AeroViz 0.1.0__py3-none-any.whl

AeroViz/rawDataReader/script/IGAC_TH.py

@@ -0,0 +1,104 @@
+# read meteorological data from google sheet
+
+
+import numpy as np
+from pandas import read_csv, concat, to_datetime
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'IGAC_TH'
+
+	def _raw_reader(self, _file):
+
+		self.meta['freq'] = self._oth_set.get('data_freq') or self.meta['freq']
+
+		with (_file).open('r', encoding='utf-8-sig', errors='ignore') as f:
+			_df = read_csv(f, low_memory=False, index_col=0)
+
+			_df.index = to_datetime(_df.index, errors='coerce', format=self._oth_set.get('date_format') or 'mixed')
+			_df.index.name = 'time'
+
+			_df.columns = _df.keys().str.strip(' ')
+
+			_df = _df.loc[_df.index.dropna()].copy()
+
+		return _df.loc[~_df.index.duplicated()]
+
+	## QC data
+	def _QC(self, _df):
+
+		## QC parameter, function (MDL SE LE)
+		_mdl = {
+			'Na+': 0.05,
+			'NH4+': 0.05,
+			'K+': 0.05,
+			'Mg2+': 0.05,
+			'Ca2+': 0.05,
+			'Cl-': 0.05,
+			'NO2-': 0.05,
+			'NO3-': 0.05,
+			'SO42-': 0.05,
+		}
+
+		def _se_le(_df_, _log=False):
+			_df_ = np.log10(_df_) if _log else _df_
+
+			_df_qua = _df_.quantile([.25, .75])
+			_df_q1, _df_q3 = _df_qua.loc[.25].copy(), _df_qua.loc[.75].copy()
+			_df_iqr = _df_q3 - _df_q1
+
+			_se = concat([_df_q1 - 1.5 * _df_iqr] * len(_df_), axis=1).T.set_index(_df_.index)
+			_le = concat([_df_q3 + 1.5 * _df_iqr] * len(_df_), axis=1).T.set_index(_df_.index)
+
+			if _log:
+				return 10 ** _se, 10 ** _le
+			return _se, _le
+
+		_cation, _anion, _main = ['Na+', 'NH4+', 'K+', 'Mg2+', 'Ca2+'], ['Cl-', 'NO2-', 'NO3-', 'SO42-', ], ['SO42-',
+																											 'NO3-',
+																											 'NH4+']
+
+		_df_salt = _df[_mdl.keys()].copy()
+		_df_pm = _df['PM2.5'].copy()
+
+		## lower than PM2.5
+		## conc. of main salt should be present at the same time (NH4+, SO42-, NO3-)
+		_df_salt = _df_salt.mask(_df_salt.sum(axis=1, min_count=1) > _df_pm).dropna(subset=_main).copy()
+
+		## mdl
+		for (_key, _df_col), _mdl_val in zip(_df_salt.items(), _mdl.values()):
+			_df_salt[_key] = _df_col.mask(_df_col < _mdl_val, _mdl_val / 2)
+
+		## group by time (per month)
+		_df_salt['tm'] = _df_salt.index.strftime('%Y-%m')
+
+		_df_lst = []
+		for _ky, _df_grp in _df_salt.groupby('tm'):
+			_df_grp = _df_grp[_mdl.keys()].copy()
+
+			## calculate SE LE
+			## salt < LE
+			_se, _le = _se_le(_df_grp, _log=True)
+			_df_grp = _df_grp.mask(_df_grp > _le).copy()
+
+			## C/A, A/C
+			_rat_CA = (_df_grp[_cation].sum(axis=1) / _df_grp[_anion].sum(axis=1)).to_frame()
+			_rat_AC = (1 / _rat_CA).copy()
+
+			_se, _le = _se_le(_rat_CA, )
+			_cond_CA = (_rat_CA < _le) & (_rat_CA > 0)
+
+			_se, _le = _se_le(_rat_AC, )
+			_cond_AC = (_rat_AC < _le) & (_rat_AC > 0)
+
+			_df_grp = _df_grp.where((_cond_CA * _cond_AC)[0]).copy()
+
+			## conc. of main salt > SE
+			_se, _le = _se_le(_df_grp[_main], _log=True)
+			_df_grp[_main] = _df_grp[_main].mask(_df_grp[_main] < _se).copy()
+
+			_df_lst.append(_df_grp)
+
+		return concat(_df_lst).reindex(_df.index)

AeroViz/rawDataReader/script/IGAC_ZM.py

@@ -0,0 +1,90 @@
+# read meteorological data from google sheet
+
+
+import numpy as np
+from pandas import read_csv, concat, to_numeric
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'IGAC_ZM'
+
+	def _raw_reader(self, _file):
+
+		with (_file).open('r', encoding='utf-8-sig', errors='ignore') as f:
+			_df = read_csv(f, parse_dates=[0], index_col=[0], na_values=['-']).apply(to_numeric, errors='coerce')
+
+			_df.columns = _df.keys().str.strip(' ')
+			_df.index.name = 'time'
+
+		return _df.loc[_df.index.dropna()].loc[~_df.index.duplicated()]
+
+	## QC data
+	def _QC(self, _df):
+
+		## QC parameter, function (MDL SE LE)
+		_mdl = {
+			'Na+': 0.06,
+			'NH4+': 0.05,
+			'K+': 0.05,
+			'Mg2+': 0.12,
+			'Ca2+': 0.07,
+			'Cl-': 0.07,
+			'NO2-': 0.05,
+			'NO3-': 0.11,
+			'SO42-': 0.08,
+		}
+		_mdl.update(self._oth_set.get('mdl', {}))
+
+		def _se_le(_df_, _log=False):
+			_df_ = np.log10(_df_) if _log else _df_
+
+			_df_qua = _df_.quantile([.25, .75])
+			_df_q1, _df_q3 = _df_qua.loc[.25].copy(), _df_qua.loc[.75].copy()
+			_df_iqr = _df_q3 - _df_q1
+
+			_se = concat([_df_q1 - 1.5 * _df_iqr] * len(_df_), axis=1).T.set_index(_df_.index)
+			_le = concat([_df_q3 + 1.5 * _df_iqr] * len(_df_), axis=1).T.set_index(_df_.index)
+
+			if _log:
+				return 10 ** _se, 10 ** _le
+			return _se, _le
+
+		_cation, _anion, _main = ['Na+', 'NH4+', 'K+', 'Mg2+', 'Ca2+'], ['Cl-', 'NO2-', 'NO3-', 'SO42-', ], ['SO42-',
+																											 'NO3-',
+																											 'NH4+']
+
+		_df_salt = _df[_mdl.keys()].copy()
+		_df_pm = _df['PM2.5'].copy()
+
+		## lower than PM2.5
+		## conc. of main salt should be present at the same time (NH4+, SO42-, NO3-)
+		_df_salt = _df_salt.mask(_df_salt.sum(axis=1, min_count=1) > _df_pm).dropna(subset=_main).copy()
+
+		## mdl
+		for (_key, _df_col), _mdl_val in zip(_df_salt.items(), _mdl.values()):
+			_df_salt[_key] = _df_col.mask(_df_col < _mdl_val, _mdl_val / 2)
+
+		## calculate SE LE
+		## salt < LE
+		_se, _le = _se_le(_df_salt, _log=True)
+		_df_salt = _df_salt.mask(_df_salt > _le).copy()
+
+		## C/A, A/C
+		_rat_CA = (_df_salt[_cation].sum(axis=1) / _df_salt[_anion].sum(axis=1)).to_frame()
+		_rat_AC = (1 / _rat_CA).copy()
+
+		_se, _le = _se_le(_rat_CA, )
+		_cond_CA = (_rat_CA < _le) & (_rat_CA > 0)
+
+		_se, _le = _se_le(_rat_AC, )
+		_cond_AC = (_rat_AC < _le) & (_rat_AC > 0)
+
+		_df_salt = _df_salt.where((_cond_CA * _cond_AC)[0]).copy()
+
+		## conc. of main salt > SE
+		_se, _le = _se_le(_df_salt[_main], _log=True)
+		_df_salt[_main] = _df_salt[_main].mask(_df_salt[_main] < _se).copy()
+
+		return _df_salt.reindex(_df.index)

AeroViz/rawDataReader/script/MA350.py

@@ -0,0 +1,45 @@
+from pandas import read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'MA350'
+
+	def _raw_reader(self, _file):
+		_df = read_csv(_file, parse_dates=['Date / time local'], index_col='Date / time local').rename_axis("Time")
+
+		_df = _df.rename(columns={
+			'UV BCc': 'BC1',
+			'Blue BCc': 'BC2',
+			'Green BCc': 'BC3',
+			'Red BCc': 'BC4',
+			'IR BCc': 'BC5',
+			'Biomass BCc  (ng/m^3)': 'BB mass',
+			'Fossil fuel BCc  (ng/m^3)': 'FF mass',
+			'Delta-C  (ng/m^3)': 'Delta-C',
+			'AAE': 'AAE',
+			'BB (%)': 'BB',
+		})
+
+		# remove data without Status=32 (Automatic Tape Advance), 65536 (Tape Move)
+		# if not self._oth_set.get('ignore_err', False):
+		#     _df = _df.where((_df['Status'] != 32) | (_df['Status'] != 65536)).copy()
+
+		return _df[['BC1', 'BC2', 'BC3', 'BC4', 'BC5', 'BB mass', 'FF mass', 'Delta-C', 'AAE', 'BB']]
+
+	# QC data
+	def _QC(self, _df):
+		# remove negative value
+		_df = _df[['BC1', 'BC2', 'BC3', 'BC4', 'BC5', 'BB mass', 'FF mass', 'AAE', 'BB']].mask((_df < 0).copy())
+
+		# call by _QC function
+		# QC data in 1 hr
+		def _QC_func(_df_1hr):
+			_df_ave = _df_1hr.mean()
+			_df_std = _df_1hr.std()
+			_df_lowb, _df_highb = _df_1hr < (_df_ave - _df_std * 1.5), _df_1hr > (_df_ave + _df_std * 1.5)
+
+			return _df_1hr.mask(_df_lowb | _df_highb).copy()
+
+		return _df.resample('1h', group_keys=False).apply(_QC_func).resample('5min').mean()

AeroViz/rawDataReader/script/NEPH.py

@@ -0,0 +1,57 @@
+from pandas import to_datetime, read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'NEPH'
+
+	def _raw_reader(self, _file):
+		with (_file).open('r', encoding='utf-8', errors='ignore') as f:
+			_df = read_csv(f, header=None, names=range(11))
+
+			_df_grp = _df.groupby(0)
+
+			## T : time
+			_df_tm = _df_grp.get_group('T')[[1, 2, 3, 4, 5, 6]].astype(int)
+
+			for _k in [2, 3, 4, 5, 6]:
+				_df_tm[_k] = _df_tm[_k].astype(int).map('{:02d}'.format).copy()
+			_df_tm = _df_tm.astype(str)
+
+			_idx_tm = to_datetime((_df_tm[1] + _df_tm[2] + _df_tm[3] + _df_tm[4] + _df_tm[5] + _df_tm[6]),
+								  format='%Y%m%d%H%M%S')
+
+			## D : data
+			## col : 3~8 B G R BB BG BR
+			## 1e6
+			_df_dt = _df_grp.get_group('D')[[1, 2, 3, 4, 5, 6, 7, 8]].set_index(_idx_tm)
+			_df_out = (_df_dt.groupby(1).get_group('NBXX')[[3, 4, 5, 6, 7, 8]] * 1e6).reindex(_idx_tm)
+			_df_out.columns = ['B', 'G', 'R', 'BB', 'BG', 'BR']
+			_df_out.index.name = 'Time'
+
+			## Y : state
+			## col : 5 RH
+			_df_st = _df_grp.get_group('Y')
+			_df_out['RH'] = _df_st[5].values
+			_df_out['status'] = _df_st[9].values
+
+			_df_out.mask(_df_out['status'] != 0)  ## 0000 -> numeric to 0
+
+		return _df_out[['B', 'G', 'R', 'BB', 'BG', 'BR', 'RH']]
+
+	## QC data
+	def _QC(self, _df):
+		## remove negative value
+		_df = _df.mask((_df <= 0).copy())
+
+		## call by _QC function
+		## QC data in 1 hr
+		def _QC_func(_df_1hr):
+			_df_ave = _df_1hr.mean()
+			_df_std = _df_1hr.std()
+			_df_lowb, _df_highb = _df_1hr < (_df_ave - _df_std * 1.5), _df_1hr > (_df_ave + _df_std * 1.5)
+
+			return _df_1hr.mask(_df_lowb | _df_highb).copy()
+
+		return _df.resample('1h', group_keys=False).apply(_QC_func)

AeroViz/rawDataReader/script/OCEC_LCRES.py

@@ -0,0 +1,34 @@
+from pandas import to_datetime, read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'OCEC_LCRES'
+
+	def _raw_reader(self, _file):
+		with open(_file, 'r', encoding='utf-8', errors='ignore') as f:
+			_df = read_csv(f, skiprows=3)
+
+			_col = {'Thermal/Optical OC (ugC/LCm^3)': 'Thermal_OC',
+					'Thermal/Optical EC (ugC/LCm^3)': 'Thermal_EC',
+					'OC=TC-BC (ugC/LCm^3)': 'Optical_OC',
+					'BC (ugC/LCm^3)': 'Optical_EC',
+					'Sample Volume Local Condition Actual m^3': 'Sample_Volume',
+					'TC (ugC/LCm^3)': 'TC', }
+
+			_tm_idx = to_datetime(_df['Start Date/Time'], errors='coerce')
+			_df['time'] = _tm_idx
+
+			_df = _df.dropna(subset='time').loc[~_tm_idx.duplicated()].set_index('time')
+
+		return _df[_col.keys()].rename(columns=_col)
+
+	## QC data
+	def _QC(self, _df):
+		_df[['Thermal_OC', 'Optical_OC']] = _df[['Thermal_OC', 'Optical_OC']].where(
+			_df[['Thermal_OC', 'Optical_OC']] > 0.3).copy()
+		_df[['Thermal_EC', 'Optical_EC']] = _df[['Thermal_EC', 'Optical_EC']].where(
+			_df[['Thermal_EC', 'Optical_EC']] > .015).copy()
+
+		return _df

AeroViz/rawDataReader/script/OCEC_RES.py

@@ -0,0 +1,28 @@
+from pandas import to_datetime, read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'OCEC_RES'
+
+	def _raw_reader(self, _file):
+		with open(_file, 'r', encoding='utf-8', errors='ignore') as f:
+			_df = read_csv(f, skiprows=3)
+
+			_col = {'OCPk1-ug C': 'OC1',
+					'OCPk2-ug C': 'OC2',
+					'OCPk3-ug C': 'OC3',
+					'OCPk4-ug C': 'OC4',
+					'Pyrolized C ug': 'PC', }
+
+			_tm_idx = to_datetime(_df['Start Date/Time'], errors='coerce')
+			_df['time'] = _tm_idx
+
+			_df = _df.dropna(subset='time').loc[~_tm_idx.duplicated()].set_index('time')
+
+		return _df[_col.keys()].rename(columns=_col)
+
+	## QC data
+	def _QC(self, _df):
+		return _df.where(_df > 0)

AeroViz/rawDataReader/script/SMPS_TH.py

@@ -0,0 +1,41 @@
+from pandas import to_datetime, read_table
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'SMPS_TH'
+
+	def _raw_reader(self, _file):
+		with open(_file, 'r', encoding='utf-8', errors='ignore') as f:
+			_df = read_table(f, skiprows=18, parse_dates={'Time': ['Date', 'Start Time']}).set_index('Time')
+			_key = list(_df.keys()[6:-26])
+
+			_newkey = {}
+			for _k in _key:
+				_newkey[_k] = float(_k).__round__(4)
+
+			# _newkey['Total Conc.(#/cm)'] = 'total'
+			# _newkey['Mode(nm)']	= 'mode'
+
+			_df_idx = to_datetime(_df.index, errors='coerce')
+		return _df[_newkey.keys()].rename(_newkey, axis=1).set_index(_df_idx).loc[_df_idx.dropna()]
+
+	## QC data
+	def _QC(self, _df):
+		import numpy as n
+
+		## mask out the data size lower than 7
+		_df['total'] = _df.sum(axis=1, min_count=1) * (n.diff(n.log(_df.keys().to_numpy(float)))).mean()
+		_df_size = _df['total'].dropna().resample('1h').size().resample(_df.index.freq).ffill()
+		_df = _df.mask(_df_size < 7)
+
+		## remove total conc. lower than 2000
+		_df = _df.mask(_df['total'] < 2000)
+
+		## remove the bin over 400 nm which num. conc. larger than 4000
+		_df_remv_ky = _df.keys()[:-2][_df.keys()[:-2] >= 400.]
+
+		_df[_df_remv_ky] = _df[_df_remv_ky].copy().mask(_df[_df_remv_ky] > 4000.)
+
+		return _df[_df.keys()[:-1]]

AeroViz/rawDataReader/script/SMPS_aim11.py

@@ -0,0 +1,51 @@
+from pandas import to_datetime, read_csv, to_numeric
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'SMPS_aim11'
+
+	def _raw_reader(self, _file):
+		with open(_file, 'r', encoding='utf-8', errors='ignore') as f:
+
+			skiprows = 0
+			for _line in f:
+
+				if _line.split(',')[0] == 'Scan Number':
+					f.seek(0)
+					break
+
+				skiprows += 1
+			# breakpoint()
+			_df = read_csv(f, skiprows=skiprows)
+			_tm_idx = to_datetime(_df['DateTime Sample Start'], format='%d/%m/%Y %X', errors='coerce')
+
+			## index
+			_df = _df.set_index(_tm_idx).loc[_tm_idx.dropna()]
+
+			## keys
+			_key = to_numeric(_df.keys(), errors='coerce')
+			_df.columns = _key
+			_df = _df.loc[:, ~_key.isna()]
+
+		return _df.apply(to_numeric, errors='coerce')
+
+	## QC data
+	def _QC(self, _df):
+		import numpy as n
+
+		## mask out the data size lower than 7
+		_df['total'] = _df.sum(axis=1, min_count=1) * (n.diff(n.log(_df.keys().to_numpy(float)))).mean()
+		_df_size = _df['total'].dropna().resample('1h').size().resample(_df.index.freq).ffill()
+		_df = _df.mask(_df_size < 7)
+
+		## remove total conc. lower than 2000
+		_df = _df.mask(_df['total'] < 2000)
+
+		## remove the bin over 400 nm which num. conc. larger than 4000
+		_df_remv_ky = _df.keys()[:-2][_df.keys()[:-2] >= 400.]
+
+		_df[_df_remv_ky] = _df[_df_remv_ky].copy().mask(_df[_df_remv_ky] > 4000.)
+
+		return _df[_df.keys()[:-1]]

AeroViz/rawDataReader/script/SMPS_genr.py

@@ -0,0 +1,51 @@
+from pandas import to_datetime, read_table, to_numeric
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'SMPS_genr'
+
+	def _raw_reader(self, _file):
+		with open(_file, 'r', encoding='utf-8', errors='ignore') as f:
+
+			skiprows = 0
+			for _line in f:
+
+				if _line.split('\t')[0] == 'Sample #':
+					f.seek(0)
+					break
+
+				skiprows += 1
+
+			_df = read_table(f, skiprows=skiprows)
+			_tm_idx = to_datetime(_df['Date'] + _df['Start Time'], format='%m/%d/%y%X', errors='coerce')
+
+			## index
+			_df = _df.set_index(_tm_idx).loc[_tm_idx.dropna()]
+
+			## keys
+			_key = to_numeric(_df.keys(), errors='coerce')
+			_df.columns = _key
+			_df = _df.loc[:, ~_key.isna()]
+
+		return _df.apply(to_numeric, errors='coerce')
+
+	## QC data
+	def _QC(self, _df):
+		import numpy as n
+
+		## mask out the data size lower than 7
+		_df['total'] = _df.sum(axis=1, min_count=1) * (n.diff(n.log(_df.keys().to_numpy(float)))).mean()
+		_df_size = _df['total'].dropna().resample('1h').size().resample(_df.index.freq).ffill()
+		_df = _df.mask(_df_size < 7)
+
+		## remove total conc. lower than 2000
+		_df = _df.mask(_df['total'] < 2000)
+
+		## remove the bin over 400 nm which num. conc. larger than 4000
+		_df_remv_ky = _df.keys()[:-2][_df.keys()[:-2] >= 400.]
+
+		_df[_df_remv_ky] = _df[_df_remv_ky].copy().mask(_df[_df_remv_ky] > 4000.)
+
+		return _df[_df.keys()[:-1]]

AeroViz/rawDataReader/script/TEOM.py

@@ -0,0 +1,46 @@
+from pandas import to_datetime, read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'TEOM'
+
+	def _raw_reader(self, _file):
+		with open(_file, 'r', encoding='utf-8', errors='ignore') as f:
+			_df = read_csv(f, skiprows=3, index_col=False)
+
+			_df = _df.rename(columns={'Time Stamp': 'time',
+									  'System status': 'status',
+									  'PM-2.5 base MC': 'PM_NV',
+									  'PM-2.5 MC': 'PM_Total',
+									  'PM-2.5 TEOM noise': 'noise', })
+
+			_time_replace = {'十一月': '11', '十二月': '12', '一月': '01', '二月': '02', '三月': '03', '四月': '04',
+							 '五月': '05', '六月': '06', '七月': '07', '八月': '08', '九月': '09', '十月': '10'}
+
+			_tm_idx = _df.time
+			for _ori, _rpl in _time_replace.items():
+				_tm_idx = _tm_idx.str.replace(_ori, _rpl)
+
+			_df = _df.set_index(to_datetime(_tm_idx, errors='coerce', format='%d - %m - %Y %X'))
+
+			_df = _df.where(_df['status'] < 1e-7)
+
+		return _df[['PM_NV', 'PM_Total', 'noise', ]]
+
+	## QC data
+	def _QC(self, _df):
+
+		_df_idx = _df.index.copy()
+
+		## remove negative value
+		_df = _df.where(_df.noise < 0.01)[['PM_NV', 'PM_Total']].mask((_df < 0).copy())
+
+		## QC data in 1 hr
+		## remove data where size < 8 in 1-hr
+		for _key in ['PM_Total', 'PM_NV']:
+			_size = _df[_key].dropna().resample('1h').size().reindex(_df_idx).ffill().copy()
+			_df[_key] = _df[_key].mask(_size < 8)
+
+		return _df.reindex(_df_idx)

AeroViz/rawDataReader/script/Table.py

@@ -0,0 +1,28 @@
+# read meteorological data from google sheet
+
+
+from pandas import read_csv, to_datetime
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'Table'
+
+	def _raw_reader(self, _file):
+		self.meta['freq'] = self._oth_set.get('data_freq') or self.meta['freq']
+
+		with (_file).open('r', encoding='utf-8-sig', errors='ignore') as f:
+			_df = read_csv(f, low_memory=False, index_col=0)
+
+			_df.index = to_datetime(_df.index, errors='coerce', format=self._oth_set.get('date_format') or 'mixed')
+			_df.index.name = 'time'
+
+			_df.columns = _df.keys().str.strip(' ')
+
+			_df = _df.loc[_df.index.dropna()].copy()
+
+		return _df.loc[~_df.index.duplicated()]
+
+	def _QC(self, _df):
+		return _df

AeroViz/rawDataReader/script/VOC_TH.py

@@ -0,0 +1,30 @@
+# read meteorological data from google sheet
+
+
+from pandas import read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'VOC_TH'
+
+	def _raw_reader(self, _file):
+		_keys = ['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']
+
+		with (_file).open('r', encoding='utf-8-sig', errors='ignore') as f:
+			_df = read_csv(f, parse_dates=[0], index_col=[0], na_values=['-', 'N.D.'])
+
+			_df.columns = _df.keys().str.strip(' ')
+			_df.index.name = 'time'
+
+			_df = _df[_keys].loc[_df.index.dropna()]
+		return _df.loc[~_df.index.duplicated()]
+
+	def _QC(self, _df):
+		return _df

AeroViz/rawDataReader/script/VOC_ZM.py

@@ -0,0 +1,37 @@
+# read meteorological data from google sheet
+
+
+from pandas import read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+	nam = 'VOC_ZM'
+
+	def _raw_reader(self, _file):
+		_keys = ['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']
+
+		with (_file).open('r', encoding='utf-8-sig', errors='ignore') as f:
+			_df = read_csv(f, parse_dates=[0], index_col=[0], na_values=['-'])
+
+			_df.columns = _df.keys().str.strip(' ')
+			_df.index.name = 'time'
+
+			_df = _df[_keys].loc[_df.index.dropna()]
+		return _df.loc[~_df.index.duplicated()]
+
+	def _QC(self, _df):
+		return _df

AeroViz/rawDataReader/script/__init__.py

@@ -0,0 +1,22 @@
+__all__ = [
+	'NEPH',
+	'Aurora',
+	'Table',
+	'EPA_vertical',
+	'APS_3321',
+	'SMPS_TH',
+	'AE33',
+	'AE43',
+	'BC1054',
+	'MA350',
+	'TEOM',
+	'OCEC_RES',
+	'OCEC_LCRES',
+	'IGAC_TH',
+	'IGAC_ZM',
+	'VOC_TH',
+	'VOC_ZM',
+	'SMPS_genr',
+	'SMPS_aim11',
+	'GRIMM'
+]

AeroViz/tools/__init__.py

@@ -0,0 +1,3 @@
+from .database import DataBase
+from .dataclassifier import DataClassifier
+from .datareader import DataReader