AeroViz 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

AeroViz/process/script/PSD_dry.py

@@ -5,90 +5,89 @@ from pandas import DataFrame, read_csv, concat
 
 from AeroViz.process.core import DataProc
 from AeroViz.process.core.SizeDist import SizeDist
-from AeroViz.tools import DataReader
 
 
 class DryPSDProc(DataProc):
-	"""
-	A class for process impact data.
-
-	Parameters
-	----------
-	reset : bool, optional
-		If True, resets the process. Default is False.
-	filename : str, optional
-		The name of the file to process. Default is None.
-
-	Methods
-	-------
-	process_data():
-		Process data and save the result.
-
-	Attributes
-	----------
-	DEFAULT_PATH : Path
-		The default path for data files.
-
-
-	Examples
-	--------
-	>>> df = DryPSDProc(reset=True, filename='PNSD_dNdlogdp_dry.csv').process_data()
-	"""
-
-	def __init__(self, file_path: Path | str = 'PNSD_dNdlogdp.csv', file_path_chem: Path | str = 'chemical.csv'):
-		super().__init__()
-		self.file_path = Path(file_path)
-		self.file_path_chem = Path(file_path_chem)
-
-		self.psd = SizeDist(read_csv(file_path, parse_dates=['Time'], index_col='Time'))
-		self.RI = read_csv(file_path_chem, parse_dates=['Time'], index_col='Time')[['n_dry', 'n_amb', 'k_dry', 'k_amb',
-																					'AS_volume_ratio',
-																					'AN_volume_ratio',
-																					'OM_volume_ratio',
-																					'Soil_volume_ratio',
-																					'SS_volume_ratio',
-																					'EC_volume_ratio',
-																					'ALWC_volume_ratio']]
-
-	def process_data(self, reset: bool = False, save_filename: Path | str = None) -> DataFrame:
-		save_filename = Path(save_filename)
-		if save_filename.exists() and not reset:
-			return read_csv(save_filename, parse_dates=['Time']).set_index('Time')
-		_df = concat([self.psd, self.RI], axis=1)
-		_df.to_csv(save_filename)
-		return _df
+    """
+    A class for process impact data.
+
+    Parameters
+    ----------
+    reset : bool, optional
+        If True, resets the process. Default is False.
+    filename : str, optional
+        The name of the file to process. Default is None.
+
+    Methods
+    -------
+    process_data():
+        Process data and save the result.
+
+    Attributes
+    ----------
+    DEFAULT_PATH : Path
+        The default path for data files.
+
+
+    Examples
+    --------
+    >>> df = DryPSDProc(reset=True, filename='PNSD_dNdlogdp_dry.csv').process_data()
+    """
+
+    def __init__(self, file_path: Path | str = 'PNSD_dNdlogdp.csv', file_path_chem: Path | str = 'chemical.csv'):
+        super().__init__()
+        self.file_path = Path(file_path)
+        self.file_path_chem = Path(file_path_chem)
+
+        self.psd = SizeDist(read_csv(file_path, parse_dates=['Time'], index_col='Time'))
+        self.RI = read_csv(file_path_chem, parse_dates=['Time'], index_col='Time')[['n_dry', 'n_amb', 'k_dry', 'k_amb',
+                                                                                    'AS_volume_ratio',
+                                                                                    'AN_volume_ratio',
+                                                                                    'OM_volume_ratio',
+                                                                                    'Soil_volume_ratio',
+                                                                                    'SS_volume_ratio',
+                                                                                    'EC_volume_ratio',
+                                                                                    'ALWC_volume_ratio']]
+
+    def process_data(self, reset: bool = False, save_filename: Path | str = None) -> DataFrame:
+        save_filename = Path(save_filename)
+        if save_filename.exists() and not reset:
+            return read_csv(save_filename, parse_dates=['Time']).set_index('Time')
+        _df = concat([self.psd, self.RI], axis=1)
+        _df.to_csv(save_filename)
+        return _df
 
 
 def dry_PNSD_process(dist, dp, **kwargs):
-	ndp = np.array(dist[:np.size(dp)])
-	gRH = resolved_gRH(dp, dist['gRH'], uniform=True)
+    ndp = np.array(dist[:np.size(dp)])
+    gRH = resolved_gRH(dp, dist['gRH'], uniform=True)
 
-	dry_dp = dp / gRH
-	belong_which_ibin = np.digitize(dry_dp, dp) - 1
+    dry_dp = dp / gRH
+    belong_which_ibin = np.digitize(dry_dp, dp) - 1
 
-	result = {}
-	for i, (ibin, dn) in enumerate(zip(belong_which_ibin, ndp)):
-		if dp[ibin] not in result:
-			result[dp[ibin]] = []
-		result[dp[ibin]].append(ndp[i])
+    result = {}
+    for i, (ibin, dn) in enumerate(zip(belong_which_ibin, ndp)):
+        if dp[ibin] not in result:
+            result[dp[ibin]] = []
+        result[dp[ibin]].append(ndp[i])
 
-	dry_ndp = []
-	for key, val in result.items():
-		dry_ndp.append(sum(val) / len(val))
+    dry_ndp = []
+    for key, val in result.items():
+        dry_ndp.append(sum(val) / len(val))
 
-	return np.array(dry_ndp)
+    return np.array(dry_ndp)
 
 
 def resolved_gRH(dp, gRH=1.31, uniform=True):
-	if uniform:
-		return np.array([gRH] * dp.size)
+    if uniform:
+        return np.array([gRH] * dp.size)
 
-	else:
-		lognorm_dist = lambda x, geoMean, geoStd: (gRH / (np.log10(geoStd) * np.sqrt(2 * np.pi))) * np.exp(
-			-(x - np.log10(geoMean)) ** 2 / (2 * np.log10(geoStd) ** 2))
-		abc = lognorm_dist(np.log10(dp), 200, 2.0)
-		return np.where(abc < 1, 1, abc)
+    else:
+        lognorm_dist = lambda x, geoMean, geoStd: (gRH / (np.log10(geoStd) * np.sqrt(2 * np.pi))) * np.exp(
+            -(x - np.log10(geoMean)) ** 2 / (2 * np.log10(geoStd) ** 2))
+        abc = lognorm_dist(np.log10(dp), 200, 2.0)
+        return np.where(abc < 1, 1, abc)
 
 
 if __name__ == '__main__':
-	pass
+    pass

AeroViz/process/script/retrieve_RI.py

@@ -1,5 +1,4 @@
 import numpy as np
-import pandas as pd
 from pandas import DataFrame
 
 from AeroViz.process.core.SizeDist import SizeDist
@@ -7,64 +6,64 @@ from AeroViz.process.method import Mie_PESD
 
 
 def retrieve_RI(_df: DataFrame,
-				_PNSD: DataFrame,
-				nMin: float = 1.33,
-				nMax: float = 1.60,
-				kMin: float = 0.00,
-				kMax: float = 0.60,
-				spaceSize: int = 31,
-				dlogdp: float = 0.014
-				) -> DataFrame:
-	nRange = np.linspace(nMin, nMax, num=spaceSize)
-	kRange = np.linspace(kMin, kMax, spaceSize)
-	Delta_array = np.zeros((spaceSize, spaceSize))
-	# 同一時間除了折射率其餘數據皆相同 因此在折射率的迴圈外
-	bext_mea, bsca_mea, babs_mea = _df['Extinction'], _df['Scattering'], _df['Absorption']
+                _PNSD: DataFrame,
+                nMin: float = 1.33,
+                nMax: float = 1.60,
+                kMin: float = 0.00,
+                kMax: float = 0.60,
+                spaceSize: int = 31,
+                dlogdp: float = 0.014
+                ) -> DataFrame:
+    nRange = np.linspace(nMin, nMax, num=spaceSize)
+    kRange = np.linspace(kMin, kMax, spaceSize)
+    Delta_array = np.zeros((spaceSize, spaceSize))
+    # 同一時間除了折射率其餘數據皆相同 因此在折射率的迴圈外
+    bext_mea, bsca_mea, babs_mea = _df['Extinction'], _df['Scattering'], _df['Absorption']
 
-	dp = SizeDist(data=_PNSD).dp
-	for ki, k in enumerate(kRange):
-		for ni, n in enumerate(nRange):
-			m = n + (1j * k)
-			ndp = np.array(_df[3:])
+    dp = SizeDist(data=_PNSD).dp
+    for ki, k in enumerate(kRange):
+        for ni, n in enumerate(nRange):
+            m = n + (1j * k)
+            ndp = np.array(_df[3:])
 
-			ext_dist, sca_dist, abs_dist = Mie_PESD(m, 550, dp, ndp)
+            ext_dist, sca_dist, abs_dist = Mie_PESD(m, 550, dp, ndp)
 
-			bext_cal = sum(ext_dist) * dlogdp
-			bsca_cal = sum(sca_dist) * dlogdp
-			babs_cal = sum(abs_dist) * dlogdp
+            bext_cal = sum(ext_dist) * dlogdp
+            bsca_cal = sum(sca_dist) * dlogdp
+            babs_cal = sum(abs_dist) * dlogdp
 
-			Delta_array[ni][ki] = ((babs_mea - babs_cal) / 18.23) ** 2 + ((bsca_mea - bsca_cal) / 83.67) ** 2
+            Delta_array[ni][ki] = ((babs_mea - babs_cal) / 18.23) ** 2 + ((bsca_mea - bsca_cal) / 83.67) ** 2
 
-	min_delta = Delta_array.argmin()
-	next_n = nRange[(min_delta // spaceSize)]
-	next_k = kRange[(min_delta % spaceSize)]
+    min_delta = Delta_array.argmin()
+    next_n = nRange[(min_delta // spaceSize)]
+    next_k = kRange[(min_delta % spaceSize)]
 
-	# 將網格變小
-	nMin_small = next_n - 0.02 if next_n > 1.33 else 1.33
-	nMax_small = next_n + 0.02
-	kMin_small = next_k - 0.04 if next_k > 0.04 else 0
-	kMax_small = next_k + 0.04
-	spaceSize_small = 41
+    # 將網格變小
+    nMin_small = next_n - 0.02 if next_n > 1.33 else 1.33
+    nMax_small = next_n + 0.02
+    kMin_small = next_k - 0.04 if next_k > 0.04 else 0
+    kMax_small = next_k + 0.04
+    spaceSize_small = 41
 
-	nRange_small = np.linspace(nMin_small, nMax_small, spaceSize_small)
-	kRange_small = np.linspace(kMin_small, kMax_small, spaceSize_small)
-	Delta_array_small = np.zeros((spaceSize_small, spaceSize_small))
-	# 所有數據與大網格一致所以使用上方便數即可
-	for ki, k in enumerate(kRange_small):
-		for ni, n in enumerate(nRange_small):
-			m = n + (1j * k)
-			ndp = np.array(_df[3:])
-			ext_dist, sca_dist, abs_dist = Mie_PESD(m, 550, dp, ndp)
+    nRange_small = np.linspace(nMin_small, nMax_small, spaceSize_small)
+    kRange_small = np.linspace(kMin_small, kMax_small, spaceSize_small)
+    Delta_array_small = np.zeros((spaceSize_small, spaceSize_small))
+    # 所有數據與大網格一致所以使用上方便數即可
+    for ki, k in enumerate(kRange_small):
+        for ni, n in enumerate(nRange_small):
+            m = n + (1j * k)
+            ndp = np.array(_df[3:])
+            ext_dist, sca_dist, abs_dist = Mie_PESD(m, 550, dp, ndp)
 
-			bext_cal = sum(ext_dist) * dlogdp
-			bsca_cal = sum(sca_dist) * dlogdp
-			babs_cal = sum(abs_dist) * dlogdp
+            bext_cal = sum(ext_dist) * dlogdp
+            bsca_cal = sum(sca_dist) * dlogdp
+            babs_cal = sum(abs_dist) * dlogdp
 
-			Delta_array_small[ni][ki] = ((bext_mea - bext_cal) / 18.23) ** 2 + ((bsca_mea - bsca_cal) / 83.67) ** 2
+            Delta_array_small[ni][ki] = ((bext_mea - bext_cal) / 18.23) ** 2 + ((bsca_mea - bsca_cal) / 83.67) ** 2
 
-	min_delta_small = Delta_array_small.argmin()
-	_df['re_real'] = (nRange_small[(min_delta_small // spaceSize_small)])
-	_df['re_imaginary'] = (kRange_small[(min_delta_small % spaceSize_small)])
+    min_delta_small = Delta_array_small.argmin()
+    _df['re_real'] = (nRange_small[(min_delta_small // spaceSize_small)])
+    _df['re_imaginary'] = (kRange_small[(min_delta_small % spaceSize_small)])
 
-	print(f'\t\tReal part:{_df['re_real']}\tIm part:{_df['re_imaginary']}', end='')
-	return _df['re_real':]
+    print(f'\t\tReal part:{_df['re_real']}\tIm part:{_df['re_imaginary']}', end='')
+    return _df['re_real':]

AeroViz/rawDataReader/__init__.py

@@ -1,68 +1,63 @@
 from datetime import datetime
+from pathlib import Path
 
+from AeroViz.rawDataReader.config.supported_instruments import meta
 from AeroViz.rawDataReader.script import *
-from AeroViz.rawDataReader.utils.config import meta
 
 __all__ = ['RawDataReader']
 
 
 def RawDataReader(instrument_name: str,
-				  _path,
-				  QC: bool = True,
-				  csv_raw: bool = True,
-				  reset: bool = False,
-				  rate: bool = False,
-				  append_data: bool = False,
-				  update_meta=None,
-				  start: datetime | None = None,
-				  end: datetime | None = None,
-				  mean_freq='1h',
-				  csv_out=True,
-				  **kwargs
-				  ):
-	# Mapping of instrument names to their respective classes
-	instrument_class_map = {
-		'NEPH': NEPH,
-		'Aurora': Aurora,
-		'Table': Table,
-		'EPA_vertical': EPA_vertical,
-		'APS_3321': APS_3321,
-		'SMPS_TH': SMPS_TH,
-		'AE33': AE33,
-		'AE43': AE43,
-		'BC1054': BC1054,
-		'MA350': MA350,
-		'TEOM': TEOM,
-		'OCEC_RES': OCEC_RES,
-		'OCEC_LCRES': OCEC_LCRES,
-		'IGAC_TH': IGAC_TH,
-		'IGAC_ZM': IGAC_ZM,
-		'VOC_TH': VOC_TH,
-		'VOC_ZM': VOC_ZM,
-		'SMPS_genr': SMPS_genr,
-		'SMPS_aim11': SMPS_aim11,
-		'GRIMM': GRIMM
-		# Add other instruments and their corresponding classes here
-	}
+                  path: Path,
+                  qc: bool = True,
+                  csv_raw: bool = True,
+                  reset: bool = False,
+                  rate: bool = False,
+                  append_data: bool = False,
+                  start: datetime | None = None,
+                  end: datetime | None = None,
+                  mean_freq='1h',
+                  csv_out=True,
+                  ):
+    # Mapping of instrument names to their respective classes
+    instrument_class_map = {
+        'NEPH': NEPH,
+        'Aurora': Aurora,
+        'SMPS_genr': SMPS_genr,
+        'SMPS_aim11': SMPS_aim11,
+        'SMPS_TH': SMPS_TH,
+        'GRIMM': GRIMM,
+        'APS_3321': APS_3321,
+        'AE33': AE33,
+        'AE43': AE43,
+        'BC1054': BC1054,
+        'MA350': MA350,
+        'TEOM': TEOM,
+        'Sunset_OCEC': Sunset_OCEC,
+        'IGAC': IGAC,
+        'VOC': VOC,
+        'Table': Table,
+        'EPA_vertical': EPA_vertical,
+        'Minion': Minion
+        # Add other instruments and their corresponding classes here
+    }
 
-	# Check if the instrument name is in the map
-	if instrument_name not in meta.keys():
-		raise ValueError(f"Instrument name '{instrument_name}' is not valid. \nMust be one of: {list(meta.keys())}")
+    # Check if the instrument name is in the map
+    if instrument_name not in meta.keys():
+        raise ValueError(f"Instrument name '{instrument_name}' is not valid. \nMust be one of: {list(meta.keys())}")
 
-	# Instantiate the class and return the instance
-	reader_module = instrument_class_map[instrument_name].Reader(
-		_path=_path,
-		QC=QC,
-		csv_raw=csv_raw,
-		reset=reset,
-		rate=rate,
-		append_data=append_data,
-		update_meta=update_meta
-	)
-	return reader_module(
-		start=start,
-		end=end,
-		mean_freq=mean_freq,
-		csv_out=csv_out,
-		**kwargs
-	)
+    # Instantiate the class and return the instance
+    reader_module = instrument_class_map[instrument_name].Reader(
+        path=path,
+        qc=qc,
+        csv_raw=csv_raw,
+        reset=reset,
+        rate=rate,
+        append_data=append_data
+    )
+    return reader_module(
+        start=start,
+        end=end,
+        mean_freq=mean_freq,
+        csv_out=csv_out,
+    )

AeroViz/rawDataReader/config/supported_instruments.py

@@ -0,0 +1,155 @@
+# Description: Configuration file for rawDataReader
+
+meta = {
+    "NEPH": {
+        "pattern": "*.dat",
+        "freq": "5min",
+        "deter_key": {"Scatter Coe. (550 nm)": ["G"]},
+    },
+
+    "Aurora": {
+        "pattern": "*.csv",
+        "freq": "1min",
+        "deter_key": {"Scatter Coe. (550 nm)": ["G"]},
+    },
+
+    "SMPS_TH": {
+        "pattern": "*.txt",
+        "freq": "6min",
+        "deter_key": {"Bins": ["all"]},
+    },
+
+    "SMPS_genr": {
+        "pattern": "*.txt",
+        "freq": "6min",
+        "deter_key": {"Bins": ["all"]},
+    },
+
+    "SMPS_aim11": {
+        "pattern": "*.csv",
+        "freq": "6min",
+        "deter_key": {"Bins": ["all"]},
+    },
+
+    "GRIMM": {
+        "pattern": "*.dat",
+        "freq": "6min",
+        "deter_key": {"Bins": ["all"]},
+    },
+
+    "APS_3321": {
+        "pattern": "*.TXT",
+        "freq": "6min",
+        "deter_key": {"Bins": ["all"]},
+    },
+
+    "AE33": {
+        "pattern": "[!ST|!CT|!FV]*[!log]_AE33*.dat",
+        "freq": "1min",
+        "deter_key": {"BC Mass Conc. (880 nm)": ["BC6"]},
+        "error_state": [],
+    },
+
+    "AE43": {
+        "pattern": "[!ST|!CT|!FV]*[!log]_AE43*.dat",
+        "freq": "1min",
+        "deter_key": {"BC Mass Conc. (880 nm)": ["BC6"]},
+        "error_state": [],
+    },
+
+    "BC1054": {
+        "pattern": "*.csv",
+        "freq": "1min",
+        "deter_key": {"BC Mass Conc. (880 nm)": ["BC9"]},
+        "error_state": [1, 2, 4, 8, 16, 32, 65536],
+    },
+
+    "MA350": {
+        "pattern": "*.csv",
+        "freq": "1min",
+        "deter_key": {"BC Mass Conc. (880 nm)": ["BC5"]},
+    },
+
+    "TEOM": {
+        "pattern": "*.csv",
+        "freq": "6min",
+        "deter_key": {
+            "PM1.0 Mass Conc.": ["PM_Total"],
+            "PM1.0 NV Mass Conc.": ["PM_NV"],
+        },
+    },
+
+    "Sunset_OCEC": {
+        "pattern": "*LCRes.csv",
+        "freq": "1h",
+        "deter_key": {
+            "Thermal OC/EC": ["Thermal_EC", "Thermal_OC"],
+            "Thermal OC": ["Thermal_OC"],
+            "Thermal EC": ["Thermal_EC"],
+            "Optical OC/EC": ["Optical_EC", "Optical_OC"],
+            "Optical OC": ["Optical_OC"],
+            "Optical EC": ["Optical_EC"],
+        },
+    },
+
+    "IGAC": {
+        "pattern": "*.csv",
+        "freq": "1h",
+        "deter_key": {
+            "Na+": ["Na+"],
+            "NH4+": ["NH4+"],
+            "K+": ["K+"],
+            "Mg2+": ["Mg2+"],
+            "Ca2+": ["Ca2+"],
+            "Cl-": ["Cl-"],
+            "NO2-": ["NO2-"],
+            "NO3-": ["NO3-"],
+            "SO42-": ["SO42-"],
+            "Main Salt (NH4+, NO3-, SO42-)": ["NO3-", "SO42-", "NH4+"],
+        },
+    },
+
+    "VOC": {
+        "pattern": "*.csv",
+        "freq": "1h",
+        "key": ['Ethane', 'Propane', 'Isobutane', 'n-Butane', 'Cyclopentane', 'Isopentane',
+                'n-Pentane', '2,2-Dimethylbutane', '2,3-Dimethylbutane', '2-Methylpentane',
+                '3-Methylpentane', 'n-Hexane', 'Methylcyclopentane', '2,4-Dimethylpentane',
+                'Cyclohexane', '2-Methylhexane', '2-Methylhexane', '3-Methylheptane',
+                '2,2,4-Trimethylpentane', 'n-Heptane', 'Methylcyclohexane',
+                '2,3,4-Trimethylpentane', '2-Methylheptane', '3-Methylhexane', 'n-Octane',
+                'n-Nonane', 'n-Decane', 'n-Undecane', 'Ethylene', 'Propylene', 't-2-Butene',
+                '1-Butene', 'cis-2-Butene', 't-2-Pentene', '1-Pentene', 'cis-2-Pentene',
+                'isoprene', 'Acetylene', 'Benzene', 'Toluene', 'Ethylbenzene', 'm,p-Xylene',
+                'Styrene', 'o-Xylene', 'Isopropylbenzene', 'n-Propylbenzene', 'm-Ethyltoluene',
+                'p-Ethyltoluene', '1,3,5-Trimethylbenzene', 'o-Ethyltoluene',
+                '1,2,4-Trimethylbenzene', '1,2,3-Trimethylbenzene', 'm-Diethylbenzene',
+                'p-Diethylbenzene'],
+
+        "key_2": ['Isopentane', 'Hexane', '2-Methylhexane', '3-Methylhexane', '2-Methylheptane', '3-Methylheptane',
+                  'Propene', '1.3-Butadiene', 'Isoprene', '1-Octene',
+                  'Benzene', 'Toluene', 'Ethylbenzene', 'm.p-Xylene', 'o-Xylene', 'Iso-Propylbenzene', 'Styrene',
+                  'n-Propylbenzene', '3.4-Ethyltoluene', '1.3.5-TMB', '2-Ethyltoluene', '1.2.4-TMB', '1.2.3-TMB',
+                  'Acetaldehyde', 'Ethanol', 'Acetone', 'IPA', 'Ethyl Acetate', 'Butyl Acetate',
+                  'VCM', 'TCE', 'PCE', '1.4-DCB', '1.2-DCB'],
+        "deter_key": None,
+    },
+
+    "Table": {
+        "pattern": "*.csv",
+        "freq": "1h",
+        "deter_key": None,
+    },
+
+    "EPA_vertical": {
+        "pattern": "*.csv",
+        "freq": "1h",
+        "deter_key": None,
+    },
+
+    "Minion": {
+        "pattern": "*.csv",
+        "freq": "1h",
+        "deter_key": None,
+    },
+}