AeroViz 0.1.4__tar.gz → 0.1.6__tar.gz

{aeroviz-0.1.4 → aeroviz-0.1.6}/AeroViz/dataProcess/Chemistry/__init__.py

@@ -1,40 +1,42 @@
 from ..core import Writer, run_process
 
-__all__ = [
-
-    'Chemistry',
-
-]
+__all__ = ['Chemistry']
 
 
 class Chemistry(Writer):
-
-    ## Reconstruction
+    # Reconstruction
     @run_process('Chemistry - reconstruction basic', 'reconstrc_basic')
-    def ReConstrc_basic(self, *df_chem, df_ref=None, df_water=None, df_density=None,
-                        nam_lst=['NH4+', 'SO42-', 'NO3-', 'Fe', 'Na+', 'OC', 'EC']):
+    def ReConstrc_basic(self, *df_chem, df_ref=None, df_water=None, df_density=None, nam_lst=None):
         from ._mass_volume import _basic
 
+        if nam_lst is None:
+            nam_lst = ['NH4+', 'SO42-', 'NO3-', 'Fe', 'Na+', 'OC', 'EC']
+
         out = _basic(df_chem, df_ref, df_water, df_density, nam_lst=nam_lst)
 
         return self, out
 
-    ## Partition
+    # Partition
     @run_process('Chemistry -  Partition', 'partition')
-    def Partition(self, *df_chem, nam_lst=['NH4+', 'SO42-', 'NO3-', 'Cl-', 'NO2', 'HNO3', 'SO2', 'NH3', 'HCl', 'temp']):
+    def Partition(self, *df_chem, nam_lst=None):
         from ._partition import _basic
 
+        if nam_lst is None:
+            nam_lst = ['NH4+', 'SO42-', 'NO3-', 'Cl-', 'NO2', 'HNO3', 'SO2', 'NH3', 'HCl', 'temp']
+
         out = _basic(df_chem, nam_lst=nam_lst)
 
         return self, out
 
-    ## ISOROPIA
+    # ISOROPIA
     @run_process('Chemistry - ISOROPIA', 'isoropia')
-    def ISOROPIA(self, *df_chem,
-                 nam_lst=['Na+', 'SO42-', 'NH4+', 'NO3-', 'Cl-', 'Ca2+', 'K+', 'Mg2+', 'NH3', 'HNO3', 'HCl', 'RH',
-                          'temp']):
+    def ISOROPIA(self, *df_chem, nam_lst=None):
         from ._isoropia import _basic
 
+        if nam_lst is None:
+            nam_lst = ['Na+', 'SO42-', 'NH4+', 'NO3-', 'Cl-', 'Ca2+',
+                       'K+', 'Mg2+', 'NH3', 'HNO3', 'HCl', 'RH', 'temp']
+
         if self.path_out is None:
             raise ValueError('Please Input "path_out" !!')
 
@@ -42,18 +44,17 @@ class Chemistry(Writer):
 
         return self, out
 
-    ## OCEC
+    # OCEC
     @run_process('Chemistry - OC/EC basic', 'ocec_basic')
-    def OCEC_basic(self, df_lcres, df_res, df_mass=None, ocec_ratio=None, ocec_ratio_month=1, hr_lim=200,
+    def OCEC_basic(self, df_lcres, df_mass=None, ocec_ratio=None, ocec_ratio_month=1, hr_lim=200,
                    least_square_range=(0.1, 2.5, 0.1), WISOC_OC_range=(0.2, 0.7, 0.01), ):
         from ._ocec import _basic
 
-        out = _basic(df_lcres, df_res, df_mass, ocec_ratio, ocec_ratio_month, hr_lim, least_square_range,
-                     WISOC_OC_range)
+        out = _basic(df_lcres, df_mass, ocec_ratio, ocec_ratio_month, hr_lim, least_square_range, WISOC_OC_range)
 
         return self, out
 
-    ## TEOM
+    # TEOM
     @run_process('Chemistry - TEOM basic', 'teom_basic')
     def TEOM_basic(self, df_teom, df_check=None):
         from ._teom import _basic

{aeroviz-0.1.4 → aeroviz-0.1.6}/AeroViz/dataProcess/Chemistry/_isoropia.py

@@ -7,9 +7,6 @@ from pandas import concat, DataFrame, to_numeric, read_csv
 from ._calculate import _ug2umol
 
 
-# TODO: fix isoropia2.exe can not run
-
-
 def _basic(df_che, path_out, nam_lst):
     # parameter
     df_all = concat(df_che, axis=1)
@@ -18,8 +15,8 @@ def _basic(df_che, path_out, nam_lst):
 
     df_umol = _ug2umol(df_all)
 
-    ## output
-    ## Na, SO4, NH3, NO3, Cl, Ca, K, Mg, RH, TEMP
+    # output
+    # Na, SO4, NH3, NO3, Cl, Ca, K, Mg, RH, TEMP
     df_input = DataFrame(index=index)
     df_out = DataFrame(index=index)
 
@@ -29,25 +26,25 @@ def _basic(df_che, path_out, nam_lst):
     pth_input.unlink(missing_ok=True)
     pth_output.unlink(missing_ok=True)
 
-    ## header
+    # header
     _header = 'Input units (0=umol/m3, 1=ug/m3)\n' + '0\n\n' + \
               'Problem type (0=forward, 1=reverse); Phase state (0=solid+liquid, 1=metastable)\n' + '0, 1\n\n' + \
               'NH4-SO4 system case\n'
 
-    ## software
+    # software
     path_iso = Path(__file__).parent / 'isrpia2.exe'
 
     # make input file and output temp input (without index)
-    ## NH3
+    # NH3
     df_input['NH3'] = df_umol['NH4+'].fillna(0).copy() + df_umol['NH3']
 
-    ## NO3
+    # NO3
     df_input['NO3'] = df_umol['HNO3'].fillna(0).copy() + df_umol['NO3-']
 
-    ## Cl
+    # Cl
     df_input['Cl'] = df_umol['HCl'].fillna(0).copy() + df_umol['Cl-']
 
-    ## temp, RH
+    # temp, RH
     df_input['RH'] = df_all['RH'] / 100
     df_input['TEMP'] = df_all['temp'] + 273.15
 
@@ -55,7 +52,7 @@ def _basic(df_che, path_out, nam_lst):
 
     df_input = df_input[['Na', 'SO4', 'NH3', 'NO3', 'Cl', 'Ca', 'K', 'Mg', 'RH', 'TEMP']].fillna('-').copy()
 
-    ## output the input data
+    # output the input data
     df_input.to_csv(pth_input, index=False)
     with (pth_input).open('r+', encoding='utf-8', errors='ignore') as _f:
         _cont = _f.read()

{aeroviz-0.1.4 → aeroviz-0.1.6}/AeroViz/dataProcess/Chemistry/_mass_volume.py

@@ -2,13 +2,14 @@ from pandas import concat, DataFrame
 
 
 def _basic(df_che, df_ref, df_water, df_density, nam_lst):
+
     df_all = concat(df_che, axis=1)
     index = df_all.index.copy()
     df_all.columns = nam_lst
 
     # parameter
     mol_A, mol_S, mol_N = df_all['NH4+'] / 18, df_all['SO42-'] / 96, df_all['NO3-'] / 62
-    df_all['status'] = (mol_A) / (2 * mol_S + mol_N)
+    df_all['status'] = mol_A / (2 * mol_S + mol_N)
 
     convert_nam = {'AS': 'SO42-',
                    'AN': 'NO3-',
@@ -92,7 +93,7 @@ def _basic(df_che, df_ref, df_water, df_density, nam_lst):
     df_mass['total'] = df_mass.sum(axis=1, min_count=6)
 
     qc_ratio = df_mass['total'] / df_ref
-    qc_cond = (qc_ratio >= 0.7) & (qc_ratio <= 1.3)
+    qc_cond = (qc_ratio >= 0.5) & (qc_ratio <= 1.5)
 
     # volume
     df_vol = DataFrame()
@@ -153,7 +154,7 @@ def _basic(df_che, df_ref, df_water, df_density, nam_lst):
     out.update(ri_dic)
 
     for _ky, _df in out.items():
-        out[_ky] = _df.reindex(index).where(qc_cond)
+        out[_ky] = _df.reindex(index)
 
     return out
 

{aeroviz-0.1.4 → aeroviz-0.1.6}/AeroViz/dataProcess/Chemistry/_ocec.py

@@ -16,7 +16,7 @@ def _min_Rsq(_oc, _ec, _rng):
 
     _out_table = DataFrame(_oc_mesh - _val_mesh * _ec_mesh, index=_oc.index, columns=_rng)
 
-    ## calculate R2
+    # calculate R2
     _r2_dic = {}
     _func = lambda _x, _sl, _inte: _sl * _x + _inte
     for _ocec, _out in _out_table.items():
@@ -30,28 +30,28 @@ def _min_Rsq(_oc, _ec, _rng):
 
         _r2_dic[round(_ocec, 3)] = 1. - _rss / _tss
 
-    ## get the min R2
+    # get the min R2
     _ratio = DataFrame(_r2_dic, index=[0]).idxmin(axis=1).values[0]
 
     return _ratio, _out_table[_ratio]
 
 
 def _ocec_ratio_cal(_nam, _lcres_splt, _hr_lim, _range_, _wisoc_range_):
-    ## parameter
+    # parameter
     _out = DataFrame(index=_lcres_splt.index)
     (_, _oc), (_, _ec) = _lcres_splt.items()
     # _oc, _ec = _lcres_splt['Thermal_OC'], _lcres_splt['Thermal_EC']
 
-    ## real data OC/EC
+    # real data OC/EC
     _ocec_ratio_real = (_oc / _ec).quantile(.5)
 
     _out[f'OC/EC_real_{_nam}'] = _ocec_ratio_real
     _out[f'POC_real_{_nam}'] = _ocec_ratio_real * _ec
     _out[f'SOC_real_{_nam}'] = _oc - _out[f'POC_real_{_nam}']
 
-    ## the least R2 method
-    ## estimated OC/EC
-    if (len(_lcres_splt) <= _hr_lim):
+    # the least R2 method
+    # estimated OC/EC
+    if len(_lcres_splt) <= _hr_lim:
         print(f"\t\t{_lcres_splt.index[0].strftime('%Y-%m-%d %X')} to {_lcres_splt.index[-1].strftime('%Y-%m-%d %X')}")
         print('\t\tPlease Modify the Values of "hour_limit" or Input Sufficient Amount of Data !!')
 
@@ -60,13 +60,13 @@ def _ocec_ratio_cal(_nam, _lcres_splt, _hr_lim, _range_, _wisoc_range_):
 
         return _out
 
-    if (len(_lcres_splt.dropna()) == 0):
+    if len(_lcres_splt.dropna()) == 0:
         _out[[f'OC/EC_{_nam}', f'POC_{_nam}', f'SOC_{_nam}', f'WISOC/OC_{_nam}', f'WSOC_{_nam}',
               f'WISOC_{_nam}']] = np.nan
 
         return _out
 
-    ## OC/EC
+    # OC/EC
     _ocec_ratio = False
     _st, _ed, _stp = _range_
 
@@ -78,12 +78,12 @@ def _ocec_ratio_cal(_nam, _lcres_splt, _hr_lim, _range_, _wisoc_range_):
 
         _ocec_ratio, _soc = _min_Rsq(_oc, _ec, _ocec_rng)
 
-    ## WISOC
+    # WISOC
     _st, _ed, _stp = _wisoc_range_
     _wisoc_rng = (np.arange(_st, _ed + _stp, _stp) * _ocec_ratio).round(5)
     _wisoc_ratio, _wsoc = _min_Rsq(_oc, _ec, _wisoc_rng)
 
-    ## out
+    # out
     _out[f'OC/EC_{_nam}'] = _ocec_ratio
     _out[f'SOC_{_nam}'] = _soc
     _out[f'POC_{_nam}'] = _oc - _out[f'SOC_{_nam}']
@@ -95,15 +95,16 @@ def _ocec_ratio_cal(_nam, _lcres_splt, _hr_lim, _range_, _wisoc_range_):
                  f'OC/EC_real_{_nam}', f'POC_real_{_nam}', f'SOC_real_{_nam}']]
 
 
-def _basic(_lcres, _res, _mass, _ocec_ratio, _ocec_ratio_month, _hr_lim, _range, _wisoc_range):
-    _lcres, _res, _mass = union_index(_lcres, _res, _mass)
+def _basic(_lcres, _mass, _ocec_ratio, _ocec_ratio_month, _hr_lim, _range, _wisoc_range):
+    _lcres, _mass = union_index(_lcres, _mass)
 
     _out = {}
 
-    ## OC1, OC2, OC3, OC4, PC
-    _df_bsc = _res / _lcres['Sample_Volume'].to_frame().values.copy()
+    # OC1, OC2, OC3, OC4, PC
+    _df_bsc = _lcres[['OC1_raw', 'OC2_raw', 'OC3_raw', 'OC4_raw']] / _lcres['Sample_Volume'].to_frame().values.copy()
+    _df_bsc.rename(columns={'OC1_raw': 'OC1', 'OC2_raw': 'OC2', 'OC3_raw': 'OC3', 'OC4_raw': 'OC4'}, inplace=True)
 
-    ## SOC, POC, OC/EC
+    # SOC, POC, OC/EC
     if _ocec_ratio is not None:
         try:
             iter(_ocec_ratio)
@@ -126,7 +127,7 @@ def _basic(_lcres, _res, _mass, _ocec_ratio, _ocec_ratio_month, _hr_lim, _range,
 
     _df_bsc = concat((_df_bsc.copy(), _prcs_df), axis=1)
 
-    ## ratio
+    # ratio
     _df_ratio = DataFrame(index=_df_bsc.index)
 
     for _ky, _val in _df_bsc.items():
@@ -144,41 +145,15 @@ def _basic(_lcres, _res, _mass, _ocec_ratio, _ocec_ratio_month, _hr_lim, _range,
         _df_ratio[f'Optical_OC/PM'] = _lcres['Optical_OC'] / _mass
         _df_ratio[f'Optical_EC/PM'] = _lcres['Optical_EC'] / _mass
 
-    ## ratio status
+    # ratio status
     _df_bsc = concat((_lcres, _df_bsc.copy()), axis=1)
 
     for _ky, _df in _df_ratio.items():
         _df_bsc[f'{_ky}_status'] = 'Normal'
         _df_bsc[f'{_ky}_status'] = _df_bsc[f'{_ky}_status'].mask(_df > 1, 'Warning')
 
-    ## out
+    # out
     _out['ratio'] = _df_ratio
     _out['basic'] = _df_bsc
 
     return _out
-
-
-'''
-_ocec_mesh, _oc_mesh = n.meshgrid(_ocec_rng, _oc)
-_ocec_mesh, _ec_mesh = n.meshgrid(_ocec_rng, _ec)
-
-_soc_table = DataFrame(_oc_mesh-_ocec_mesh*_ec_mesh, index=_oc.index, columns=_ocec_rng)
-
-## calculate R2
-_r2_dic = {}
-_func = lambda _x, _sl, _inte : _sl*_x+_inte
-for _ocec, _soc in _soc_table.items():
-
-	_df = DataFrame([_soc.values, _ec.values]).T.dropna()
-	_x, _y = _df[0], _df[1]
-
-	_opt, _ = curve_fit(_func, _x, _y)
-
-	_tss = n.sum((_y - _y.mean())**2.)
-	_rss = n.sum((_y - _func(_x, *_opt))**2.)
-
-	_r2_dic[round(_ocec,2)] = 1. - _rss / _tss
-
-## get the min R2
-_ocec_ratio = DataFrame(_r2_dic, index=[0]).idxmin(axis=1).values[0]
-# '''

{aeroviz-0.1.4 → aeroviz-0.1.6}/AeroViz/dataProcess/Optical/_IMPROVE.py

@@ -1,8 +1,7 @@
-import pickle as pkl
 from pathlib import Path
 
 import numpy as np
-from pandas import DataFrame
+from pandas import DataFrame, read_pickle
 
 from AeroViz.dataProcess.core import union_index
 
@@ -12,7 +11,7 @@ def _revised(_df_mass, _df_RH):
 
     # fRH
     with (Path(__file__).parent / 'fRH.pkl').open('rb') as f:
-        _fRH = pkl.load(f)
+        _fRH = read_pickle(f)
         _fRH.loc[np.nan] = np.nan
 
     def fRH(_RH):

{aeroviz-0.1.4 → aeroviz-0.1.6}/AeroViz/dataProcess/SizeDistr/__init__.py

@@ -1,15 +1,11 @@
 from ..core import Writer, run_process
 
-__all__ = [
-
-    'SizeDistr',
-
-]
+__all__ = ['SizeDistr']
 
 
 class SizeDistr(Writer):
 
-    ## basic
+    # basic
     @run_process('SizeDistr - basic', 'distr_basic')
     def basic(self, df, hybrid_bin_start_loc=None, unit='nm', bin_range=(0, 20000), input_type='norm'):
         from ._size_distr import _basic
@@ -18,7 +14,7 @@ class SizeDistr(Writer):
 
         return self, out
 
-    ## merge
+    # merge
     @run_process('SizeDistr - merge_SMPS_APS_v4', 'distr_merge')
     def merge_SMPS_APS_v4(self, df_smps, df_aps, df_pm25, aps_unit='um',
                           smps_overlap_lowbound=500, aps_fit_highbound=1000, dndsdv_alg=True,
@@ -30,7 +26,7 @@ class SizeDistr(Writer):
 
         return self, out
 
-    ## merge
+    # merge
     @run_process('SizeDistr - merge_SMPS_APS_v3', 'distr_merge')
     def merge_SMPS_APS_v3(self, df_smps, df_aps, aps_unit='um',
                           smps_overlap_lowbound=500, aps_fit_highbound=1000, dndsdv_alg=True):
@@ -40,7 +36,7 @@ class SizeDistr(Writer):
 
         return self, out
 
-    ## merge
+    # merge
     @run_process('SizeDistr - merge_SMPS_APS_v2', 'distr_merge')
     def merge_SMPS_APS_v2(self, df_smps, df_aps, aps_unit='um',
                           smps_overlap_lowbound=500, aps_fit_highbound=1000):
@@ -50,7 +46,7 @@ class SizeDistr(Writer):
 
         return self, out
 
-    ## merge
+    # merge
     @run_process('SizeDistr - merge_SMPS_APS_v1', 'distr_merge')
     def merge_SMPS_APS(self, df_smps, df_aps, aps_unit='um', shift_mode='mobility',
                        smps_overlap_lowbound=523, aps_fit_highbound=800):

{aeroviz-0.1.4 → aeroviz-0.1.6}/AeroViz/dataProcess/VOC/__init__.py

@@ -1,15 +1,10 @@
 from ..core import Writer, run_process
 
-__all__ = [
-
-    'VOC',
-
-]
+__all__ = ['VOC']
 
 
 class VOC(Writer):
 
-    ## Reconstruction
     @run_process('VOC - basic', 'voc_basic')
     def VOC_basic(self, _df_voc):
         from ._potential_par import _basic

aeroviz-0.1.6/AeroViz/dataProcess/VOC/_potential_par.py

@@ -0,0 +1,108 @@
+from pathlib import Path
+
+from pandas import DataFrame, read_json, concat
+
+
+def _basic(_df_voc):
+    with (Path(__file__).parent / 'support_voc.json').open('r', encoding='utf-8', errors='ignore') as f:
+        _par = read_json(f)
+
+    # parameter
+    _keys = _df_voc.keys()
+
+    invalid_keys = [key for key in _df_voc.keys() if key not in set(_par.keys())]
+
+    if invalid_keys:
+        raise KeyError(f'\n\t\t{invalid_keys} are not supported keys.'
+                       f'\n\t\tPlease check the\033[91m support_voc.md\033[0m file to use the correct name.')
+
+    _MW, _MIR, _SOAP, _KOH = _par.loc['MW', :], _par.loc['MIR', :], _par.loc['SOAP', :], _par.loc['KOH', :]
+
+    _voc_classify = {
+        'alkane_total': ['Ethane', 'Propane', 'Isobutane', 'n-Butane', 'Isopentane', 'n-Pentane', 'n-Hexane',
+                         'n-Heptane', 'n-Octane', 'n-Nonane', 'n-Decane', 'n-Undecane', 'n-Dodecane',
+
+                         'Cyclopentane', 'Methylcyclopentane', 'Cyclohexane', 'Methylcyclohexane',
+
+                         '2,2-Dimethylbutane', '2,3-Dimethylbutane', '2-Methylpentane', '3-Methylpentane',
+                         '2,4-Dimethylpentane', '2-Methylhexane', '3-Methylhexane',
+                         '2,2,4-Trimethylpentane', '2,3,4-Trimethylpentane', '2-Methylheptane', '3-Methylheptane'],
+
+        'alkene_total': ['Ethylene', 'Propylene', '1-Butene', 't-2-Butene', 'cis-2-Butene', '1-Pentene', 't-2-Pentene',
+                         'cis-2-Pentene', '1-Hexene', 'Isoprene', '1.3-Butadiene', '1-Octene'],
+
+        'aromatic_total': ['Benzene', 'Toluene', 'Ethylbenzene', 'm/p-Xylene', 'o-Xylene', 'Styrene',
+                           'Isopropylbenzene',
+                           'n-Propylbenzene', 'm-Ethyltoluene', 'p-Ethyltoluene', 'o-Ethyltoluene', 'm-Diethylbenzene',
+                           'p-Diethylbenzene', '1,2,4-Trimethylbenzene', '1,2,3-Trimethylbenzene',
+                           '1,3,5-Trimethylbenzene', ],
+
+        'alkyne_total': ['Acetylene'],
+
+        'OVOC': ['Acetaldehyde', 'Ethanol', 'Acetone', 'IPA', 'Ethyl Acetate', 'Butyl Acetate'],
+
+        'ClVOC': ['VCM', 'TCE', 'PCE', '1.4-DCB', '1.2-DCB'],
+    }
+
+    _df_MW = (_df_voc * _MW).copy()
+    _df_dic = {
+        'Conc': _df_voc.copy(),
+        'OFP': _df_MW / 48 * _MIR,
+        'SOAP': _df_MW / 24.5 * _SOAP / 100 * 0.054,
+        'LOH': _df_MW / 24.5 / _MW * 0.602 * _KOH,
+    }
+
+    # calculate
+    _out = {}
+    for _nam, _df in _df_dic.items():
+
+        _df_out = DataFrame(index=_df_voc.index)
+
+        for _voc_nam, _voc_lst in _voc_classify.items():
+            _lst = list(set(_keys) & set(_voc_lst))
+            if len(_lst) == 0:
+                continue
+
+            _df_out = concat([_df[_lst], _df_out], axis=1)
+
+            _df_out[_voc_nam] = _df[_lst].sum(axis=1, min_count=1)
+
+        _df_out['Total'] = _df.sum(axis=1, min_count=1)
+
+        _out[_nam] = _df_out
+
+    return _out
+
+
+def markdown_table_to_dataframe():
+    import pandas as pd
+    from pathlib import Path
+
+    # support_voc.md
+    with open(Path(__file__).parent / 'support_voc.md', 'r', encoding='utf-8') as file:
+        markdown_content = file.read()
+
+    # 將內容分割成行
+    lines = markdown_content.strip().split('\n')
+
+    # 提取表頭
+    headers = [col.strip() for col in lines[0].split('|')[1:-1]]
+
+    # 解析數據行
+    data = []
+    for line in lines[2:]:  # 跳過表頭和分隔行
+        columns = [col.strip() for col in line.split('|')[1:-1]]
+        data.append(columns)
+
+    # 創建 DataFrame
+    df = pd.DataFrame(data, columns=headers)
+
+    # 轉換數據類型
+    numeric_columns = ['MIR', 'MW', 'SOAP', 'KOH']
+    for col in numeric_columns:
+        df[col] = pd.to_numeric(df[col], errors='coerce')
+    df = df.set_index('Species').T
+
+    df = df.iloc[:, :-7]
+
+    df.to_json(Path(__file__).parent / 'support_voc.json', indent=4)