AeroViz 0.1.2__py3-none-any.whl → 0.1.3b0__py3-none-any.whl

AeroViz/rawDataReader/script/IGAC_ZM.py

@@ -8,83 +8,83 @@ from AeroViz.rawDataReader.core import AbstractReader
 
 
 class Reader(AbstractReader):
-	nam = 'IGAC_ZM'
+    nam = 'IGAC_ZM'
 
-	def _raw_reader(self, _file):
+    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')
+        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'
+            _df.columns = _df.keys().str.strip(' ')
+            _df.index.name = 'time'
 
-		return _df.loc[_df.index.dropna()].loc[~_df.index.duplicated()]
+        return _df.loc[_df.index.dropna()].loc[~_df.index.duplicated()]
 
-	## QC data
-	def _QC(self, _df):
+    ## 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', {}))
+        ## 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_
+        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
+            _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)
+            _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
+            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+']
+        _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()
+        _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()
+        ## 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)
+        ## 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()
+        ## 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()
+        ## 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_CA, )
+        _cond_CA = (_rat_CA < _le) & (_rat_CA > 0)
 
-		_se, _le = _se_le(_rat_AC, )
-		_cond_AC = (_rat_AC < _le) & (_rat_AC > 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()
+        _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()
+        ## 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)
+        return _df_salt.reindex(_df.index)

AeroViz/rawDataReader/script/MA350.py

@@ -4,42 +4,42 @@ 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()
+    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

@@ -4,77 +4,77 @@ 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
-			try:
-				_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']]
-
-			except ValueError:
-				group_sizes = _df_grp.size()
-				print(group_sizes)
-				# Define the valid groups
-				valid_groups = {'B', 'G', 'R', 'D', 'T', 'Y', 'Z'}
-
-				# Find the rows where the value in the first column is not in valid_groups
-				invalid_indices = _df[~_df[0].isin(valid_groups)].index
-
-				# Print the invalid indices and their corresponding values
-				invalid_values = _df.loc[invalid_indices, 0]
-				print("Invalid values and their indices:")
-				for idx, value in zip(invalid_indices, invalid_values):
-					print(f"Index: {idx}, Value: {value}")
-
-				# If there's a length mismatch, return an empty DataFrame with the same index and column names
-				columns = ['B', 'G', 'R', 'BB', 'BG', 'BR', 'RH']
-				_df_out = DataFrame(index=_idx_tm, columns=columns)
-				_df_out.index.name = 'Time'
-				print(f'\n\t\t\t Length mismatch in {_file} data. Returning an empty DataFrame.')
-				return _df_out
-
-	# 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)
+    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
+            try:
+                _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']]
+
+            except ValueError:
+                group_sizes = _df_grp.size()
+                print(group_sizes)
+                # Define the valid groups
+                valid_groups = {'B', 'G', 'R', 'D', 'T', 'Y', 'Z'}
+
+                # Find the rows where the value in the first column is not in valid_groups
+                invalid_indices = _df[~_df[0].isin(valid_groups)].index
+
+                # Print the invalid indices and their corresponding values
+                invalid_values = _df.loc[invalid_indices, 0]
+                print("Invalid values and their indices:")
+                for idx, value in zip(invalid_indices, invalid_values):
+                    print(f"Index: {idx}, Value: {value}")
+
+                # If there's a length mismatch, return an empty DataFrame with the same index and column names
+                columns = ['B', 'G', 'R', 'BB', 'BG', 'BR', 'RH']
+                _df_out = DataFrame(index=_idx_tm, columns=columns)
+                _df_out.index.name = 'Time'
+                print(f'\n\t\t\t Length mismatch in {_file} data. Returning an empty DataFrame.')
+                return _df_out
+
+    # 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

@@ -4,31 +4,31 @@ from AeroViz.rawDataReader.core import AbstractReader
 
 
 class Reader(AbstractReader):
-	nam = 'OCEC_LCRES'
+    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)
+    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', }
+            _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
+            _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')
+            _df = _df.dropna(subset='time').loc[~_tm_idx.duplicated()].set_index('time')
 
-		return _df[_col.keys()].rename(columns=_col)
+        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()
+    ## 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
+        return _df

AeroViz/rawDataReader/script/OCEC_RES.py

@@ -4,25 +4,25 @@ from AeroViz.rawDataReader.core import AbstractReader
 
 
 class Reader(AbstractReader):
-	nam = 'OCEC_RES'
+    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)
+    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', }
+            _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
+            _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')
+            _df = _df.dropna(subset='time').loc[~_tm_idx.duplicated()].set_index('time')
 
-		return _df[_col.keys()].rename(columns=_col)
+        return _df[_col.keys()].rename(columns=_col)
 
-	## QC data
-	def _QC(self, _df):
-		return _df.where(_df > 0)
+    ## QC data
+    def _QC(self, _df):
+        return _df.where(_df > 0)

AeroViz/rawDataReader/script/SMPS_TH.py

@@ -4,38 +4,38 @@ from AeroViz.rawDataReader.core import AbstractReader
 
 
 class Reader(AbstractReader):
-	nam = 'SMPS_TH'
+    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])
+    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 = {}
+            for _k in _key:
+                _newkey[_k] = float(_k).__round__(4)
 
-			# _newkey['Total Conc.(#/cm)'] = 'total'
-			# _newkey['Mode(nm)']	= 'mode'
+            # _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()]
+            _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
+    ## 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)
+        ## 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 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.]
+        ## 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.)
+        _df[_df_remv_ky] = _df[_df_remv_ky].copy().mask(_df[_df_remv_ky] > 4000.)
 
-		return _df[_df.keys()[:-1]]
+        return _df[_df.keys()[:-1]]

AeroViz/rawDataReader/script/SMPS_aim11.py

@@ -4,48 +4,48 @@ from AeroViz.rawDataReader.core import AbstractReader
 
 
 class Reader(AbstractReader):
-	nam = 'SMPS_aim11'
+    nam = 'SMPS_aim11'
 
-	def _raw_reader(self, _file):
-		with open(_file, 'r', encoding='utf-8', errors='ignore') as f:
+    def _raw_reader(self, _file):
+        with open(_file, 'r', encoding='utf-8', errors='ignore') as f:
 
-			skiprows = 0
-			for _line in f:
+            skiprows = 0
+            for _line in f:
 
-				if _line.split(',')[0] == 'Scan Number':
-					f.seek(0)
-					break
+                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')
+                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()]
+            ## 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()]
+            ## keys
+            _key = to_numeric(_df.keys(), errors='coerce')
+            _df.columns = _key
+            _df = _df.loc[:, ~_key.isna()]
 
-		return _df.apply(to_numeric, errors='coerce')
+        return _df.apply(to_numeric, errors='coerce')
 
-	## QC data
-	def _QC(self, _df):
-		import numpy as n
+    ## 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)
+        ## 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 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.]
+        ## 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.)
+        _df[_df_remv_ky] = _df[_df_remv_ky].copy().mask(_df[_df_remv_ky] > 4000.)
 
-		return _df[_df.keys()[:-1]]
+        return _df[_df.keys()[:-1]]