""" Sensospot Data Parser Parsing the numerical output from Sensovations Sensospot image analysis. """ from pathlib import Path from collections import namedtuple import numpy from defusedxml import ElementTree from .columns import ( COL_NAME_EXPOSURE_ID, COL_NAME_PARAMETERS_TIME, COL_NAME_PARAMETERS_CHANNEL, ) ExposureInfo = namedtuple("ExposureInfo", ["channel", "time"]) def _search_measurement_params_file(folder): """ searches for a exposure settings file in a folder """ folder_path = Path(folder) params_folder = folder_path / "Parameters" if not params_folder.is_dir(): return None param_files = list(params_folder.glob("**/*.svexp")) if len(param_files) == 1: return param_files[0] else: return None def _parse_measurement_params(params_file): """ parses the cannel informations from a settings file """ file_path = Path(params_file) with file_path.open("r") as file_handle: tree = ElementTree.parse(file_handle) result = {} for child in tree.find("Channels"): # child.tag == "ChannelConfig1" exposure = int(child.tag[-1]) channel_description = child.attrib["Description"] # channel_description == "[Cy3|Cy5] Green" channel = channel_description.rsplit(" ", 1)[-1] time = float(child.attrib["ExposureTimeMs"]) result[exposure] = ExposureInfo(channel.lower(), time) return result def get_measurement_params(folder): """ returns measurement parameters """ params_file = _search_measurement_params_file(folder) if params_file is not None: return _parse_measurement_params(params_file) return None def _add_measurement_params(data_frame, params): """ adds measurement parameters to a data frame """ for exposure_id, info in params.items(): mask = data_frame[COL_NAME_EXPOSURE_ID] == exposure_id data_frame.loc[mask, COL_NAME_PARAMETERS_CHANNEL] = info.channel data_frame.loc[mask, COL_NAME_PARAMETERS_TIME] = info.time data_frame[COL_NAME_PARAMETERS_CHANNEL] = data_frame[ COL_NAME_PARAMETERS_CHANNEL ].astype("category") return data_frame def add_optional_measurement_parameters(data_frame, folder): """ adds measurement params to the data frame, if they could be parsed """ data_frame[COL_NAME_PARAMETERS_CHANNEL] = numpy.nan data_frame[COL_NAME_PARAMETERS_TIME] = numpy.nan params = get_measurement_params(folder) if params: available_exposures = set(data_frame[COL_NAME_EXPOSURE_ID].unique()) if available_exposures == set(params.keys()): return _add_measurement_params(data_frame, params) return data_frame