def funcP(iP, axP):
siteNo = siteNoLst[iP]
df = dbBasin.readSiteTS(siteNo, varLst=codeP, freq='D')
area = dfCrd.loc[siteNo]['DRAIN_SQKM']
for k, code in enumerate(codeP):
axplot.plotTS(axP[k], df.index, df[code].values, cLst='k')
axP[k].set_title('{} of {} {}'.format(code, siteNo, area))
def funcP(iP, axP):
siteNo = siteNoSel[iP]
df = dbBasin.readSiteTS(siteNo, varLst=codeSel, freq='D')
area = dfCrd.loc[siteNo]['DRAIN_SQKM']
axplot.multiTS(axP, df.index.values, df[codeSel].values, labelLst=codeSel)
figP.subplots_adjust(hspace=0)
figP.suptitle('{} {}'.format(siteNo, area))
import torch
import os
import json
import numpy as np
import pandas as pd
import time
import matplotlib.pyplot as plt
from hydroDL.data import dbBasin
siteNo = '06800500'
codeLst = ['00915', '00925']
df = GLASS.readBasin(siteNo)
# plot data
df = dbBasin.readSiteTS(siteNo, varLst=codeLst, freq='D')
nc = len(codeLst)
fig, axes = plt.subplots(nc, 1, figsize=(12, 3))
for k, code in enumerate(codeLst):
axplot.plotTS(axes[k], df.index, df[code].values, cLst='k')
fig.show()
# load data
sd = '1982-01-01'
ed = '2018-12-31'
siteNoLst = [siteNo]
dm = dbBasin.DataModelFull.new('test', siteNoLst, sdStr=sd, edStr=ed)
# load data
varF = gridMET.varLst + ntn.varLst
varC = usgs.varC
wT = s1 / s2
wS = s2 / np.sum(s2)
iS = np.random.choice(ns, nbatch, p=wS)
iT = np.zeros(nbatch)
for k in range(nbatch):
iT[k] = np.random.choice(nt - rho, p=wT[:, iS[k]]) + rho
# plot weights
fig, axes = plt.subplots(ns, 1, figsize=(12, 3))
for k in range(ns):
axes[k].plot(np.arange(nt), wT[:, k])
ax2 = axes[k].twinx()
ax2.plot(np.arange(nt), y[:, k, 1], 'r*')
fig.show()
df = dbBasin.readSiteTS(siteNoLst[0],
varLst=varY + varX,
freq='D',
sd=np.datetime64(sd),
ed=np.datetime64(ed))
fig, ax = plt.subplots(1, 1, figsize=(12, 3))
k = 1
j = 15
yTemp = yTensor.detach().cpu().numpy()
xTemp = xTensor.detach().cpu().numpy()
datenum = transform.transOutAll(xTemp[:, :, -3:-2], ['norm'], [statTup[0][-3]])
ax.plot(dataTupRaw[0][:, 0, -3], dataTup[2][:, 0, k], 'k*')
# ax.plot(df['datenum'], np.log(df[varTup[2][k]]+1), 'k*')
ax.plot(datenum[:, j, 0], yTemp[:, j, k], 'r.')
fig.show()
from hydroDL.data import ntn, dbBasin, usgs
from hydroDL.post import axplot, figplot
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
# read time series
siteNo = '01184000'
df = dbBasin.readSiteTS(siteNo,
dbBasin.io.varTLst,
ed=np.datetime64('2010-01-01'))
fig, axes = plt.subplots(3, 1, figsize=(12, 6))
axplot.plotTS(axes[0], df.index, df['datenum'], styLst='-', cLst='k')
axplot.plotTS(axes[1], df.index, df['sinT'], styLst='-', cLst='k')
axplot.plotTS(axes[2], df.index, df['cosT'], styLst='-', cLst='k')
fig.show()
df = dbBasin.readSiteTS(siteNo, usgs.varC + usgs.varQ)
fig, axes = plt.subplots(3, 1, figsize=(12, 6))
axplot.plotTS(axes[0], df.index, df['runoff'], styLst='-', cLst='k')
axplot.plotTS(axes[1], df.index, df['00915'], styLst='*', cLst='k')
axplot.plotTS(axes[2], df.index, df['00945'], styLst='*', cLst='k')
fig.show()
from hydroDL.data import ntn, dbBasin
from hydroDL.post import axplot, figplot
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
dfSite = ntn.loadSite()
lat = dfSite['latitude']
lon = dfSite['longitude']
yr = pd.to_datetime(
dfSite['startdate']).values.astype('M8[Y]').astype(str).astype(int)
fig, ax = plt.subplots(1, 1, figsize=(6, 8))
axplot.mapPoint(ax, lat, lon, yr, s=16)
fig.show()
# read time series
siteNo = '01184000'
df = dbBasin.readSiteTS(siteNo, ntn.varLst)
fig, axes = plt.subplots(2, 1, figsize=(6, 8))
axplot.plotTS(axes[0], df.index, df['Ca'], styLst='-', cLst='k')
axplot.plotTS(axes[1], df.index, df['distNTN'], styLst='-', cLst='k')
fig.show()
def calWRTDS(siteNo,
freq='D',
trainSet='B10',
the=[150, 50],
fitAll=True,
codeLst=usgs.varC,
reCal=False):
dirRoot = os.path.join(kPath.dirWQ, 'modelStat', 'WRTDS-{}'.format(freq))
dirOut = os.path.join(dirRoot, trainSet)
saveName = os.path.join(dirOut, siteNo)
if os.path.exists(saveName):
print('calculated {}'.format(siteNo))
if reCal is False:
return
t0 = time.time()
varQ = '00060'
varLst = codeLst + [varQ]
df = dbBasin.readSiteTS(siteNo, varLst=varLst, freq=freq)
dfYP = pd.DataFrame(index=df.index, columns=codeLst)
dfX = pd.DataFrame({'date': df.index}).set_index('date')
dfX = dfX.join(np.log(df[varQ] + sn)).rename(columns={varQ: 'logQ'})
yr = dfX.index.year.values
t = yr + dfX.index.dayofyear.values / 365
dfX['sinT'] = np.sin(2 * np.pi * t)
dfX['cosT'] = np.cos(2 * np.pi * t)
dfX['yr'] = yr
dfX['t'] = t
xVarLst = ['yr', 'logQ', 'sinT', 'cosT']
ind1, ind2 = defineTrainSet(df.index, trainSet)
# train / test
fitCodeLst = list()
for code in codeLst:
b1 = df.iloc[ind1][code].dropna().shape[0] > the[0]
b2 = df.iloc[ind2][code].dropna().shape[0] > the[1]
if b1 and b2:
fitCodeLst.append(code)
for code in fitCodeLst:
dfXY = dfX.join(np.log(df[code] + sn))
df1 = dfXY.iloc[ind1].dropna()
if fitAll:
df2 = dfXY[xVarLst + ['t']].dropna()
else:
df2 = dfXY.iloc[ind2].dropna() # only fit for observations now
n = len(df1)
if n == 0:
break
# calculate weight
h = np.array([7, 2, 0.5]) # window [Y Q S] from EGRET
tLst = df2.index.tolist()
for t in tLst:
dY = np.abs((df2.loc[t]['t'] - df1['t']).values)
dQ = np.abs((df2.loc[t]['logQ'] - df1['logQ']).values)
dS = np.min(np.stack(
[abs(np.ceil(dY) - dY),
abs(dY - np.floor(dY))]),
axis=0)
d = np.stack([dY, dQ, dS])
ww, ind = calWeight(d)
# fit WLS
Y = df1.iloc[ind][code].values
X = df1.iloc[ind][xVarLst].values
model = sm.WLS(Y, X, weights=ww).fit()
xp = df2.loc[t][xVarLst].values
yp = model.predict(xp)[0]
dfYP.loc[t][code] = np.exp(yp) - sn
t1 = time.time()
print(siteNo, code, t1 - t0)
saveName = os.path.join(dirOut, siteNo)
dfYP.to_csv(saveName)
return dfYP