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

AeroViz/dataProcess/Optical/_absorption.py

@@ -1,54 +1,28 @@
-def _absCoe(df, abs_band):
-    import numpy as n
-    from scipy.optimize import curve_fit
+def _absCoe(df, instru, specified_band: list):
+    import numpy as np
+    from pandas import concat
+    from .Angstrom_exponent import get_Angstrom_exponent, get_species_wavelength
 
-    band = n.array([370, 470, 520, 590, 660, 880, 950])
+    band_AE33 = np.array([370, 470, 520, 590, 660, 880, 950])
+    band_BC1054 = np.array([370, 430, 470, 525, 565, 590, 660, 700, 880, 950])
 
-    df_out = {}
+    MAE_AE33 = np.array([18.47, 14.54, 13.14, 11.58, 10.35, 7.77, 7.19]) * 1e-3
+    MAE_BC1054 = np.array([18.48, 15.90, 14.55, 13.02, 12.10, 11.59, 10.36, 9.77, 7.77, 7.20]) * 1e-3
 
-    def _get_slope(__df):
-        func = lambda _x, _sl, _int: _sl * _x + _int
-        popt, pcov = curve_fit(func, band, __df.values)
+    band = band_AE33 if instru == 'AE33' else band_BC1054
+    MAE = MAE_AE33 if instru == 'AE33' else MAE_BC1054
+    eBC = 'BC6' if instru == 'AE33' else 'BC9'
 
-        return func(n.array(abs_band), *popt)
+    # calculate
+    df_abs = (df.copy().dropna() * MAE).copy()
 
-    MAE = n.array([18.47, 14.54, 13.14, 11.58, 10.35, 7.77, 7.19]) * 1e-3
-    df_abs = (df.copy() * MAE).dropna().copy()
+    df_out = df_abs.apply(get_species_wavelength, axis=1, result_type='expand', args=(specified_band,))
+    df_out.columns = [f'abs_{_band}' for _band in specified_band]
+    df_out['eBC'] = df[eBC]
 
-    df_out = df_abs.apply(_get_slope, axis=1, result_type='expand').reindex(df.index)
-    df_out.columns = [f'abs_{_band}' for _band in abs_band]
+    df_AAE = df_abs.apply(get_Angstrom_exponent, axis=1, result_type='expand', args=(band,))
+    df_AAE.columns = ['AAE', 'AAE_intercept']
+    df_AAE = df_AAE.mask((-df_AAE['AAE'] < 0.8) | (-df_AAE['AAE'] > 2.)).copy()
 
-    df_out['eBC'] = df['BC6']
-
-    return df_out
-
-
-def _AAE(df):
-    import numpy as n
-    from scipy.optimize import curve_fit
-
-    def _AAEcalc(_df):
-        ## parameter
-        MAE = n.array([18.47, 14.54, 13.14, 11.58, 10.35, 7.77, 7.19]) * 1e-3
-        band = n.array([370, 470, 520, 590, 660, 880, 950])
-        _df *= MAE
-
-        ## 7 pts fitting
-        ## function
-        def _get_slope(__df):
-            func = lambda _x, _sl, _int: _sl * _x + _int
-            popt, pcov = curve_fit(func, n.log(band), n.log(__df))
-
-            return popt
-
-        ## calculate
-        _AAE = _df.apply(_get_slope, axis=1, result_type='expand')
-        _AAE.columns = ['slope', 'intercept']
-
-        return _AAE
-
-    df_out = _AAEcalc(df[['BC1', 'BC2', 'BC3', 'BC4', 'BC5', 'BC6', 'BC7']].dropna())
-    df_out = df_out.mask((-df_out.slope < 0.8) | (-df_out.slope > 2.)).copy()
-
-    df_out['eBC'] = df['BC6']
-    return df_out.reindex(df.index)
+    _df = concat([df_out, df_AAE['AAE']], axis=1)
+    return _df.reindex(df.index)

AeroViz/dataProcess/Optical/_extinction.py

@@ -1,37 +1,42 @@
 from pandas import DataFrame
 
-from AeroViz.dataProcess.core import _union_index
+from AeroViz.dataProcess.core import union_index
 
 
-def _basic(df_abs, df_sca, df_ec, df_mass, df_no2):
-    df_abs, df_sca, df_ec, df_mass, df_no2 = _union_index(df_abs, df_sca, df_ec, df_mass, df_no2)
+def _basic(df_sca, df_abs, df_mass, df_no2, df_temp):
+    df_sca, df_abs, df_mass, df_no2, df_temp = union_index(df_sca, df_abs, df_mass, df_no2, df_temp)
 
     df_out = DataFrame()
 
-    ## abs and sca coe
-    df_out['abs'] = df_abs.copy()
-    df_out['sca'] = df_sca.copy()
+    # abs and sca coe
+    df_out['abs'] = df_abs['abs_550'].copy()
+    df_out['sca'] = df_sca['sca_550'].copy()
 
-    ## extinction coe.
+    # extinction coe.
     df_out['ext'] = df_out['abs'] + df_out['sca']
 
-    ## SSA
+    # SSA
     df_out['SSA'] = df_out['sca'] / df_out['ext']
 
-    ## MAE, MSE, MEE
+    # SAE, AAE, eBC
+    df_out['SAE'] = df_sca['SAE'].copy()
+    df_out['AAE'] = df_abs['AAE'].copy()
+    df_out['eBC'] = df_abs['eBC'].copy() / 1e3
+
+    # MAE, MSE, MEE
     if df_mass is not None:
         df_out['MAE'] = df_out['abs'] / df_mass
         df_out['MSE'] = df_out['sca'] / df_mass
         df_out['MEE'] = df_out['MSE'] + df_out['MAE']
 
-    ## gas absorbtion
+    # gas absorbtion
     if df_no2 is not None:
         df_out['abs_gas'] = df_no2 * .33
-        df_out['sca_gas'] = 10
-        df_out['ext_all'] = df_out['ext'] + df_out['abs_gas'] + df_out['sca_gas']
 
-    ## other
-    if df_ec is not None:
-        df_out['eBC'] = df_ec / 1e3
+    if df_temp is not None:
+        df_out['sca_gas'] = (11.4 * 293 / (273 + df_temp))
+
+    if df_no2 is not None and df_temp is not None:
+        df_out['ext_all'] = df_out['ext'] + df_out['abs_gas'] + df_out['sca_gas']
 
     return df_out

AeroViz/dataProcess/Optical/_mie.py

@@ -1,5 +1,4 @@
 # from PyMieScatt import Mie_SD
-# from PyMieScatt import Mie_SD
 
 from ._mie_sd import Mie_SD
 

AeroViz/dataProcess/Optical/_scattering.py

@@ -1,30 +1,29 @@
 import numpy as np
-from scipy.optimize import curve_fit
+from pandas import concat
 
-__all__ = [
-    '_SAE',
-]
+__all__ = ['_scaCoe']
 
 
-def _SAE(df):
-    def _SAEcalc(_df):
-        ## parameter
-        band = np.array([450, 550, 700]) * 1e-3
+def _scaCoe(df, instru, specified_band: list):
+    from .Angstrom_exponent import get_Angstrom_exponent, get_species_wavelength
+    band_Neph = np.array([450, 550, 700])
+    band_Aurora = np.array([450, 525, 635])
 
-        ## 3 pts fitting
-        ## function
-        def _get_slope(__df):
-            func = lambda _x, _sl, _int: _sl * _x + _int
-            popt, pcov = curve_fit(func, np.log(band), np.log(__df))
+    band = band_Neph if instru == 'Neph' else band_Aurora
 
-            return popt
+    df_sca = df.copy().dropna()
 
-        ## calculate
-        _SAE = _df.apply(_get_slope, axis=1, result_type='expand')
-        _SAE.columns = ['slope', 'intercept']
+    if instru == 'Neph':
+        df_out = df_sca[['B']].copy()
+        df_out.columns = [f'sca_{_band}' for _band in specified_band]
+    else:
+        df_out = df_sca.apply(get_species_wavelength, axis=1, result_type='expand', args=(specified_band,))
+        df_out.columns = [f'sca_{_band}' for _band in specified_band]
 
-        return _SAE
+    # calculate
+    df_SAE = df[['B', 'G', 'R']].dropna().apply(get_Angstrom_exponent, axis=1, result_type='expand', args=(band,))
+    df_SAE.columns = ['SAE', 'SAE_intercept']
 
-    df_out = _SAEcalc(df[['B', 'G', 'R']].dropna())
+    _df = concat([df_out, df_SAE['SAE']], axis=1)
 
-    return df_out.reindex(df.index)
+    return _df.reindex(df.index)

AeroViz/dataProcess/SizeDistr/__init__.py

@@ -1,4 +1,4 @@
-from ..core import _writter, _run_process
+from ..core import Writer, run_process
 
 __all__ = [
 
@@ -7,10 +7,10 @@ __all__ = [
 ]
 
 
-class SizeDistr(_writter):
+class SizeDistr(Writer):
 
     ## basic
-    @_run_process('SizeDistr - basic', 'distr_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
 
@@ -19,7 +19,7 @@ class SizeDistr(_writter):
         return self, out
 
     ## merge
-    @_run_process('SizeDistr - merge_SMPS_APS_v4', 'distr_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,
                           times_range=(0.8, 1.25, .05)):
@@ -31,7 +31,7 @@ class SizeDistr(_writter):
         return self, out
 
     ## merge
-    @_run_process('SizeDistr - merge_SMPS_APS_v3', 'distr_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):
         from ._merge_v3 import merge_SMPS_APS
@@ -41,7 +41,7 @@ class SizeDistr(_writter):
         return self, out
 
     ## merge
-    @_run_process('SizeDistr - merge_SMPS_APS_v2', 'distr_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):
         from ._merge_v2 import merge_SMPS_APS
@@ -51,7 +51,7 @@ class SizeDistr(_writter):
         return self, out
 
     ## merge
-    @_run_process('SizeDistr - merge_SMPS_APS_v1', 'distr_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):
         from ._merge_v1 import _merge_SMPS_APS

AeroViz/dataProcess/SizeDistr/_merge.py

@@ -5,7 +5,7 @@ from pandas import DataFrame, to_datetime
 # from scipy.interpolate import interp1d
 from scipy.interpolate import UnivariateSpline as unvpline, interp1d
 
-from AeroViz.dataProcess.core import _union_index
+from AeroViz.dataProcess.core import union_index
 
 __all__ = ['merge_SMPS_APS']
 
@@ -195,7 +195,7 @@ def _merge_data(_smps_ori, _aps_ori, _shift_ori, _smps_lb, _aps_hb, _coe, _shift
 
 
 def merge_SMPS_APS(df_smps, df_aps, aps_unit='um', smps_overlap_lowbound=500, aps_fit_highbound=1000):
-    df_smps, df_aps = _union_index(df_smps, df_aps)
+    df_smps, df_aps = union_index(df_smps, df_aps)
 
     ## set to the same units
     smps, aps_ori = df_smps.copy(), df_aps.copy()

AeroViz/dataProcess/SizeDistr/_merge_v1.py

@@ -5,7 +5,7 @@ from pandas import DataFrame, to_datetime
 # from scipy.interpolate import interp1d
 from scipy.interpolate import UnivariateSpline as unvpline, interp1d
 
-from AeroViz.dataProcess.core import _union_index
+from AeroViz.dataProcess.core import union_index
 
 __all__ = ['_merge_SMPS_APS']
 
@@ -203,7 +203,7 @@ def _merge_data(_smps_ori, _aps_ori, _shift_ori, _shift_mode, _smps_lb, _aps_hb,
 
 ## aps_fit_highbound : the diameter I choose randomly
 def _merge_SMPS_APS(df_smps, df_aps, aps_unit, shift_mode, smps_overlap_lowbound, aps_fit_highbound):
-    df_smps, df_aps = _union_index(df_smps, df_aps)
+    df_smps, df_aps = union_index(df_smps, df_aps)
 
     # print(f'\nMerge data :')
     # print(f' APS fittint higher diameter : {aps_fit_highbound:4d} nm')

AeroViz/dataProcess/SizeDistr/_merge_v2.py

@@ -5,7 +5,7 @@ from pandas import DataFrame, to_datetime
 # from scipy.interpolate import interp1d
 from scipy.interpolate import UnivariateSpline as unvpline, interp1d
 
-from AeroViz.dataProcess.core import _union_index
+from AeroViz.dataProcess.core import union_index
 
 __all__ = ['_merge_SMPS_APS']
 
@@ -196,7 +196,7 @@ def _merge_data(_smps_ori, _aps_ori, _shift_ori, _smps_lb, _aps_hb, _coe, _shift
 
 
 def merge_SMPS_APS(df_smps, df_aps, aps_unit='um', smps_overlap_lowbound=500, aps_fit_highbound=1000):
-    df_smps, df_aps = _union_index(df_smps, df_aps)
+    df_smps, df_aps = union_index(df_smps, df_aps)
 
     ## set to the same units
     smps, aps_ori = df_smps.copy(), df_aps.copy()

AeroViz/dataProcess/SizeDistr/_merge_v3.py

@@ -1,4 +1,4 @@
-# from ContainerHandle.dataProcess.utils import _union_index
+# from ContainerHandle.dataProcess.config import _union_index
 
 from datetime import datetime as dtm
 

AeroViz/dataProcess/SizeDistr/_merge_v4.py

@@ -1,4 +1,4 @@
-# from ContainerHandle.dataProcess.utils import _union_index
+# from ContainerHandle.dataProcess.config import _union_index
 
 import warnings
 from datetime import datetime as dtm

AeroViz/dataProcess/VOC/__init__.py

@@ -1,16 +1,11 @@
-from ..core import _writter, _run_process
+from ..core import Writer, run_process
 
-__all__ = [
+__all__ = ['VOC']
 
-    'VOC',
 
-]
+class VOC(Writer):
 
-
-class VOC(_writter):
-
-    ## Reconstruction
-    @_run_process('VOC - basic', 'voc_basic')
+    @run_process('VOC - basic', 'voc_basic')
     def VOC_basic(self, _df_voc):
         from ._potential_par import _basic
 

AeroViz/dataProcess/VOC/_potential_par.py

@@ -1,44 +1,41 @@
-import pickle as pkl
 from pathlib import Path
 
-from pandas import DataFrame, read_json
+from pandas import DataFrame, read_json, concat
 
 
 def _basic(_df_voc):
-    ## parameter
+    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()
 
-    with (Path(__file__).parent / 'voc_par.pkl').open('rb') as f:
-        _par = pkl.load(f)
-        _MW, _MIR, _SOAP, _KOH = _par.loc['MW', _keys], _par.loc['MIR', _keys], _par.loc['SOAP', _keys], _par.loc[
-            'KOH', _keys]
-
-    with (Path(__file__).parent / 'voc_par.json').open('r', encoding='utf-8', errors='ignore') as f:
-        _parr = read_json(f)
-        _MW, _MIR, _SOAP, _KOH = _par.loc['MW', _keys], _par.loc['MIR', _keys], _par.loc['SOAP', _keys], _par.loc[
-            'KOH', _keys]
-
-    _voc_clasfy = {
-        'alkane_total': ['Isopentane', 'n-Butane', '2-Methylhexane', 'Cyclopentane', '3-Methylpentane',
-                         '2,3-Dimethylbutane',
-                         '2-Methylheptane', 'n-Nonane', 'Methylcyclohexane', '2,4-Dimethylpentane', '2-Methylpentane',
-                         'n-Decane',
-                         'n-Heptane', 'Cyclohexane', 'n-Octane', 'Isobutane', '2,2-Dimethylbutane',
-                         'Methylcyclopentane', 'n-Hexane',
-                         '2,3,4-Trimethylpentane', '3-Methylhexane', 'n-Undecane', '3-Methylheptane', 'Hexane',
-                         '2,2,4-Trimethylpentane', 'n-Pentane', 'Ethane', 'Propane'],
-
-        'alkane_total': ['Isoprene', '1-Butene', 'cis-2-Butene', 'Propene', '1.3-Butadiene',
-                         't-2-Butene', 'cis-2-Pentene', 'Propylene', 'isoprene', '1-Pentene',
-                         'Ethylene', 't-2-Pentene', '1-Octene'],
-
-        'aromatic_total': ['o-Ethyltoluene', '1,3,5-Trimethylbenzene', 'Ethylbenzene', 'm,p-Xylene', 'n-Propylbenzene',
-                           'Benzene', 'Toluene', '1.2.4-TMB', 'Styrene', 'p-Ethyltoluene', 'o-Xylene',
-                           'm-Diethylbenzene',
-                           '1.2.3-TMB', 'Isopropylbenzene', 'm-Ethyltoluene', '2-Ethyltoluene', '1.3.5-TMB',
-                           'Iso-Propylbenzene',
-                           '3.4-Ethyltoluene', 'p-Diethylbenzene', '1,2,4-Trimethylbenzene', 'm.p-Xylene',
-                           '1,2,3-Trimethylbenzene'],
+    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'],
 
@@ -55,15 +52,18 @@ def _basic(_df_voc):
         'LOH': _df_MW / 24.5 / _MW * 0.602 * _KOH,
     }
 
-    ## calculate
+    # calculate
     _out = {}
     for _nam, _df in _df_dic.items():
 
         _df_out = DataFrame(index=_df_voc.index)
 
-        for _voc_nam, _voc_lst in _voc_clasfy.items():
+        for _voc_nam, _voc_lst in _voc_classify.items():
             _lst = list(set(_keys) & set(_voc_lst))
-            if len(_lst) == 0: continue
+            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)
 
@@ -72,3 +72,37 @@ def _basic(_df_voc):
         _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)