaw.feature.hills import (

alpharaw/feature/hills.py

@@ -1,4 +1,5 @@
 import numpy as np
+import pandas as pd
 from alphatims.utils import threadpool
 from numba import njit
 from alpharaw.feature.centroids import connect_centroids

alpharaw/feature/isotope_pattern.py

@@ -10,13 +10,9 @@
 
 from alpharaw.feature.chem import (
     mass_to_dist,
-    maximum_offset,
     DELTA_M,
     DELTA_S,
     M_PROTON,
-    averagine_aa,
-    isotopes,
-    Isotope,
 )
 
 
@@ -394,13 +390,13 @@ def grow(
 
         y = pattern[seed + relative_pos]  # This is a reference peak
 
-        l = sortindex_[y]
+        ll = sortindex_[y]
 
         mass2 = stats[y, 0]
         delta_mass2 = stats[y, 1]
 
-        start = hill_ptrs[l]
-        end = hill_ptrs[l + 1]
+        start = hill_ptrs[ll]
+        end = hill_ptrs[ll + 1]
         idx_ = hill_data[start:end]
         int_2 = int_data[idx_]
         scans_2 = scan_idx[idx_]
@@ -564,7 +560,6 @@ def plot_pattern(
     pattern: np.ndarray,
     sorted_hills: np.ndarray,
     centroids: np.ndarray,
-    hill_data: np.ndarray,
 ):
     """Helper function to plot a pattern.
 
@@ -574,19 +569,17 @@ def plot_pattern(
         centroids (np.ndarray): 1D Array containing the masses of the centroids.
         hill_data (np.ndarray): Array containing the indices to hills.
     """
+    import matplotlib.pyplot as plt
+
     f, (ax1, ax2) = plt.subplots(2, 1, sharex=True, figsize=(10, 10))
     centroid_dtype = [("mz", float), ("int", float), ("scan_no", int), ("rt", float)]
 
-    mzs = []
-    rts = []
-    ints = []
     for entry in pattern:
         hill = sorted_hills[entry]
         hill_data = np.array(
             [centroids[_[0]][_[1]] for _ in hill], dtype=centroid_dtype
         )
 
-        int_profile = hill_data["int"]
         ax1.plot(hill_data["rt"], hill_data["int"])
         ax2.scatter(hill_data["rt"], hill_data["mz"], s=hill_data["int"] / 5e5)
 
@@ -947,9 +940,6 @@ def isolate_isotope_pattern(
     return champion_trace, champion_charge
 
 
-from typing import Callable, Union
-
-
 def get_isotope_patterns(
     pre_isotope_patterns: list,
     hill_ptrs: np.ndarray,
@@ -1109,13 +1099,6 @@ def report_(
     int_max_idx = np.argmax(isotope_data[:, 2])
     mz_most_abundant = isotope_data[:, 0][int_max_idx]
 
-    int_max = isotope_data[:, 2][int_max_idx]
-
-    rt_start = isotope_data[
-        int_max_idx, 4
-    ]  # This is the start of the most abundant trace
-    rt_end = isotope_data[int_max_idx, 5]
-
     rt_min_ = min(isotope_data[:, 4])
     rt_max_ = max(isotope_data[:, 5])
 

alpharaw/match/match_utils.py

@@ -1,8 +1,5 @@
 import numpy as np
 import numba
-import pandas as pd
-import tqdm
-import os
 
 from typing import Tuple
 

alpharaw/match/psm_match.py

@@ -6,12 +6,10 @@
 
 from alpharaw import register_readers
 
-register_readers()
 
 from alphabase.peptide.fragment import (
     create_fragment_mz_dataframe,
     get_charged_frag_types,
-    concat_precursor_fragment_dataframes,
 )
 
 from alpharaw.ms_data_base import (
@@ -31,6 +29,9 @@
 from alpharaw.dia.normal_dia import NormalDIAGrouper
 
 
+register_readers()  # TODO remove this import side effect
+
+
 class PepSpecMatch:
     """
     Extract fragment ions from MS2 data.

alpharaw/match/psm_match_alphatims.py

@@ -9,10 +9,9 @@
 
 from alpharaw.wrappers.alphatims_wrapper import AlphaTimsWrapper
 
-from alpharaw.wrappers.alphapept_wrapper import AlphaPept_HDF_MS2_Reader
+from alpharaw.wrappers.alphapept_wrapper import AlphaPept_HDF_MS2_Reader  # noqa: F401  # TODO remove import side effect
 
 from .psm_match import PepSpecMatch
-from ..utils.ms_path_utils import parse_ms_files_to_dict
 
 alphatims_hdf_types = [
     "alphatims",

alpharaw/mzml.py

@@ -157,7 +157,7 @@ def parse_mzml_entry(item_dict: dict) -> tuple:
                 nce = float(filter_string.split("@cid")[1].split(" ")[0])
             else:
                 nce = np.nan
-        except:
+        except Exception:
             nce = np.nan
     return (
         rt,

alpharaw/raw_access/clr_utils.py

@@ -1,7 +1,9 @@
-import clr
+# ruff: noqa: E402  #Module level import not at top of file
 import os
 import numpy as np
 
+import clr
+
 clr.AddReference("System")
 # from System.Runtime.InteropServices import Marshal
 # from System import IntPtr, Int64

alpharaw/raw_access/pysciexwifffilereader.py

@@ -1,15 +1,15 @@
+# ruff: noqa: E402  #Module level import not at top of file
 import os
-import sys
 import numpy as np
-import time
 
 from alpharaw.utils.centroiding import naive_centroid
 
 # require pythonnet, pip install pythonnet on Windows
 import clr
 
 clr.AddReference("System")
-import System
+
+import System  # noqa: F401
 from System.Threading import Thread
 from System.Globalization import CultureInfo
 
@@ -25,8 +25,8 @@
 clr.AddReference(os.path.join(ext_dir, "sciex/Clearcore2.Data.dll"))
 clr.AddReference(os.path.join(ext_dir, "sciex/WiffOps4Python.dll"))
 
-import Clearcore2
-import WiffOps4Python
+import Clearcore2  # noqa: F401
+import WiffOps4Python  # noqa: F401
 from WiffOps4Python import WiffOps as DotNetWiffOps
 from Clearcore2.Data.AnalystDataProvider import (
     AnalystWiffDataProvider,

alpharaw/raw_access/pythermorawfilereader.py

@@ -1,7 +1,5 @@
+# ruff: noqa: E402  #Module level import not at top of file
 import os
-import sys
-import numpy as np
-import time
 import warnings
 
 from collections import defaultdict
@@ -311,13 +309,6 @@ def GetScanEventStringForScanNum(self, scanNumber):
         """This function returns scan event information as a string for the specified scan number."""
         return self.source.GetScanEventStringForScanNumber(scanNumber)
 
-    def GetStatusLogForRetentionTime(self, rt):
-        logEntry = self.source.GetStatusLogForRetentionTime(rt)
-        return dict(zip(logEntry.Labels, logEntry.Values))
-
-    def GetStatusLogForScanNum(self, scan):
-        return self.GetStatusLogForRetentionTime(self.RTFromScanNum(scan))
-
     def GetScanEventForScanNum(self, scanNumber):
         return IScanEventBase(self.source.GetScanEventForScanNumber(scanNumber))
 

alpharaw/sciex.py

@@ -1,6 +1,3 @@
-import numpy as np
-import pandas as pd
-import os
 import warnings
 import alpharaw.raw_access.pysciexwifffilereader as pysciexwifffilereader
 from .ms_data_base import MSData_Base

alpharaw/thermo.py

@@ -1,7 +1,5 @@
 import numpy as np
-import pandas as pd
 import platform
-import os
 import multiprocessing as mp
 from functools import partial
 from tqdm import tqdm

docs/conf.py

@@ -49,7 +49,7 @@
 # This pattern also affects html_static_path and html_extra_path.
 exclude_patterns = ["_build", "Thumbs.db", ".DS_Store", "_modidx,py"]
 
-code_url = f"https://github.com/mannlabs/alpharaw/blob/main"
+code_url = "https://github.com/mannlabs/alpharaw/blob/main"
 
 
 def linkcode_resolve(domain, info):

pyproject.toml

@@ -0,0 +1,6 @@
+
+[tool.ruff.lint]
+select = ["E","F"]
+ignore = [
+    "E501"  # Line too long  (ruff wraps code, but not docstrings)
+]

setup.py

@@ -3,7 +3,6 @@
 # builtin
 import setuptools
 import re
-import os
 
 # local
 import alpharaw as package2install