def DateTimeFromDoY(ds,Year_in,DoY_in,Hdh_in): year,f,a = qcutils.GetSeriesasMA(ds,Year_in) doy,f,a = qcutils.GetSeriesasMA(ds,DoY_in) hdh,f,a = qcutils.GetSeriesasMA(ds,Hdh_in) idx = numpy.ma.where((numpy.ma.getmaskarray(year)==False)& (numpy.ma.getmaskarray(doy)==False)& (numpy.ma.getmaskarray(hdh)==False))[0] year = year[idx] doy = doy[idx] hdh = hdh[idx] hour = numpy.array(hdh,dtype=numpy.integer) minute = numpy.array((hdh-hour)*60,dtype=numpy.integer) dt = [datetime.datetime(int(y),1,1,h,m)+datetime.timedelta(int(d)-1) for y,d,h,m in zip(year,doy,hour,minute)] nRecs = len(dt) ds.series["DateTime"] = {} ds.series["DateTime"]["Data"] = dt ds.series["DateTime"]["Flag"] = numpy.zeros(len(dt),dtype=numpy.int32) ds.series["DateTime"]["Attr"] = {} ds.series["DateTime"]["Attr"]["long_name"] = "Datetime in local timezone" ds.series["DateTime"]["Attr"]["units"] = "None" # now remove any "data"" from empty lines series_list = ds.series.keys() if "DateTime" in series_list: series_list.remove("DateTime") for item in series_list: ds.series[item]["Data"] = ds.series[item]["Data"][idx] ds.series[item]["Flag"] = ds.series[item]["Flag"][idx] ds.globalattributes["nc_nrecs"] = nRecs return 1
def CoordinateFluxGaps(cf, ds, Fc_in='Fc', Fe_in='Fe', Fh_in='Fh'): if not qcutils.cfoptionskey(cf, Key='CoordinateFluxGaps'): return if qcutils.cfkeycheck(cf, Base='FunctionArgs', ThisOne='gapsvars'): vars = ast.literal_eval(cf['FunctionArgs']['gapsvars']) Fc_in = vars[0] Fe_in = vars[1] Fh_in = vars[2] Fc, f = qcutils.GetSeriesasMA(ds, Fc_in) Fe, f = qcutils.GetSeriesasMA(ds, Fe_in) Fh, f = qcutils.GetSeriesasMA(ds, Fh_in) index = numpy.ma.where((Fc.mask == True) | (Fe.mask == True) | (Fh.mask == True))[0] # the following for ... in loop is not necessary for i in range(len(index)): j = index[i] if Fc.mask[j] == False: Fc.mask[j] = True Fc[j] = numpy.float64(-9999) ds.series[Fc_in]['Flag'][j] = numpy.int32(19) if Fe.mask[j] == False: Fe.mask[j] = True Fe[j] = numpy.float64(-9999) ds.series[Fe_in]['Flag'][j] = numpy.int32(19) if Fh.mask[j] == False: Fh.mask[j] = True Fh[j] = numpy.float64(-9999) ds.series[Fh_in]['Flag'][j] = numpy.int32(19) ds.series[Fc_in]['Data'] = numpy.ma.filled(Fc, float(-9999)) ds.series[Fe_in]['Data'] = numpy.ma.filled(Fe, float(-9999)) ds.series[Fh_in]['Data'] = numpy.ma.filled(Fh, float(-9999)) log.info(' Finished gap co-ordination')
def AhfromRH(ds,Ah_out,RH_in,Ta_in): """ Purpose: Function to calculate absolute humidity given relative humidity and air temperature. Absolute humidity is not calculated if any of the input series are missing or if the specified output series already exists in the data structure. The calculated absolute humidity is created as a new series in the data structure. Usage: qcfunc.AhfromRH(ds,"Ah_HMP_2m","RH_HMP_2m","Ta_HMP_2m") Author: PRI Date: September 2015 """ for item in [RH_in,Ta_in]: if item not in ds.series.keys(): msg = " AhfromRH: Requested series "+item+" not found, "+Ah_out+" not calculated" log.error(msg) return 0 if Ah_out in ds.series.keys(): msg = " AhfromRH: Output series "+Ah_out+" already exists, skipping ..." log.error(msg) return 0 RH_data,RH_flag,RH_attr = qcutils.GetSeriesasMA(ds,RH_in) Ta_data,Ta_flag,Ta_attr = qcutils.GetSeriesasMA(ds,Ta_in) Ah_data = mf.absolutehumidityfromRH(Ta_data,RH_data) Ah_attr = qcutils.MakeAttributeDictionary(long_name="Absolute humidity calculated from "+RH_in+" and "+Ta_in, height=RH_attr["height"], units="g/m3") qcutils.CreateSeries(ds,Ah_out,Ah_data,FList=[RH_in,Ta_in],Attr=Ah_attr) return 1
def do_dependencycheck(cf,ds,section='',series='',code=23,mode="quiet"): if len(section)==0 and len(series)==0: return if len(section)==0: section = qcutils.get_cfsection(cf,series=series,mode='quiet') if "DependencyCheck" not in cf[section][series].keys(): return if "Source" not in cf[section][series]["DependencyCheck"]: msg = " DependencyCheck: keyword Source not found for series "+series+", skipping ..." log.error(msg) return if mode=="verbose": msg = " Doing DependencyCheck for "+series log.info(msg) # get the precursor source list from the control file source_list = ast.literal_eval(cf[section][series]["DependencyCheck"]["Source"]) # get the data dependent_data,dependent_flag,dependent_attr = qcutils.GetSeriesasMA(ds,series) # loop over the precursor source list for item in source_list: # check the precursor is in the data structure if item not in ds.series.keys(): msg = " DependencyCheck: "+series+" precursor series "+item+" not found, skipping ..." continue # get the precursor data precursor_data,precursor_flag,precursor_attr = qcutils.GetSeriesasMA(ds,item) # mask the dependent data where the precurso is masked dependent_data = numpy.ma.masked_where(numpy.ma.getmaskarray(precursor_data)==True,dependent_data) # get an index of masked precursor data index = numpy.ma.where(numpy.ma.getmaskarray(precursor_data)==True)[0] # set the dependent QC flag dependent_flag[index] = numpy.int32(code) # put the data back into the data structure dependent_attr["DependencyCheck_source"] = str(source_list) qcutils.CreateSeries(ds,series,dependent_data,Flag=dependent_flag,Attr=dependent_attr) if 'do_dependencychecks' not in ds.globalattributes['Functions']: ds.globalattributes['Functions'] = ds.globalattributes['Functions']+',do_dependencychecks'
def AhfromMR(ds,Ah_out,MR_in,Ta_in,ps_in): """ Purpose: Function to calculate absolute humidity given the water vapour mixing ratio, air temperature and pressure. Absolute humidity is not calculated if any of the input series are missing or if the specified output series already exists in the data structure. The calculated absolute humidity is created as a new series in the data structure. Usage: qcfunc.AhfromMR(ds,"Ah_IRGA_Av","H2O_IRGA_Av","Ta_HMP_2m","ps") Author: PRI Date: September 2015 """ for item in [MR_in,Ta_in,ps_in]: if item not in ds.series.keys(): msg = " AhfromMR: Requested series "+item+" not found, "+Ah_out+" not calculated" log.error(msg) return 0 if Ah_out in ds.series.keys(): msg = " AhfromMR: Output series "+Ah_out+" already exists, skipping ..." log.error(msg) return 0 MR_data,MR_flag,MR_attr = qcutils.GetSeriesasMA(ds,MR_in) Ta_data,Ta_flag,Ta_attr = qcutils.GetSeriesasMA(ds,Ta_in) ps_data,ps_flag,ps_attr = qcutils.GetSeriesasMA(ds,ps_in) Ah_data = mf.h2o_gpm3frommmolpmol(MR_data,Ta_data,ps_data) long_name = "Absolute humidity calculated from "+MR_in+", "+Ta_in+" and "+ps_in Ah_attr = qcutils.MakeAttributeDictionary(long_name=long_name, height=MR_attr["height"], units="g/m3") qcutils.CreateSeries(ds,Ah_out,Ah_data,FList=[MR_in,Ta_in,ps_in],Attr=Ah_attr) return 1
def MRfromRH(ds, MR_out, RH_in, Ta_in, ps_in): """ Purpose: Calculate H2O mixing ratio from RH. """ nRecs = int(ds.globalattributes["nc_nrecs"]) zeros = numpy.zeros(nRecs, dtype=numpy.int32) ones = numpy.ones(nRecs, dtype=numpy.int32) for item in [RH_in, Ta_in, ps_in]: if item not in ds.series.keys(): msg = " MRfromRH: Requested series " + item + " not found, " + MR_out + " not calculated" logger.error(msg) return 0 if MR_out in ds.series.keys(): msg = " MRfromRH: Output series " + MR_out + " already exists, skipping ..." logger.error(msg) return 0 RH_data, RH_flag, RH_attr = qcutils.GetSeriesasMA(ds, RH_in) Ta_data, Ta_flag, Ta_attr = qcutils.GetSeriesasMA(ds, Ta_in) Ah_data = mf.absolutehumidityfromRH(Ta_data, RH_data) ps_data, ps_flag, ps_attr = qcutils.GetSeriesasMA(ds, ps_in) MR_data = mf.h2o_mmolpmolfromgpm3(Ah_data, Ta_data, ps_data) MR_attr = qcutils.MakeAttributeDictionary( long_name="H2O mixing ratio calculated from " + RH_in + ", " + Ta_in + " and " + ps_in, height=RH_attr["height"], units="mmol/mol") flag = numpy.where(numpy.ma.getmaskarray(MR_data) == True, ones, zeros) qcutils.CreateSeries(ds, MR_out, MR_data, flag, MR_attr) return 1
def get_radiation(ds_60minutes): for i in range(0,3): for j in range(0,3): label_Fn = "Fn_"+str(i)+str(j) label_Fsd = "Fsd_"+str(i)+str(j) label_Fld = "Fld_"+str(i)+str(j) label_Fsu = "Fsu_"+str(i)+str(j) label_Flu = "Flu_"+str(i)+str(j) label_Fn_sw = "Fn_sw_"+str(i)+str(j) label_Fn_lw = "Fn_lw_"+str(i)+str(j) Fsd,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fsd) Fld,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fld) Fn_sw,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fn_sw) Fn_lw,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fn_lw) Fsu = Fsd - Fn_sw Flu = Fld - Fn_lw Fn = (Fsd-Fsu)+(Fld-Flu) attr = qcutils.MakeAttributeDictionary(long_name='Up-welling long wave', standard_name='surface_upwelling_longwave_flux_in_air', units='W/m2') qcutils.CreateSeries(ds_60minutes,label_Flu,Flu,Flag=f,Attr=attr) attr = qcutils.MakeAttributeDictionary(long_name='Up-welling short wave', standard_name='surface_upwelling_shortwave_flux_in_air', units='W/m2') qcutils.CreateSeries(ds_60minutes,label_Fsu,Fsu,Flag=f,Attr=attr) attr = qcutils.MakeAttributeDictionary(long_name='Calculated net radiation', standard_name='surface_net_allwave_radiation', units='W/m2') qcutils.CreateSeries(ds_60minutes,label_Fn,Fn,Flag=f,Attr=attr) return
def get_windspeedanddirection(ds_60minutes): for i in range(0,3): for j in range(0,3): u_label = "u_"+str(i)+str(j) v_label = "v_"+str(i)+str(j) Ws_label = "Ws_"+str(i)+str(j) u,f,a = qcutils.GetSeriesasMA(ds_60minutes,u_label) v,f,a = qcutils.GetSeriesasMA(ds_60minutes,v_label) Ws = numpy.sqrt(u*u+v*v) attr = qcutils.MakeAttributeDictionary(long_name="Wind speed", units="m/s",height="10m") qcutils.CreateSeries(ds_60minutes,Ws_label,Ws,Flag=f,Attr=attr) # wind direction from components for i in range(0,3): for j in range(0,3): u_label = "u_"+str(i)+str(j) v_label = "v_"+str(i)+str(j) Wd_label = "Wd_"+str(i)+str(j) u,f,a = qcutils.GetSeriesasMA(ds_60minutes,u_label) v,f,a = qcutils.GetSeriesasMA(ds_60minutes,v_label) Wd = float(270) - numpy.ma.arctan2(v,u)*float(180)/numpy.pi index = numpy.ma.where(Wd>360)[0] if len(index)>0: Wd[index] = Wd[index] - float(360) attr = qcutils.MakeAttributeDictionary(long_name="Wind direction", units="degrees",height="10m") qcutils.CreateSeries(ds_60minutes,Wd_label,Wd,Flag=f,Attr=attr) return
def get_absolutehumidity(ds_60minutes): for i in range(0,3): for j in range(0,3): Ta_label = "Ta_"+str(i)+str(j) RH_label = "RH_"+str(i)+str(j) Ah_label = "Ah_"+str(i)+str(j) Ta,f,a = qcutils.GetSeriesasMA(ds_60minutes,Ta_label) RH,f,a = qcutils.GetSeriesasMA(ds_60minutes,RH_label) Ah = mf.absolutehumidityfromRH(Ta, RH) attr = qcutils.MakeAttributeDictionary(long_name='Absolute humidity', units='g/m3',standard_name='not defined') qcutils.CreateSeries(ds_60minutes,Ah_label,Ah,Flag=f,Attr=attr) return
def get_availableenergy(ds_60miutes): for i in range(0,3): for j in range(0,3): label_Fg = "Fg_"+str(i)+str(j) label_Fn = "Fn_"+str(i)+str(j) label_Fa = "Fa_"+str(i)+str(j) Fn,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fn) Fg,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fg) Fa = Fn - Fg attr = qcutils.MakeAttributeDictionary(long_name='Calculated available energy', standard_name='not defined',units='W/m2') qcutils.CreateSeries(ds_60minutes,label_Fa,Fa,Flag=f,Attr=attr) return
def get_relativehumidity(ds_60minutes): for i in range(0,3): for j in range(0,3): q_label = "q_"+str(i)+str(j) Ta_label = "Ta_"+str(i)+str(j) ps_label = "ps_"+str(i)+str(j) RH_label = "RH_"+str(i)+str(j) q,f,a = qcutils.GetSeriesasMA(ds_60minutes,q_label) Ta,f,a = qcutils.GetSeriesasMA(ds_60minutes,Ta_label) ps,f,a = qcutils.GetSeriesasMA(ds_60minutes,ps_label) RH = mf.RHfromspecifichumidity(q, Ta, ps) attr = qcutils.MakeAttributeDictionary(long_name='Relative humidity', units='%',standard_name='not defined') qcutils.CreateSeries(ds_60minutes,RH_label,RH,Flag=f,Attr=attr) return
def get_groundheatflux(ds_60minutes): for i in range(0,3): for j in range(0,3): label_Fg = "Fg_"+str(i)+str(j) label_Fn = "Fn_"+str(i)+str(j) label_Fh = "Fh_"+str(i)+str(j) label_Fe = "Fe_"+str(i)+str(j) Fn,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fn) Fh,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fh) Fe,f,a = qcutils.GetSeriesasMA(ds_60minutes,label_Fe) Fg = Fn - Fh - Fe attr = qcutils.MakeAttributeDictionary(long_name='Calculated ground heat flux', standard_name='downward_heat_flux_in_soil', units='W/m2') qcutils.CreateSeries(ds_60minutes,label_Fg,Fg,Flag=f,Attr=attr) return
def changeunits_soilmoisture(ds_60minutes): attr = qcutils.GetAttributeDictionary(ds_60minutes,"Sws_00") for i in range(0,3): for j in range(0,3): label = "Sws_"+str(i)+str(j) Sws,f,a = qcutils.GetSeriesasMA(ds_60minutes,label) Sws = Sws/float(100) attr["units"] = "frac" qcutils.CreateSeries(ds_60minutes,label,Sws,Flag=f,Attr=attr) return
def changeunits_pressure(ds_60minutes): attr = qcutils.GetAttributeDictionary(ds_60minutes,"ps_00") if attr["units"] == "Pa": for i in range(0,3): for j in range(0,3): label = "ps_"+str(i)+str(j) ps,f,a = qcutils.GetSeriesasMA(ds_60minutes,label) ps = ps/float(1000) attr["units"] = "kPa" qcutils.CreateSeries(ds_60minutes,label,ps,Flag=f,Attr=attr) return
def changeunits_soiltemperature(ds_60minutes): attr = qcutils.GetAttributeDictionary(ds_60minutes,"Ts_00") if attr["units"] == "K": for i in range(0,3): for j in range(0,3): label = "Ts_"+str(i)+str(j) Ts,f,a = qcutils.GetSeriesasMA(ds_60minutes,label) Ts = Ts - c.C2K attr["units"] = "C" qcutils.CreateSeries(ds_60minutes,label,Ts,Flag=f,Attr=attr) return
def CoordinateFluxGaps(cf,ds,Fc_in='Fc',Fe_in='Fe',Fh_in='Fh'): if qcutils.cfkeycheck(cf,Base='FunctionArgs',ThisOne='gapsvars'): vars = ast.literal_eval(cf['FunctionArgs']['gapsvars']) Fc_in = vars[0] Fe_in = vars[1] Fh_in = vars[2] Fc,flagC,a = qcutils.GetSeriesasMA(ds,Fc_in) Fe,flagE,a = qcutils.GetSeriesasMA(ds,Fe_in) Fh,flagH,a = qcutils.GetSeriesasMA(ds,Fh_in) index = numpy.ma.where((numpy.mod(flagC,10)!=0) | (numpy.mod(flagE,10)!=0) | (numpy.mod(flagH,10)!=0))[0] rC_i = numpy.ma.where((numpy.mod(flagC,10)==0) & ((numpy.mod(flagE,10)!=0) | (numpy.mod(flagH,10)!=0)))[0] rE_i = numpy.ma.where((numpy.mod(flagE,10)==0) & ((numpy.mod(flagC,10)!=0) | (numpy.mod(flagH,10)!=0)))[0] rH_i = numpy.ma.where((numpy.mod(flagH,10)==0) & ((numpy.mod(flagC,10)!=0) | (numpy.mod(flagE,10)!=0)))[0] ds.series[Fc_in]['Flag'][rC_i] = numpy.int32(19) ds.series[Fe_in]['Flag'][rE_i] = numpy.int32(19) ds.series[Fh_in]['Flag'][rH_i] = numpy.int32(19) flux_series = [Fc_in,Fe_in,Fh_in] for ThisOne in flux_series: index = numpy.where(ds.series[ThisOne]['Flag'] == 19)[0] ds.series[ThisOne]['Data'][index] = numpy.float64(c.missing_value) log.info(' Finished gap co-ordination')
def do_lowercheck(cf, ds, section, series, code=2): """ Purpose: Usage: Author: PRI Date: February 2017 """ # check to see if LowerCheck requested for this variable if "LowerCheck" not in cf[section][series]: return # Check to see if limits have been specified if len(cf[section][series]["LowerCheck"].keys()) == 0: msg = "do_lowercheck: no date ranges specified" logger.info(msg) return ldt = ds.series["DateTime"]["Data"] ts = ds.globalattributes["time_step"] data, flag, attr = qcutils.GetSeriesasMA(ds, series) lc_list = list(cf[section][series]["LowerCheck"].keys()) for n, item in enumerate(lc_list): # this should be a list and we should probably check for compliance lwr_info = cf[section][series]["LowerCheck"][item] attr["lowercheck_" + str(n)] = str(lwr_info) start_date = dateutil.parser.parse(lwr_info[0]) su = float(lwr_info[1]) end_date = dateutil.parser.parse(lwr_info[2]) eu = float(lwr_info[3]) # get the start and end indices si = qcutils.GetDateIndex(ldt, start_date, ts=ts, default=0, match="exact") ei = qcutils.GetDateIndex(ldt, end_date, ts=ts, default=len(ldt) - 1, match="exact") # get the segment of data between this start and end date seg_data = data[si:ei + 1] seg_flag = flag[si:ei + 1] x = numpy.arange(si, ei + 1, 1) lower = numpy.interp(x, [si, ei], [su, eu]) index = numpy.ma.where((seg_data < lower))[0] seg_data[index] = numpy.ma.masked seg_flag[index] = numpy.int32(code) data[si:ei + 1] = seg_data flag[si:ei + 1] = seg_flag # now put the data back into the data structure qcutils.CreateSeries(ds, series, data, Flag=flag, Attr=attr) return
def plotxy(cf, nFig, plt_cf, dsa, dsb, si, ei): SiteName = dsa.globalattributes['site_name'] PlotDescription = cf['Plots'][str(nFig)]['Title'] fig = plt.figure(int(nFig)) fig.clf() plt.figtext(0.5, 0.95, SiteName + ': ' + PlotDescription, ha='center', size=16) XSeries = ast.literal_eval(plt_cf['XSeries']) YSeries = ast.literal_eval(plt_cf['YSeries']) log.info(' Plotting xy: ' + str(XSeries) + ' v ' + str(YSeries)) if dsa == dsb: for xname, yname in zip(XSeries, YSeries): xa, flag = qcutils.GetSeriesasMA(dsa, xname, si=si, ei=ei) ya, flag = qcutils.GetSeriesasMA(dsa, yname, si=si, ei=ei) xyplot(xa, ya, sub=[1, 1, 1], regr=1, xlabel=xname, ylabel=yname) else: for xname, yname in zip(XSeries, YSeries): xa, flag = qcutils.GetSeriesasMA(dsa, xname, si=si, ei=ei) ya, flag = qcutils.GetSeriesasMA(dsa, yname, si=si, ei=ei) xb, flag = qcutils.GetSeriesasMA(dsb, xname, si=si, ei=ei) yb, flag = qcutils.GetSeriesasMA(dsb, yname, si=si, ei=ei) xyplot(xa, ya, sub=[1, 2, 1], xlabel=xname, ylabel=yname) xyplot(xb, yb, sub=[1, 2, 2], regr=1, xlabel=xname, ylabel=yname) fig.show()
def AhfromRH(ds, Ah_out, RH_in, Ta_in): """ Purpose: Function to calculate absolute humidity given relative humidity and air temperature. Absolute humidity is not calculated if any of the input series are missing or if the specified output series already exists in the data structure. The calculated absolute humidity is created as a new series in the data structure. Usage: qcfunc.AhfromRH(ds,"Ah_HMP_2m","RH_HMP_2m","Ta_HMP_2m") Author: PRI Date: September 2015 """ nRecs = int(ds.globalattributes["nc_nrecs"]) zeros = numpy.zeros(nRecs, dtype=numpy.int32) ones = numpy.ones(nRecs, dtype=numpy.int32) for item in [RH_in, Ta_in]: if item not in ds.series.keys(): msg = " AhfromRH: Requested series " + item + " not found, " + Ah_out + " not calculated" logger.error(msg) return 0 if Ah_out in ds.series.keys(): msg = " AhfromRH: Output series " + Ah_out + " already exists, skipping ..." logger.error(msg) return 0 RH_data, RH_flag, RH_attr = qcutils.GetSeriesasMA(ds, RH_in) Ta_data, Ta_flag, Ta_attr = qcutils.GetSeriesasMA(ds, Ta_in) Ah_data = mf.absolutehumidityfromRH(Ta_data, RH_data) Ah_attr = qcutils.MakeAttributeDictionary( long_name="Absolute humidity calculated from " + RH_in + " and " + Ta_in, height=RH_attr["height"], units="g/m3") flag = numpy.where(numpy.ma.getmaskarray(Ah_data) == True, ones, zeros) qcutils.CreateSeries(ds, Ah_out, Ah_data, flag, Ah_attr) return 1
def ImportSeries(cf, ds): # check to see if there is an Imports section if "Imports" not in cf.keys(): return # number of records nRecs = int(ds.globalattributes["nc_nrecs"]) # get the start and end datetime ldt = ds.series["DateTime"]["Data"] start_date = ldt[0] end_date = ldt[-1] # loop over the series in the Imports section for label in cf["Imports"].keys(): import_filename = qcutils.get_keyvaluefromcf(cf, ["Imports", label], "file_name", default="") if import_filename == "": msg = " ImportSeries: import filename not found in control file, skipping ..." logger.warning(msg) continue var_name = qcutils.get_keyvaluefromcf(cf, ["Imports", label], "var_name", default="") if var_name == "": msg = " ImportSeries: variable name not found in control file, skipping ..." logger.warning(msg) continue ds_import = qcio.nc_read_series(import_filename) ts_import = ds_import.globalattributes["time_step"] ldt_import = ds_import.series["DateTime"]["Data"] si = qcutils.GetDateIndex(ldt_import, str(start_date), ts=ts_import, default=0, match="exact") ei = qcutils.GetDateIndex(ldt_import, str(end_date), ts=ts_import, default=len(ldt_import) - 1, match="exact") data = numpy.ma.ones(nRecs) * float(c.missing_value) flag = numpy.ma.ones(nRecs) data_import, flag_import, attr_import = qcutils.GetSeriesasMA( ds_import, var_name, si=si, ei=ei) ldt_import = ldt_import[si:ei + 1] index = qcutils.FindIndicesOfBInA(ldt_import, ldt) data[index] = data_import flag[index] = flag_import qcutils.CreateSeries(ds, label, data, flag, attr_import)
def do_rangecheck(cf, ds, section, series, code=2): """ Purpose: Applies a range check to data series listed in the control file. Data values that are less than the lower limit or greater than the upper limit are replaced with c.missing_value and the corresponding QC flag element is set to 2. Usage: Author: PRI Date: Back in the day """ # check that RangeCheck has been requested for this series if 'RangeCheck' not in cf[section][series].keys(): return # check that the upper and lower limits have been given if ("Lower" not in cf[section][series]["RangeCheck"].keys() or "Upper" not in cf[section][series]["RangeCheck"].keys()): msg = "RangeCheck: key not found in control file for " + series + ", skipping ..." logger.warning(msg) return # get the upper and lower limits upr = numpy.array(eval(cf[section][series]['RangeCheck']['Upper'])) valid_upper = numpy.min(upr) upr = upr[ds.series['Month']['Data'] - 1] lwr = numpy.array(eval(cf[section][series]['RangeCheck']['Lower'])) valid_lower = numpy.min(lwr) lwr = lwr[ds.series['Month']['Data'] - 1] # get the data, flag and attributes data, flag, attr = qcutils.GetSeriesasMA(ds, series) # convert the data from a masked array to an ndarray so the range check works data = numpy.ma.filled(data, fill_value=c.missing_value) # get the indices of elements outside this range idx = numpy.where((data < lwr) | (data > upr))[0] # set elements outside range to missing and set the QC flag data[idx] = numpy.float64(c.missing_value) flag[idx] = numpy.int32(code) # update the variable attributes attr["rangecheck_lower"] = cf[section][series]["RangeCheck"]["Lower"] attr["rangecheck_upper"] = cf[section][series]["RangeCheck"]["Upper"] attr["valid_range"] = str(valid_lower) + "," + str(valid_upper) # and now put the data back into the data structure qcutils.CreateSeries(ds, series, data, Flag=flag, Attr=attr) # now we can return return
def plotxy(cf, nFig, plt_cf, dsa, dsb, si, ei): SiteName = dsa.globalattributes['site_name'] PlotDescription = cf['Plots'][str(nFig)]['Title'] fig = plt.figure(numpy.int32(nFig)) fig.clf() plt.figtext(0.5, 0.95, SiteName + ': ' + PlotDescription, ha='center', size=16) XSeries = ast.literal_eval(plt_cf['XSeries']) YSeries = ast.literal_eval(plt_cf['YSeries']) log.info(' Plotting xy: ' + str(XSeries) + ' v ' + str(YSeries)) if dsa == dsb: for xname, yname in zip(XSeries, YSeries): xa, flag, attr = qcutils.GetSeriesasMA(dsa, xname, si=si, ei=ei) ya, flag, attr = qcutils.GetSeriesasMA(dsa, yname, si=si, ei=ei) xyplot(xa, ya, sub=[1, 1, 1], regr=1, xlabel=xname, ylabel=yname) else: for xname, yname in zip(XSeries, YSeries): xa, flag, attr = qcutils.GetSeriesasMA(dsa, xname, si=si, ei=ei) ya, flag, attr = qcutils.GetSeriesasMA(dsa, yname, si=si, ei=ei) xb, flag, attr = qcutils.GetSeriesasMA(dsb, xname, si=si, ei=ei) yb, flag, attr = qcutils.GetSeriesasMA(dsb, yname, si=si, ei=ei) xyplot(xa, ya, sub=[1, 2, 1], xlabel=xname, ylabel=yname) xyplot(xb, yb, sub=[1, 2, 2], regr=1, xlabel=xname, ylabel=yname) STList = [] ETList = [] if ei == -1: L1XArray = numpy.array(dsa.series['DateTime']['Data'][si:ei]) else: L1XArray = numpy.array(dsa.series['DateTime']['Data'][si:ei + 1]) for fmt in ['%Y', '_', '%m', '_', '%d', '_', '%H', '%M']: STList.append(L1XArray[0].strftime(fmt)) if ei == -1: ETList.append(dsa.series['DateTime']['Data'][-1].strftime(fmt)) else: ETList.append(L1XArray[-1].strftime(fmt)) if qcutils.cfkeycheck( cf, Base='Output', ThisOne='PNGFile') and cf['Output']['PNGFile'] == 'True': log.info(' Generating a PNG file of the plot') PNGFileName = cf['Files']['PNG'][ 'PNGFilePath'] + 'Fig' + nFig + '_' + ''.join( STList) + '-' + ''.join(ETList) + '.png' plt.savefig(PNGFileName) fig.show()
def read_isd_file(isd_file_path): """ Purpose: Reads an ISD CSV file (gz or uncompressed) and returns the data in a data structure. Assumptions: Usage: Author: PRI Date: June 2017 """ isd_file_name = os.path.split(isd_file_path)[1] msg = "Reading ISD file " + isd_file_name logger.info(msg) isd_site_id = isd_file_name.split("-") isd_site_id = isd_site_id[0] + "-" + isd_site_id[1] # read the file if os.path.splitext(isd_file_path)[1] == ".gz": with gzip.open(isd_file_path, 'rb') as fp: content = fp.readlines() else: with open(isd_file_path) as fp: content = fp.readlines() # get a data structure ds = qcio.DataStructure() # get the site latitude, longitude and altitude ds.globalattributes["altitude"] = float(content[0][46:51]) ds.globalattributes["latitude"] = float(content[0][28:34]) / float(1000) ds.globalattributes["longitude"] = float(content[0][34:41]) / float(1000) ds.globalattributes["isd_site_id"] = isd_site_id # initialise the data structure ds.series["DateTime"] = { "Data": [], "Flag": [], "Attr": { "long_name": "Datetime", "units": "none" } } ds.series["Wd"] = { "Data": [], "Flag": [], "Attr": { "long_name": "Wind direction", "units": "degrees" } } ds.series["Ws"] = { "Data": [], "Flag": [], "Attr": { "long_name": "Wind speed", "units": "m/s" } } ds.series["Ta"] = { "Data": [], "Flag": [], "Attr": { "long_name": "Air temperature", "units": "C" } } ds.series["Td"] = { "Data": [], "Flag": [], "Attr": { "long_name": "Dew point temperature", "units": "C" } } ds.series["ps"] = { "Data": [], "Flag": [], "Attr": { "long_name": "Surface pressure", "units": "kPa" } } ds.series["Precip"] = { "Data": [], "Flag": [], "Attr": { "long_name": "Precipitation", "units": "mm" } } # define the codes for good data in the ISD file OK_obs_code = [ "AUTO ", "CRN05", "CRN15", "FM-12", "FM-15", "FM-16", "SY-MT" ] # iterate over the lines in the file and decode the data for i in range(len(content) - 1): #for i in range(10): # filter out anything other than hourly data if content[i][41:46] not in OK_obs_code: continue YY = int(content[i][15:19]) MM = int(content[i][19:21]) DD = int(content[i][21:23]) HH = int(content[i][23:25]) mm = int(content[i][25:27]) dt = datetime.datetime(YY, MM, DD, HH, mm, 0) ds.series["DateTime"]["Data"].append(pytz.utc.localize(dt)) # wind direction, degT try: ds.series["Wd"]["Data"].append(float(content[i][60:63])) except: ds.series["Wd"]["Data"].append(float(999)) # wind speed, m/s try: ds.series["Ws"]["Data"].append( float(content[i][65:69]) / float(10)) except: ds.series["Ws"]["Data"].append(float(999.9)) # air temperature, C try: ds.series["Ta"]["Data"].append( float(content[i][87:92]) / float(10)) except: ds.series["Ta"]["Data"].append(float(999.9)) # dew point temperature, C try: ds.series["Td"]["Data"].append( float(content[i][93:98]) / float(10)) except: ds.series["Td"]["Data"].append(float(999.9)) # sea level pressure, hPa try: ds.series["ps"]["Data"].append( float(content[i][99:104]) / float(10)) except: ds.series["ps"]["Data"].append(float(9999.9)) # precipitation, mm if content[i][108:111] == "AA1": try: ds.series["Precip"]["Data"].append( float(content[i][113:117]) / float(10)) except: ds.series["Precip"]["Data"].append(float(999.9)) else: ds.series["Precip"]["Data"].append(float(999.9)) # add the time zone to the DateTime ataributes ds.series["DateTime"]["Attr"]["time_zone"] = "UTC" # convert from lists to masked arrays f0 = numpy.zeros(len(ds.series["DateTime"]["Data"])) f1 = numpy.ones(len(ds.series["DateTime"]["Data"])) ds.series["DateTime"]["Data"] = numpy.array(ds.series["DateTime"]["Data"]) ds.series["DateTime"]["Flag"] = f0 ds.globalattributes["nc_nrecs"] = len(f0) dt_delta = qcutils.get_timestep(ds) ts = scipy.stats.mode(dt_delta)[0] / 60 ds.globalattributes["time_step"] = ts[0] ds.series["Wd"]["Data"] = numpy.ma.masked_equal(ds.series["Wd"]["Data"], 999) ds.series["Wd"]["Flag"] = numpy.where( numpy.ma.getmaskarray(ds.series["Wd"]["Data"]) == True, f1, f0) ds.series["Ws"]["Data"] = numpy.ma.masked_equal(ds.series["Ws"]["Data"], 999.9) ds.series["Ws"]["Flag"] = numpy.where( numpy.ma.getmaskarray(ds.series["Ws"]["Data"]) == True, f1, f0) ds.series["Ta"]["Data"] = numpy.ma.masked_equal(ds.series["Ta"]["Data"], 999.9) ds.series["Ta"]["Flag"] = numpy.where( numpy.ma.getmaskarray(ds.series["Ta"]["Data"]) == True, f1, f0) ds.series["Td"]["Data"] = numpy.ma.masked_equal(ds.series["Td"]["Data"], 999.9) ds.series["Td"]["Flag"] = numpy.where( numpy.ma.getmaskarray(ds.series["Td"]["Data"]) == True, f1, f0) # hPa to kPa ds.series["ps"]["Data"] = numpy.ma.masked_equal(ds.series["ps"]["Data"], 9999.9) / float(10) ds.series["ps"]["Flag"] = numpy.where( numpy.ma.getmaskarray(ds.series["ps"]["Data"]) == True, f1, f0) # convert sea level pressure to station pressure site_altitude = float(ds.globalattributes["altitude"]) cfac = numpy.ma.exp( (-1 * site_altitude) / ((ds.series["Ta"]["Data"] + 273.15) * 29.263)) ds.series["ps"]["Data"] = ds.series["ps"]["Data"] * cfac # do precipitation and apply crude limits ds.series["Precip"]["Data"] = numpy.ma.masked_equal( ds.series["Precip"]["Data"], 999.9) condition = (ds.series["Precip"]["Data"] < 0) | (ds.series["Precip"]["Data"] > 100) ds.series["Precip"]["Data"] = numpy.ma.masked_where( condition, ds.series["Precip"]["Data"]) ds.series["Precip"]["Flag"] = numpy.where( numpy.ma.getmaskarray(ds.series["Precip"]["Data"]) == True, f1, f0) # get the humidities from Td Ta, flag, attr = qcutils.GetSeriesasMA(ds, "Ta") Td, flag, attr = qcutils.GetSeriesasMA(ds, "Td") ps, flag, attr = qcutils.GetSeriesasMA(ds, "ps") RH = mf.RHfromdewpoint(Td, Ta) flag = numpy.where(numpy.ma.getmaskarray(RH) == True, f1, f0) attr = {"long_name": "Relative humidity", "units": "%"} qcutils.CreateSeries(ds, "RH", RH, Flag=flag, Attr=attr) Ah = mf.absolutehumidityfromRH(Ta, RH) flag = numpy.where(numpy.ma.getmaskarray(Ah) == True, f1, f0) attr = {"long_name": "Absolute humidity", "units": "g/m3"} qcutils.CreateSeries(ds, "Ah", Ah, Flag=flag, Attr=attr) q = mf.specifichumidityfromRH(RH, Ta, ps) flag = numpy.where(numpy.ma.getmaskarray(q) == True, f1, f0) attr = {"long_name": "Specific humidity", "units": "kg/kg"} qcutils.CreateSeries(ds, "q", q, Flag=flag, Attr=attr) # return the data return ds
def ApplyTurbulenceFilter(cf,ds,ustar_threshold=None): """ Purpose: Usage: Author: Date: """ opt = ApplyTurbulenceFilter_checks(cf,ds) if not opt["OK"]: return # local point to datetime series ldt = ds.series["DateTime"]["Data"] # time step ts = int(ds.globalattributes["time_step"]) # dictionary of utar thresold values if ustar_threshold==None: ustar_dict = qcrp.get_ustar_thresholds(cf,ldt) else: ustar_dict = qcrp.get_ustar_thresholds_annual(ldt,ustar_threshold) # initialise a dictionary for the indicator series indicators = {} # get data for the indicator series ustar,ustar_flag,ustar_attr = qcutils.GetSeriesasMA(ds,"ustar") Fsd,f,a = qcutils.GetSeriesasMA(ds,"Fsd") if "solar_altitude" not in ds.series.keys(): qcts.get_synthetic_fsd(ds) Fsd_syn,f,a = qcutils.GetSeriesasMA(ds,"Fsd_syn") sa,f,a = qcutils.GetSeriesasMA(ds,"solar_altitude") # get the day/night indicator series # indicators["day"] = 1 ==> day time, indicators["day"] = 0 ==> night time indicators["day"] = qcrp.get_day_indicator(cf,Fsd,Fsd_syn,sa) ind_day = indicators["day"]["values"] # get the turbulence indicator series if opt["turbulence_filter"].lower()=="ustar": # indicators["turbulence"] = 1 ==> turbulent, indicators["turbulence"] = 0 ==> not turbulent indicators["turbulence"] = qcrp.get_turbulence_indicator_ustar(ldt,ustar,ustar_dict,ts) elif opt["turbulence_filter"].lower()=="ustar_evg": # ustar >= threshold ==> ind_ustar = 1, ustar < threshold == ind_ustar = 0 indicators["ustar"] = qcrp.get_turbulence_indicator_ustar(ldt,ustar,ustar_dict,ts) ind_ustar = indicators["ustar"]["values"] # ustar >= threshold during day AND ustar has been >= threshold since sunset ==> indicators["turbulence"] = 1 # indicators["turbulence"] = 0 during night once ustar has dropped below threshold even if it # increases above the threshold later in the night indicators["turbulence"] = qcrp.get_turbulence_indicator_ustar_evg(ldt,ind_day,ind_ustar,ustar,ustar_dict,ts) elif opt["turbulence_filter"].lower()=="l": #indicators["turbulence] = get_turbulence_indicator_l(ldt,L,z,d,zmdonL_threshold) indicators["turbulence"] = numpy.ones(len(ldt)) msg = " Use of L as turbulence indicator not implemented, no filter applied" log.warning(msg) else: msg = " Unrecognised turbulence filter option (" msg = msg+opt["turbulence_filter"]+"), no filter applied" log.error(msg) return # initialise the final indicator series as the turbulence indicator # subsequent filters will modify the final indicator series # we must use copy.deepcopy() otherwise the "values" array will only # be copied by reference not value. Damn Python's default of copy by reference! indicators["final"] = copy.deepcopy(indicators["turbulence"]) # check to see if the user wants to accept all day time observations # regardless of ustar value if opt["accept_day_times"].lower()=="yes": # if yes, then we force the final indicator to be 1 # if ustar is below the threshold during the day. idx = numpy.where(indicators["day"]["values"]==1)[0] indicators["final"]["values"][idx] = numpy.int(1) indicators["final"]["attr"].update(indicators["day"]["attr"]) # get the evening indicator series indicators["evening"] = qcrp.get_evening_indicator(cf,Fsd,Fsd_syn,sa,ts) indicators["dayevening"] = {"values":indicators["day"]["values"]+indicators["evening"]["values"]} indicators["dayevening"]["attr"] = indicators["day"]["attr"].copy() indicators["dayevening"]["attr"].update(indicators["evening"]["attr"]) if opt["use_evening_filter"].lower()=="yes": idx = numpy.where(indicators["dayevening"]["values"]==0)[0] indicators["final"]["values"][idx] = numpy.int(0) indicators["final"]["attr"].update(indicators["dayevening"]["attr"]) # save the indicator series ind_flag = numpy.zeros(len(ldt)) long_name = "Turbulence indicator, 1 for turbulent, 0 for non-turbulent" ind_attr = qcutils.MakeAttributeDictionary(long_name=long_name,units="None") qcutils.CreateSeries(ds,"turbulence_indicator",indicators["turbulence"]["values"],Flag=ind_flag,Attr=ind_attr) long_name = "Day indicator, 1 for day time, 0 for night time" ind_attr = qcutils.MakeAttributeDictionary(long_name=long_name,units="None") qcutils.CreateSeries(ds,"day_indicator",indicators["day"]["values"],Flag=ind_flag,Attr=ind_attr) long_name = "Evening indicator, 1 for evening, 0 for not evening" ind_attr = qcutils.MakeAttributeDictionary(long_name=long_name,units="None") qcutils.CreateSeries(ds,"evening_indicator",indicators["evening"]["values"],Flag=ind_flag,Attr=ind_attr) long_name = "Day/evening indicator, 1 for day/evening, 0 for not day/evening" ind_attr = qcutils.MakeAttributeDictionary(long_name=long_name,units="None") qcutils.CreateSeries(ds,"dayevening_indicator",indicators["dayevening"]["values"],Flag=ind_flag,Attr=ind_attr) long_name = "Final indicator, 1 for use data, 0 for don't use data" ind_attr = qcutils.MakeAttributeDictionary(long_name=long_name,units="None") qcutils.CreateSeries(ds,"final_indicator",indicators["final"]["values"],Flag=ind_flag,Attr=ind_attr) # loop over the series to be filtered for series in opt["filter_list"]: msg = " Applying "+opt["turbulence_filter"]+" filter to "+series log.info(msg) # get the data data,flag,attr = qcutils.GetSeriesasMA(ds,series) # continue to next series if this series has been filtered before if "turbulence_filter" in attr: msg = " Series "+series+" has already been filtered, skipping ..." log.warning(msg) continue # save the non-filtered data qcutils.CreateSeries(ds,series+"_nofilter",data,Flag=flag,Attr=attr) # now apply the filter data_filtered = numpy.ma.masked_where(indicators["final"]["values"]==0,data,copy=True) flag_filtered = numpy.copy(flag) idx = numpy.where(indicators["final"]["values"]==0)[0] flag_filtered[idx] = numpy.int32(61) # update the series attributes for item in indicators["final"]["attr"].keys(): attr[item] = indicators["final"]["attr"][item] # and write the filtered data to the data structure qcutils.CreateSeries(ds,series,data_filtered,Flag=flag_filtered,Attr=attr) # and write a copy of the filtered datas to the data structure so it # will still exist once the gap filling has been done qcutils.CreateSeries(ds,series+"_filtered",data_filtered,Flag=flag_filtered,Attr=attr) return
ds_aws_60minute.globalattributes["time_step"] = str(60) # put the Python datetime into the data structure ds_aws_60minute.series["DateTime"] = {} ds_aws_60minute.series["DateTime"]["Data"] = dt_aws_60minute ds_aws_60minute.series["DateTime"]["Flag"] = numpy.zeros(nRecs_60minute, dtype=numpy.int32) ds_aws_60minute.series["DateTime"][ "Attr"] = qcutils.MakeAttributeDictionary( long_name="DateTime in local time zone", units="None") # add the Excel datetime, year, month etc qcutils.get_xldatefromdatetime(ds_aws_60minute) qcutils.get_ymdhmsfromdatetime(ds_aws_60minute) # loop over the series and take the average (every thing but Precip) or sum (Precip) for item in series_list: if "Precip" in item: data_30minute, flag_30minute, attr = qcutils.GetSeriesasMA( ds_aws_30minute, item, si=si_wholehour, ei=ei_wholehour) data_2d = numpy.reshape(data_30minute, (nRecs_30minute / 2, 2)) flag_2d = numpy.reshape(flag_30minute, (nRecs_30minute / 2, 2)) data_60minute = numpy.ma.sum(data_2d, axis=1) flag_60minute = numpy.ma.max(flag_2d, axis=1) qcutils.CreateSeries(ds_aws_60minute, item, data_60minute, flag_60minute, attr) elif "Wd" in item: Ws_30minute, flag_30minute, attr = qcutils.GetSeriesasMA( ds_aws_30minute, item, si=si_wholehour, ei=ei_wholehour) Wd_30minute, flag_30minute, attr = qcutils.GetSeriesasMA( ds_aws_30minute, item, si=si_wholehour, ei=ei_wholehour) U_30minute, V_30minute = qcutils.convert_WsWdtoUV( Ws_30minute, Wd_30minute) U_2d = numpy.reshape(U_30minute, (nRecs_30minute / 2, 2)) V_2d = numpy.reshape(V_30minute, (nRecs_30minute / 2, 2))
def climatology(cf): nc_filename = qcio.get_infilenamefromcf(cf) if not qcutils.file_exists(nc_filename): return xl_filename = nc_filename.replace(".nc", "_Climatology.xls") xlFile = xlwt.Workbook() ds = qcio.nc_read_series(nc_filename) # calculate Fa if it is not in the data structure if "Fa" not in ds.series.keys(): if "Fn" in ds.series.keys() and "Fg" in ds.series.keys(): qcts.CalculateAvailableEnergy(ds, Fa_out='Fa', Fn_in='Fn', Fg_in='Fg') else: log.warning(" Climatology: Fn or Fg not in data struicture") # get the time step ts = int(ds.globalattributes['time_step']) # get the site name SiteName = ds.globalattributes['site_name'] # get the datetime series dt = ds.series['DateTime']['Data'] Hdh = ds.series['Hdh']['Data'] Month = ds.series['Month']['Data'] # get the initial start and end dates StartDate = str(dt[0]) EndDate = str(dt[-1]) # find the start index of the first whole day (time=00:30) si = qcutils.GetDateIndex(dt, StartDate, ts=ts, default=0, match='startnextday') # find the end index of the last whole day (time=00:00) ei = qcutils.GetDateIndex(dt, EndDate, ts=ts, default=-1, match='endpreviousday') # get local views of the datetime series ldt = dt[si:ei + 1] Hdh = Hdh[si:ei + 1] Month = Month[si:ei + 1] # get the number of time steps in a day and the number of days in the data ntsInDay = int(24.0 * 60.0 / float(ts)) nDays = int(len(ldt)) / ntsInDay for ThisOne in cf['Variables'].keys(): if "AltVarName" in cf['Variables'][ThisOne].keys(): ThisOne = cf['Variables'][ThisOne]["AltVarName"] if ThisOne in ds.series.keys(): log.info(" Doing climatology for " + ThisOne) data, f, a = qcutils.GetSeriesasMA(ds, ThisOne, si=si, ei=ei) if numpy.ma.count(data) == 0: log.warning(" No data for " + ThisOne + ", skipping ...") continue fmt_str = get_formatstring(cf, ThisOne, fmt_def='') xlSheet = xlFile.add_sheet(ThisOne) Av_all = do_diurnalstats(Month, Hdh, data, xlSheet, format_string=fmt_str, ts=ts) # now do it for each day # we want to preserve any data that has been truncated by the use of the "startnextday" # and "endpreviousday" match options used above. Here we revisit the start and end indices # and adjust these backwards and forwards respectively if data has been truncated. nDays_daily = nDays ei_daily = ei si_daily = si sdate = ldt[0] edate = ldt[-1] # is there data after the current end date? if dt[-1] > ldt[-1]: # if so, push the end index back by 1 day so it is included ei_daily = ei + ntsInDay nDays_daily = nDays_daily + 1 edate = ldt[-1] + datetime.timedelta(days=1) # is there data before the current start date? if dt[0] < ldt[0]: # if so, push the start index back by 1 day so it is included si_daily = si - ntsInDay nDays_daily = nDays_daily + 1 sdate = ldt[0] - datetime.timedelta(days=1) # get the data and use the "pad" option to add missing data if required to # complete the extra days data, f, a = qcutils.GetSeriesasMA(ds, ThisOne, si=si_daily, ei=ei_daily, mode="pad") data_daily = data.reshape(nDays_daily, ntsInDay) xlSheet = xlFile.add_sheet(ThisOne + '(day)') write_data_1columnpertimestep(xlSheet, data_daily, ts, startdate=sdate, format_string=fmt_str) data_daily_i = do_2dinterpolation(data_daily) xlSheet = xlFile.add_sheet(ThisOne + 'i(day)') write_data_1columnpertimestep(xlSheet, data_daily_i, ts, startdate=sdate, format_string=fmt_str) elif ThisOne == "EF": log.info(" Doing evaporative fraction") EF = numpy.ma.zeros([48, 12]) + float(c.missing_value) Hdh, f, a = qcutils.GetSeriesasMA(ds, 'Hdh', si=si, ei=ei) Fa, f, a = qcutils.GetSeriesasMA(ds, 'Fa', si=si, ei=ei) Fe, f, a = qcutils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) for m in range(1, 13): mi = numpy.where(Month == m)[0] Fa_Num, Hr, Fa_Av, Sd, Mx, Mn = get_diurnalstats( Hdh[mi], Fa[mi], ts) Fe_Num, Hr, Fe_Av, Sd, Mx, Mn = get_diurnalstats( Hdh[mi], Fe[mi], ts) index = numpy.ma.where((Fa_Num > 4) & (Fe_Num > 4)) EF[:, m - 1][index] = Fe_Av[index] / Fa_Av[index] # reject EF values greater than upper limit or less than lower limit upr, lwr = get_rangecheck_limit(cf, 'EF') EF = numpy.ma.filled( numpy.ma.masked_where((EF > upr) | (EF < lwr), EF), float(c.missing_value)) # write the EF to the Excel file xlSheet = xlFile.add_sheet('EF') write_data_1columnpermonth(xlSheet, EF, ts, format_string='0.00') # do the 2D interpolation to fill missing EF values EFi = do_2dinterpolation(EF) xlSheet = xlFile.add_sheet('EFi') write_data_1columnpermonth(xlSheet, EFi, ts, format_string='0.00') # now do EF for each day Fa, f, a = qcutils.GetSeriesasMA(ds, 'Fa', si=si, ei=ei) Fe, f, a = qcutils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) EF = Fe / Fa EF = numpy.ma.filled( numpy.ma.masked_where((EF > upr) | (EF < lwr), EF), float(c.missing_value)) EF_daily = EF.reshape(nDays, ntsInDay) xlSheet = xlFile.add_sheet('EF(day)') write_data_1columnpertimestep(xlSheet, EF_daily, ts, startdate=ldt[0], format_string='0.00') EFi = do_2dinterpolation(EF_daily) xlSheet = xlFile.add_sheet('EFi(day)') write_data_1columnpertimestep(xlSheet, EFi, ts, startdate=ldt[0], format_string='0.00') elif ThisOne == "BR": log.info(" Doing Bowen ratio") BR = numpy.ma.zeros([48, 12]) + float(c.missing_value) Fe, f, a = qcutils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) Fh, f, a = qcutils.GetSeriesasMA(ds, 'Fh', si=si, ei=ei) for m in range(1, 13): mi = numpy.where(Month == m)[0] Fh_Num, Hr, Fh_Av, Sd, Mx, Mn = get_diurnalstats( Hdh[mi], Fh[mi], ts) Fe_Num, Hr, Fe_Av, Sd, Mx, Mn = get_diurnalstats( Hdh[mi], Fe[mi], ts) index = numpy.ma.where((Fh_Num > 4) & (Fe_Num > 4)) BR[:, m - 1][index] = Fh_Av[index] / Fe_Av[index] # reject BR values greater than upper limit or less than lower limit upr, lwr = get_rangecheck_limit(cf, 'BR') BR = numpy.ma.filled( numpy.ma.masked_where((BR > upr) | (BR < lwr), BR), float(c.missing_value)) # write the BR to the Excel file xlSheet = xlFile.add_sheet('BR') write_data_1columnpermonth(xlSheet, BR, ts, format_string='0.00') # do the 2D interpolation to fill missing EF values BRi = do_2dinterpolation(BR) xlSheet = xlFile.add_sheet('BRi') write_data_1columnpermonth(xlSheet, BRi, ts, format_string='0.00') # now do BR for each day ... Fe, f, a = qcutils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) Fh, f, a = qcutils.GetSeriesasMA(ds, 'Fh', si=si, ei=ei) BR = Fh / Fe BR = numpy.ma.filled( numpy.ma.masked_where((BR > upr) | (BR < lwr), BR), float(c.missing_value)) BR_daily = BR.reshape(nDays, ntsInDay) xlSheet = xlFile.add_sheet('BR(day)') write_data_1columnpertimestep(xlSheet, BR_daily, ts, startdate=ldt[0], format_string='0.00') BRi = do_2dinterpolation(BR_daily) xlSheet = xlFile.add_sheet('BRi(day)') write_data_1columnpertimestep(xlSheet, BRi, ts, startdate=ldt[0], format_string='0.00') elif ThisOne == "WUE": log.info(" Doing ecosystem WUE") WUE = numpy.ma.zeros([48, 12]) + float(c.missing_value) Fe, f, a = qcutils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) Fc, f, a = qcutils.GetSeriesasMA(ds, 'Fc', si=si, ei=ei) for m in range(1, 13): mi = numpy.where(Month == m)[0] Fc_Num, Hr, Fc_Av, Sd, Mx, Mn = get_diurnalstats( Hdh[mi], Fc[mi], ts) Fe_Num, Hr, Fe_Av, Sd, Mx, Mn = get_diurnalstats( Hdh[mi], Fe[mi], ts) index = numpy.ma.where((Fc_Num > 4) & (Fe_Num > 4)) WUE[:, m - 1][index] = Fc_Av[index] / Fe_Av[index] # reject WUE values greater than upper limit or less than lower limit upr, lwr = get_rangecheck_limit(cf, 'WUE') WUE = numpy.ma.filled( numpy.ma.masked_where((WUE > upr) | (WUE < lwr), WUE), float(c.missing_value)) # write the WUE to the Excel file xlSheet = xlFile.add_sheet('WUE') write_data_1columnpermonth(xlSheet, WUE, ts, format_string='0.00000') # do the 2D interpolation to fill missing EF values WUEi = do_2dinterpolation(WUE) xlSheet = xlFile.add_sheet('WUEi') write_data_1columnpermonth(xlSheet, WUEi, ts, format_string='0.00000') # now do WUE for each day ... Fe, f, a = qcutils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) Fc, f, a = qcutils.GetSeriesasMA(ds, 'Fc', si=si, ei=ei) WUE = Fc / Fe WUE = numpy.ma.filled( numpy.ma.masked_where((WUE > upr) | (WUE < lwr), WUE), float(c.missing_value)) WUE_daily = WUE.reshape(nDays, ntsInDay) xlSheet = xlFile.add_sheet('WUE(day)') write_data_1columnpertimestep(xlSheet, WUE_daily, ts, startdate=ldt[0], format_string='0.00000') WUEi = do_2dinterpolation(WUE_daily) xlSheet = xlFile.add_sheet('WUEi(day)') write_data_1columnpertimestep(xlSheet, WUEi, ts, startdate=ldt[0], format_string='0.00000') else: log.warning(" qcclim.climatology: requested variable " + ThisOne + " not in data structure") continue log.info(" Saving Excel file " + xl_filename) xlFile.save(xl_filename)
def rpLT_createdict(cf, ds, series): """ Purpose: Creates a dictionary in ds to hold information about estimating ecosystem respiration using the Lloyd-Taylor method. Usage: Author: PRI Date October 2015 """ # get the section of the control file containing the series section = qcutils.get_cfsection(cf, series=series, mode="quiet") # return without doing anything if the series isn't in a control file section if len(section) == 0: logger.error("ERUsingLloydTaylor: Series " + series + " not found in control file, skipping ...") return # check that none of the drivers have missing data driver_list = ast.literal_eval( cf[section][series]["ERUsingLloydTaylor"]["drivers"]) target = cf[section][series]["ERUsingLloydTaylor"]["target"] for label in driver_list: data, flag, attr = qcutils.GetSeriesasMA(ds, label) if numpy.ma.count_masked(data) != 0: logger.error("ERUsingLloydTaylor: driver " + label + " contains missing data, skipping target " + target) return # create the dictionary keys for this series rpLT_info = {} # site name rpLT_info["site_name"] = ds.globalattributes["site_name"] # source series for ER opt = qcutils.get_keyvaluefromcf(cf, [section, series, "ERUsingLloydTaylor"], "source", default="Fc") rpLT_info["source"] = opt # target series name rpLT_info["target"] = cf[section][series]["ERUsingLloydTaylor"]["target"] # list of drivers rpLT_info["drivers"] = ast.literal_eval( cf[section][series]["ERUsingLloydTaylor"]["drivers"]) # name of SOLO output series in ds rpLT_info["output"] = cf[section][series]["ERUsingLloydTaylor"]["output"] # results of best fit for plotting later on rpLT_info["results"] = { "startdate": [], "enddate": [], "No. points": [], "r": [], "Bias": [], "RMSE": [], "Frac Bias": [], "NMSE": [], "Avg (obs)": [], "Avg (LT)": [], "Var (obs)": [], "Var (LT)": [], "Var ratio": [], "m_ols": [], "b_ols": [] } # create the configuration dictionary rpLT_info["configs_dict"] = get_configs_dict(cf, ds) # create an empty series in ds if the output series doesn't exist yet if rpLT_info["output"] not in ds.series.keys(): data, flag, attr = qcutils.MakeEmptySeries(ds, rpLT_info["output"]) qcutils.CreateSeries(ds, rpLT_info["output"], data, flag, attr) # create the merge directory in the data structure if "merge" not in dir(ds): ds.merge = {} if "standard" not in ds.merge.keys(): ds.merge["standard"] = {} # create the dictionary keys for this series ds.merge["standard"][series] = {} # output series name ds.merge["standard"][series]["output"] = series # source ds.merge["standard"][series]["source"] = ast.literal_eval( cf[section][series]["MergeSeries"]["Source"]) # create an empty series in ds if the output series doesn't exist yet if ds.merge["standard"][series]["output"] not in ds.series.keys(): data, flag, attr = qcutils.MakeEmptySeries( ds, ds.merge["standard"][series]["output"]) qcutils.CreateSeries(ds, ds.merge["standard"][series]["output"], data, flag, attr) return rpLT_info
def rpLT_plot(pd, ds, series, driverlist, targetlabel, outputlabel, LT_info, si=0, ei=-1): """ Plot the results of the Lloyd-Taylor run. """ # get the time step ts = int(ds.globalattributes['time_step']) # get a local copy of the datetime series if ei == -1: dt = ds.series['DateTime']['Data'][si:] else: dt = ds.series['DateTime']['Data'][si:ei + 1] xdt = numpy.array(dt) Hdh, f, a = qcutils.GetSeriesasMA(ds, 'Hdh', si=si, ei=ei) # get the observed and modelled values obs, f, a = qcutils.GetSeriesasMA(ds, targetlabel, si=si, ei=ei) mod, f, a = qcutils.GetSeriesasMA(ds, outputlabel, si=si, ei=ei) # make the figure if LT_info["show_plots"]: plt.ion() else: plt.ioff() fig = plt.figure(pd["fig_num"], figsize=(13, 8)) fig.clf() fig.canvas.set_window_title(targetlabel + " (LT): " + pd["startdate"] + " to " + pd["enddate"]) plt.figtext(0.5, 0.95, pd["title"], ha='center', size=16) # XY plot of the diurnal variation rect1 = [0.10, pd["margin_bottom"], pd["xy_width"], pd["xy_height"]] ax1 = plt.axes(rect1) # get the diurnal stats of the observations mask = numpy.ma.mask_or(obs.mask, mod.mask) obs_mor = numpy.ma.array(obs, mask=mask) dstats = qcutils.get_diurnalstats(dt, obs_mor, LT_info) ax1.plot(dstats["Hr"], dstats["Av"], 'b-', label="Obs") # get the diurnal stats of all SOLO predictions dstats = qcutils.get_diurnalstats(dt, mod, LT_info) ax1.plot(dstats["Hr"], dstats["Av"], 'r-', label="LT(all)") mod_mor = numpy.ma.masked_where(numpy.ma.getmaskarray(obs) == True, mod, copy=True) dstats = qcutils.get_diurnalstats(dt, mod_mor, LT_info) ax1.plot(dstats["Hr"], dstats["Av"], 'g-', label="LT(obs)") plt.xlim(0, 24) plt.xticks([0, 6, 12, 18, 24]) ax1.set_ylabel(targetlabel) ax1.set_xlabel('Hour') ax1.legend(loc='upper right', frameon=False, prop={'size': 8}) # XY plot of the 30 minute data rect2 = [0.40, pd["margin_bottom"], pd["xy_width"], pd["xy_height"]] ax2 = plt.axes(rect2) ax2.plot(mod, obs, 'b.') ax2.set_ylabel(targetlabel + '_obs') ax2.set_xlabel(targetlabel + '_LT') # plot the best fit line coefs = numpy.ma.polyfit(numpy.ma.copy(mod), numpy.ma.copy(obs), 1) xfit = numpy.ma.array([numpy.ma.minimum(mod), numpy.ma.maximum(mod)]) yfit = numpy.polyval(coefs, xfit) r = numpy.ma.corrcoef(mod, obs) ax2.plot(xfit, yfit, 'r--', linewidth=3) eqnstr = 'y = %.3fx + %.3f, r = %.3f' % (coefs[0], coefs[1], r[0][1]) ax2.text(0.5, 0.875, eqnstr, fontsize=8, horizontalalignment='center', transform=ax2.transAxes) # write the fit statistics to the plot numpoints = numpy.ma.count(obs) numfilled = numpy.ma.count(mod) - numpy.ma.count(obs) diff = mod - obs bias = numpy.ma.average(diff) LT_info["er"][series]["results"]["Bias"].append(bias) rmse = numpy.ma.sqrt(numpy.ma.mean((obs - mod) * (obs - mod))) plt.figtext(0.725, 0.225, 'No. points') plt.figtext(0.825, 0.225, str(numpoints)) LT_info["er"][series]["results"]["No. points"].append(numpoints) plt.figtext(0.725, 0.200, 'No. filled') plt.figtext(0.825, 0.200, str(numfilled)) plt.figtext(0.725, 0.175, 'Slope') plt.figtext(0.825, 0.175, str(qcutils.round2sig(coefs[0], sig=4))) LT_info["er"][series]["results"]["m_ols"].append(coefs[0]) plt.figtext(0.725, 0.150, 'Offset') plt.figtext(0.825, 0.150, str(qcutils.round2sig(coefs[1], sig=4))) LT_info["er"][series]["results"]["b_ols"].append(coefs[1]) plt.figtext(0.725, 0.125, 'r') plt.figtext(0.825, 0.125, str(qcutils.round2sig(r[0][1], sig=4))) LT_info["er"][series]["results"]["r"].append(r[0][1]) plt.figtext(0.725, 0.100, 'RMSE') plt.figtext(0.825, 0.100, str(qcutils.round2sig(rmse, sig=4))) LT_info["er"][series]["results"]["RMSE"].append(rmse) var_obs = numpy.ma.var(obs) LT_info["er"][series]["results"]["Var (obs)"].append(var_obs) var_mod = numpy.ma.var(mod) LT_info["er"][series]["results"]["Var (LT)"].append(var_mod) LT_info["er"][series]["results"]["Var ratio"].append(var_obs / var_mod) LT_info["er"][series]["results"]["Avg (obs)"].append(numpy.ma.average(obs)) LT_info["er"][series]["results"]["Avg (LT)"].append(numpy.ma.average(mod)) # time series of drivers and target ts_axes = [] rect = [ pd["margin_left"], pd["ts_bottom"], pd["ts_width"], pd["ts_height"] ] ts_axes.append(plt.axes(rect)) #ts_axes[0].plot(xdt,obs,'b.',xdt,mod,'r-') ts_axes[0].scatter(xdt, obs, c=Hdh) ts_axes[0].plot(xdt, mod, 'r-') plt.axhline(0) ts_axes[0].set_xlim(xdt[0], xdt[-1]) TextStr = targetlabel + '_obs (' + ds.series[targetlabel]['Attr'][ 'units'] + ')' ts_axes[0].text(0.05, 0.85, TextStr, color='b', horizontalalignment='left', transform=ts_axes[0].transAxes) TextStr = outputlabel + '(' + ds.series[outputlabel]['Attr']['units'] + ')' ts_axes[0].text(0.85, 0.85, TextStr, color='r', horizontalalignment='right', transform=ts_axes[0].transAxes) for ThisOne, i in zip(driverlist, range(1, pd["nDrivers"] + 1)): this_bottom = pd["ts_bottom"] + i * pd["ts_height"] rect = [ pd["margin_left"], this_bottom, pd["ts_width"], pd["ts_height"] ] ts_axes.append(plt.axes(rect, sharex=ts_axes[0])) data, flag, attr = qcutils.GetSeriesasMA(ds, ThisOne, si=si, ei=ei) data_notgf = numpy.ma.masked_where(flag != 0, data) data_gf = numpy.ma.masked_where(flag == 0, data) ts_axes[i].plot(xdt, data_notgf, 'b-') ts_axes[i].plot(xdt, data_gf, 'r-') plt.setp(ts_axes[i].get_xticklabels(), visible=False) TextStr = ThisOne + '(' + ds.series[ThisOne]['Attr']['units'] + ')' ts_axes[i].text(0.05, 0.85, TextStr, color='b', horizontalalignment='left', transform=ts_axes[i].transAxes) # save a hard copy of the plot sdt = xdt[0].strftime("%Y%m%d") edt = xdt[-1].strftime("%Y%m%d") plot_path = LT_info["plot_path"] + "L6/" if not os.path.exists(plot_path): os.makedirs(plot_path) figname = plot_path + pd["site_name"].replace(" ", "") + "_LT_" + pd["label"] figname = figname + "_" + sdt + "_" + edt + '.png' fig.savefig(figname, format='png') # draw the plot on the screen if LT_info["show_plots"]: plt.draw() plt.pause(1) plt.ioff() else: plt.close(fig) plt.ion()
# and remove the datetime if "DateTime" in series_list: series_list.remove("DateTime") # and then we loop over the variables to be copied for label in series_list: # append a number, unique to each ISD station, to the variable label all_label = label + "_" + str(i) # create empty data and flag arrays variable = qcutils.create_empty_variable(all_label, nrecs) qcutils.CreateSeries(ds_all, all_label, variable["Data"], Flag=variable["Flag"], Attr=variable["Attr"]) # read the data out of the ISD site data structure data, flag, attr = qcutils.GetSeriesasMA(ds_out[i], label) # add the ISD site ID attr["isd_site_id"] = isd_site_id # put the data, flag and attributes into the all-in-one data structure ds_all.series[all_label]["Data"][idx] = data ds_all.series[all_label]["Flag"][idx] = flag ds_all.series[all_label]["Attr"] = copy.deepcopy(attr) # write the netCDF file with the combined data for this year if len(fluxnet_id) == 0: nc_dir_path = os.path.join(out_base_path, site, "Data", "ISD") nc_file_name = site + "_ISD_" + str(year) + ".nc" else: nc_dir_path = os.path.join(out_base_path, fluxnet_id, "Data", "ISD") nc_file_name = fluxnet_id + "_ISD_" + str(year) + ".nc" if not os.path.exists(nc_dir_path):
def interpolate_ds(ds_in, ts, k=3): """ Purpose: Interpolate the contents of a data structure onto a different time step. Assumptions: Usage: Author: PRI Date: June 2017 """ # instance the output data structure ds_out = qcio.DataStructure() # copy the global attributes for key in ds_in.globalattributes.keys(): ds_out.globalattributes[key] = ds_in.globalattributes[key] # add the time step ds_out.globalattributes["time_step"] = str(ts) # generate a regular time series at the required time step dt = ds_in.series["DateTime"]["Data"] dt0 = dt[0] - datetime.timedelta(minutes=30) start = datetime.datetime(dt0.year, dt0.month, dt0.day, dt0.hour, 0, 0) dt1 = dt[-1] + datetime.timedelta(minutes=30) end = datetime.datetime(dt1.year, dt1.month, dt1.day, dt1.hour, 0, 0) idt = [ result for result in perdelta(start, end, datetime.timedelta(minutes=ts)) ] x1 = numpy.array([toTimestamp(dt[i]) for i in range(len(dt))]) x2 = numpy.array([toTimestamp(idt[i]) for i in range(len(idt))]) # loop over the series in the data structure and interpolate ds_out.series["DateTime"] = {} ds_out.series["DateTime"]["Data"] = idt ds_out.series["DateTime"]["Flag"] = numpy.zeros(len(idt)) ds_out.series["DateTime"]["Attr"] = { "long_name": "Datetime", "units": "none" } ds_out.globalattributes["nc_nrecs"] = len(idt) series_list = list(ds_in.series.keys()) if "DateTime" in series_list: series_list.remove("DateTime") for label in series_list: #print label data_in, flag_in, attr_in = qcutils.GetSeriesasMA(ds_in, label) # check if we are dealing with precipitation if "Precip" in label: # precipitation shouldn't be interpolated, just assign any precipitation # to the ISD time stamp. data_out = numpy.ma.zeros(len(idt), dtype=numpy.float64) idx = numpy.searchsorted(x2, numpy.intersect1d(x2, x1)) data_out[idx] = data_in else: # interpolate everything else data_out = interpolate_1d(x1, data_in, x2) flag_out = numpy.zeros(len(idt)) attr_out = attr_in qcutils.CreateSeries(ds_out, label, data_out, Flag=flag_out, Attr=attr_out) return ds_out