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 = pfp_utils.GetSeriesasMA(ds, RH_in) Ta_data, Ta_flag, Ta_attr = pfp_utils.GetSeriesasMA(ds, Ta_in) Ah_data = pfp_mf.absolutehumidityfromRH(Ta_data, RH_data) ps_data, ps_flag, ps_attr = pfp_utils.GetSeriesasMA(ds, ps_in) MR_data = pfp_mf.h2o_mmolpmolfromgpm3(Ah_data, Ta_data, ps_data) MR_attr = pfp_utils.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) pfp_utils.CreateSeries(ds, MR_out, MR_data, flag, MR_attr) return 1
def DateTimeFromDoY(ds, dt_out, Year_in, DoY_in, Hdh_in): year, f, a = pfp_utils.GetSeriesasMA(ds, Year_in) doy, f, a = pfp_utils.GetSeriesasMA(ds, DoY_in) hdh, f, a = pfp_utils.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[dt_out] = {} ds.series[dt_out]["Data"] = dt ds.series[dt_out]["Flag"] = numpy.zeros(len(dt), dtype=numpy.int32) ds.series[dt_out]["Attr"] = {} ds.series[dt_out]["Attr"]["long_name"] = "Datetime in local timezone" ds.series[dt_out]["Attr"]["units"] = "None" # now remove any "data"" from empty lines series_list = ds.series.keys() if dt_out in series_list: series_list.remove(dt_out) 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 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: pfp_func.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 = pfp_utils.GetSeriesasMA(ds,RH_in) Ta_data,Ta_flag,Ta_attr = pfp_utils.GetSeriesasMA(ds,Ta_in) Ah_data = pfp_mf.absolutehumidityfromRH(Ta_data,RH_data) Ah_attr = pfp_utils.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) pfp_utils.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 = pfp_utils.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 = pfp_utils.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 = pfp_io.nc_read_series(import_filename) ts_import = ds_import.globalattributes["time_step"] ldt_import = ds_import.series["DateTime"]["Data"] si = pfp_utils.GetDateIndex(ldt_import,str(start_date),ts=ts_import,default=0,match="exact") ei = pfp_utils.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 = pfp_utils.GetSeriesasMA(ds_import,var_name,si=si,ei=ei) ldt_import = ldt_import[si:ei+1] index = pfp_utils.FindIndicesOfBInA(ldt_import,ldt) data[index] = data_import flag[index] = flag_import pfp_utils.CreateSeries(ds,label,data,flag,attr_import)
def gfClimatology_interpolateddaily(ds,series,output,xlbooks): """ Gap fill using data interpolated over a 2D array where the days are the rows and the time of day is the columns. """ # gap fill from interpolated 30 minute data xlfilename = ds.climatology[output]["file_name"] sheet_name = series+'i(day)' if sheet_name not in xlbooks[xlfilename].sheet_names(): msg = " gfClimatology: sheet "+sheet_name+" not found, skipping ..." logger.warning(msg) return ldt = ds.series["DateTime"]["Data"] thissheet = xlbooks[xlfilename].sheet_by_name(sheet_name) datemode = xlbooks[xlfilename].datemode basedate = datetime.datetime(1899, 12, 30) nts = thissheet.ncols - 1 ndays = thissheet.nrows - 2 # read the time stamp values from the climatology worksheet tsteps = thissheet.row_values(1,start_colx=1,end_colx=nts+1) # read the data from the climatology workbook val1d = numpy.ma.zeros(ndays*nts,dtype=numpy.float64) # initialise an array for the datetime of the climatological values cdt = [None]*nts*ndays # loop over the rows (days) of data for xlRow in range(ndays): # get the Excel datetime value xldatenumber = int(thissheet.cell_value(xlRow+2,0)) # convert this to a Python Datetime xldatetime = basedate+datetime.timedelta(days=xldatenumber+1462*datemode) # fill the climatology datetime array cdt[xlRow*nts:(xlRow+1)*nts] = [xldatetime+datetime.timedelta(hours=hh) for hh in tsteps] # fill the climatological value array val1d[xlRow*nts:(xlRow+1)*nts] = thissheet.row_values(xlRow+2,start_colx=1,end_colx=nts+1) # get the data to be filled with climatological values data,flag,attr = pfp_utils.GetSeriesasMA(ds,series) # get an index of missing values idx = numpy.where(numpy.ma.getmaskarray(data)==True)[0] #idx = numpy.ma.where(numpy.ma.getmaskarray(data)==True)[0] # there must be a better way to do this ... # simply using the index (idx) to set a slice of the data array to the gap filled values in val1d # does not seem to work (mask stays true on replaced values in data), the work around is to # step through the indices, find the time of the missing value in data, find the same time in the # gap filled values val1d and set the missing element of data to this element of val1d # actually ... # this may not be the fastest but it may be the most robust because it matches dates of missing data # to dates in the climatology file for ii in idx: try: jj = pfp_utils.find_nearest_value(cdt, ldt[ii]) data[ii] = val1d[jj] flag[ii] = numpy.int32(40) except ValueError: data[ii] = numpy.float64(c.missing_value) flag[ii] = numpy.int32(41) # put the gap filled data back into the data structure pfp_utils.CreateSeries(ds,output,data,flag,attr)
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 = pfp_utils.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 = pfp_utils.GetDateIndex(ldt, start_date, ts=ts, default=0, match="exact") ei = pfp_utils.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 pfp_utils.CreateSeries(ds, series, data, Flag=flag, Attr=attr) return
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: pfp_func.AhfromMR(ds,"Ah_IRGA_Av","H2O_IRGA_Av","Ta_HMP_2m","ps") 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 [MR_in, Ta_in, ps_in]: if item not in ds.series.keys(): msg = " AhfromMR: Requested series " + item + " not found, " + Ah_out + " not calculated" logger.error(msg) return 0 if Ah_out in ds.series.keys(): msg = " AhfromMR: Output series " + Ah_out + " already exists, skipping ..." logger.error(msg) return 0 MR_data, MR_flag, MR_attr = pfp_utils.GetSeriesasMA(ds, MR_in) Ta_data, Ta_flag, Ta_attr = pfp_utils.GetSeriesasMA(ds, Ta_in) ps_data, ps_flag, ps_attr = pfp_utils.GetSeriesasMA(ds, ps_in) Ah_data = pfp_mf.h2o_gpm3frommmolpmol(MR_data, Ta_data, ps_data) long_name = "Absolute humidity calculated from " + MR_in + ", " + Ta_in + " and " + ps_in Ah_attr = pfp_utils.MakeAttributeDictionary(long_name=long_name, height=MR_attr["height"], units="g/m3") flag = numpy.where(numpy.ma.getmaskarray(Ah_data) == True, ones, zeros) pfp_utils.CreateSeries(ds, Ah_out, Ah_data, flag, Ah_attr) return 1
def CoordinateFluxGaps(cf, ds, Fc_in='Fc', Fe_in='Fe', Fh_in='Fh'): if not pfp_utils.cfoptionskeylogical(cf, Key='CoordinateFluxGaps'): return if pfp_utils.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, a = pfp_utils.GetSeriesasMA(ds, Fc_in) Fe, f, a = pfp_utils.GetSeriesasMA(ds, Fe_in) Fh, f, a = pfp_utils.GetSeriesasMA(ds, Fh_in) # April 2015 PRI - changed numpy.ma.where to numpy.where index = numpy.where((numpy.ma.getmaskarray(Fc) == True) | (numpy.ma.getmaskarray(Fe) == True) | (numpy.ma.getmaskarray(Fh) == True))[0] #index = numpy.ma.where((numpy.ma.getmaskarray(Fc)==True)| #(numpy.ma.getmaskarray(Fe)==True)| #(numpy.ma.getmaskarray(Fh)==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(c.missing_value) ds.series[Fc_in]['Flag'][j] = numpy.int32(19) if Fe.mask[j] == False: Fe.mask[j] = True Fe[j] = numpy.float64(c.missing_value) ds.series[Fe_in]['Flag'][j] = numpy.int32(19) if Fh.mask[j] == False: Fh.mask[j] = True Fh[j] = numpy.float64(c.missing_value) ds.series[Fh_in]['Flag'][j] = numpy.int32(19) ds.series[Fc_in]['Data'] = numpy.ma.filled(Fc, float(c.missing_value)) ds.series[Fe_in]['Data'] = numpy.ma.filled(Fe, float(c.missing_value)) ds.series[Fh_in]['Data'] = numpy.ma.filled(Fh, float(c.missing_value)) logger.info(' Finished gap co-ordination')
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 = pfp_utils.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 pfp_utils.CreateSeries(ds, series, data, Flag=flag, Attr=attr) # now we can return return
def climatology(cf): nc_filename = pfp_io.get_infilenamefromcf(cf) if not pfp_utils.file_exists(nc_filename): return xl_filename = nc_filename.replace(".nc","_Climatology.xls") xlFile = xlwt.Workbook() ds = pfp_io.nc_read_series(nc_filename) # calculate Fa if it is not in the data structure got_Fa = True if "Fa" not in ds.series.keys(): if "Fn" in ds.series.keys() and "Fg" in ds.series.keys(): pfp_ts.CalculateAvailableEnergy(ds,Fa_out='Fa',Fn_in='Fn',Fg_in='Fg') else: got_Fa = False logger.warning(" 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 = numpy.array([(d.hour + d.minute/float(60)) for d in dt]) Month = numpy.array([d.month for d in dt]) # 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 = pfp_utils.GetDateIndex(dt,StartDate,ts=ts,default=0,match='startnextday') # find the end index of the last whole day (time=00:00) ei = pfp_utils.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(): logger.info(" Doing climatology for "+ThisOne) data,f,a = pfp_utils.GetSeriesasMA(ds,ThisOne,si=si,ei=ei) if numpy.ma.count(data)==0: logger.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 = pfp_utils.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) else: logger.warning(" Requested variable "+ThisOne+" not in data structure") continue logger.info(" Saving Excel file "+os.path.split(xl_filename)[1]) xlFile.save(xl_filename)
def rpLT_plot(pd, ds, output, drivers, target, iel, si=0, ei=-1): """ Plot the results of the Lloyd-Taylor run. """ ieli = iel["info"] ielo = iel["outputs"] # 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 = pfp_utils.GetSeriesasMA(ds, 'Hdh', si=si, ei=ei) Hdh = numpy.array( [d.hour + (d.minute + d.second / float(60)) / float(60) for d in xdt]) # get the observed and modelled values obs, f, a = pfp_utils.GetSeriesasMA(ds, target, si=si, ei=ei) mod, f, a = pfp_utils.GetSeriesasMA(ds, output, si=si, ei=ei) # make the figure if iel["gui"]["show_plots"]: plt.ion() else: plt.ioff() fig = plt.figure(pd["fig_num"], figsize=(13, 8)) fig.clf() fig.canvas.set_window_title(target + " (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 = pfp_utils.get_diurnalstats(xdt, obs_mor, ieli) ax1.plot(dstats["Hr"], dstats["Av"], 'b-', label="Obs") # get the diurnal stats of all SOLO predictions dstats = pfp_utils.get_diurnalstats(xdt, mod, ieli) 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 = pfp_utils.get_diurnalstats(xdt, mod_mor, ieli) ax1.plot(dstats["Hr"], dstats["Av"], 'g-', label="LT(obs)") plt.xlim(0, 24) plt.xticks([0, 6, 12, 18, 24]) ax1.set_ylabel(target) 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(target + '_obs') ax2.set_xlabel(target + '_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.reduce(mod), numpy.ma.maximum.reduce(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) ielo[output]["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)) ielo[output]["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(pfp_utils.round2sig(coefs[0], sig=4))) ielo[output]["results"]["m_ols"].append(coefs[0]) plt.figtext(0.725, 0.150, 'Offset') plt.figtext(0.825, 0.150, str(pfp_utils.round2sig(coefs[1], sig=4))) ielo[output]["results"]["b_ols"].append(coefs[1]) plt.figtext(0.725, 0.125, 'r') plt.figtext(0.825, 0.125, str(pfp_utils.round2sig(r[0][1], sig=4))) ielo[output]["results"]["r"].append(r[0][1]) plt.figtext(0.725, 0.100, 'RMSE') plt.figtext(0.825, 0.100, str(pfp_utils.round2sig(rmse, sig=4))) ielo[output]["results"]["RMSE"].append(rmse) var_obs = numpy.ma.var(obs) ielo[output]["results"]["Var (obs)"].append(var_obs) var_mod = numpy.ma.var(mod) ielo[output]["results"]["Var (LT)"].append(var_mod) ielo[output]["results"]["Var ratio"].append(var_obs / var_mod) ielo[output]["results"]["Avg (obs)"].append(numpy.ma.average(obs)) ielo[output]["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 = target + '_obs (' + ds.series[target]['Attr']['units'] + ')' ts_axes[0].text(0.05, 0.85, TextStr, color='b', horizontalalignment='left', transform=ts_axes[0].transAxes) TextStr = output + '(' + ds.series[output]['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(drivers, 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 = pfp_utils.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") if not os.path.exists(ieli["plot_path"]): os.makedirs(ieli["plot_path"]) figname = ieli["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 iel["gui"]["show_plots"]: plt.draw() #plt.pause(1) mypause(1) plt.ioff() else: plt.close(fig) plt.ion()
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 = pfp_rp.get_ustar_thresholds(cf, ldt) else: ustar_dict = pfp_rp.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 = pfp_utils.GetSeriesasMA(ds, "ustar") Fsd, f, a = pfp_utils.GetSeriesasMA(ds, "Fsd") if "solar_altitude" not in ds.series.keys(): pfp_ts.get_synthetic_fsd(ds) Fsd_syn, f, a = pfp_utils.GetSeriesasMA(ds, "Fsd_syn") sa, f, a = pfp_utils.GetSeriesasMA(ds, "solar_altitude") # get the day/night indicator series # indicators["day"] = 1 ==> day time, indicators["day"] = 0 ==> night time indicators["day"] = pfp_rp.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"] = pfp_rp.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"] = pfp_rp.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"] = pfp_rp.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" logger.warning(msg) else: msg = " Unrecognised turbulence filter option (" msg = msg + opt["turbulence_filter"] + "), no filter applied" logger.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"] = pfp_rp.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 = pfp_utils.MakeAttributeDictionary(long_name=long_name, units="None") pfp_utils.CreateSeries(ds, "turbulence_indicator", indicators["turbulence"]["values"], ind_flag, ind_attr) long_name = "Day indicator, 1 for day time, 0 for night time" ind_attr = pfp_utils.MakeAttributeDictionary(long_name=long_name, units="None") pfp_utils.CreateSeries(ds, "day_indicator", indicators["day"]["values"], ind_flag, ind_attr) long_name = "Evening indicator, 1 for evening, 0 for not evening" ind_attr = pfp_utils.MakeAttributeDictionary(long_name=long_name, units="None") pfp_utils.CreateSeries(ds, "evening_indicator", indicators["evening"]["values"], ind_flag, ind_attr) long_name = "Day/evening indicator, 1 for day/evening, 0 for not day/evening" ind_attr = pfp_utils.MakeAttributeDictionary(long_name=long_name, units="None") pfp_utils.CreateSeries(ds, "dayevening_indicator", indicators["dayevening"]["values"], ind_flag, ind_attr) long_name = "Final indicator, 1 for use data, 0 for don't use data" ind_attr = pfp_utils.MakeAttributeDictionary(long_name=long_name, units="None") pfp_utils.CreateSeries(ds, "final_indicator", indicators["final"]["values"], ind_flag, ind_attr) # loop over the series to be filtered for series in opt["filter_list"]: msg = " Applying " + opt["turbulence_filter"] + " filter to " + series logger.info(msg) # get the data data, flag, attr = pfp_utils.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 ..." logger.warning(msg) continue # save the non-filtered data pfp_utils.CreateSeries(ds, series + "_nofilter", data, flag, 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 pfp_utils.CreateSeries(ds, series, data_filtered, flag_filtered, 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 pfp_utils.CreateSeries(ds, series + "_filtered", data_filtered, flag_filtered, attr) return
def gfalternate_matchstartendtimes(ds,ds_alternate): """ Purpose: Match the start and end times of the alternate and tower data. The logic is as follows: - if there is no overlap between the alternate and tower data then dummy series with missing data are created for the alternate data for the period of the tower data - if the alternate and tower data overlap then truncate or pad (with missing values) the alternate data series so that the periods of the tower data and alternate data match. Usage: gfalternate_matchstartendtimes(ds,ds_alternate) where ds is the data structure containing the tower data ds_alternate is the data structure containing the alternate data Author: PRI Date: July 2015 """ # check the time steps are the same ts_tower = int(ds.globalattributes["time_step"]) ts_alternate = int(ds_alternate.globalattributes["time_step"]) if ts_tower!=ts_alternate: msg = " GapFillFromAlternate: time step for tower and alternate data are different, returning ..." logger.error(msg) ds.returncodes["GapFillFromAlternate"] = "error" return # get the start and end times of the tower and the alternate data and see if they overlap ldt_alternate = ds_alternate.series["DateTime"]["Data"] start_alternate = ldt_alternate[0] ldt_tower = ds.series["DateTime"]["Data"] end_tower = ldt_tower[-1] # since the datetime is monotonically increasing we need only check the start datetime overlap = start_alternate<=end_tower # do the alternate and tower data overlap? if overlap: # index of alternate datetimes that are also in tower datetimes #alternate_index = pfp_utils.FindIndicesOfBInA(ldt_tower,ldt_alternate) #alternate_index = [pfp_utils.find_nearest_value(ldt_tower, dt) for dt in ldt_alternate] # index of tower datetimes that are also in alternate datetimes #tower_index = pfp_utils.FindIndicesOfBInA(ldt_alternate,ldt_tower) #tower_index = [pfp_utils.find_nearest_value(ldt_alternate, dt) for dt in ldt_tower] tower_index, alternate_index = pfp_utils.FindMatchingIndices(ldt_tower, ldt_alternate) # check that the indices point to the same times ldta = [ldt_alternate[i] for i in alternate_index] ldtt = [ldt_tower[i] for i in tower_index] if ldta!=ldtt: # and exit with a helpful message if they dont msg = " Something went badly wrong and I'm giving up" logger.error(msg) sys.exit() # get a list of alternate series alternate_series_list = [item for item in ds_alternate.series.keys() if "_QCFlag" not in item] # number of records in truncated or padded alternate data nRecs_tower = len(ldt_tower) # force the alternate dattime to be the tower date time ds_alternate.series["DateTime"] = ds.series["DateTime"] # loop over the alternate series and truncate or pad as required # truncation or padding is handled by the indices for series in alternate_series_list: if series in ["DateTime","DateTime_UTC"]: continue # get the alternate data data,flag,attr = pfp_utils.GetSeriesasMA(ds_alternate,series) # create an array of missing data of the required length data_overlap = numpy.full(nRecs_tower,c.missing_value,dtype=numpy.float64) flag_overlap = numpy.ones(nRecs_tower,dtype=numpy.int32) # replace missing data with alternate data where times match data_overlap[tower_index] = data[alternate_index] flag_overlap[tower_index] = flag[alternate_index] # write the truncated or padded series back into the alternate data structure pfp_utils.CreateSeries(ds_alternate,series,data_overlap,flag_overlap,attr) # update the number of records in the file ds_alternate.globalattributes["nc_nrecs"] = nRecs_tower else: # there is no overlap between the alternate and tower data, create dummy series nRecs = len(ldt_tower) ds_alternate.globalattributes["nc_nrecs"] = nRecs ds_alternate.series["DateTime"] = ds.series["DateTime"] alternate_series_list = [item for item in ds_alternate.series.keys() if "_QCFlag" not in item] for series in alternate_series_list: if series in ["DateTime","DateTime_UTC"]: continue _, _, attr = pfp_utils.GetSeriesasMA(ds_alternate, series) data = numpy.full(nRecs, c.missing_value, dtype=numpy.float64) flag = numpy.ones(nRecs, dtype=numpy.int32) pfp_utils.CreateSeries(ds_alternate, series, data, flag, attr) ds.returncodes["GapFillFromAlternate"] = "normal"
def climatology(cf): nc_filename = pfp_io.get_infilenamefromcf(cf) if not pfp_utils.file_exists(nc_filename): return xl_filename = nc_filename.replace(".nc", "_Climatology.xls") xlFile = xlwt.Workbook() ds = pfp_io.nc_read_series(nc_filename) # calculate Fa if it is not in the data structure got_Fa = True if "Fa" not in ds.series.keys(): if "Fn" in ds.series.keys() and "Fg" in ds.series.keys(): pfp_ts.CalculateAvailableEnergy(ds, Fa_out='Fa', Fn_in='Fn', Fg_in='Fg') else: got_Fa = False logger.warning(" 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 = numpy.array([(d.hour + d.minute / float(60)) for d in dt]) Month = numpy.array([d.month for d in dt]) # 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 = pfp_utils.GetDateIndex(dt, StartDate, ts=ts, default=0, match='startnextday') # find the end index of the last whole day (time=00:00) ei = pfp_utils.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(): logger.info(" Doing climatology for " + ThisOne) data, f, a = pfp_utils.GetSeriesasMA(ds, ThisOne, si=si, ei=ei) if numpy.ma.count(data) == 0: logger.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 = pfp_utils.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" and got_Fa: logger.info(" Doing evaporative fraction") EF = numpy.ma.zeros([48, 12]) + float(c.missing_value) Hdh, f, a = pfp_utils.GetSeriesasMA(ds, 'Hdh', si=si, ei=ei) Fa, f, a = pfp_utils.GetSeriesasMA(ds, 'Fa', si=si, ei=ei) Fe, f, a = pfp_utils.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 = pfp_utils.GetSeriesasMA(ds, 'Fa', si=si, ei=ei) Fe, f, a = pfp_utils.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": logger.info(" Doing Bowen ratio") BR = numpy.ma.zeros([48, 12]) + float(c.missing_value) Fe, f, a = pfp_utils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) Fh, f, a = pfp_utils.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 = pfp_utils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) Fh, f, a = pfp_utils.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": logger.info(" Doing ecosystem WUE") WUE = numpy.ma.zeros([48, 12]) + float(c.missing_value) Fe, f, a = pfp_utils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) Fc, f, a = pfp_utils.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 = pfp_utils.GetSeriesasMA(ds, 'Fe', si=si, ei=ei) Fc, f, a = pfp_utils.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: logger.warning(" Requested variable " + ThisOne + " not in data structure") continue logger.info(" Saving Excel file " + os.path.split(xl_filename)[1]) 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 = pfp_utils.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 = pfp_utils.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 = pfp_utils.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 = pfp_utils.MakeEmptySeries(ds, rpLT_info["output"]) pfp_utils.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 = pfp_utils.MakeEmptySeries( ds, ds.merge["standard"][series]["output"]) pfp_utils.CreateSeries(ds, ds.merge["standard"][series]["output"], data, flag, attr) return rpLT_info