AeroViz 0.1.3b0__py3-none-any.whl → 0.1.5__py3-none-any.whl

AeroViz/process/__init__.py

@@ -5,10 +5,10 @@ from pandas import read_csv, concat
 from AeroViz.process.script import (ImpactProc, ImproveProc, ChemicalProc, ParticleSizeDistProc,
                                     ExtinctionDistProc, OthersProc)
 
-__all__ = ['DataProcess']
+__all__ = ['DataProcessor', 'ImpactProc', 'ImproveProc', 'ChemicalProc', 'ParticleSizeDistProc', 'ExtinctionDistProc', ]
 
 
-class DataProcess:
+class DataProcessor:
     def __new__(cls, file_path, reset: bool = False, save_file: Path | str = 'All_data.csv'):
         file_path = Path(file_path)
 

AeroViz/process/script/AbstractDistCalc.py

@@ -64,7 +64,7 @@ class ExtinctionDistCalc(AbstractDistCalc):
     def __init__(self,
                  psd: SizeDist,
                  RI: DataFrame,
-                 method: Literal['internal', 'external', 'utils-shell', 'sensitivity'],
+                 method: Literal['internal', 'external', 'config-shell', 'sensitivity'],
                  result_type: Literal['extinction', 'scattering', 'absorption'] = 'extinction'
                  ):
         self.psd = psd

AeroViz/process/script/Chemical.py

@@ -1,7 +1,7 @@
 from pathlib import Path
 
 import numpy as np
-from pandas import read_csv, concat, notna, DataFrame
+from pandas import read_csv, concat, notna, DataFrame, to_numeric
 
 from AeroViz.process.core import DataProc
 from AeroViz.tools.datareader import DataReader
@@ -72,7 +72,7 @@ class ChemicalProc(DataProc):
                 _df['AN'] = 0
 
         _df['OM'] = 1.8 * OC
-        _df['Soil'] = 28.57 * Soil
+        _df['Soil'] = 28.57 * Soil / 1000
         _df['SS'] = 2.54 * SS
         _df['EC'] = EC
         _df['SIA'] = _df['AS'] + _df['AN']
@@ -159,9 +159,10 @@ class ChemicalProc(DataProc):
         if save_file.exists() and not reset:
             return read_csv(save_file, parse_dates=['Time'], index_col='Time')
         else:
-            df = concat([DataReader(file) for file in self.file_paths], axis=1)
+            df = concat([DataReader(file) for file in self.file_paths], axis=1).apply(to_numeric, errors='coerce')
 
-            df_mass = df[['NH4+', 'SO42-', 'NO3-', 'O_OC', 'Fe', 'Na+', 'O_EC', 'PM25']].dropna().apply(self.mass,
+            df_mass = df[['NH4+', 'SO42-', 'NO3-', 'Optical_OC', 'Fe', 'Na+', 'Optical_EC', 'PM2.5']].dropna().apply(
+                self.mass,
                                                                                                         axis=1)
             df_mass['ALWC'] = df['ALWC']
             df_volume = df_mass[['AS', 'AN', 'OM', 'Soil', 'SS', 'EC', 'total_mass', 'ALWC']].dropna().apply(

AeroViz/process/script/Others.py

@@ -58,7 +58,7 @@ class OthersProc(DataProc):
             # results['fRH_PNSD'] = df['Bext_internal'] / df['Bext_dry']
             results['fRH_IMPR'] = df['total_ext'] / df['total_ext_dry']
             results['OCEC_ratio'] = df['O_OC'] / df['O_EC']
-            results['PM1/PM25'] = np.where(df['PM1'] / df['PM25'] < 1, df['PM1'] / df['PM25'], np.nan)
+            results['PM1/PM25'] = np.where(df['PM1'] / df['PM2.5'] < 1, df['PM1'] / df['PM2.5'], np.nan)
             # results['MEE_PNSD'] = df['Bext_internal'] / df['PM25']
             # results['MEE_dry_PNSD'] = df['Bext_dry'] / df['PM25']
 

AeroViz/rawDataReader/__init__.py

@@ -1,47 +1,93 @@
 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,
+                  path: 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
                   ):
+    """
+    Factory function to instantiate the appropriate reader module for a given instrument and
+    return the processed data over the specified time range.
+
+    Parameters
+    ----------
+    instrument_name : str
+        The name of the instrument for which to read data. Must be a valid key in the `meta` dictionary.
+    path : Path
+        The directory where raw data files for the instrument are stored.
+    qc : bool, optional (default=True)
+        If True, apply quality control (QC) to the raw data.
+    csv_raw : bool, optional (default=True)
+        If True, read raw data from CSV files.
+    reset : bool, optional (default=False)
+        If True, reset the state and reprocess the data from scratch.
+    rate : bool, optional (default=False)
+        If True, calculate rates from the data.
+    append_data : bool, optional (default=False)
+        If True, append new data to the existing dataset instead of overwriting it.
+    start : datetime, optional
+        Start time for filtering the data. If None, no start time filtering will be applied.
+    end : datetime, optional
+        End time for filtering the data. If None, no end time filtering will be applied.
+    mean_freq : str, optional (default='1h')
+        Resampling frequency for averaging the data. Example: '1h' for hourly mean.
+    csv_out : bool, optional (default=True)
+        If True, output the processed data as a CSV file.
+
+    Return
+    ------
+    reader_module : Reader
+        An instance of the reader module corresponding to the specified instrument, which processes
+        the data and returns it in a usable format.
+
+    Raises
+    ------
+    ValueError
+        If the `instrument_name` provided is not a valid key in the `meta` dictionary.
+
+    Example
+    -------
+    To read and process data for the BC1054 instrument:
+
+    >>> from pathlib import Path
+    >>> from datetime import datetime
+    >>> data = RawDataReader(instrument_name='BC1054', path=Path('/path/to/data'),
+    >>>                      start=datetime(2024, 1, 1), end=datetime(2024, 2, 1))
+    """
     # 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_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,
-        '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
+        'Sunset_OCEC': Sunset_OCEC,
+        'IGAC': IGAC,
+        'VOC': VOC,
+        'Table': Table,
+        'EPA_vertical': EPA_vertical,
+        'Minion': Minion
         # Add other instruments and their corresponding classes here
     }
 
@@ -51,18 +97,16 @@ def RawDataReader(instrument_name: str,
 
     # Instantiate the class and return the instance
     reader_module = instrument_class_map[instrument_name].Reader(
-        _path=_path,
-        QC=QC,
+        path=path,
+        qc=qc,
         csv_raw=csv_raw,
         reset=reset,
         rate=rate,
-        append_data=append_data,
-        update_meta=update_meta
+        append_data=append_data
     )
     return reader_module(
         start=start,
         end=end,
         mean_freq=mean_freq,
         csv_out=csv_out,
-        **kwargs
     )

AeroViz/rawDataReader/{utils/config.py → config/supported_instruments.py}

@@ -1,22 +1,8 @@
 # Description: Configuration file for rawDataReader
 
-instrument = [
-    "NEPH",
-    "Aurora",
-    "AE33",
-    "AE43",
-    "Table",
-    "EPA_vertical",
-    "SMPS_NTU(SMPS_3080_3788)",
-    "SMPS_TH(SMPS_3080_3772)",
-    "APS_3321",
-    "TEOM",
-    "OCEC"
-]
-
 meta = {
     "NEPH": {
-        "pattern": "*.DAT",
+        "pattern": "*.dat",
         "freq": "5min",
         "deter_key": {"Scatter Coe. (550 nm)": ["G"]},
     },
@@ -27,18 +13,6 @@ meta = {
         "deter_key": {"Scatter Coe. (550 nm)": ["G"]},
     },
 
-    "Table": {
-        "pattern": "*.csv",
-        "freq": "1h",
-        "deter_key": None,
-    },
-
-    "EPA_vertical": {
-        "pattern": "*.csv",
-        "freq": "1h",
-        "deter_key": None,
-    },
-
     "SMPS_TH": {
         "pattern": "*.txt",
         "freq": "6min",
@@ -73,18 +47,21 @@ meta = {
         "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)": ["BC6"]},
+        "deter_key": {"BC Mass Conc. (880 nm)": ["BC9"]},
+        "error_state": [1, 2, 4, 8, 16, 32, 65536],
     },
 
     "MA350": {
@@ -102,26 +79,18 @@ meta = {
         },
     },
 
-    "OCEC_LCRES": {
+    "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"],
         },
     },
 
-    "OCEC_RES": {
-        "pattern": "*[!LC|!Blanks]Res.csv",
-        "freq": "1h",
-        "deter_key": None,
-    },
-
-    "IGAC_TH": {
+    "IGAC": {
         "pattern": "*.csv",
         "freq": "1h",
         "deter_key": {
@@ -138,32 +107,42 @@ meta = {
         },
     },
 
-    "IGAC_ZM": {
+    "VOC": {
         "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_TH": {
+        "key": [
+            'Benzene', 'Toluene', 'Ethylbenzene', 'm/p-Xylene', 'o-Xylene', 'Ethane', 'Propane', 'Isobutane',
+            'n-Butane', 'Isopentane', 'n-Pentane', 'n-Hexane', 'n-Heptane', 'n-Octane', 'n-Nonane', 'n-Decane',
+            'n-Undecane', 'n-Dodecane', 'Ethylene', 'Propylene', '1-Butene', 't-2-Butene', 'cis-2-Butene',
+            '1-Pentene', 't-2-Pentene', 'cis-2-Pentene', '1-Hexene', 'Acetylene', 'Cyclopentane', 'Methylcyclopentane',
+            'Cyclohexane', 'Methylcyclohexane', 'Isoprene', '2,2-Dimethylbutane', '2,3-Dimethylbutane',
+            '2-Methylpentane', '3-Methylpentane', '2,4-Dimethylpentane', '2-Methylhexane', '2,3-Dimethylpentane',
+            '3-Methylheptane', '2,2,4-Trimethylpentane', '2,3,4-Trimethylpentane', '2-Methylheptane', '3-Methylhexane',
+            'Styrene', 'Isopropylbenzene', 'n-Propylbenzene', 'm-Ethyltoluene', 'p-Ethyltoluene', 'm-Diethylbenzene',
+            'p-Diethylbenzene', '1,3,5-Trimethylbenzene', 'o-Ethyltoluene', '1,2,4-Trimethylbenzene',
+            '1,2,3-Trimethylbenzene',
+            '1.2-DCB', '1.4-DCB', '1.3-Butadiene', '1-Octene', '2-Ethyltoluene', '3.4-Ethyltoluene', 'Acetaldehyde',
+            'Acetone', 'Butyl Acetate', 'Ethanol', 'Ethyl Acetate', 'Hexane', 'IPA', 'Iso-Propylbenzene',
+            'PCE', 'Propene', 'TCE', 'VCM',
+        ],
+        "deter_key": None,
+    },
+
+    "Table": {
         "pattern": "*.csv",
         "freq": "1h",
         "deter_key": None,
     },
 
-    "VOC_ZM": {
+    "EPA_vertical": {
         "pattern": "*.csv",
         "freq": "1h",
         "deter_key": None,
     },
 
+    "Minion": {
+        "pattern": "*.csv",
+        "freq": "1h",
+        "deter_key": None,
+    },
 }