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

AeroViz/rawDataReader/script/Sunset_OCEC.py

@@ -0,0 +1,66 @@
+from pandas import to_datetime, read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+    nam = 'Sunset_OCEC'
+
+    def _raw_reader(self, file):
+        with open(file, 'r', encoding='utf-8', errors='ignore') as f:
+            _df = read_csv(f, skiprows=3, nrows=25)
+
+            _df['Start Date/Time'] = _df['Start Date/Time'].str.strip()
+            _df['time'] = to_datetime(_df['Start Date/Time'], format='%m/%d/%Y %I:%M:%S %p', errors='coerce')
+            _df = _df.set_index('time')
+            _df.index = _df.index.round('1h')
+
+            _df = _df.rename(columns={
+                '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',
+                'TC (ugC/LCm^3)': 'TC',
+
+                'OC ugC/m^3 (Thermal/Optical)': 'Thermal_OC',
+                'EC ugC/m^3 (Thermal/Optical)': 'Thermal_EC',
+                'OC by diff ugC (TC-OptEC)': 'Optical_OC',
+                'OptEC ugC/m^3': 'Optical_EC',
+                'TC ugC/m^3': 'TC',
+
+                'Sample Volume Local Condition Actual m^3': 'Sample_Volume',
+
+                'OCPk1-ug C': 'OC1_raw',
+                'OCPk2-ug C': 'OC2_raw',
+                'OCPk3-ug C': 'OC3_raw',
+                'OCPk4-ug C': 'OC4_raw',
+                'ECPk1-ug C': 'EC1_raw',
+                'ECPk2-ug C': 'EC2_raw',
+                'ECPk3-ug C': 'EC3_raw',
+                'ECPk4-ug C': 'EC4_raw',
+                'ECPk5-ug C': 'EC5_raw',
+            })
+
+            _df = _df[['Thermal_OC', 'Optical_OC', 'Thermal_EC', 'Optical_EC', 'TC', 'Sample_Volume',
+                       'OC1_raw', 'OC2_raw', 'OC3_raw', 'OC4_raw', 'EC1_raw', 'EC2_raw', 'EC3_raw', 'EC4_raw',
+                       'EC5_raw']]
+
+            return _df.loc[~_df.index.duplicated() & _df.index.notna()]
+
+    # QC data
+    def _QC(self, _df):
+        import numpy as np
+
+        _df = _df.where(_df > 0)
+
+        thresholds = {
+            'Thermal_OC': 0.3,
+            'Optical_OC': 0.3,
+            'Thermal_EC': 0.015,
+            'Optical_EC': 0.015
+        }
+
+        for col, thresh in thresholds.items():
+            _df.loc[_df[col] <= thresh, col] = np.nan
+
+        return _df

AeroViz/rawDataReader/script/TEOM.py

@@ -6,8 +6,8 @@ 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:
+    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',
@@ -27,18 +27,20 @@ class Reader(AbstractReader):
 
             _df = _df.where(_df['status'] < 1e-7)
 
-        return _df[['PM_NV', 'PM_Total', 'noise', ]]
+        _df = _df[['PM_NV', 'PM_Total', 'noise', ]]
 
-    ## QC data
+        return _df.loc[~_df.index.duplicated() & _df.index.notna()]
+
+    # 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())
+        # 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
+        # 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)

AeroViz/rawDataReader/script/Table.py

@@ -1,6 +1,5 @@
 # read meteorological data from google sheet
 
-
 from pandas import read_csv, to_datetime
 
 from AeroViz.rawDataReader.core import AbstractReader
@@ -9,20 +8,20 @@ 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:
+    def _raw_reader(self, file):
+        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 = to_datetime(_df.index, errors='coerce')
             _df.index.name = 'time'
 
             _df.columns = _df.keys().str.strip(' ')
 
-            _df = _df.loc[_df.index.dropna()].copy()
-
-        return _df.loc[~_df.index.duplicated()]
+        return _df.loc[~_df.index.duplicated() & _df.index.notna()]
 
     def _QC(self, _df):
-        return _df
+        # remove negative value
+        _df = _df.mask((_df < 0).copy())
+
+        # QC data in 6h
+        return _df.resample('6h').apply(self.basic_QC).resample(self.meta.get("freq")).mean()

AeroViz/rawDataReader/script/VOC.py

@@ -0,0 +1,33 @@
+from pandas import read_csv
+
+from AeroViz.rawDataReader.core import AbstractReader
+
+
+class Reader(AbstractReader):
+    nam = 'VOC'
+
+    def _raw_reader(self, file):
+        with file.open('r', encoding='utf-8-sig', errors='ignore') as f:
+            _df = read_csv(f, parse_dates=True, index_col=0, na_values=('-', 'N.D.'))
+
+            _df.columns = _df.keys().str.strip(' ')
+            _df.index.name = 'time'
+
+            support_voc = set(self.meta["key"])
+
+            valid_keys = [key for key in _df.keys() if key in support_voc]
+            invalid_keys = [key for key in _df.keys() if key not in support_voc]
+
+            if invalid_keys:
+                self.logger.warning(f'{invalid_keys} are not supported keys.')
+                print(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.')
+
+            if valid_keys:
+                return _df[valid_keys].loc[~_df.index.duplicated() & _df.index.notna()]
+            else:
+                self.logger.warning("沒有找到匹配的鍵。返回原始DataFrame並移除含NaN的行。")
+                return _df.loc[~_df.index.duplicated() & _df.index.notna()]
+
+    def _QC(self, _df):
+        return _df

AeroViz/rawDataReader/script/__init__.py

@@ -1,22 +1,20 @@
 __all__ = [
     'NEPH',
     'Aurora',
-    'Table',
-    'EPA_vertical',
-    'APS_3321',
     'SMPS_TH',
+    'SMPS_genr',
+    'SMPS_aim11',
+    'APS_3321',
+    'GRIMM',
     'AE33',
     'AE43',
     'BC1054',
     'MA350',
     'TEOM',
-    'OCEC_RES',
-    'OCEC_LCRES',
-    'IGAC_TH',
-    'IGAC_ZM',
-    'VOC_TH',
-    'VOC_ZM',
-    'SMPS_genr',
-    'SMPS_aim11',
-    'GRIMM'
+    'Sunset_OCEC',
+    'IGAC',
+    'VOC',
+    'Table',
+    'EPA_vertical',
+    'Minion'
 ]

AeroViz/tools/database.py

@@ -45,7 +45,8 @@ def load_dataset_by_url(dataset_name: Literal["Tunghai", "Taipei"] = "Tunghai")
     response = requests.get(url)
 
     if response.status_code == 200:
-        return read_csv(StringIO(response.text), parse_dates=['Time'], index_col='Time')
+        return read_csv(StringIO(response.text), na_values=('E', 'F', '-', '_', '#', '*'), index_col=0,
+                        parse_dates=True, low_memory=False)
     else:
         print(f"Failed to download file: {response.status_code}")
         print(response.text)  # Print the response text for debugging
@@ -54,7 +55,7 @@ def load_dataset_by_url(dataset_name: Literal["Tunghai", "Taipei"] = "Tunghai")
 
 def load_dataset_local(dataset_name: Literal["Tunghai", "Taipei", "PNSD"] = "Tunghai") -> DataFrame:
     base_dir = Path(__file__).resolve().parent.parent
-    config_dir = base_dir / 'config'
+    config_dir = base_dir / 'data'
 
     dataset_paths = {
         "Tunghai": config_dir / 'DEFAULT_DATA.csv',
@@ -70,7 +71,8 @@ def load_dataset_local(dataset_name: Literal["Tunghai", "Taipei", "PNSD"] = "Tun
     if not file_path.exists():
         raise FileNotFoundError(f"The file {file_path} does not exist.")
 
-    return read_csv(file_path, parse_dates=['Time'], index_col='Time', na_values=('-', 'E', 'F'), low_memory=False)
+    return read_csv(file_path, na_values=('E', 'F', '-', '_', '#', '*'), index_col=0, parse_dates=True,
+                    low_memory=False)
 
 
 class DataBase:
@@ -79,15 +81,11 @@ class DataBase:
         if file_path is not None:
             file_path = Path(file_path)
             if file_path.exists():
-                return read_csv(file_path, parse_dates=['Time'], index_col='Time', na_values=('-', 'E', 'F'),
+                return read_csv(file_path, na_values=('E', 'F', '-', '_', '#', '*'), index_col=0, parse_dates=True,
                                 low_memory=False)
 
         if load_data ^ load_PSD:
-            if load_data:
-                return load_dataset_local("Tunghai")
-
-            elif load_PSD:
-                return load_dataset_local("PNSD")
+            return load_dataset_local("Tunghai") if load_data else load_dataset_local("PNSD")
 
         else:
             raise ValueError("Exactly one of 'load_data' or 'load_PSD' must be True.")

AeroViz/tools/datareader.py

@@ -14,8 +14,8 @@ class FileHandler(ABC):
 
 class CsvFileHandler(FileHandler):
     def read_data(self, file_path: Path) -> DataFrame:
-        return read_csv(file_path, na_values=('-', 'E', 'F', '#', '*'),
-                        parse_dates=['Time'], index_col='Time', low_memory=False)
+        return read_csv(file_path, na_values=('E', 'F', '-', '_', '#', '*'), index_col=0, parse_dates=True,
+                        low_memory=False)
 
 
 class JsonFileHandler(FileHandler):
@@ -25,7 +25,7 @@ class JsonFileHandler(FileHandler):
 
 class ExcelFileHandler(FileHandler):
     def read_data(self, file_path: Path) -> DataFrame:
-        return read_excel(file_path, parse_dates=['Time'])
+        return read_excel(file_path, index_col=0, parse_dates=True, )
 
 
 class DataReaderFactory:

{AeroViz-0.1.3b0.dist-info → AeroViz-0.1.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: AeroViz
-Version: 0.1.3b0
+Version: 0.1.5
 Summary: Aerosol science
 Home-page: https://github.com/Alex870521/AeroViz
 Author: alex

AeroViz-0.1.5.dist-info/RECORD

@@ -0,0 +1,114 @@
+AeroViz/__init__.py,sha256=A5W6SR71uY_eW44Sh-Yk6blJQ_G1aHrkSzeP2YTPQc4,371
+AeroViz/data/DEFAULT_DATA.csv,sha256=eeeyeh8vSLKkE5tAF0TYnUNOyQIH98VA41bJaAP204Y,2248526
+AeroViz/data/DEFAULT_PNSD_DATA.csv,sha256=imLvLA80oYwo_jzXZtlQn5hZ76d47HUIlK2jp0tZPrg,2636511
+AeroViz/dataProcess/__init__.py,sha256=D3rTVUiGfs_daGuaotVtbijOgLAp6HaRWchj-zoEnHw,828
+AeroViz/dataProcess/Chemistry/__init__.py,sha256=fyyomjxkQcUNWDx4R5jPrHafAftN-v2liUZii9OlaiU,2058
+AeroViz/dataProcess/Chemistry/_calculate.py,sha256=q7ojTFPok0vg8k_1PMECNdP5CPanR9NWQ4Rx5iTcHew,599
+AeroViz/dataProcess/Chemistry/_isoropia.py,sha256=3wp_FXdN230awlStMbctutwld4oot9WaAVXETGd6PSs,3255
+AeroViz/dataProcess/Chemistry/_mass_volume.py,sha256=oqFjRDYZ1om0_kG4g8XNi2QpUPcHsukpnWKydQoNEVg,5394
+AeroViz/dataProcess/Chemistry/_ocec.py,sha256=gqDTs9rOyr0RXdN1Nrxv6Vgvh04IFgHwk4gAJUgZZGc,5437
+AeroViz/dataProcess/Chemistry/_partition.py,sha256=tKhb6BJns46UiUlEq6Zq7ahYnvUJ_whY3tWE54C3bqU,1023
+AeroViz/dataProcess/Chemistry/_teom.py,sha256=IiM-TrifWpQLTbKllG-4k4c3mvQulfcmjswWu6muCXA,486
+AeroViz/dataProcess/Chemistry/isrpia.cnf,sha256=iWXTqsOZFmNrJxAI9nYuilZ9h6ru1icdPFVim7YKc_k,566
+AeroViz/dataProcess/Chemistry/isrpia2.exe,sha256=xFYPTXHSjl_-atmVcTmqqOkTZgUn1p8h-kFMcoGMIQw,1560032
+AeroViz/dataProcess/Optical/Angstrom_exponent.py,sha256=KSGM_hf2oUPsLoLuhYSRDK5zdekwce9KgqhzRnf2Y4g,706
+AeroViz/dataProcess/Optical/_IMPROVE.py,sha256=_u0uyKC9ZQpB4uLMx3x8Dm5hSUMcdGUifBcC2bGaM9c,1675
+AeroViz/dataProcess/Optical/__init__.py,sha256=h_IYhaum0DhK7Qw6lWFvjAEv7uAqLVVPEwU0V4hJnX4,1371
+AeroViz/dataProcess/Optical/_absorption.py,sha256=pYHIoj_R23wKvxR4acUqqU9JXKY40wgsFvZH78rETrY,1234
+AeroViz/dataProcess/Optical/_extinction.py,sha256=anUemSXmLvJi2CSxqTYgQCgUW4pSUqgZ0q0xZ4zs0zY,1189
+AeroViz/dataProcess/Optical/_mie.py,sha256=K_I8NqRStCdExRVxq2rX5hQdvYmfKuu9JCkNtL1OzfE,352
+AeroViz/dataProcess/Optical/_mie_sd.py,sha256=cbWSorfG-l92csaXsZJ7005f8ij2H_VZopIhNPCwx70,4812
+AeroViz/dataProcess/Optical/_scattering.py,sha256=w5xXXOfafV9a_dXY60YqTyzFDZppjBJeLcKl5PeCQe4,961
+AeroViz/dataProcess/Optical/fRH.pkl,sha256=PhJ-BYTaUDjl2Lp5Wz0zeiLQCzrsNdq8nP7Jd1BXyXE,4528
+AeroViz/dataProcess/SizeDistr/__init__.py,sha256=PJVAdb-v1q8h38JXIkpVcr6q4mg38V26sk4xD_2Mjlc,2186
+AeroViz/dataProcess/SizeDistr/__merge.py,sha256=A-ZmduUA9a0nVM8szhG1AWhsfUPu2UhGIaqFLcmg7Lk,9422
+AeroViz/dataProcess/SizeDistr/_merge.py,sha256=CyZwUc2M4lL-OE74e8mXq41nC6X0LJTAV8TwpO3fS2o,9176
+AeroViz/dataProcess/SizeDistr/_merge_v1.py,sha256=6Anb8DszoatK66tc9ccA6ZApbqtL7pZRPR5TKHj-Tbs,9526
+AeroViz/dataProcess/SizeDistr/_merge_v2.py,sha256=8OzUKw7hTg-yuQBipuFKgBS_7c7zbApN_BNr00G8q9c,9046
+AeroViz/dataProcess/SizeDistr/_merge_v3.py,sha256=HN2ARFmeWOawOWRPPv_pHEGBBZNgXVbH4dDTxcN7rdY,18749
+AeroViz/dataProcess/SizeDistr/_merge_v4.py,sha256=b8RVAievGIOLrmJHJXRsKXQ1tkMkm6rx43S7XAfeXE4,16228
+AeroViz/dataProcess/SizeDistr/_size_distr.py,sha256=o5fTwLH7j9j5129e3uciSJrOR8AGCN3tkAyGffoPENg,3127
+AeroViz/dataProcess/VOC/__init__.py,sha256=8GNP0RMymTkJXK18pSgfLHqrKPWboN-3x1_Ke4UrI44,259
+AeroViz/dataProcess/VOC/_potential_par.py,sha256=h3rVdvtBvC6xHa_ZG4Oq5eXezeSZtHNy6T6I40maIcM,3863
+AeroViz/dataProcess/VOC/support_voc.json,sha256=tMYp_NERqhSriVRE2NavXh33CQ5CnsbJHtmMFlE5q_E,6804
+AeroViz/dataProcess/core/__init__.py,sha256=FhGwqlP8ZwXZQS0LjH0YOz2g1Q2yJniUUhRZ_jDOQ6k,2707
+AeroViz/plot/__init__.py,sha256=BxoarxAeDHNdMHizS1bCTwV8NEuUCgeDB75GbSEsNWs,394
+AeroViz/plot/bar.py,sha256=cSPKJLWGifCzICCZVPcbZtrDrea_AStlwSli9-b-lsA,4246
+AeroViz/plot/box.py,sha256=8zDd8jYndSv5f0P1lFeX0m7VWYh9okYgJTClh2Lj7Dg,2115
+AeroViz/plot/pie.py,sha256=PVOqc_tAMlfjojTggP7HPL9Nk3ImigETo_EUFD6K2BY,7421
+AeroViz/plot/regression.py,sha256=mTCNrCAYvH7QjIb_5WlltCR1Kqwer1anpGEsxmO2S3o,7292
+AeroViz/plot/scatter.py,sha256=2Q_Um7Ai-pym2nUiMk6tY_zEXwbKE-BpkgrDkMyNbYA,6293
+AeroViz/plot/violin.py,sha256=pU2Z2yTWocEtImmCAmbtn0WvXtUOrnCGOdDOrLxjooU,2689
+AeroViz/plot/distribution/__init__.py,sha256=nhbIegWczkuEfWsE7-2jfF0dnpmPDzJJzjq8Fuh6q5k,28
+AeroViz/plot/distribution/distribution.py,sha256=sAjqtqKavFwQqI8PGPFnpvZFSU-w2UKjcTTC5L91f4E,20595
+AeroViz/plot/meteorology/__init__.py,sha256=hhGfQE3IUzS3Eaju_nO7LomPPHJnd-zAAZZweXOXs2M,27
+AeroViz/plot/meteorology/meteorology.py,sha256=h5KiaReatt238FXZyGjP9CAMkzTF1aVjOaFAGq3CKRY,11197
+AeroViz/plot/optical/__init__.py,sha256=5S2WPq8NouPYgc46c1XBveSL8Cxs3w8wNYN7vWIpB-s,23
+AeroViz/plot/optical/optical.py,sha256=xtuJuaonyM4OUS_BlkxKudLZKEteCS1u_-Svj3lQPco,13728
+AeroViz/plot/templates/__init__.py,sha256=VXp73SqrSF1WR9WYhHpHtbhvFcb1CR4JeV1tPQvCEEI,227
+AeroViz/plot/templates/ammonium_rich.py,sha256=a46rfwhSZ3LIj71LxdOnklAFyy6Xe_VQ-kh1komnZ5g,1225
+AeroViz/plot/templates/contour.py,sha256=fAM6Wn_EmENQM1IW6KJpwmLva6D9P2dEAaK6cNQBtdQ,1678
+AeroViz/plot/templates/corr_matrix.py,sha256=VeiwBwmg_v6LYslJvhSqweiLBheR3vGfPYxrtHoqJRI,3507
+AeroViz/plot/templates/diurnal_pattern.py,sha256=Vp8nDzSe95ppZBCDkFXnpUEh1cb-19yDS3H0qftoPaw,1434
+AeroViz/plot/templates/koschmieder.py,sha256=XmsYn8x9lu2BgN1FXKHb0quZdRw7Etv1dT5LBjBB0ok,3199
+AeroViz/plot/templates/metal_heatmap.py,sha256=ngqJFiOPCoExPKv-lHvgB1XCSr9fF_jSKmx4VwjUUXQ,4961
+AeroViz/plot/timeseries/__init__.py,sha256=LQ_aE32pvp5ouC--BRa0NwSJ48DYO3rFaOt4AKGmn_s,50
+AeroViz/plot/timeseries/template.py,sha256=E9dxaH_Y5QxnkIHK4VH59IVShnf4i1-TT_QE4NqVqrQ,1460
+AeroViz/plot/timeseries/timeseries.py,sha256=EitNnjleHj3Qu1PBHClWNi9kCgJ8tULGZSicS3xhoZw,14626
+AeroViz/plot/utils/__init__.py,sha256=sxp3nfUnyVIIXYd-F874gEHkhQiDnMPDE1nJ_Z98270,104
+AeroViz/plot/utils/_color.py,sha256=Vhjo-v4UWFME1JbbBR_Ro8FRj6dHB2O5Sud_9lpdu_U,2797
+AeroViz/plot/utils/_unit.py,sha256=Abum0WDnq08DzkSoxkKvBc0mYKo8izIDmgduPo9Q27A,1671
+AeroViz/plot/utils/fRH.json,sha256=t-2ux4TLOYAB-4jJ72LSM4jv1jk9XkaxKYNMDepMHIg,6038
+AeroViz/plot/utils/plt_utils.py,sha256=7Au3r2-7AZQmzrO2OfcyTFomJRLHgu1Npb7wxQqUvzY,3438
+AeroViz/plot/utils/sklearn_utils.py,sha256=hKFfkVkYLRxkIDKvO9COHXwhjD_UWqQigdT3mDToni4,2098
+AeroViz/plot/utils/units.json,sha256=JKcqvLA6dkc8REV_NhX85Jl9LA4iAZxzw9RJp6JTla0,2965
+AeroViz/process/__init__.py,sha256=vqXO0vhowU9yNW5tnVYNg3ceBxLt96PgBNkZ2KUxKXw,1309
+AeroViz/process/core/DataProc.py,sha256=6MBDcHyQmVU16Z0oDo0GItvhU5f7fWLXFMGqUyoW1eQ,419
+AeroViz/process/core/SizeDist.py,sha256=V6CpxTRfWjsZ8GwIEOqyKJ8_qcz7dO0ZmfHQvR6SgW4,2097
+AeroViz/process/core/__init__.py,sha256=WmVSFDx97urX0WPA8dtRVoQF04IDaU-IgxHK979-kM8,98
+AeroViz/process/method/PyMieScatt_update.py,sha256=g3vlzATjzYSYZd3LwmwxEmdkpo4cHJ3KY4rePY4jwZk,21065
+AeroViz/process/method/__init__.py,sha256=_yxoNAbbI82ORhrVsi-6x8vPnWQNHavjZUXy-ioZ2wg,123
+AeroViz/process/method/mie_theory.py,sha256=EC3SsUaq5G3SdQyPMQxcosbEokqAgJw-4Gz6moJiOsk,8666
+AeroViz/process/method/prop.py,sha256=7f18SOkkLgDiY_g1c1We8g-3WDJJIFcxkfR4F99jUgc,1845
+AeroViz/process/script/AbstractDistCalc.py,sha256=wXF7OA634m_i-Y79lU4THj0c0yZx5NUtLNvORH1FWZg,5351
+AeroViz/process/script/Chemical.py,sha256=jjBIdILe0fO5Rqidb4pg3CP6qmMLqFvst-ZSz8mbb7Q,6413
+AeroViz/process/script/IMPACT.py,sha256=Zz1GRQLJopNQGw5qUTdWl7Zxy_CBnFBsL1B-CCemaDQ,1520
+AeroViz/process/script/IMPROVE.py,sha256=5FNl33S_785J7CsSue_CvZP58TWevpwGr2ePQM6qScw,5709
+AeroViz/process/script/Others.py,sha256=TOtSKVZ9Z-zX1LFfE4p36H0hMjfmyyQw_Xaeq8HgMBk,2325
+AeroViz/process/script/PSD.py,sha256=unSvyHp1RqgQecY-Lab-wRFGP2u45blSO4NCNTaxcRQ,3721
+AeroViz/process/script/PSD_dry.py,sha256=P9rSQVA78jHXrY2bDiC1iQvG0w9Js8QiBNfooPOXzfY,3269
+AeroViz/process/script/__init__.py,sha256=QExUHHK79oiwZXvk8u00P8rLwWhGOc1fpZY2Fx8Vkxg,188
+AeroViz/process/script/retrieve_RI.py,sha256=9OQJU1w6VzVqKz00e9GdWswRAnaETe_1meAHp5N_s54,2711
+AeroViz/rawDataReader/__init__.py,sha256=kouHFAxpbl1Xj4IBHqzNaUExuxi0vF6E59l8Oryktq8,3949
+AeroViz/rawDataReader/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+AeroViz/rawDataReader/config/supported_instruments.py,sha256=6pkjRqe4Kz5023N_C3OQhX3u9PtfCpeUWhIA25Y9T7Q,4273
+AeroViz/rawDataReader/core/__init__.py,sha256=oBxig1HXb2QmWAdPwEKXx8L_85LPX8CPbBc0eYR9C5A,10744
+AeroViz/rawDataReader/script/AE33.py,sha256=Nv0u0w_V50sDjsLh17ZkNT6A75TjIo2A1O6GYc4zkJg,1107
+AeroViz/rawDataReader/script/AE43.py,sha256=Qq9MdiBKzDuKIEFPanmn7wUbkN5VeSTG6Dopw8i0W90,1056
+AeroViz/rawDataReader/script/APS_3321.py,sha256=bzE-GaElXU16xmOgYr6tR62GAtgRZxYqRrifbBRuU-0,1694
+AeroViz/rawDataReader/script/Aurora.py,sha256=b0XPs2gc_2UJj4HnOHwW7o255zsCPp459goaDqeAJA8,1387
+AeroViz/rawDataReader/script/BC1054.py,sha256=QGU1SRDoE8e4yNXUX7RsdK5zh72fNd2Q0IpUy7iFzrg,1486
+AeroViz/rawDataReader/script/EPA_vertical.py,sha256=MpcbOzbigivsuldCxzn_B6POtQMzahGQhM_sWRDVP9s,1669
+AeroViz/rawDataReader/script/GRIMM.py,sha256=s2z3aNfpPOd_07Zl8jbHa7CxsR2EjrtoZw_HRjR5ykc,946
+AeroViz/rawDataReader/script/IGAC.py,sha256=BDhmsNy02EvLY0sd75NM6XvLGVTEJlxyQQbprhdFQmU,2948
+AeroViz/rawDataReader/script/MA350.py,sha256=YRY19R2V6nyHMpGMOLVZvK8_41OCCzdTcSnuZR-OJsU,1287
+AeroViz/rawDataReader/script/Minion.py,sha256=c128ZkkxakV6wq1k9NtEq0scdi1mh9Mn0jhQFqz_uVE,3940
+AeroViz/rawDataReader/script/NEPH.py,sha256=OSDtbJ4sujtnf3bzbENXoyJwA-RIeOkPXNCEJ6MvkPQ,2735
+AeroViz/rawDataReader/script/SMPS_TH.py,sha256=4bK8Fm4oyPZd3GegcOttjamZf2ZqcL_uaKUXdNtv8_0,1468
+AeroViz/rawDataReader/script/SMPS_aim11.py,sha256=lop0YmOOWde9vBKMXV3nqwqZOxR-OCbYZznSf4QWuGs,1632
+AeroViz/rawDataReader/script/SMPS_genr.py,sha256=rR5OO63ozDKMcGBfNFPi_f49gUbx2qYx60GMSgC9jwg,1609
+AeroViz/rawDataReader/script/Sunset_OCEC.py,sha256=6TyosCQ4N6jB9yZOfAJHwiIvkTYCwCThmMbhe4_U9a0,2322
+AeroViz/rawDataReader/script/TEOM.py,sha256=Hx_DDnvGSfSl9cgIVmuf4VmphaFfNCY60mqPWoLmNvw,1796
+AeroViz/rawDataReader/script/Table.py,sha256=othBoQSFVcjfWX0_Q4y8BkjCBc5CihvC6LyrhyJWywk,800
+AeroViz/rawDataReader/script/VOC.py,sha256=JaMDojHrLJL37LdcNzI7xEGy_592feokJw9kedcwL20,1273
+AeroViz/rawDataReader/script/__init__.py,sha256=UndjtWjvJHMma7WtArL5sF9UHiQsanx5sT2otQDqzng,270
+AeroViz/tools/__init__.py,sha256=tPUmCI9Fi1LgE-QSVnzan5jRdYQBIENH9PRDXB_DhTw,109
+AeroViz/tools/database.py,sha256=05VzjJyhlRrhsZdhfFQ__7CxGm4MdFekLjz3_Is5h9U,3430
+AeroViz/tools/dataclassifier.py,sha256=_wpv0PlZ5EGkcNqHxfFtdEsYvHP5FVE8sMZXikhm_YE,4492
+AeroViz/tools/dataprinter.py,sha256=Jq2Yztpa9YCOeLDVTrRs7PhSdNIPhEAexVj1YSuJ7hY,2249
+AeroViz/tools/datareader.py,sha256=iTQ0U8hdNMjCdbiH7EiKW10UEoxzxXRHc4s5_1IikJo,1933
+AeroViz-0.1.5.dist-info/LICENSE,sha256=E-679GpGGkp3irmtuJXiT7R4cNUA4cmsH6Q7QUgPf5U,1069
+AeroViz-0.1.5.dist-info/METADATA,sha256=dWKrlnoRNBUgRf5R1VvNVcurimM8slO9RMiSeEw6Stk,5323
+AeroViz-0.1.5.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+AeroViz-0.1.5.dist-info/top_level.txt,sha256=BYsmTst_o4FZOKRP1XIvIMlN6mMTTXNfnSToL2_nVbQ,8
+AeroViz-0.1.5.dist-info/RECORD,,

AeroViz/rawDataReader/script/IGAC_TH.py

@@ -1,104 +0,0 @@
-# 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/OCEC_LCRES.py

@@ -1,34 +0,0 @@
-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

@@ -1,28 +0,0 @@
-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/VOC_TH.py

@@ -1,30 +0,0 @@
-# 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

@@ -1,37 +0,0 @@
-# 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