def insertAMTCruiseTraj():
server = 'Rainier'
tableName = 'tblCruise_Trajectory'
usecols = ['Cruise_name', 'time', 'lat', 'lon']
rawFilePath = cfgv.rep_AMT_cruises_raw + 'amt/'
rawFileName = 'master_AMT.csv'
path = rawFilePath + rawFileName
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
os.chdir(rawFilePath)
df = pd.read_csv(rawFilePath + rawFileName, sep=',', usecols=usecols)
for Cruise_name in df['Cruise_name'].unique():
export_path = '%s%s.csv' % (exportBase, Cruise_name)
print(Cruise_name)
cruise_df = df[df['Cruise_name'] ==
Cruise_name] #selects only df of cruise
Cruise_ID = iF.findID_CRUISE(Cruise_name[0:3] + Cruise_name[-2:])
cruise_df['Cruise_ID'] = Cruise_ID
cruise_df = ip.removeMissings(['time', 'lat', 'lon'], cruise_df)
cruise_df = ip.convertYYYYMMDD(cruise_df)
cruise_df = ip.NaNtoNone(cruise_df)
cruise_df = ip.colDatatypes(cruise_df)
cruise_df = ip.convertYYYYMMDD(cruise_df)
cruise_df = ip.removeDuplicates(cruise_df)
cruise_df = cruise_df[['Cruise_ID', 'time', 'lat', 'lon']]
cruise_df.to_csv(export_path, index=False)
ip.sortByTimeLatLon(cruise_df, export_path, 'time', 'lat', 'lon')
print('export path: ', Cruise_name + export_path)
iF.toSQLbcp(export_path, tableName, server)
def insertSeaFlowCruiseTraj():
server = 'Rainier'
tableName = 'tblCruise_Trajectory'
rawFilePath = cfgv.rep_allSeaFlowCruises_raw
os.chdir(rawFilePath)
sfl_cruise_list = glob.glob('*.sfl*')
usecols_sfl = ['DATE', 'LAT', 'LON']
for cruise in sfl_cruise_list:
prefix = cruise[:-8] + '_traj'
rawFileName = cruise
path = rawFilePath + rawFileName
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
export_path = '%s%s.csv' % (exportBase, prefix)
print(cruise)
Cruise_ID = iF.findID_CRUISE(cruise[:-8])
df = pd.read_csv(cruise, sep='\t', usecols=usecols_sfl)
df['DATE'] = pd.to_datetime(df['DATE'], format='%Y-%m-%dT%H:%M:%S')
df['Cruise_ID'] = Cruise_ID
df.rename(columns={
'DATE': 'time',
'LAT': 'lat',
'LON': 'lon'
},
inplace=True)
df = df[['Cruise_ID', 'time', 'lat', 'lon']]
df = ip.removeMissings(['time', 'lat', 'lon'], df)
df = ip.NaNtoNone(df)
df = ip.colDatatypes(df)
df = ip.convertYYYYMMDD(df)
df = ip.removeDuplicates(df)
df.to_csv(export_path, index=False)
ip.sortByTimeLatLon(df, export_path, 'time', 'lat', 'lon')
print('export path: ', export_path)
# print(export_path,tableName)
iF.toSQLbcp(export_path, tableName, server)
def makeHL2A_diel_metagenomics(rawFilePath, rawFileName, tableName):
path = rawFilePath + rawFileName
prefix = tableName
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
export_path = '%s%s.csv' % (exportBase, prefix)
df = pd.read_excel(path, sep=',',sheet_name='data', usecols=usecols)
df = ip.removeMissings(['time','lat', 'lon','depth'], df)
df = ip.NaNtoNone(df)
df = ip.colDatatypes(df)
df = ip.addIDcol(df)
df = ip.removeDuplicates(df)
df.to_csv(export_path, index=False)
ip.sortByTimeLatLonDepth(df, export_path, 'time', 'lat', 'lon', 'depth')
print('export path: ' ,export_path)
return export_path
def makeMesoscope_km1709(rawFilePath, rawFileName, tableName):
path = rawFilePath + rawFileName
prefix = tableName
df = pd.read_excel(path, 'data')
df = ip.removeMissings(['time', 'lat', 'lon', 'depth'], df)
df = ip.colDatatypes(df)
df['time'] = pd.to_datetime(df['time'], format='%Y-%m-%d')
df['ID'] = None
df = ip.removeDuplicates(df)
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
export_path = '%s%s.csv' % (exportBase, prefix)
df.to_csv(export_path, index=False)
ip.sortByTimeLatLonDepth(df, export_path, 'time', 'lat', 'lon', 'depth')
df.to_csv(export_path, index=False)
print('export path: ', export_path)
return export_path
def makeSingleCellGenomes_Chisholm(rawFilePath, rawFileName, tableName):
path = rawFilePath + rawFileName
prefix = tableName
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
export_path = '%s%s.csv' % (exportBase, prefix)
df = pd.read_excel(path, 'data')
df = ip.removeMissings(['time', 'lat', 'lon', 'depth'], df)
df = ip.NaNtoNone(df)
df = ip.colDatatypes(df)
df = ip.convertYYYYMMDD(df)
df = ip.addIDcol(df)
df = ip.removeDuplicates(df)
df.to_csv(export_path, index=False)
ip.sortByTimeLatLonDepth(df, export_path, 'time', 'lat', 'lon', 'depth')
df.to_csv(export_path, index=False)
print('export path: ', export_path)
return export_path
def makeFlombaum(rawFilePath, rawFileName, tableName):
path = rawFilePath + rawFileName
prefix = tableName
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
export_path = '%s%s.csv' % (exportBase, prefix)
df = pd.read_excel(path, sep=',', sheet_name='data')
df = ip.removeMissings(['time', 'lat', 'lon', 'depth'], df)
df = ip.NaNtoNone(df)
df = ip.colDatatypes(df)
df = ip.convertYYYYMMDD(df)
df = ip.addIDcol(df)
df = ip.removeDuplicates(df)
df['lon'] = df['lon'].abs()
df.to_csv(export_path, index=False)
ip.mapTo180180(export_path, 'lon')
ip.sortByTimeLatLonDepth(df, export_path, 'time', 'lat', 'lon', 'depth')
print('export path: ', export_path)
return export_path
def insertSeaFlowCruiseSalinity():
server = 'Rainier'
tableName = 'tblCruise_Salinity'
rawFilePath = cfgv.rep_allSeaFlowCruises_raw
os.chdir(rawFilePath)
sfl_cruise_list = glob.glob('*.sfl*')
usecols_sfl = ['DATE', 'LAT', 'LON', 'SALINITY']
for cruise in sfl_cruise_list:
prefix = cruise[:-8] + '_temp'
rawFileName = cruise
path = rawFilePath + rawFileName
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
export_path = '%s%s.csv' % (exportBase, prefix)
print(cruise)
Cruise_ID = iF.findID_CRUISE(cruise[:-8])
df = pd.read_csv(cruise, sep='\t', usecols=usecols_sfl)
df['DATE'] = pd.to_datetime(df['DATE'], format='%Y-%m-%dT%H:%M:%S')
df['DEPTH'] = 5.0
df['Cruise_ID'] = Cruise_ID
df.rename(columns={
'DATE': 'time',
'LAT': 'lat',
'LON': 'lon',
'DEPTH': 'depth',
'SALINITY': 'salinity'
},
inplace=True)
df = df[['Cruise_ID', 'time', 'lat', 'lon', 'depth', 'salinity']]
df = ip.removeMissings(['time', 'lat', 'lon', 'depth'], df)
df = df[pd.to_numeric(df['salinity'], errors='coerce').notnull()]
df = ip.NaNtoNone(df)
df = ip.colDatatypes(df)
df = ip.convertYYYYMMDD(df)
df = ip.removeDuplicates(df)
print(df.head())
if df.empty:
print(cruise +
' had no salinity values. Not inserted into database')
else:
df.to_csv(export_path, index=False)
ip.sortByTimeLatLon(df, export_path, 'time', 'lat', 'lon')
print('export path: ', export_path)
# print(export_path,tableName)
iF.toSQLbcp(export_path, tableName, server)
def insertAMTCruiseTemperature():
server = 'Rainier'
tableName = 'tblCruise_Temperature'
usecols = ['Cruise_name', 'time', 'lat', 'lon', 'temp', 'temp_flag']
rawFilePath = cfgv.rep_AMT_cruises_raw + 'amt/'
rawFileName = 'master_AMT.csv'
path = rawFilePath + rawFileName
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
os.chdir(rawFilePath)
df = pd.read_csv(rawFilePath + rawFileName, sep=',', usecols=usecols)
for Cruise_name in df['Cruise_name'].unique():
export_path = '%s%s%s.csv' % (exportBase, Cruise_name, tableName)
print(Cruise_name)
cruise_df = df[df['Cruise_name'] ==
Cruise_name] #selects only df of cruise
Cruise_ID = iF.findID_CRUISE(Cruise_name[0:3] + Cruise_name[-2:])
cruise_df['Cruise_ID'] = Cruise_ID
cruise_df = cruise_df[(cruise_df['temp_flag'] != 'N')
& (cruise_df['temp_flag'] != 'S') &
(cruise_df['temp_flag'] != 'M') &
(cruise_df['temp_flag'] != 'L')]
cruise_df = ip.removeMissings(['time', 'lat', 'lon'], cruise_df)
cruise_df = ip.convertYYYYMMDD(cruise_df)
cruise_df = ip.colDatatypes(cruise_df)
cruise_df = ip.convertYYYYMMDD(cruise_df)
cruise_df = ip.removeDuplicates(cruise_df)
cruise_df = ip.renameCol(cruise_df, 'temp', 'temperature')
cruise_df = cruise_df[[
'Cruise_ID', 'time', 'lat', 'lon', 'temperature'
]]
cruise_df = cruise_df.dropna(subset=['temperature'])
cruise_df = ip.NaNtoNone(cruise_df)
if cruise_df.empty:
print(Cruise_name +
' had no temperature values. Not inserted into database')
else:
cruise_df.to_csv(export_path, index=False)
ip.sortByTimeLatLon(cruise_df, export_path, 'time', 'lat', 'lon')
print('export path: ', export_path)
iF.toSQLbcp(export_path, tableName, server)
def makeGlobal_PicoPhytoPlankton(rawFilePath, rawFileName, tableName):
path = rawFilePath + rawFileName
prefix = tableName
exportBase = cfgv.opedia_proj + 'db/dbInsert/export/'
export_path = '%s%s.csv' % (exportBase, prefix)
df = pd.read_excel(path, sep=',', sheet_name='data', usecols=usecols)
df['year'] = df['year'].astype('str')
df['month'] = ((df['month'].astype('str')).apply(lambda x: x.zfill(2)))
df['day'] = ((df['day'].astype('str')).apply(lambda x: x.zfill(2)))
print(len(df))
df = df[(df['day'] != '-9') & (df['day'] != '-1')]
df['year'] = df['year'].replace('10', '2010')
df['year'] = df['year'].replace('11', '2011')
df['year'] = df['year'].replace('6', '2006')
# df = df[(df['year'] != '10') & (df['year'] != '11')& (df['year'] != '6')]
df['time'] = pd.to_datetime(df[['year', 'month', 'day']], format='%Y%m%d')
ip.renameCol(df, 'Lat', 'lat')
ip.renameCol(df, 'Long', 'lon')
ip.renameCol(df, 'Depth', 'depth')
ip.renameCol(df, 'PromL', 'prochlorococcus_abundance')
ip.renameCol(df, 'SynmL', 'synechococcus_abundance')
ip.renameCol(df, 'PEukmL', 'picoeukaryote_abundance')
ip.renameCol(df, 'pico_abund', 'picophytoplankton_abundance')
ip.renameCol(df, 'picophyto [ug C/L]', 'picophytoplankton_biomass')
ip.removeColumn(['year', 'day', 'month'], df)
df = ip.reorderCol(df, [
'time', 'lat', 'lon', 'depth', 'prochlorococcus_abundance',
'synechococcus_abundance', 'picoeukaryote_abundance',
'picophytoplankton_abundance', 'picophytoplankton_biomass'
])
df = ip.removeMissings(['time', 'lat', 'lon', 'depth'], df)
df = ip.NaNtoNone(df)
df = ip.colDatatypes(df)
df = ip.addIDcol(df)
df = ip.removeDuplicates(df)
df.to_csv(export_path, index=False)
ip.sortByTimeLatLonDepth(df, export_path, 'time', 'lat', 'lon', 'depth')
print('export path: ', export_path)
return export_path
