chore: add many minor changes

pyproject.toml

@@ -82,7 +82,7 @@ sources = ["src"]
 
 # testing
 [tool.pytest.ini_options]
-minversion = "6.0"
+minversion = "7.0"
 pythonpath = "src"
 addopts = [
     "--import-mode=importlib",
@@ -96,6 +96,34 @@ testpaths = [
 
 [tool.coverage.run]
 source = ["src"]
+omit = [
+    "*/example_fixtures/*",
+    ]
+
+[tool.coverage.report]
+# Regexes for lines to exclude from consideration
+exclude_also = [
+    # Don't complain about missing debug-only code:
+    "def __repr__",
+    "if self\\.debug",
+
+    # Don't complain if tests don't hit defensive assertion code:
+    "raise AssertionError",
+    "raise NotImplementedError",
+
+    # Don't complain if non-runnable code isn't run:
+    "if 0:",
+    "if __name__ == .__main__.:",
+
+    # Don't complain about abstract methods, they aren't run:
+    "@(abc\\.)?abstractmethod",
+    ]
+
+ignore_errors = true
+
+[tool.coverage.html]
+directory = "coverage_html_report"
+
 
 [tool.bumpversion]
 current_version = "0.8.0"
@@ -117,16 +145,6 @@ filename= "README.md"
 search = "The current version is v{current_version}"
 replace = "The current version is v{new_version}"
 
-# [[bumpversion.files]]
-# filename= "src/raman_fitting/__init__.py"
-# search = "__version__ = '{current_version}'"
-# replace = "__version__ = '{new_version}'"
-
-# [[bumpversion.files]]
-# filename= "src/raman_fitting/_version.py"
-# search = "version = '{current_version}'"
-# replace = "version = '{new_version}'"
-
 [[tool.bumpversion.files]]
 filename= "pyproject.toml"
 search = "current_version = '{current_version}'"

src/raman_fitting/delegating/main_delegator.py

@@ -1,7 +1,6 @@
 # pylint: disable=W0614,W0401,W0611,W0622,C0103,E0401,E0402
 from dataclasses import dataclass, field
 from typing import Dict, List, Sequence, Any
-from typing import TypeAlias
 
 
 from raman_fitting.config.path_settings import (
@@ -16,8 +15,6 @@
 from raman_fitting.models.deconvolution.base_model import (
     get_models_and_peaks_from_definitions,
 )
-from raman_fitting.models.spectrum import SpectrumData
-from raman_fitting.models.fit_models import SpectrumFitModel
 from raman_fitting.models.splitter import RegionNames
 from raman_fitting.exports.exporter import ExportManager
 from raman_fitting.imports.files.file_indexer import (
@@ -34,12 +31,11 @@
 from raman_fitting.delegating.pre_processing import (
     prepare_aggregated_spectrum_from_files,
 )
-
-from loguru import logger
+from raman_fitting.types import LMFitModelCollection
+from .run_fit_spectrum import run_fit_over_selected_models
 
 
-LMFitModelCollection: TypeAlias = Dict[str, Dict[str, BaseLMFitModel]]
-SpectrumFitModelCollection: TypeAlias = Dict[str, Dict[str, SpectrumFitModel]]
+from loguru import logger
 
 
 @dataclass
@@ -53,6 +49,7 @@ class MainDelegator:
     """
 
     run_mode: RunModes
+    use_multiprocessing: bool = False
     lmfit_models: LMFitModelCollection = field(
         default_factory=get_models_and_peaks_from_definitions
     )
@@ -142,6 +139,7 @@ def main_run(self):
             logger.info("No fit models were selected.")
 
         results = {}
+
         for group_name, grp in groupby_sample_group(selection):
             results[group_name] = {}
             for sample_id, sample_grp in groupby_sample_id(grp):
@@ -162,13 +160,17 @@ def main_run(self):
                     _error_msg = f"Handle multiple source files for a single position on a sample, {group_name} {sample_id}"
                     results[group_name][sample_id]["errors"] = _error_msg
                     logger.debug(_error_msg)
-                model_result = run_fit_over_selected_models(sgrp, self.selected_models)
+                model_result = run_fit_over_selected_models(
+                    sgrp,
+                    self.selected_models,
+                    use_multiprocessing=self.use_multiprocessing,
+                )
                 results[group_name][sample_id]["fit_results"] = model_result
         self.results = results
 
 
-def run_fit_over_selected_models(
-    raman_files: List[RamanFileInfo], models: LMFitModelCollection
+def get_results_over_selected_models(
+    raman_files: List[RamanFileInfo], models: LMFitModelCollection, fit_model_results
 ) -> Dict[RegionNames, AggregatedSampleSpectrumFitResult]:
     results = {}
     for region_name, region_grp in models.items():
@@ -177,12 +179,6 @@ def run_fit_over_selected_models(
         )
         if aggregated_spectrum is None:
             continue
-        fit_model_results = {}
-        for model_name, model in region_grp.items():
-            spectrum_fit = run_sample_fit_with_model(
-                aggregated_spectrum.spectrum, model
-            )
-            fit_model_results[model_name] = spectrum_fit
         fit_region_results = AggregatedSampleSpectrumFitResult(
             region_name=region_name,
             aggregated_spectrum=aggregated_spectrum,
@@ -192,21 +188,6 @@ def run_fit_over_selected_models(
     return results
 
 
-def run_sample_fit_with_model(
-    spectrum: SpectrumData, model: BaseLMFitModel
-) -> SpectrumFitModel:
-    name = model.name
-    region = model.region_name.name
-    spec_fit = SpectrumFitModel(spectrum=spectrum, model=model, region=region)
-    #  include optional https://lmfit.github.io/lmfit-py/model.html#saving-and-loading-modelresults
-    spec_fit.run_fit()
-    logger.debug(
-        f"Fit with model {name} on {region} success: {spec_fit.fit_result.success} in {spec_fit.elapsed_time:.2f}s."
-    )
-    # spec_fit.fit_result.plot(show_init=True)
-    return spec_fit
-
-
 def make_examples():
     # breakpoint()
     _main_run = MainDelegator(

src/raman_fitting/imports/spectrum/datafile_parsers.py

@@ -1,8 +1,7 @@
-from typing import List, Sequence
+from typing import Sequence
 from pathlib import Path
 
 import numpy as np
-import pandas as pd
 from tablib import Dataset
 
 from loguru import logger
@@ -84,27 +83,3 @@ def use_np_loadtxt(filepath, usecols=(0, 1), **kwargs) -> np.array:
         logger.error(_msg)
         raise ValueError(_msg) from exc
     return array
-
-
-def cast_array_into_spectrum_frame(array, keys: List[str] = None) -> pd.DataFrame:
-    """cast array into spectrum frame"""
-    if array.ndim != len(keys):
-        raise ValueError(
-            f"Array dimension {array.ndim} does not match the number of keys {len(keys)}"
-        )
-
-    try:
-        spectrum_data = pd.DataFrame(array, columns=keys)
-        return spectrum_data
-    except Exception as exc:
-        _msg = f"Can not create DataFrame from array object: {array}\n{exc}"
-        logger.error(_msg)
-        raise ValueError(_msg) from exc
-
-
-def load_spectrum_from_txt(filepath, **kwargs) -> pd.DataFrame:
-    """load spectrum from txt file"""
-    keys = kwargs.pop("keys")
-    array = use_np_loadtxt(filepath, **kwargs)
-    spectrum_data = cast_array_into_spectrum_frame(array, keys=keys)
-    return spectrum_data

src/raman_fitting/imports/spectrumdata_parser.py

@@ -38,7 +38,7 @@
 }
 
 
-def get_file_parser(filepath: Path) -> Callable[Path, Dataset]:
+def get_file_parser(filepath: Path) -> Callable[[Path], Dataset]:
     "Get callable file parser function."
     suffix = filepath.suffix
     parser = SPECTRUM_FILETYPE_PARSERS[suffix]["method"]
@@ -49,9 +49,9 @@ def get_file_parser(filepath: Path) -> Callable[Path, Dataset]:
 @dataclass
 class SpectrumReader:
     """
-    Reads a clean spectrum from a file Path or str
+    Reads a spectrum from a 'raw' data file Path or str
 
-    with columns "ramanshift" and "intensity".
+    with spectrum_data_keys "ramanshift" and "intensity".
     Double checks the values
     Sets a hash attribute afterwards
     """
@@ -65,14 +65,14 @@ class SpectrumReader:
     spectrum_hash: str = field(default=None, repr=False)
     spectrum_length: int = field(default=0, init=False)
 
-    def __post_init__(self, **kwargs):
+    def __post_init__(self):
         super().__init__()
 
         self.filepath = validate_filepath(self.filepath)
         self.spectrum_length = 0
 
         if self.filepath is None:
-            return
+            raise ValueError(f"File is not valid. {self.filepath}")
         parser = get_file_parser(self.filepath)
         parsed_spectrum = parser(self.filepath, self.spectrum_data_keys)
         if parsed_spectrum is None:
@@ -86,7 +86,11 @@ def __post_init__(self, **kwargs):
                 logger.warning(
                     f"The values of {spectrum_key} of this spectrum are invalid. {validator}"
                 )
-        spec_init = {"label": self.label, "region_name": self.region_name}
+        spec_init = {
+            "label": self.label,
+            "region_name": self.region_name,
+            "source": self.filepath,
+        }
         _parsed_spec_dict = {
             k: parsed_spectrum[k] for k in spectrum_keys_expected_values.keys()
         }

src/raman_fitting/models/deconvolution/base_peak.py

@@ -18,6 +18,7 @@
     parmeter_to_dict,
 )
 from raman_fitting.config.default_models import load_config_from_toml_files
+from raman_fitting.utils.string_operations import prepare_text_from_param
 
 ParamHintDict = Dict[str, Dict[str, Optional[float | bool | str]]]
 
@@ -197,19 +198,8 @@ def __str__(self):
 
 
 def make_string_from_param_hints(param_hints: Parameters) -> str:
-    text = ""
     param_center = param_hints.get("center", {})
-    if param_center:
-        center_txt = ""
-        center_val = param_center.value
-        center_min = param_center.min
-        if center_min != center_val:
-            center_txt += f"{center_min} < "
-        center_txt += f"{center_val}"
-        center_max = param_center.max
-        if center_max != center_val:
-            center_txt += f" > {center_max}"
-        text += f", center : {center_txt}"
+    text = prepare_text_from_param(param_center)
     return text
 
 

src/raman_fitting/models/deconvolution/lmfit_parameter.py

@@ -1,7 +1,7 @@
-from logging import warn
 import math
 from enum import StrEnum
 from typing import List, Optional, Dict
+from warnings import warn
 
 from lmfit import Parameter
 from lmfit.models import GaussianModel, LorentzianModel, Model, VoigtModel

src/raman_fitting/models/spectrum.py

@@ -16,7 +16,7 @@ class SpectrumData(BaseModel):
     intensity: pnd.Np1DArrayFp32 = Field(repr=False)
     label: str
     region_name: str | None = None
-    source: Sequence[str] | None = None
+    source: FilePath | Sequence[FilePath] | str | Sequence[str] | None = None
 
     @model_validator(mode="after")
     def validate_equal_length(self):

src/raman_fitting/models/splitter.py

@@ -29,6 +29,7 @@ def process_spectrum(self) -> "SplitSpectrum":
             self.spectrum.intensity,
             spec_region_limits=self.region_limits,
             label=self.spectrum.label,
+            source=self.spectrum.source,
         )
         self.spec_regions = spec_regions
         return self
@@ -56,7 +57,11 @@ def get_default_spectrum_region_limits(
 
 
 def split_spectrum_data_in_regions(
-    ramanshift: np.array, intensity: np.array, spec_region_limits=None, label=None
+    ramanshift: np.array,
+    intensity: np.array,
+    spec_region_limits=None,
+    label=None,
+    source=None,
 ) -> Dict[str, SpectrumData]:
     """
     For splitting of spectra into the several SpectrumRegionLimits,
@@ -78,6 +83,7 @@ def split_spectrum_data_in_regions(
             "intensity": intensity[ind],
             "label": region_lbl,
             "region_name": region_name,
+            "source": source,
         }
         spec_regions[region_lbl] = SpectrumData(**_data)
     return spec_regions

src/raman_fitting/processing/baseline_subtraction.py

@@ -40,7 +40,7 @@ def subtract_baseline_per_region(spec: SpectrumData, split_spectrum: SplitSpectr
 
 
 def subtract_baseline_from_split_spectrum(
-    split_spectrum: SplitSpectrum, label=None
+    split_spectrum: SplitSpectrum = None, label=None
 ) -> SplitSpectrum:
     _bl_spec_regions = {}
     _info = {}
@@ -53,7 +53,8 @@ def subtract_baseline_from_split_spectrum(
                 "ramanshift": spec.ramanshift,
                 "intensity": blcorr_int,
                 "label": new_label,
-                "regionn_name": region_name,
+                "region_name": region_name,
+                "source": spec.source,
             }
         )
         _bl_spec_regions.update(**{region_name: spec})
@@ -62,15 +63,3 @@ def subtract_baseline_from_split_spectrum(
         update={"spec_regions": _bl_spec_regions, "info": _info}
     )
     return bl_corrected_spectra
-
-
-def subtract_baseline(
-    ramanshift: np.array, intensity: np.array, label: str = None
-) -> SplitSpectrum:
-    "Subtract the a baseline of background intensity of a spectrum."
-    spectrum = SpectrumData(ramanshift=ramanshift, intensity=intensity, label=label)
-    split_spectrum = SplitSpectrum(spectrum=spectrum)
-    blcorrected_spectrum = subtract_baseline_from_split_spectrum(
-        split_spectrum, label=label
-    )
-    return blcorrected_spectrum

src/raman_fitting/processing/despike.py

@@ -23,7 +23,7 @@ class SpectrumDespiker(BaseModel):
     moving_region_size: int = 1
     ignore_lims: Tuple[int, int] = (20, 46)
     info: Dict = Field(default_factory=dict)
-    despiked_spectrum: SpectrumData = Field(None)
+    processed_spectrum: SpectrumData = Field(None)
 
     @model_validator(mode="after")
     def process_spectrum(self) -> "SpectrumDespiker":
@@ -36,7 +36,7 @@ def process_spectrum(self) -> "SpectrumDespiker":
             update={"intensity": despiked_intensity}, deep=True
         )
         SpectrumData.model_validate(despiked_spec, from_attributes=True)
-        self.despiked_spectrum = despiked_spec
+        self.processed_spectrum = despiked_spec
         self.info.update(**result_info)
         return self