pychemstation 0.10.2__tar.gz → 0.10.4__tar.gz

pychemstation-0.10.4/.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.11.2
+  hooks:
+    # Run the linter.
+    - id: ruff
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format

{pychemstation-0.10.2 → pychemstation-0.10.4}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: pychemstation
-Version: 0.10.2
-Summary: Library to interact with Chemstation software, primarily used in Hein lagit branch -mb
+Version: 0.10.4
+Summary: Library to interact with Chemstation software, primarily used in Hein lab
 Project-URL: Documentation, https://pychemstation-e5a086.gitlab.io/pychemstation.html
 Project-URL: Repository, https://gitlab.com/heingroup/device-api/pychemstation
 Author-email: lucyhao <hao.lucyy@gmail.com>
@@ -18,6 +18,7 @@ Requires-Dist: matplotlib>=3.7.5
 Requires-Dist: pandas>=2.0.3
 Requires-Dist: pdoc>=14.7.0
 Requires-Dist: polling>=0.3.2
+Requires-Dist: pre-commit>=4.2.0
 Requires-Dist: pytest>=7.3.5
 Requires-Dist: rainbow-api>=1.0.10
 Requires-Dist: result>=0.17.0
@@ -79,29 +80,55 @@ HPLCTalk_Run
 
 ```python
 from pychemstation.control import HPLCController
+from pychemstation.utils.method_types import *
 import pandas as pd
 
-# these paths will be unique to your Chemstation setup
-DEFAULT_METHOD = "GENERAL-POROSHELL"
-DEFAULT_COMMAND_PATH = "C:\\Users\\User\\Desktop\\Lucy\\"
 DEFAULT_METHOD_DIR = "C:\\ChemStation\\1\\Methods\\"
-DATA_DIR_2 = "C:\\Users\\Public\\Documents\\ChemStation\\2\\Data\\"
-DATA_DIR_3 = "C:\\Users\\Public\\Documents\\ChemStation\\3\\Data\\"
-SEQUENCE_DIR = "C:\\USERS\\PUBLIC\\DOCUMENTS\\CHEMSTATION\\2\\Sequence\\"
+SEQUENCE_DIR = "C:\\USERS\\PUBLIC\\DOCUMENTS\\CHEMSTATION\\3\\Sequence"
+DEFAULT_COMMAND_PATH = "C:\\Users\\User\\Desktop\\Lucy\\"
+DATA_DIR_2 = "C:\\Users\\Public\\Documents\\ChemStation\\2\\Data"
+DATA_DIR_3 = "C:\\Users\\Public\\Documents\\ChemStation\\3\\Data"
 
+# Initialize HPLC Controller
 hplc_controller = HPLCController(data_dirs=[DATA_DIR_2, DATA_DIR_3],
                                  comm_dir=DEFAULT_COMMAND_PATH,
-                                 sequence_dir=SEQUENCE_DIR,
-                                 method_dir=DEFAULT_METHOD_DIR)
-
-hplc_controller.preprun()
-hplc_controller.switch_method(method_name=DEFAULT_METHOD)
-hplc_controller.run_method(experiment_name="Run 10")
+                                 method_dir=DEFAULT_METHOD_DIR,
+                                 sequence_dir=SEQUENCE_DIR)
+
+# Switching a method
+hplc_controller.switch_method("General-Poroshell")
+
+# Editing a method
+new_method = MethodDetails(
+    name="General-Poroshell",
+    params=HPLCMethodParams(
+        organic_modifier=7,
+        flow=0.44),
+    timetable=[
+        TimeTableEntry(
+            start_time=0.10,
+            organic_modifer=7,
+            flow=0.34
+        ),
+        TimeTableEntry(
+            start_time=4,
+            organic_modifer=99,
+            flow=0.55
+        )
+    ],
+    stop_time=5,
+    post_time=2
+)
+hplc_controller.edit_method(new_method)
+
+# Run a method and get a report or data from last run method
+hplc_controller.run_method(experiment_name="test_experiment")
+report = hplc_controller.get_last_run_method_report()
+vial_location = report.vial_location
+
+# Save, analyze or plot the data!
 chrom = hplc_controller.get_last_run_method_data()
-
-# afterwards, save, analyze or plot the data!
-values = {"x": chrom.A.x, "y": chrom.A.y}
-chromatogram_data = pd.DataFrame.from_dict(values)
+chromatogram_data = pd.DataFrame.from_dict({"x": chrom.A.x, "y": chrom.A.y})
 chromatogram_data.to_csv("Run 10.csv", index=False) 
 ```
 
@@ -122,7 +149,6 @@ Lucy Hao, Maria Politi
 - Adapted from [**AnalyticalLabware**](https://github.com/croningp/analyticallabware), created by members in the Cronin
   Group. Copyright © Cronin Group, used under the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/) license.
 - Adapted from the [MACROS](https://github.com/Bourne-Group/HPLCMethodOptimisationGUI) used in [**Operator-free HPLC
-  automated method development guided by Bayesian optimization
-  **](https://pubs.rsc.org/en/content/articlelanding/2024/dd/d4dd00062e),
+  automated method development guided by Bayesian optimization**](https://pubs.rsc.org/en/content/articlelanding/2024/dd/d4dd00062e),
   created by members in the Bourne Group. Copyright © Bourne Group, used under
   the [MIT](https://opensource.org/license/mit) license.

{pychemstation-0.10.2 → pychemstation-0.10.4}/README.md

@@ -49,29 +49,55 @@ HPLCTalk_Run
 
 ```python
 from pychemstation.control import HPLCController
+from pychemstation.utils.method_types import *
 import pandas as pd
 
-# these paths will be unique to your Chemstation setup
-DEFAULT_METHOD = "GENERAL-POROSHELL"
-DEFAULT_COMMAND_PATH = "C:\\Users\\User\\Desktop\\Lucy\\"
 DEFAULT_METHOD_DIR = "C:\\ChemStation\\1\\Methods\\"
-DATA_DIR_2 = "C:\\Users\\Public\\Documents\\ChemStation\\2\\Data\\"
-DATA_DIR_3 = "C:\\Users\\Public\\Documents\\ChemStation\\3\\Data\\"
-SEQUENCE_DIR = "C:\\USERS\\PUBLIC\\DOCUMENTS\\CHEMSTATION\\2\\Sequence\\"
+SEQUENCE_DIR = "C:\\USERS\\PUBLIC\\DOCUMENTS\\CHEMSTATION\\3\\Sequence"
+DEFAULT_COMMAND_PATH = "C:\\Users\\User\\Desktop\\Lucy\\"
+DATA_DIR_2 = "C:\\Users\\Public\\Documents\\ChemStation\\2\\Data"
+DATA_DIR_3 = "C:\\Users\\Public\\Documents\\ChemStation\\3\\Data"
 
+# Initialize HPLC Controller
 hplc_controller = HPLCController(data_dirs=[DATA_DIR_2, DATA_DIR_3],
                                  comm_dir=DEFAULT_COMMAND_PATH,
-                                 sequence_dir=SEQUENCE_DIR,
-                                 method_dir=DEFAULT_METHOD_DIR)
-
-hplc_controller.preprun()
-hplc_controller.switch_method(method_name=DEFAULT_METHOD)
-hplc_controller.run_method(experiment_name="Run 10")
+                                 method_dir=DEFAULT_METHOD_DIR,
+                                 sequence_dir=SEQUENCE_DIR)
+
+# Switching a method
+hplc_controller.switch_method("General-Poroshell")
+
+# Editing a method
+new_method = MethodDetails(
+    name="General-Poroshell",
+    params=HPLCMethodParams(
+        organic_modifier=7,
+        flow=0.44),
+    timetable=[
+        TimeTableEntry(
+            start_time=0.10,
+            organic_modifer=7,
+            flow=0.34
+        ),
+        TimeTableEntry(
+            start_time=4,
+            organic_modifer=99,
+            flow=0.55
+        )
+    ],
+    stop_time=5,
+    post_time=2
+)
+hplc_controller.edit_method(new_method)
+
+# Run a method and get a report or data from last run method
+hplc_controller.run_method(experiment_name="test_experiment")
+report = hplc_controller.get_last_run_method_report()
+vial_location = report.vial_location
+
+# Save, analyze or plot the data!
 chrom = hplc_controller.get_last_run_method_data()
-
-# afterwards, save, analyze or plot the data!
-values = {"x": chrom.A.x, "y": chrom.A.y}
-chromatogram_data = pd.DataFrame.from_dict(values)
+chromatogram_data = pd.DataFrame.from_dict({"x": chrom.A.x, "y": chrom.A.y})
 chromatogram_data.to_csv("Run 10.csv", index=False) 
 ```
 
@@ -92,7 +118,6 @@ Lucy Hao, Maria Politi
 - Adapted from [**AnalyticalLabware**](https://github.com/croningp/analyticallabware), created by members in the Cronin
   Group. Copyright © Cronin Group, used under the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/) license.
 - Adapted from the [MACROS](https://github.com/Bourne-Group/HPLCMethodOptimisationGUI) used in [**Operator-free HPLC
-  automated method development guided by Bayesian optimization
-  **](https://pubs.rsc.org/en/content/articlelanding/2024/dd/d4dd00062e),
+  automated method development guided by Bayesian optimization**](https://pubs.rsc.org/en/content/articlelanding/2024/dd/d4dd00062e),
   created by members in the Bourne Group. Copyright © Bourne Group, used under
   the [MIT](https://opensource.org/license/mit) license.

{pychemstation-0.10.2/build/lib → pychemstation-0.10.4}/pychemstation/__init__.py

@@ -1,3 +1,3 @@
 """
 .. include:: ../README.md
-"""
+"""

pychemstation-0.10.4/pychemstation/analysis/__init__.py

@@ -0,0 +1,4 @@
+from .process_report import CSVProcessor
+from .process_report import TXTProcessor
+
+__all__ = ["CSVProcessor", "TXTProcessor"]

{pychemstation-0.10.2/build/lib → pychemstation-0.10.4}/pychemstation/analysis/base_spectrum.py

@@ -197,10 +197,10 @@ class AbstractSpectrum(ABC):
             return (self.x.copy()[full_mask], self.y.copy()[full_mask])
 
     def show_spectrum(
-            self,
-            filename=None,
-            title=None,
-            label=None,
+        self,
+        filename=None,
+        title=None,
+        label=None,
     ):
         """Plots the spectral data using matplotlib.pyplot module.
 
@@ -249,7 +249,7 @@ class AbstractSpectrum(ABC):
             os.makedirs(path, exist_ok=True)
             fig.savefig(os.path.join(path, f"{filename}.png"), dpi=150)
 
-    def find_peaks(self, threshold=1, min_width=.1, min_dist=None, area=None):
+    def find_peaks(self, threshold=1, min_width=0.1, min_dist=None, area=None):
         """Finds all peaks above the threshold with at least min_width width.
 
         Args:
@@ -385,12 +385,12 @@ class AbstractSpectrum(ABC):
 
         if rule == "trapz":
             return integrate.trapz(
-                self.y[left_idx: right_idx + 1], self.x[left_idx: right_idx + 1]
+                self.y[left_idx : right_idx + 1], self.x[left_idx : right_idx + 1]
             )
 
         elif rule == "simps":
             return integrate.simps(
-                self.y[left_idx: right_idx + 1], self.x[left_idx: right_idx + 1]
+                self.y[left_idx : right_idx + 1], self.x[left_idx : right_idx + 1]
             )
 
         else:

{pychemstation-0.10.2/build/lib/pychemstation/utils → pychemstation-0.10.4/pychemstation/analysis}/chromatogram.py

@@ -6,8 +6,9 @@ from dataclasses import dataclass
 
 import numpy as np
 
-from ..analysis import AbstractSpectrum
-from .parsing import CHFile
+
+from ..utils.parsing import CHFile
+from ..analysis.base_spectrum import AbstractSpectrum
 
 ACQUISITION_PARAMETERS = "acq.txt"
 
@@ -36,12 +37,11 @@ class AgilentHPLCChromatogram(AbstractSpectrum):
     }
 
     def __init__(self, path=None, autosaving=False):
-
         if path is not None:
             os.makedirs(path, exist_ok=True)
             self.path = path
         else:
-            self.path = os.path.join(".", "hplc_data")
+            self.path = os.path.join("../utils", "hplc_data")
             os.makedirs(self.path, exist_ok=True)
 
         super().__init__(path=path, autosaving=autosaving)

{pychemstation-0.10.2 → pychemstation-0.10.4}/pychemstation/analysis/process_report.py

@@ -17,19 +17,19 @@ from aghplctools.ingestion.text import (
 )
 from result import Err, Ok, Result
 
-from pychemstation.utils.chromatogram import AgilentHPLCChromatogram
-from pychemstation.utils.tray_types import FiftyFourVialPlate, Tray
+from ..analysis.chromatogram import AgilentHPLCChromatogram
+from ..utils.tray_types import FiftyFourVialPlate, Tray
 
 
 @dataclass
 class AgilentPeak:
+    peak_number: Optional[int]
     retention_time: float
+    peak_type: Optional[str]
     width: float
     area: float
     height: float
-    peak_number: Optional[int]
-    peak_type: Optional[str]
-    height_percent: Optional[float]
+    area_percent: Optional[float]
 
 
 @dataclass
@@ -73,12 +73,14 @@ class CSVProcessor(ReportProcessor):
         """
         Method to parse details from CSV report.
 
-        :returns: subset of complete report details, specifically the sample location, solvents in pumps,
+        :return: subset of complete report details, specifically the sample location, solvents in pumps,
          and list of peaks at each wavelength channel.
         """
-        labels = os.path.join(self.path, 'REPORT00.CSV')
+        labels = os.path.join(self.path, "REPORT00.CSV")
         if os.path.exists(labels):
-            df_labels: Dict[int, Dict[int: AnyStr]] = pd.read_csv(labels, encoding="utf-16", header=None).to_dict()
+            df_labels: Dict[int, Dict[int:AnyStr]] = pd.read_csv(
+                labels, encoding="utf-16", header=None
+            ).to_dict()
             vial_location = []
             signals = {}
             solvents = {}
@@ -91,18 +93,28 @@ class CSVProcessor(ReportProcessor):
                 elif val == "Number of Signals":
                     num_signals = int(df_labels[1][pos])
                     for s in range(1, num_signals + 1):
-                        df = pd.read_csv(os.path.join(self.path, f'REPORT0{s}.CSV'),
-                                         encoding="utf-16", header=None)
+                        df = pd.read_csv(
+                            os.path.join(self.path, f"REPORT0{s}.CSV"),
+                            encoding="utf-16",
+                            header=None,
+                        )
                         peaks = df.apply(lambda row: AgilentPeak(*row), axis=1)
-                        wavelength = df_labels[1][pos + s].partition(",4 Ref=off")[0][-3:]
-                        signals[wavelength] = peaks
+                        wavelength = df_labels[1][pos + s].partition(",4 Ref=off")[0][
+                            -3:
+                        ]
+                        signals[wavelength] = list(peaks)
                     break
 
-            return Ok(AgilentReport(
-                signals=[Signals(wavelength=w, peaks=s, data=None) for w, s in signals.items()],
-                vial_location=FiftyFourVialPlate.from_int(int(vial_location)),
-                solvents=solvents
-            ))
+            return Ok(
+                AgilentReport(
+                    signals=[
+                        Signals(wavelength=int(w), peaks=s, data=None)
+                        for w, s in signals.items()
+                    ],
+                    vial_location=FiftyFourVialPlate.from_int(int(vial_location)),
+                    solvents=solvents,
+                )
+            )
 
         return Err("No report found")
 
@@ -111,34 +123,39 @@ class TXTProcessor(ReportProcessor):
     """
     Regex matches for column and unit combinations, courtesy of Veronica Lai.
     """
+
     _column_re_dictionary = {
-        'Peak': {  # peak index
-            '#': '[ ]+(?P<Peak>[\d]+)',  # number
+        "Peak": {  # peak index
+            "#": "[ ]+(?P<Peak>[\d]+)",  # number
         },
-        'RetTime': {  # retention time
-            '[min]': '(?P<RetTime>[\d]+.[\d]+)',  # minutes
+        "RetTime": {  # retention time
+            "[min]": "(?P<RetTime>[\d]+.[\d]+)",  # minutes
         },
-        'Type': {  # peak type
-            '': '(?P<Type>[A-Z]{1,3}(?: [A-Z]{1,2})*)',  # todo this is different from <4.8.8 aghplc tools
+        "Type": {  # peak type
+            "": "(?P<Type>[A-Z]{1,3}(?: [A-Z]{1,2})*)",  # todo this is different from <4.8.8 aghplc tools
         },
-        'Width': {  # peak width
-            '[min]': '(?P<Width>[\d]+.[\d]+[e+-]*[\d]+)',
+        "Width": {  # peak width
+            "[min]": "(?P<Width>[\d]+.[\d]+[e+-]*[\d]+)",
         },
-        'Area': {  # peak area
-            '[mAU*s]': '(?P<Area>[\d]+.[\d]+[e+-]*[\d]+)',  # area units
-            '%': '(?P<percent>[\d]+.[\d]+[e+-]*[\d]+)',  # percent
+        "Area": {  # peak area
+            "[mAU*s]": "(?P<Area>[\d]+.[\d]+[e+-]*[\d]+)",  # area units
+            "%": "(?P<percent>[\d]+.[\d]+[e+-]*[\d]+)",  # percent
         },
-        'Height': {  # peak height
-            '[mAU]': '(?P<Height>[\d]+.[\d]+[e+-]*[\d]+)',
+        "Height": {  # peak height
+            "[mAU]": "(?P<Height>[\d]+.[\d]+[e+-]*[\d]+)",
         },
-        'Name': {
-            '': '(?P<Name>[^\s]+(?:\s[^\s]+)*)',  # peak name
+        "Name": {
+            "": "(?P<Name>[^\s]+(?:\s[^\s]+)*)",  # peak name
         },
     }
 
-    def __init__(self, path: str, min_ret_time: int = 0,
-                 max_ret_time: int = 999,
-                 target_wavelength_range: List[int] = range(200, 300)):
+    def __init__(
+        self,
+        path: str,
+        min_ret_time: int = 0,
+        max_ret_time: int = 999,
+        target_wavelength_range: List[int] = range(200, 300),
+    ):
         """
         Class to process reports in CSV form.
 
@@ -155,16 +172,17 @@ class TXTProcessor(ReportProcessor):
     def process_report(self) -> Result[AgilentReport, AnyStr]:
         """
         Method to parse details from CSV report.
-
-        :returns: subset of complete report details, specifically the sample location, solvents in pumps,
-         and list of peaks at each wavelength channel.
-
         If you want more functionality, use `aghplctools`.
         `from aghplctools.ingestion.text import pull_hplc_area_from_txt`
         `signals = pull_hplc_area_from_txt(file_path)`
+
+        :return: subset of complete report details, specifically the sample location, solvents in pumps,
+         and list of peaks at each wavelength channel.
         """
 
-        with open(os.path.join(self.path, "REPORT.TXT"), 'r', encoding='utf-16') as openfile:
+        with open(
+            os.path.join(self.path, "REPORT.TXT"), "r", encoding="utf-16"
+        ) as openfile:
             text = openfile.read()
 
         try:
@@ -172,25 +190,33 @@ class TXTProcessor(ReportProcessor):
         except ValueError as e:
             return Err("No peaks found: " + str(e))
 
-        signals = {key: signals[key] for key in self.target_wavelength_range if key in signals}
+        signals = {
+            key: signals[key] for key in self.target_wavelength_range if key in signals
+        }
 
         parsed_signals = []
         for wavelength, wavelength_dict in signals.items():
-            current_wavelength_signals = Signals(wavelength=wavelength, peaks=[], data=None)
+            current_wavelength_signals = Signals(
+                wavelength=int(wavelength), peaks=[], data=None
+            )
             for ret_time, ret_time_dict in wavelength_dict.items():
                 if self.min_ret_time <= ret_time <= self.max_ret_time:
-                    current_wavelength_signals.peaks.append(AgilentPeak(retention_time=ret_time,
-                                                                        area=ret_time_dict['Area'],
-                                                                        width=ret_time_dict['Width'],
-                                                                        height=ret_time_dict['Height'],
-                                                                        peak_number=None,
-                                                                        peak_type=ret_time_dict['Type'],
-                                                                        height_percent=None))
+                    current_wavelength_signals.peaks.append(
+                        AgilentPeak(
+                            retention_time=ret_time,
+                            area=ret_time_dict["Area"],
+                            width=ret_time_dict["Width"],
+                            height=ret_time_dict["Height"],
+                            peak_number=None,
+                            peak_type=ret_time_dict["Type"],
+                            area_percent=None,
+                        )
+                    )
             parsed_signals.append(current_wavelength_signals)
 
-        return Ok(AgilentReport(vial_location=None,
-                                solvents=None,
-                                signals=parsed_signals))
+        return Ok(
+            AgilentReport(vial_location=None, solvents=None, signals=parsed_signals)
+        )
 
     def parse_area_report(self, report_text: str) -> Dict:
         """
@@ -206,7 +232,7 @@ class TXTProcessor(ReportProcessor):
         should be able to use the `parse_area_report` method of aghplctools v4.8.8
         """
         if re.search(_no_peaks_re, report_text):  # There are no peaks in Report.txt
-            raise ValueError('No peaks found in Report.txt')
+            raise ValueError("No peaks found in Report.txt")
         blocks = _header_block_re.split(report_text)
         signals = {}  # output dictionary
         for ind, block in enumerate(blocks):
@@ -219,23 +245,28 @@ class TXTProcessor(ReportProcessor):
                     si = _signal_info_re.match(table)
                     if si is not None:
                         # some error state (e.g. 'not found')
-                        if si.group('error') != '':
+                        if si.group("error") != "":
                             continue
-                        wavelength = float(si.group('wavelength'))
+                        wavelength = float(si.group("wavelength"))
                         if wavelength in signals:
                             # placeholder error raise just in case (this probably won't happen)
                             raise KeyError(
-                                f'The wavelength {float(si.group("wavelength"))} is already in the signals dictionary')
+                                f"The wavelength {float(si.group('wavelength'))} is already in the signals dictionary"
+                            )
                         signals[wavelength] = {}
                         # build peak regex
                         peak_re = self.build_peak_regex(table)
-                        if peak_re is None:  # if there are no columns (empty table), continue
+                        if (
+                            peak_re is None
+                        ):  # if there are no columns (empty table), continue
                             continue
-                        for line in table.split('\n'):
+                        for line in table.split("\n"):
                             peak = peak_re.match(line)
                             if peak is not None:
-                                signals[wavelength][float(peak.group('RetTime'))] = {}
-                                current = signals[wavelength][float(peak.group('RetTime'))]
+                                signals[wavelength][float(peak.group("RetTime"))] = {}
+                                current = signals[wavelength][
+                                    float(peak.group("RetTime"))
+                                ]
                                 for key in self._column_re_dictionary:
                                     if key in peak.re.groupindex:
                                         try:  # try float conversion, otherwise continue
@@ -254,30 +285,35 @@ class TXTProcessor(ReportProcessor):
         :param signal_table: block of lines associated with an area table
         :return: peak line regex object (<=3.6 _sre.SRE_PATTERN, >=3.7 re.Pattern)
         """
-        split_table = signal_table.split('\n')
+        split_table = signal_table.split("\n")
         if len(split_table) <= 4:  # catch peak table with no values
             return None
         # todo verify that these indicies are always true
         column_line = split_table[2]  # table column line
         unit_line = split_table[3]  # column unit line
-        length_line = [len(val) + 1 for val in split_table[4].split('|')]  # length line
+        length_line = [len(val) + 1 for val in split_table[4].split("|")]  # length line
 
         # iterate over header values and units to build peak table regex
         peak_re_string = []
         for header, unit in zip(
-                chunk_string(column_line, length_line),
-                chunk_string(unit_line, length_line)
+            chunk_string(column_line, length_line), chunk_string(unit_line, length_line)
         ):
-            if header == '':  # todo create a better catch for an undefined header
+            if header == "":  # todo create a better catch for an undefined header
                 continue
             try:
                 peak_re_string.append(
-                    self._column_re_dictionary[header][unit]  # append the appropriate regex
+                    self._column_re_dictionary[header][
+                        unit
+                    ]  # append the appropriate regex
                 )
             except KeyError:  # catch for undefined regexes (need to be built)
-                raise KeyError(f'The header/unit combination "{header}" "{unit}" is not defined in the peak regex '
-                               f'dictionary. Let Lars know.')
+                raise KeyError(
+                    f'The header/unit combination "{header}" "{unit}" is not defined in the peak regex '
+                    f"dictionary. Let Lars know."
+                )
         return re.compile(
-            '[ ]+'.join(peak_re_string)  # constructed string delimited by 1 or more spaces
-            + '[\s]*'  # and any remaining white space
+            "[ ]+".join(
+                peak_re_string
+            )  # constructed string delimited by 1 or more spaces
+            + "[\s]*"  # and any remaining white space
         )