def Output_files(New_combined, myBaseforResults, Site_ID, versionID):
New_combined_grouped = New_combined.groupby([lambda x: x.year])
for year_index in New_combined_grouped:
print year_index[0]
print "Starting output for EddyProc MPI online tool"
#Check for place to put results - does it exist? If not create
if not os.path.isdir(myBaseforResults):
os.mkdir(myBaseforResults)
#Then subdirectories
if not os.path.isdir(myBaseforResults + "/REddyProc"):
os.mkdir(myBaseforResults + "/REddyProc")
mypathforResults = myBaseforResults + "/REddyProc/"
#Calculate RH_con
New_combined['RH_Con'] = metfuncs.RHfromabsolutehumidity(
New_combined['Ah_Con'], New_combined['Ta_Con'])
#Convert VPD in kPa to hPa.
#We need to update VPD for input here so also need e and es
# Calculate vapour pressure from absolute humidity and temperature
# Ah - absolute humidity, g/m3
# Ta - air temperature, C
New_combined['VPD_hPa_Con'] = (metfuncs.es(
New_combined['Ta_Con'])) - (metfuncs.vapourpressure(
New_combined['Ah_Con'], New_combined['Ta_Con'])) / 10
REddyProc_DF = New_combined[[
'Fc', 'Fe', 'Fh', 'Fg', 'Ta_Con', 'Ts_Con', 'RH_Con',
'VPD_hPa_Con', 'ustar'
]]
#The date/time components are separated into columns. E.g. first column: julian day, second column: decimal hour.
#Possible date formats are indicated in the input form. Never use an hour of 24 with the time
#format 'year', 'month', 'day', 'hour', 'minute' (use 0 instead). Hour '0' is interpreted as first hour of the day,
#i.e. when you have transition from one to another it must be like (day, 23 --> day+1, 0) not like (day, 23 --> day, 0),
#because then the data set is not chronological (this misunderstanding happened before).
#REddyProc_DF['DT1','DT2','DT3','DT4','DT5','DT5']=REddyProc_DF.index.timetuple()
REddyProc_DF['DTcopy'] = REddyProc_DF.index
REddyProc_DF['Day'] = REddyProc_DF['DTcopy'].apply(
lambda x: int(x.strftime('%j')))
REddyProc_DF['Year'] = REddyProc_DF['DTcopy'].apply(
lambda x: int(x.strftime('%Y')))
REddyProc_DF['Hour'] = REddyProc_DF['DTcopy'].apply(
lambda x: float(x.strftime('%H')) + (float(x.strftime('%M')) / 60))
#Select current year of yaer only
REddyProc_DF = REddyProc_DF[REddyProc_DF['Year'] == year_index[0]]
#Calculate some things for plots
n_datapoints = len(REddyProc_DF)
startdate = REddyProc_DF.index[0]
enddate = REddyProc_DF.index[n_datapoints - 1]
print n_datapoints, startdate, enddate
header_names = [
'Year', 'Day', 'Hour', 'NEE', 'LE', 'H', 'Rg', 'Tair', 'Tsoil',
'rH', 'VPD', 'Ustar'
]
columns_out = [
'Year', 'Day', 'Hour', 'Fc', 'Fe', 'Fh', 'Fg', 'Ta_Con', 'Ts_Con',
'RH_Con', 'VPD_hPa_Con', 'ustar'
]
newline1 = 'Year \t DoY \t Hour \t NEE \t LE \t H \t Rg \t Tair \t Tsoil \t rH \t VPD \t Ustar'
newline2 = " -- \t -- \t -- \t umolm-2s-1 \t Wm-2 \t Wm-2 \t Wm-2 \t degC \t degC \t % \t hPa \t ms-1"
#newline1='Year,Day,Hour,NEE,LE,H,Rg,Tair,Tsoil,rH,VPD,Ustar'
#newline2="--,--,--,umolm-2s-1,Wm-2,Wm-2,Wm-2,degC,degC,%,hPa,ms-1"
output_temp_filename = mypathforResults + '/REddyProc_temp_' + Site_ID + '_' + str(
year_index[0]) + '_' + versionID + '.txt'
output_filename = mypathforResults + '/REddyProc_' + Site_ID + '_' + str(
year_index[0]) + '_' + versionID + '.txt'
REddyProc_DF.to_csv(output_temp_filename,
sep='\t',
na_rep='-9999',
float_format='%.3f',
cols=columns_out,
header=False,
index=False,
index_label=None,
mode='w')
#Now add another line with units
#Open txt file
with open(output_temp_filename) as infile:
with open(output_filename, "w") as outfile:
outfile.write(newline1 + "\n")
outfile.write(newline2 + "\n")
for i, line in enumerate(infile):
outfile.write(line)
os.remove(output_temp_filename)
#####################
# Finish up
######################
print "FINISHED writing out files for use in EddyProc MPI online tool "
flag = numpy.zeros(len(Ta_erai_tts), dtype=numpy.int32)
attr = qcutils.MakeAttributeDictionary(long_name="Air temperature",
units="C")
qcutils.CreateSeries(ds_erai, "Ta", Ta_erai_tts, Flag=flag, Attr=attr)
# Interpolate the 3 hourly dew point temperature to the tower time step
# and convert to Ah, RH and q
# NOTE: ERA-I variables are dimensioned [time,latitude,longitude]
Td_3d = erai_file.variables["d2m"][:, :, :]
Td_erai_3hr = Td_3d[:, site_lat_index, site_lon_index] - 273.15
# get the spline interpolation function
s = InterpolatedUnivariateSpline(erai_time_3hr, Td_erai_3hr, k=1)
# get the dew point temperature at the towespeedr time step
Td_erai_tts = s(erai_time_tts)
# get the relative humidity
es_erai_tts = mf.es(Ta_erai_tts)
e_erai_tts = mf.es(Td_erai_tts)
VPD_erai_tts = es_erai_tts - e_erai_tts
flag = numpy.zeros(len(VPD_erai_tts), dtype=numpy.int32)
attr = qcutils.MakeAttributeDictionary(
long_name="Vapour pressure deficit", units="kPa")
qcutils.CreateSeries(ds_erai,
"VPD",
VPD_erai_tts,
Flag=flag,
Attr=attr)
RH_erai_tts = float(100) * e_erai_tts / es_erai_tts
flag = numpy.zeros(len(RH_erai_tts), dtype=numpy.int32)
attr = qcutils.MakeAttributeDictionary(long_name="Relative humidity",
units="percent")
qcutils.CreateSeries(ds_erai, "RH", RH_erai_tts, Flag=flag, Attr=attr)
def Output_files(New_combined,myBaseforResults,Site_ID,versionID,Ws_variable_name):
#Do any calculations on the whole datasewt before grouping
#Calculate RH_con
New_combined['RH_Con']=metfuncs.RHfromabsolutehumidity(New_combined['Ah_Con'],New_combined['Ta_Con'])
#Convert VPD in kPa to hPa.
#We need to update VPD for input here so also need e and es
# Calculate vapour pressure from absolute humidity and temperature
# Ah - absolute humidity, g/m3
# Ta - air temperature, C
New_combined['VPD_kPa_Con']=(metfuncs.es(New_combined['Ta_Con']))-(metfuncs.vapourpressure(New_combined['Ah_Con'],New_combined['Ta_Con']))
#Do timestamp operations
#Make a copy of timestamp to the df
#Take mean first (equal to mid day) then convert to DOY, day, month and year
New_combined['DTcopy']=New_combined.index
New_combined['Year']=New_combined['DTcopy'].apply(lambda x: int(x.strftime('%Y')))
#Group DF by year
New_combined_grouped=New_combined.groupby([lambda x: x.year])
for year_index in New_combined_grouped:
print year_index[0]
print "Starting output for NASA"
#Check for place to put results - does it exist? If not create
if not os.path.isdir(myBaseforResults):
os.mkdir(myBaseforResults)
#Then subdirectories
if not os.path.isdir(myBaseforResults+"/NASA_out"):
os.mkdir(myBaseforResults+"/NASA_out")
mypathforResults=myBaseforResults+"/NASA_out/"
#Subset the DF to make it easier
#WD removed here as its not required for NASA and for some sites SD variable names are not standard
if Ws_variable_name=="Ws_CSAT":
REddyProc_DF=New_combined[['DTcopy','Year','Ah_Con','Cc','eta','Fa','Fc_ustar','GPP_Con','Fre_Con','Fe_Con','Fg_Con','Fh_Con','Fld_Con','Flu_Con','Fm','Fn_Con','Fsd_Con','Fsu_Con','ps_Con','Precip_Con','Sws_Con','Ta_Con','Ts_Con','ustar','Ws_CSAT_Con','RH_Con','VPD_kPa_Con','Ah_Con_QCFlag','Fc_Con_QCFlag','Fe_Con_QCFlag','Fg_Con_QCFlag','Fh_Con_QCFlag','Fld_Con_QCFlag','Flu_Con_QCFlag','Fn_Con_QCFlag','Fsd_Con_QCFlag','Fsu_Con_QCFlag','ps_Con_QCFlag','Precip_Con_QCFlag','Sws_Con_QCFlag','Ta_Con_QCFlag','Ts_Con_QCFlag']]
else:
REddyProc_DF=New_combined[['DTcopy','Year','Ah_Con','Cc','eta','Fa','Fc_ustar','GPP_Con','Fre_Con','Fe_Con','Fg_Con','Fh_Con','Fld_Con','Flu_Con','Fm','Fn_Con','Fsd_Con','Fsu_Con','ps_Con','Precip_Con','Sws_Con','Ta_Con','Ts_Con','ustar','Ws_Con','RH_Con','VPD_kPa_Con','Ah_Con_QCFlag','Fc_Con_QCFlag','Fe_Con_QCFlag','Fg_Con_QCFlag','Fh_Con_QCFlag','Fld_Con_QCFlag','Flu_Con_QCFlag','Fn_Con_QCFlag','Fsd_Con_QCFlag','Fsu_Con_QCFlag','ps_Con_QCFlag','Precip_Con_QCFlag','Sws_Con_QCFlag','Ta_Con_QCFlag','Ts_Con_QCFlag']]
#Select current year of yaer only
REddyProc_DF=REddyProc_DF[REddyProc_DF['Year']==year_index[0]]
#Calculate some things for plots
n_datapoints=len(REddyProc_DF)
startdate= REddyProc_DF.index[0]
enddate= REddyProc_DF.index[n_datapoints-1]
print n_datapoints,startdate,enddate
#Calculate the DAILY means/sums from the half hourly data
tempDF_mean=REddyProc_DF.groupby(lambda x : x.dayofyear).mean().add_suffix('_mean')
tempDF_sum=REddyProc_DF.groupby(lambda x : x.dayofyear).sum().add_suffix('_sum')
tempDF=tempDF_mean.join(tempDF_sum,how='left')
#Add QC counts to the means DF
#Good QC value not gap filled is 1. Get sall values ==1 then do a count. Divide by 48 for 48 half hour periods in the day
tempDF['Rn_qc']=REddyProc_DF['Fn_Con_QCFlag'][REddyProc_DF['Fn_Con_QCFlag']==1.].groupby(lambda x : x.dayofyear).count()/48
tempDF['Rn_qc'].fillna(value=0,inplace=True)
tempDF['Rs_qc']=REddyProc_DF['Fsd_Con_QCFlag'][REddyProc_DF['Fsd_Con_QCFlag']==1.].groupby(lambda x : x.dayofyear).count()/48
tempDF['Rs_qc'].fillna(value=0,inplace=True)
tempDF['Ta_qc']=REddyProc_DF['Ta_Con_QCFlag'][REddyProc_DF['Ta_Con_QCFlag']==1.].groupby(lambda x : x.dayofyear).count()/48
tempDF['Ta_qc'].fillna(value=0,inplace=True)
tempDF['VPD_qc']=REddyProc_DF['Ah_Con_QCFlag'][REddyProc_DF['Ah_Con_QCFlag']==1.].groupby(lambda x : x.dayofyear).count()/48
tempDF['VPD_qc'].fillna(value=0,inplace=True)
tempDF['Ts_qc']=REddyProc_DF['Ts_Con_QCFlag'][REddyProc_DF['Ts_Con_QCFlag']==1.].groupby(lambda x : x.dayofyear).count()/48
tempDF['Ts_qc'].fillna(value=0,inplace=True)
tempDF['NEE_qc']=REddyProc_DF['Fc_Con_QCFlag'][REddyProc_DF['Fc_Con_QCFlag']==1.].groupby(lambda x : x.dayofyear).count()/48
tempDF['NEE_qc'].fillna(value=0,inplace=True)
tempDF['GPP_qc']=REddyProc_DF['Fc_Con_QCFlag'][REddyProc_DF['Fc_Con_QCFlag']==1.].groupby(lambda x : x.dayofyear).count()/48
tempDF['GPP_qc'].fillna(value=0,inplace=True)
tempDF['Reco_qc']=REddyProc_DF['Fc_Con_QCFlag'][REddyProc_DF['Fc_Con_QCFlag']==1.].groupby(lambda x : x.dayofyear).count()/48
tempDF['Reco_qc'].fillna(value=0,inplace=True)
#add a site lable to columns
tempDF['Site_ID']=Site_ID
tempDF['DTmean']=REddyProc_DF['DTcopy'].groupby(lambda x : x.dayofyear).min()
tempDF['Day']=tempDF['DTmean'].apply(lambda x: int(x.strftime('%d')))
tempDF['Month']=tempDF['DTmean'].apply(lambda x: int(x.strftime('%m')))
tempDF['Year']=tempDF['DTmean'].apply(lambda x: int(x.strftime('%Y')))
# Jan the 1st is day 1
#tempDF['DOY'] = (tempDF['DTmean'] - dt.datetime(year_index[0], 1, 1))
tempDF['DOY'] = tempDF['DTmean'].apply(lambda x: int(x.strftime('%j')))
#Do conversions for Carbon variables (convert from umol to g C for NASA)
tempDF['Fc_ustar_mean']=tempDF['Fc_ustar_mean']*60*60*24/1000000*12
tempDF['GPP_Con_mean']=tempDF['GPP_Con_mean']*60*60*24/1000000*12
tempDF['Fre_Con_mean']=tempDF['Fre_Con_mean']*60*60*24/1000000*12
#Do conversions for Radiation variables (convert Wm-2 to MJ m-2 day-1)
tempDF['Fsd_Con_mean']=tempDF['Fsd_Con_mean']*60*60*24/1000000
tempDF['Fn_Con_mean']=tempDF['Fn_Con_mean'] *60*60*24/1000000
newline2="ID, Year, Mo, Day, DOY, Rn_f, Rn_qc, Rs_f, Rs_qc, Ta, Ta_qc, VPD, VPD_qc, Ts_f, Ts_qc, PREC, SWC, NEE, NEE_qc, GPP, GPP_qc, Reco, Reco_qc, PRESS, SNOWD"
newline3="-, -, -, -, -, MJ m-2 day-1, -, MJ m-2 day-1, -, oC, -, kPa, -, oC, -, mm day-1, m3/m3, gC m-2 day-1, -, gC m-2 day-1, -, gC m-2 day-1, -, MPa day-1, mm"
columns_out = ['Site_ID','Year','Month','Day','DOY', 'Fn_Con_mean','Rn_qc','Fsd_Con_mean','Rs_qc', 'Ta_Con_mean', 'Ta_qc', 'VPD_kPa_Con_mean', 'VPD_qc', 'Ts_Con_mean', 'Ts_qc', 'Precip_Con_sum', 'Sws_Con_mean', 'Fc_ustar_mean', 'NEE_qc', 'GPP_Con_mean', 'GPP_qc','Fre_Con_mean', 'Reco_qc', 'ps_Con_mean']
output_temp_filename=mypathforResults+'/NASA_SMAP_temp_'+Site_ID+'_'+str(year_index[0])+'_'+versionID +'.csv'
output_filename=mypathforResults+'/NASA_SMAP_'+Site_ID+'_'+str(year_index[0])+'_'+versionID +'.csv'
tempDF[columns_out].to_csv(output_temp_filename, na_rep='-9999', float_format='%.3f', header=False, index=False, index_label=None, mode='w')
#Now add another line with units
#Open txt file
with open(output_temp_filename) as infile:
with open(output_filename,"w") as outfile:
#outfile.write(newline1+"\n")
outfile.write(newline2+"\n")
outfile.write(newline3+"\n")
for i,line in enumerate(infile):
outfile.write(line)
os.remove(output_temp_filename)
#####################
# Finish up
######################
print "FINISHED writing out files for use for NASA "
def Output_files(New_combined,myBaseforResults,Site_ID,versionID):
New_combined_grouped=New_combined.groupby([lambda x: x.year])
for year_index in New_combined_grouped:
print year_index[0]
print "Starting output for WAVES"
#Check for place to put results - does it exist? If not create
if not os.path.isdir(myBaseforResults):
os.mkdir(myBaseforResults)
#Then subdirectories
if not os.path.isdir(myBaseforResults+"/WAVES"):
os.mkdir(myBaseforResults+"/WAVES")
mypathforResults=myBaseforResults+"/WAVES/"
#Calculate RH_con
New_combined['RH_Con']=metfuncs.RHfromabsolutehumidity(New_combined['Ah_Con'],New_combined['Ta_Con'])
#Convert VPD in kPa to hPa.
#We need to update VPD for input here so also need e and es
# Calculate vapour pressure from absolute humidity and temperature
# Ah - absolute humidity, g/m3
# Ta - air temperature, C
New_combined['VPD_hPa_Con']=(metfuncs.es(New_combined['Ta_Con']))-(metfuncs.vapourpressure(New_combined['Ah_Con'],New_combined['Ta_Con']))/10
REddyProc_DF=New_combined[['Ah_Con','Cc','eta','Fa','Fc_Con','Fe_Con','Fg_Con','Fh_Con','Fld_Con','Flu_Con','Fm','Fn_Con','Fsd_Con','Fsu_Con','ps_Con','Precip_Con','Sws_Con','Sws_5cma','Sws_50cma','Ta_Con','theta','Ts_Con','ustar','Ws_CSAT_Con','Wd_CSAT','RH_Con','VPD_hPa_Con']]
#The date/time components are separated into columns. E.g. first column: julian day, second column: decimal hour.
#Possible date formats are indicated in the input form. Never use an hour of 24 with the time
#format 'year', 'month', 'day', 'hour', 'minute' (use 0 instead). Hour '0' is interpreted as first hour of the day,
#i.e. when you have transition from one to another it must be like (day, 23 --> day+1, 0) not like (day, 23 --> day, 0),
#because then the data set is not chronological (this misunderstanding happened before).
#REddyProc_DF['DT1','DT2','DT3','DT4','DT5','DT5']=REddyProc_DF.index.timetuple()
REddyProc_DF['DTcopy']=REddyProc_DF.index
REddyProc_DF['Day']=REddyProc_DF['DTcopy'].apply(lambda x: int(x.strftime('%j')))
REddyProc_DF['Year']=REddyProc_DF['DTcopy'].apply(lambda x: int(x.strftime('%Y')))
REddyProc_DF['Hour']=REddyProc_DF['DTcopy'].apply(lambda x: float(x.strftime('%H'))+(float(x.strftime('%M'))/60))
#Select current year of yaer only
REddyProc_DF=REddyProc_DF[REddyProc_DF['Year']==year_index[0]]
#Calculate some things for plots
n_datapoints=len(REddyProc_DF)
startdate= REddyProc_DF.index[0]
enddate= REddyProc_DF.index[n_datapoints-1]
print n_datapoints,startdate,enddate
#newline1="TIMESTAMP,Merged from Ah_HMP_23m Ah_7500_Av Ah_HMP_2m,CO2 concentration average,Merged from Cc_7500_Av converted to umol/mol,Horizontal rotation angle,Available energy using Fn Fg,CO2 flux rotated to natural wind coordinates WPL corrected Fc converted to umol/m2/s,Latent heat flux rotated to natural wind coordinates WPL corrected Fe,Element-wise average of series Fg_8cma Fg_8cmb Fg_8cmc Fg_8cmd Soil heat flux corrected for storage,Sensible heat flux rotated to natural wind coordinates Fh rotated and converted from virtual heat flux,Down-welling long wave,Up-welling long wave,Momentum flux rotated to natural wind coordinates,Merged from Fn_KZ Fn_NR Down-welling short wave Up-welling short wave,Air pressure standard deviation,Element-wise average of series Sws_10cma Sws_10cmb,Soil water fraction sensor 2a,Soil water fraction sensor 3a,Merged from Ta_HMP_23m Ta_CSAT Ta_HMP_2m,Vertical rotation angle,Element-wise average of series Ts_8cma,Friction velocity rotated to natural wind coordinates,ustar filtered for low turbulence conditions (<0.25),Wind speed,Wind direction"
newline2="DSN,g/m3,mg/m3,deg,W/m2,umol/m2/s,W/m2,W/m2,W/m2,W/m2,W/m2,kg/m/s2,W/m2,W/m2,W/m2,kPa,mm,frac,frac,frac,C,deg,C,m/s,m/s,deg,hPa,frac"
newline3= "TIMESTAMP,Ah_Con,Cc,eta,Fa,Fc_Con,Fe_Con,Fg_Con,Fh_Con,Fld_Con,Flu_Con,Fm,Fn_Con,Fsd_Con,Fsu_Con,ps_Con,Precip_Con,Sws_Con,Sws_5cm,Sws_50cm,Ta_Con,theta,Ts_Con,ustar,Ws_CSAT_Con,Wd_CSAT,RH_Con,VPD_hPa_Con"
columns_out = ['DTcopy','Ah_Con','Cc','eta','Fa','Fc_Con','Fe_Con','Fg_Con','Fh_Con','Fld_Con','Flu_Con','Fm','Fn_Con','Fsd_Con','Fsu_Con','ps_Con','Precip_Con','Sws_Con','Sws_5cma','Sws_50cma','Ta_Con','theta','Ts_Con','ustar','Ws_CSAT_Con','Wd_CSAT','RH_Con','VPD_hPa_Con']
output_temp_filename=mypathforResults+'/WAVES_temp_'+Site_ID+'_'+str(year_index[0])+'_'+versionID +'.csv'
output_filename=mypathforResults+'/WAVES_'+Site_ID+'_'+str(year_index[0])+'_'+versionID +'.csv'
REddyProc_DF.to_csv(output_temp_filename, na_rep='-9999', float_format='%.3f', cols=columns_out, header=False, index=False, index_label=None, mode='w')
#Now add another line with units
#Open txt file
with open(output_temp_filename) as infile:
with open(output_filename,"w") as outfile:
#outfile.write(newline1+"\n")
outfile.write(newline2+"\n")
outfile.write(newline3+"\n")
for i,line in enumerate(infile):
outfile.write(line)
os.remove(output_temp_filename)
#####################
# Finish up
######################
print "FINISHED writing out files for use for WAVES "
def Output_files(New_combined,myBaseforResults,Site_ID,versionID):
New_combined_grouped=New_combined.groupby([lambda x: x.year])
for year_index in New_combined_grouped:
print year_index[0]
print "Starting output for WAVES"
#Check for place to put results - does it exist? If not create
if not os.path.isdir(myBaseforResults):
os.mkdir(myBaseforResults)
#Then subdirectories
if not os.path.isdir(myBaseforResults+"/WAVES"):
os.mkdir(myBaseforResults+"/WAVES")
mypathforResults=myBaseforResults+"/WAVES/"
#Calculate RH_con
New_combined['RH_Con']=metfuncs.RHfromabsolutehumidity(New_combined['Ah_Con'],New_combined['Ta_Con'])
#Convert VPD in kPa to hPa.
#We need to update VPD for input here so also need e and es
# Calculate vapour pressure from absolute humidity and temperature
# Ah - absolute humidity, g/m3
# Ta - air temperature, C
New_combined['VPD_hPa_Con']=(metfuncs.es(New_combined['Ta_Con']))-(metfuncs.vapourpressure(New_combined['Ah_Con'],New_combined['Ta_Con']))/10
REddyProc_DF=New_combined[['Ah_Con','Cc','eta','Fa','Fc_Con','Fe_Con','Fg_Con','Fh_Con','Fld_Con','Flu_Con','Fm','Fn_Con','Fsd_Con','Fsu_Con','ps_Con','Precip_Con','Sws_Con','Sws_05','Sws_50','Ta_Con','theta','Ts_Con','ustar','Ws_CSAT_Con','Wd_CSAT','RH_Con','VPD_hPa_Con']]
#The date/time components are separated into columns. E.g. first column: julian day, second column: decimal hour.
#Possible date formats are indicated in the input form. Never use an hour of 24 with the time
#format 'year', 'month', 'day', 'hour', 'minute' (use 0 instead). Hour '0' is interpreted as first hour of the day,
#i.e. when you have transition from one to another it must be like (day, 23 --> day+1, 0) not like (day, 23 --> day, 0),
#because then the data set is not chronological (this misunderstanding happened before).
#REddyProc_DF['DT1','DT2','DT3','DT4','DT5','DT5']=REddyProc_DF.index.timetuple()
REddyProc_DF['DTcopy']=REddyProc_DF.index
REddyProc_DF['Day']=REddyProc_DF['DTcopy'].apply(lambda x: int(x.strftime('%j')))
REddyProc_DF['Year']=REddyProc_DF['DTcopy'].apply(lambda x: int(x.strftime('%Y')))
REddyProc_DF['Hour']=REddyProc_DF['DTcopy'].apply(lambda x: float(x.strftime('%H'))+(float(x.strftime('%M'))/60))
#Select current year of yaer only
REddyProc_DF=REddyProc_DF[REddyProc_DF['Year']==year_index[0]]
#Calculate some things for plots
n_datapoints=len(REddyProc_DF)
startdate= REddyProc_DF.index[0]
enddate= REddyProc_DF.index[n_datapoints-1]
print n_datapoints,startdate,enddate
#newline1="TIMESTAMP,Merged from Ah_HMP_23m Ah_7500_Av Ah_HMP_2m,CO2 concentration average,Merged from Cc_7500_Av converted to umol/mol,Horizontal rotation angle,Available energy using Fn Fg,CO2 flux rotated to natural wind coordinates WPL corrected Fc converted to umol/m2/s,Latent heat flux rotated to natural wind coordinates WPL corrected Fe,Element-wise average of series Fg_8cma Fg_8cmb Fg_8cmc Fg_8cmd Soil heat flux corrected for storage,Sensible heat flux rotated to natural wind coordinates Fh rotated and converted from virtual heat flux,Down-welling long wave,Up-welling long wave,Momentum flux rotated to natural wind coordinates,Merged from Fn_KZ Fn_NR Down-welling short wave Up-welling short wave,Air pressure standard deviation,Element-wise average of series Sws_10cma Sws_10cmb,Soil water fraction sensor 2a,Soil water fraction sensor 3a,Merged from Ta_HMP_23m Ta_CSAT Ta_HMP_2m,Vertical rotation angle,Element-wise average of series Ts_8cma,Friction velocity rotated to natural wind coordinates,ustar filtered for low turbulence conditions (<0.25),Wind speed,Wind direction"
newline2="DSN,g/m3,mg/m3,deg,W/m2,umol/m2/s,W/m2,W/m2,W/m2,W/m2,W/m2,kg/m/s2,W/m2,W/m2,W/m2,kPa,mm,frac,frac,frac,C,deg,C,m/s,m/s,deg,hPa,frac"
newline3= "TIMESTAMP,Ah_Con,Cc,eta,Fa,Fc_Con,Fe_Con,Fg_Con,Fh_Con,Fld_Con,Flu_Con,Fm,Fn_Con,Fsd_Con,Fsu_Con,ps_Con,Precip_Con,Sws_Con,Sws_5cm,Sws_50cm,Ta_Con,theta,Ts_Con,ustar,Ws_CSAT_Con,Wd_CSAT,RH_Con,VPD_hPa_Con"
columns_out = ['DTcopy','Ah_Con','Cc','eta','Fa','Fc_Con','Fe_Con','Fg_Con','Fh_Con','Fld_Con','Flu_Con','Fm','Fn_Con','Fsd_Con','Fsu_Con','ps_Con','Precip_Con','Sws_Con','Sws_05','Sws_50','Ta_Con','theta','Ts_Con','ustar','Ws_CSAT_Con','Wd_CSAT','RH_Con','VPD_hPa_Con']
output_temp_filename=mypathforResults+'/WAVES_temp_'+Site_ID+'_'+str(year_index[0])+'_'+versionID +'.csv'
output_filename=mypathforResults+'/WAVES_'+Site_ID+'_'+str(year_index[0])+'_'+versionID +'.csv'
REddyProc_DF.to_csv(output_temp_filename, na_rep='-9999', float_format='%.3f', cols=columns_out, header=False, index=False, index_label=None, mode='w')
#Now add another line with units
#Open txt file
with open(output_temp_filename) as infile:
with open(output_filename,"w") as outfile:
for i,line in enumerate(infile):
if i==0:
#outfile.write(newline1+"\n")
outfile.write(newline2+"\n")
outfile.write(newline3+"\n")
else:
outfile.write(line)
os.remove(output_temp_filename)
#####################
# Finish up
######################
print "FINISHED writing out files for use for WAVES "
def Output_files(New_combined,myBaseforResults,Site_ID,versionID):
New_combined_grouped=New_combined.groupby([lambda x: x.year])
for year_index in New_combined_grouped:
print year_index[0]
print "Starting output for EddyProc MPI online tool"
#Check for place to put results - does it exist? If not create
if not os.path.isdir(myBaseforResults):
os.mkdir(myBaseforResults)
#Then subdirectories
if not os.path.isdir(myBaseforResults+"/REddyProc"):
os.mkdir(myBaseforResults+"/REddyProc")
mypathforResults=myBaseforResults+"/REddyProc/"
#Calculate RH_con
New_combined['RH_Con']=metfuncs.RHfromabsolutehumidity(New_combined['Ah_Con'],New_combined['Ta_Con'])
#Convert VPD in kPa to hPa.
#We need to update VPD for input here so also need e and es
# Calculate vapour pressure from absolute humidity and temperature
# Ah - absolute humidity, g/m3
# Ta - air temperature, C
New_combined['VPD_hPa_Con']=(metfuncs.es(New_combined['Ta_Con']))-(metfuncs.vapourpressure(New_combined['Ah_Con'],New_combined['Ta_Con']))/10
REddyProc_DF=New_combined[['Fc','Fe','Fh','Fg','Ta_Con','Ts_Con','RH_Con','VPD_hPa_Con','ustar']]
#The date/time components are separated into columns. E.g. first column: julian day, second column: decimal hour.
#Possible date formats are indicated in the input form. Never use an hour of 24 with the time
#format 'year', 'month', 'day', 'hour', 'minute' (use 0 instead). Hour '0' is interpreted as first hour of the day,
#i.e. when you have transition from one to another it must be like (day, 23 --> day+1, 0) not like (day, 23 --> day, 0),
#because then the data set is not chronological (this misunderstanding happened before).
#REddyProc_DF['DT1','DT2','DT3','DT4','DT5','DT5']=REddyProc_DF.index.timetuple()
REddyProc_DF['DTcopy']=REddyProc_DF.index
REddyProc_DF['Day']=REddyProc_DF['DTcopy'].apply(lambda x: int(x.strftime('%j')))
REddyProc_DF['Year']=REddyProc_DF['DTcopy'].apply(lambda x: int(x.strftime('%Y')))
REddyProc_DF['Hour']=REddyProc_DF['DTcopy'].apply(lambda x: float(x.strftime('%H'))+(float(x.strftime('%M'))/60))
#Select current year of yaer only
REddyProc_DF=REddyProc_DF[REddyProc_DF['Year']==year_index[0]]
#Calculate some things for plots
n_datapoints=len(REddyProc_DF)
startdate= REddyProc_DF.index[0]
enddate= REddyProc_DF.index[n_datapoints-1]
print n_datapoints,startdate,enddate
header_names = ['Year','Day','Hour','NEE','LE','H' ,'Rg','Tair' ,'Tsoil' ,'rH', 'VPD', 'Ustar']
columns_out = ['Year','Day','Hour','Fc', 'Fe','Fh','Fg','Ta_Con','Ts_Con','RH_Con','VPD_hPa_Con','ustar']
newline1='Year \t DoY \t Hour \t NEE \t LE \t H \t Rg \t Tair \t Tsoil \t rH \t VPD \t Ustar'
newline2=" -- \t -- \t -- \t umolm-2s-1 \t Wm-2 \t Wm-2 \t Wm-2 \t degC \t degC \t % \t hPa \t ms-1"
#newline1='Year,Day,Hour,NEE,LE,H,Rg,Tair,Tsoil,rH,VPD,Ustar'
#newline2="--,--,--,umolm-2s-1,Wm-2,Wm-2,Wm-2,degC,degC,%,hPa,ms-1"
output_temp_filename=mypathforResults+'/REddyProc_temp_'+Site_ID+'_'+str(year_index[0])+'_'+versionID +'.txt'
output_filename=mypathforResults+'/REddyProc_'+Site_ID+'_'+str(year_index[0])+'_'+versionID +'.txt'
REddyProc_DF.to_csv(output_temp_filename, sep='\t', na_rep='-9999', float_format='%.3f', cols=columns_out, header=False, index=False, index_label=None, mode='w')
#Now add another line with units
#Open txt file
with open(output_temp_filename) as infile:
with open(output_filename,"w") as outfile:
for i,line in enumerate(infile):
if i==0:
outfile.write(newline1+"\n")
outfile.write(newline2+"\n")
else:
outfile.write(line)
os.remove(output_temp_filename)
#####################
# Finish up
######################
print "FINISHED writing out files for use in EddyProc MPI online tool "
def ANN_gapfill_func(myBaseforResults,New_combined,Site_ID,list_in,list_out,iterations,index_str,is_this_all,ANN_label_all,ANN_label,frequency,Use_Fc_Storage):
###########################################################################################################
## START MAIN CODE
###########################################################################################################
if 'Fc' in list_out:
units="umol.m-2.s-1"
elif ('Fe' or 'Fh' or 'Fg') in list_out:
units="W.m-2"
else:
units=" "
###### User-set IO file locations ######
print "Starting ANN gap filling"
#Check for place to put results - does it exist? If not create
if not os.path.isdir(myBaseforResults):
os.mkdir(myBaseforResults)
#Then subdirectories
if not os.path.isdir(myBaseforResults+"/ANN"):
os.mkdir(myBaseforResults+"/ANN")
mypathforResults=myBaseforResults+"/ANN"
#We need to update VPD for input here so also need e and es
# Calculate vapour pressure from absolute humidity and temperature
# Ah - absolute humidity, g/m3
# Ta - air temperature, C
New_combined['VPD_Con']=(metfuncs.es(New_combined['Ta_Con']))-(metfuncs.vapourpressure(New_combined['Ah_Con'],New_combined['Ta_Con']))
number_of_inputs=len(list_in)
number_of_outputs=len(list_out)
#startdate=dt.date(2008,7,1)
#enddate=dt.date(2008,8,1)
alllist=list_in + list_out
xnow=New_combined[alllist] #[startdate:enddate]
xnow=xnow.dropna(how='any')
#Drop nans and missing values so that Good data only is used in the training
xarray=np.array(xnow.dropna().reset_index(drop=True))
#Define inputs and targets for NN from DF
inputs = xarray[:, :number_of_inputs] #first 2 columns
lastcolums=(-1*number_of_outputs)
targets = xarray[:, lastcolums:] #last column
# Generate standard layered network architecture and create network
#different network architectures avaiable
#conec = mlgraph((number_of_inputs,24,16,number_of_outputs)) # Creates standard multilayer network architecture
conec = tmlgraph((number_of_inputs,24,16,number_of_outputs)) # Creates multilayer network full connectivity list
#conec = imlgraph((number_of_inputs,24,16,number_of_outputs)) # Creates multilayer architecture with independent outputs
net = ffnet(conec)
print "TRAINING NETWORK..."
net.train_tnc(inputs, targets, maxfun = iterations, messages=1)
#net.train_rprop(inputs, targets, maxiter=iterations)
#net.train_momentum(inputs, targets, maxfun = iterations, messages=1)
#net.train_genetic(inputs, targets, maxfun = iterations, messages=1)
#net.train_cg(inputs, targets, maxfun = iterations, messages=1)
#net.train_bfgs(inputs, targets, maxfun = iterations, messages=1)
# Test network
print "TESTING NETWORK..."
output, regression = net.test(inputs, targets, iprint = 0)
print "R-squared: %s " %str(regression[0][2])
#print "max. absolute error: %s " %str(abs( array(output).reshape( len(output) ) - array(targets) ).max())
output, regress = net.test(inputs, targets)
#Create array for results. Then loop through elements on the original data to predict the ANN value
predicted=np.empty((len(xarray),number_of_outputs))
observed=np.empty((len(xarray),number_of_outputs))
for index,rowdata in enumerate(xarray):
predicted[index]=net([rowdata[0:number_of_inputs]])
observed[index]=np.array(rowdata[-1.0*number_of_outputs : ])
#observed[index]=np.array(rowdata[(-1.0*number_of_outputs)])
############################################
# Generate output and return new variables
############################################
#Create a new variable called '_NN'
for index, item in enumerate(list_out):
ANN_label=str(item+"_NN")
ANN_label_all=str(item+"_NN_all")
if is_this_all == True:
New_combined[ANN_label_all]=net.call(New_combined[list_in])[:,index]
else:
New_combined[ANN_label]=net.call(New_combined[list_in])[:,index]
for index, item in enumerate(list_out):
#####################################################
# Plots
#####################################################
#Plot time series of all 30 minute data
mintimeseries_plot(mypathforResults,predicted,observed,regress,item, Site_ID,units,targets,output,list_out,index_str)
#Plot regression of Tower versus ANN
regressionANN2(mypathforResults,predicted,observed,regress,item, Site_ID,units,list_out,index_str)
#Plot diurnals for every second month 6 graphs - only when enough months so all or annual
if frequency=="all" or frequency=="annual" or is_this_all==True:
Doplots_diurnal_monthly(mypathforResults,New_combined,item, Site_ID,units,list_out,index_str,is_this_all)
#Plot diurnals for every second month 6 graphs
Doplots_diurnal(mypathforResults,New_combined,item, Site_ID,units,list_out,index_str,frequency)
#Plot timeseries of monthly over all periods
Doplots_monthly(mypathforResults,New_combined,item, Site_ID,units,list_out,index_str,frequency)
return New_combined