# # test error train on different year
trLst = [[20150402, 20160401], [20160401, 20170401], [20170401, 20180401]]
statPLst = list()
statFLst = list()
for k in range(3):
trTrain = trLst[k]
taTrain = utils.time.tRange2Array(trTrain)
taAll = utils.time.tRange2Array([20150402, 20180401])
indTrain, ind2 = utils.time.intersect(taAll, taTrain)
indTest = np.delete(np.arange(len(taAll)), indTrain)
tempYp = ypLst[k][:, indTest]
tempYf = yfLst[k][:, indTest]
tempMask = maskF[:, indTest]
tempObs = obs[:, indTest]
tempStatP = stat.statError(utils.fillNan(tempYp, tempMask),
utils.fillNan(tempObs, tempMask))
tempStatF = stat.statError(utils.fillNan(tempYf, tempMask),
utils.fillNan(tempObs, tempMask))
statPLst.append(tempStatP)
statFLst.append(tempStatF)
# plot map and time series
import importlib
importlib.reload(plot)
dataGrid = [
statPLst[0]['RMSE'] - statFLst[0]['RMSE'],
statPLst[1]['RMSE'] - statFLst[1]['RMSE'],
statPLst[2]['RMSE'] - statFLst[2]['RMSE']
]
prcp = df.getDataTs('APCP_FORA').squeeze()
temp = 1
else:
if temp != 0:
temp = temp + 1
ind = np.random.randint(0, ngrid)
print(np.array([maskObs[ind, :], maskDay[ind, :]]))
maskObsDay = maskObs * maskDay
unique, counts = np.unique(maskDay, return_counts=True)
print(np.asarray((unique, counts)).T)
print(counts / ngrid / nt)
fLst = [1, 2, 3]
statLstF = list()
statLstP = list()
maskF = (maskDay >= 1) & (maskDay <= 3)
statP = stat.statError(utils.fillNan(yp, maskF), utils.fillNan(obs, maskF))
statF = stat.statError(utils.fillNan(yf, maskF), utils.fillNan(obs, maskF))
for nf in fLst:
xp = np.full([ngrid, nt], np.nan)
xf = np.full([ngrid, nt], np.nan)
y = np.full([ngrid, nt], np.nan)
xf[maskObsDay == nf] = yf[maskObsDay == nf]
xp[maskObsDay == nf] = yp[maskObsDay == nf]
y[maskObsDay == nf] = obs[maskObsDay == nf]
statLstF.append(stat.statError(xf, y))
statLstP.append(stat.statError(xp, y))
# plot box - forecast
matplotlib.rcParams.update({'font.size': 11})
matplotlib.rcParams.update({'lines.linewidth': 2})
matplotlib.rcParams.update({'lines.markersize': 12})
maskDay = np.zeros(maskObs.shape).astype(int)
ngrid, nt = maskObs.shape
for j in range(ngrid):
temp = 0
for i in range(nt):
maskDay[j, i] = temp
if maskObs[j, i] == 1:
temp = 1
else:
if temp != 0:
temp = temp + 1
ind = np.random.randint(0, ngrid)
maskObsDay = maskObs * maskDay
unique, counts = np.unique(maskObsDay, return_counts=True)
maskF = (maskDay >= 1) & (maskDay <= 3)
statP = stat.statError(utils.fillNan(yp, maskF), utils.fillNan(obs, maskF))
statF = stat.statError(utils.fillNan(yf, maskF), utils.fillNan(obs, maskF))
maskObsDay = maskObs * maskDay
print(np.array([maskObs[ind, :], maskDay[ind, :]]))
print(np.asarray((unique, counts)).T)
print(counts / ngrid / nt)
# see result for different seasons
tRangeLst = [[20160401, 20160701], [20160701, 20161001], [20161001, 20170101],
[20170101, 20170401], [20170401, 20170701], [20170701, 20171001],
[20171001, 20180101], [20180101, 20180401]]
tAllA = utils.time.tRange2Array(tAllR)
statPLst = list()
statFLst = list()
for i in range(nt):
maskDay[j, i] = temp
if maskObs[j, i] == 1:
temp = 1
else:
if temp != 0:
temp = temp + 1
maskObsDay = maskObs * maskDay
fLst = [1, 2, 3]
statLst = list()
for nf in fLst:
maskF = maskDay == nf
temp = list()
for yf in yfLst:
statErr = stat.statError(utils.fillNan(yf, maskF),
utils.fillNan(obs, maskF))
temp.append(statErr)
statLst.append(temp)
# load result from RK
dirRK = r'D:\\data\\Koster17\\'
fileNameLst = ['rmse_lead_{}.dat'.format(x) for x in [1, 2, 3]]
tempLst = list()
for k in range(3):
# lon lat are identical. Tested
temp = np.loadtxt(os.path.join(dirRK, fileNameLst[k]))
tempLst.append(temp[:, 2])
RKlon = temp[:, 0]
RKlat = temp[:, 1]
lat, lon = df.getGeo()
maskDay[j, i] = temp
if maskObs[j, i] == 1:
temp = 1
else:
if temp != 0:
temp = temp + 1
ind = np.random.randint(0, ngrid)
maskObsDay = maskObs * maskDay
maskF = (maskDay >= 1) & (maskDay <= 3)
# figure out train and test time index
tR0 = [20150402, 20180401]
tA0 = utils.time.tRange2Array(tR0)
nt = len(tA0)
tTrainLst = list()
tTestLst = list()
for k in range(len(yrLst)):
tR = tRangeLst[k]
tA = utils.time.tRange2Array(tR)
ind0 = np.array(range(nt))
ind1, ind2 = utils.time.intersect(tA0, tA)
tTestLst.append(np.delete(ind0, ind1))
tTrainLst.append(ind1)
# calculate stat
for k in range(len(yrLst)):
yfTemp = utils.fillNan(yfLst[k], maskF)
yfTemp = yfTemp[:, tTestLst[k]]
statP = stat.statError(yfTemp, utils.fillNan(obs, maskF))
statF = stat.statError(yfTemp, utils.fillNan(obs, maskF))
statPLst = list()
statFLst = list()
for j in range(3):
tempPLst = list()
tempFLst = list()
for i in range(3):
trTest = trLst[i]
taTest = utils.time.tRange2Array(trTest)
taAll = utils.time.tRange2Array([20150402, 20180401])
ind, ind2 = utils.time.intersect(taAll, taTest)
tempYp = ypLst[j][:, ind]
tempYf = yfLst[j][:, ind]
tempMask = maskF[:, ind]
tempObs = obs[:, ind]
tempStatP = stat.statError(
utils.fillNan(tempYp, tempMask), utils.fillNan(tempObs, tempMask))
tempStatF = stat.statError(
utils.fillNan(tempYf, tempMask), utils.fillNan(tempObs, tempMask))
tempPLst.append(tempStatP)
tempFLst.append(tempStatF)
statPLst.append(tempPLst)
statFLst.append(tempFLst)
# # plot forecast error train on different year
# keyLst = ['RMSE', 'Corr']
# yrStrLst = ['2015', '2016', '2017']
# [lat, lon] = df.getGeo()
# fig, axes = plt.subplots(2, 2, figsize=[8, 4])
# key = 'RMSE'
# for j in range(2):
# jLst = [0, 2]
ngrid, nt = maskObs.shape
for j in range(ngrid):
temp = 0
for i in range(nt):
maskDay[j, i] = temp
if maskObs[j, i] == 1:
temp = 1
else:
if temp != 0:
temp = temp + 1
ind = np.random.randint(0, ngrid)
maskObsDay = maskObs * maskDay
maskF = (maskDay >= 1) & (maskDay <= 3)
statP = stat.statError(yp, obs)
statLst = [
stat.statError(utils.fillNan(x, maskF), utils.fillNan(obs, maskF))
for x in yfLst
]
# if 'post' in doLst:
caseLst = ['Predict'] + [str(nd) + 'd latency' for nd in dLst]
keyLst = list(statLst[0].keys())
dataBox = list()
for iS in range(len(keyLst)):
key = keyLst[iS]
temp = list()
temp.append(statP[key])
print(key, np.nanmedian(statP[key]))
for k in range(len(statLst)):
data = statLst[k][key]
temp.append(data)