out = os.path.join(cDir, 'output', 'CONUSv4f1')
rootDB = os.path.join(cDir, 'data')
nEpoch = 100
tRange = [20160401, 20170401]
# load data
df, yp, yt = master.test(
out, tRange=[20160401, 20170401], subset='CONUSv4f1', epoch=100, reTest=True)
yp = yp.squeeze()
yt = yt.squeeze()
# calculate stat
statErr = stat.statError(yp, yt)
dataGrid = [statErr['RMSE'], statErr['Corr']]
dataTs = [yp, yt]
t = df.getT()
crd = df.getGeo()
mapNameLst = ['RMSE', 'Correlation']
tsNameLst = ['LSTM', 'SMAP']
# plot map and time series
plot.plotTsMap(
dataGrid,
dataTs,
lat=crd[0],
lon=crd[1],
t=t,
mapNameLst=mapNameLst,
tsNameLst=tsNameLst,
isGrid=True)
ax=None,
lat=gagelat,
lon=gagelon,
title='Delta NSE',
shape=None)
# plot TS map
t = utils.time.tRange2Array(tRange)
tsdata = list()
tsdata.append(obs.squeeze())
npred = 2
for ii in range(npred):
tsdata.append(predLst[ii].squeeze())
plot.plotTsMap(dataMap=deltaNSE,
dataTs=tsdata,
t=t,
lat=gagelat,
lon=gagelon,
tsNameLst=['USGS', 'LSTM', 'DA-1'])
# plot multiple NSE maps
plt.rcParams['font.size'] = 13
gageinfo = camels.gageDict
gagelat = gageinfo['lat']
gagelon = gageinfo['lon']
fig, axs = plt.subplots(3, 2, figsize=(12, 8), constrained_layout=True)
axs = axs.flat
for ii in range(len(axs)):
data = statDictLst[ii]['NSE']
ax = axs[ii]
if ii == 0:
subtitle = 'LSTM'
yp = train.testModel(model, x, batchSize=100).squeeze()
ypLst.append(
dbCsv.transNorm(yp, rootDB=rootDB, fieldName='SMAP_AM', fromRaw=False))
modelName = 'LSTM-DA'
model = train.loadModel(outFolder, nEpoch, modelName=modelName)
yp = train.testModel(model, x, z=y, batchSize=100).squeeze()
ypLst.append(
dbCsv.transNorm(yp, rootDB=rootDB, fieldName='SMAP_AM', fromRaw=False))
##
statErr1 = stat.statError(ypLst[0], yt)
statErr2 = stat.statError(ypLst[1], yt)
dataGrid = [statErr2['RMSE'], statErr2['RMSE'] - statErr1['RMSE']]
dataTs = [ypLst[0], ypLst[1], yt]
t = df.getT()
crd = df.getGeo()
mapNameLst = ['DA', 'DA-LSTM']
tsNameLst = ['LSTM', 'DA', 'SMAP']
colorMap = None
colorTs = None
plot.plotTsMap(
dataGrid,
dataTs,
crd,
t,
colorMap=colorMap,
mapNameLst=mapNameLst,
tsNameLst=tsNameLst)
statPLst[0]['RMSE'] - statFLst[0]['RMSE'],
statPLst[1]['RMSE'] - statFLst[1]['RMSE'],
statPLst[2]['RMSE'] - statFLst[2]['RMSE']
]
prcp = df.getDataTs('APCP_FORA').squeeze()
dataTs = [[obs, ypLst[0], yfLst[0]], [obs, ypLst[1], yfLst[1]],
[obs, ypLst[2], yfLst[2]], [prcp]]
crd = df.getGeo()
t = df.getT()
mapNameLst = ['dRMSE 2015', 'dRMSE 2016', 'dRMSE 2017']
tsNameLst = ['obs', 'prj', 'fore']
plot.plotTsMap(dataGrid,
dataTs,
lat=crd[0],
lon=crd[1],
t=t,
tBar=[utils.time.t2dt(20160401),
utils.time.t2dt(20170401)],
mapNameLst=mapNameLst,
isGrid=True,
multiTS=True)
# plot pixel time series
import importlib
importlib.reload(plot)
matplotlib.rcParams.update({'font.size': 12})
matplotlib.rcParams.update({'lines.linewidth': 1})
matplotlib.rcParams.update({'lines.markersize': 6})
matplotlib.rcParams.update({'legend.fontsize': 12})
indLst = [1442, 1023]
indYLst = [0, 2]
nts = len(indLst)
dataGrid = [
statPtemp['RMSE'] / statFtemp['RMSE'],
statPtemp['Corr'] / statFtemp['Corr']
]
prcp = df.getDataTs('APCP_FORA')
dataTs = [obs, yp, yf]
dataTs2 = [prcp]
crd = df.getGeo()
t = df.getT()
mapNameLst = ['ratio RMSE', 'ratio Correlation']
tsNameLst = ['obs', 'prj', 'fore']
plot.plotTsMap(dataGrid,
dataTs,
dataTs2=dataTs2,
lat=crd[0],
lon=crd[1],
t=t,
mapNameLst=mapNameLst,
tsNameLst=tsNameLst,
isGrid=True)
# plot map and time series
# obsL4 = df.getDataTs('SMAP_L4', doNorm=False, rmNan=False).squeeze()
dataGrid = [
statPLst[0]['RMSE'] - statFLst[0]['RMSE'],
# statPLst[1]['RMSE'] / statFLst[1]['RMSE'],
statPLst[2]['RMSE'] - statFLst[2]['RMSE'],
# statPLst[3]['RMSE'] / statFLst[3]['RMSE'],
]
prcp = df.getDataTs('APCP_FORA')
dataTs = [obs, yp, yf]
]
prcp = df.getDataTs('APCP_FORA').squeeze()
dataTs = [[obs, ypLst[0], yfLst[0]], [obs, ypLst[1], yfLst[1]],
[obs, ypLst[2], yfLst[2]], [prcp]]
crd = df.getGeo()
t = df.getT()
mapNameLst = ['dRMSE 2015', 'dRMSE 2016', 'dRMSE 2017']
tsNameLst = ['obs', 'prj', 'fore']
tBar = [utils.time.t2dt(20160401), utils.time.t2dt(20170401)]
#plt.tight_layout()
plot.plotTsMap(dataGrid,
dataTs,
lat=crd[0],
lon=crd[1],
t=t,
mapNameLst=mapNameLst,
isGrid=True,
multiTS=True,
linewidth=1,
figsize=(10, 10),
tBar=tBar)
# see result for different seasons
tRangeLst = [[20180101, 20180201], [20180201, 20180301], [20180301, 20180401],
[20160401, 20160501], [20160501, 20160601], [20160601, 20160701],
[20160701, 20160801], [20160801, 20160901], [20160901, 20161001],
[20161001, 20161101], [20161101, 20161201], [20161201, 20170101],
[20170101, 20170201], [20170201, 20170301], [20170301, 20170401],
[20170401, 20170501], [20170501, 20170601], [20170601, 20170701],
[20170701, 20170801], [20170801, 20170901], [20170901, 20171001],
[20171001, 20171101], [20171101, 20171201], [20171201, 20180101]]
statErr2 = stat.statError(yp2, yt2)
dataMap = [statErr2['Corr'], statErr1['Corr'] - statErr2['Corr']]
dataTs = [yt2, yp2]
t = df2.getT()
crd = df2.getGeo()
mapNameLst = ['Test Corr', 'Train Corr - Test Corr']
tsNameLst = ['USGS', 'LSTM']
colorMap = None
colorTs = None
import imp
imp.reload(plot)
plot.plotTsMap(dataMap,
dataTs,
lat=crd[:, 0],
lon=crd[:, 1],
t=t,
colorMap=colorMap,
mapNameLst=mapNameLst,
tsNameLst=tsNameLst)
# plot time series
t = utils.time.tRange2Array([20100101, 20150101])
fig, axes = plt.subplots(5, 1, figsize=(12, 8))
iLst = [10, 52, 178, 404, 620]
for k in range(5):
iGrid = np.random.randint(0, 671)
iGrid = iLst[k]
yPlot = [yt2[iGrid, :], yp2[iGrid, :]]
gageId = camels.gageDict['id'][iGrid]
if k == 0:
plot.plotTS(t,