def funcPoint(iP, axP):
[axTS, axH1, axH2, axH3, axP1, axP2] = axP
siteNo = siteNoLstCode[iP]
outName1 = '{}-{}-{}-{}'.format(dataName, 'comb', 'QTFP_C', trainSet)
outName2 = '{}-{}-{}-{}'.format(dataName, 'comb', 'QT_C', trainSet)
dfL1 = basins.loadSeq(outName1, siteNo)
dfL2 = basins.loadSeq(outName2, siteNo)
dfW = pd.read_csv(os.path.join(dirWRTDS, siteNo),
index_col=None).set_index('date')
dfO = waterQuality.readSiteTS(siteNo, codeLst + ['00060'], freq='W')
dfOD = waterQuality.readSiteTS(siteNo, codeLst + ['00060'], freq='D')
t = dfO.index
# ts
tBar = np.datetime64('2010-01-01')
sd = np.datetime64('1980-01-01')
legLst = ['LSTM QTFP', 'LSTM QT', 'WRTDS', 'Obs']
axplot.plotTS(axTS,
t, [dfL1[code], dfL2[code], dfW[code], dfO[code]],
tBar=tBar,
sd=sd,
styLst='---*',
cLst='mrbk',
legLst=legLst)
corrL = corrMat[indS[iP], iCode, 0]
corrW = corrMat[indS[iP], iCode, 1]
axplot.titleInner(axTS,
'siteNo {} {:.2f} {:.2f}'.format(siteNo, corrL, corrW))
axTS.legend()
# hist
axH1.hist(dfOD[code].values, density=True, bins=50)
axplot.titleInner(axH1, 'histogram {}'.format(shortName))
axH2.hist(dfOD['00060'].values, density=True, bins=50)
axplot.titleInner(axH2, 'histogram {}'.format('Q'))
axH3.hist(np.log(dfOD['00060'].values + 1), density=True, bins=50)
axplot.titleInner(axH3, 'histogram {}'.format('log Q'))
# periodgram
freqQ, powerQ, pQ = calPower('00060', dfOD)
freqC, powerC, pC = calPower(code, dfOD)
axP1.plot(1 / freqQ, powerC, '-*b', label='Periodograms')
axP1.plot(1 / freqQ, pQ, '-*r', label='baluev probability')
axplot.titleInner(axP1, 'streamflow')
axP1.legend()
axP2.plot(1 / freqC, powerC, '-*b', label='Periodograms')
axP2.plot(1 / freqC, pC, '-*r', label='baluev probability')
axplot.titleInner(axP2, shortName)
axP2.legend()
# attr vs diff
fig, axes = plt.subplots(nfy, nfx)
for k, code in enumerate(codeLst2):
j, i = utils.index2d(k, nfy, nfx)
ax = axes[j, i]
ic = codeLst.index(code)
x = cMat[:, k] if cMat.ndim == 2 else cMat
# y = corrMat[:, ic, 1]**2-corrMat[:, ic, 2]**2
y = rmseMat[:, ic, 1]**2-rmseMat[:, ic, 2]**2
ax.plot(x, y, '*')
ax.plot([np.nanmin(x), np.nanmax(x)], [0, 0], 'k-')
ax.set_ylim([-0.5, 0.5])
# ax.set_xlim([0, 200])
titleStr = '{} {} '.format(
code, usgs.codePdf.loc[code]['shortName'])
axplot.titleInner(ax, titleStr)
fig.show()
indC = [codeLst.index(code) for code in codeLst2]
labelLst = ['{} {}'.format(code, usgs.codePdf.loc[code]['shortName'])
for code in codeLst2]
xMat = rmseMat[:, indC, 1]
yMat = rmseMat[:, indC, 2]
nXY = [nfx, nfy]
def funcM():
figM, axM = figplot.scatter121Batch(
xMat, yMat, cMat, labelLst, nXY, optCb=1, cR=cR)
figM.suptitle('corr of LSTM vs WRTDS colored by {}'.format(cVar))
# Q of Nine random sites
indLst = np.random.randint(0, ns, 9)
nfy, nfx = (3, 3)
bins = 10
fig, axes = plt.subplots(nfy, nfx)
for k, indS in enumerate(indLst):
j, i = utils.index2d(k, nfy, nfx)
ax = axes[j, i]
ic = DF.varC.index(code)
q1 = np.log(q[:, indS]+1)
ind = np.where(~np.isnan(c[:, indS]))[0]
q2 = np.log(q[ind, indS]+1)
axplot.plotCDF(ax, [q1, q2])
# ax.hist([q1, q2], bins=bins, density=True)
nData = np.sum(~np.isnan(DF.c[:, indS, ic]))
shortName = usgs.codePdf.loc[code]['shortName']
titleStr = '{} {}'.format(
DF.siteNoLst[indS], nData)
axplot.titleInner(ax, titleStr, top=False)
fig.show()
q1 = np.log(q+1).flatten()
b = ~np.isnan(c)
q2 = np.log(q[b]+1)
fig, axes = plt.subplots(2, 1)
axplot.plotCDF(axes[0], [q1, q2])
axes[1].hist([q1, q2], bins=20, density=True)
fig.show()
s, p = scipy.stats.ks_2samp(q1, q2)
