def extract_flowlines(self, source, destination, HUC8, verbose = True):
"""Extracts flowlines from the source datafile to the destination using
the HUC8 for the query."""
# open the flowline file
if verbose: print('reading the flowline file\n')
shapefile = Reader(source, shapeType = 3)
records = shapefile.records()
# figure out which field codes are the Reach code and comid
reach_index = shapefile.fields.index(['REACHCODE', 'C', 14, 0]) - 1
# go through the reach indices, add add them to the list of flowlines
# if in the watershed; also make a list of the corresponding comids
if verbose: print('searching for flowlines in the watershed\n')
indices = []
i = 0
for record in records:
if record[reach_index][:8] == HUC8: indices.append(i)
i+=1
if len(indices) == 0:
if verbose: print('error: query returned no values')
raise
# write the data from the HUC8 to a new shapefile
w = Writer(shapeType = 3)
for field in shapefile.fields: w.field(*field)
for i in indices:
shape = shapefile.shape(i)
w.poly(shapeType = 3, parts = [shape.points])
record = records[i]
# little work around for blank GNIS_ID and GNIS_NAME values
if isinstance(record[3], bytes):
record[3] = record[3].decode('utf-8')
if isinstance(record[4], bytes):
record[4] = record[4].decode('utf-8')
w.record(*record)
w.save(destination)
if verbose:
l = len(indices)
print('queried {} flowlines from original shapefile\n'.format(l))
def extract_catchments(self,
source,
destination,
flowlinefile,
verbose = True,
):
"""
Extracts the catchments from the source data file to the destination
using the list of comids for the query.
"""
# make a list of the comids
comids = self.get_comids(flowlinefile)
# open the catchment shapefile
if verbose: print('reading the catchment shapefile\n')
shapefile = Reader(source)
# get the index of the feature id, which links to the flowline comid
featureid_index = shapefile.fields.index(['FEATUREID', 'N', 9, 0]) - 1
# go through the comids from the flowlines and add the corresponding
# catchment to the catchment list
if verbose: print('searching the catchments in the watershed\n')
records = shapefile.records()
indices = []
i = 0
for record in records:
if record[featureid_index] in comids: indices.append(i)
i+=1
if len(indices) == 0:
print('query returned no values, returning\n')
raise
# create the new shapefile
if verbose: print('writing the new catchment shapefile\n')
w = Writer()
for field in shapefile.fields: w.field(*field)
for i in indices:
shape = shapefile.shape(i)
w.poly(shapeType = 5, parts = [shape.points])
w.record(*records[i])
w.save(destination)
def set_metadata(self,
gagefile,
):
"""
Opens the gage file with the station metadata.
"""
# metadata for stations
self.gages = []
self.day1s = []
self.dayns = []
self.drains = []
self.states = []
self.sites = []
self.nwiss = []
self.aves = []
self.names = []
gagereader = Reader(gagefile, shapeType = 1)
# get the fields with pertinent info
day1_index = gagereader.fields.index(['DAY1', 'N', 19, 0]) - 1
dayn_index = gagereader.fields.index(['DAYN', 'N', 19, 0]) - 1
drain_index = gagereader.fields.index(['DA_SQ_MILE', 'N', 19, 2]) - 1
HUC8_index = gagereader.fields.index(['HUC', 'C', 8, 0]) - 1
state_index = gagereader.fields.index(['STATE', 'C', 2, 0]) - 1
site_index = gagereader.fields.index(['SITE_NO', 'C', 15, 0]) - 1
nwis_index = gagereader.fields.index(['NWISWEB', 'C', 75, 0]) - 1
ave_index = gagereader.fields.index(['AVE', 'N', 19, 3]) - 1
name_index = gagereader.fields.index(['STATION_NM', 'C', 60, 0]) - 1
# iterate through the records
for r in gagereader.records():
gage = r[site_index]
day1 = r[day1_index]
dayn = r[dayn_index]
drain = r[drain_index]
state = r[state_index]
nwis = r[nwis_index]
ave = r[ave_index]
name = r[name_index]
site = r[site_index]
self.gages.append(gage)
self.day1s.append(day1)
self.dayns.append(dayn)
self.drains.append(drain)
self.states.append(state)
self.sites.append(site)
self.nwiss.append(nwis)
self.aves.append(ave)
self.names.append(name)
def get_comids(self, flowlinefile):
"""Finds the comids from the flowline file."""
# open the file
shapefile = Reader(flowlinefile)
# find the index of the comids
comid_index = shapefile.fields.index(['COMID', 'N', 9, 0]) - 1
# make a list of the comids
comids = [r[comid_index] for r in shapefile.records()]
return comids
def climate(self,
HUC8,
s,
e,
verbose = True,
):
subbasinfile = '{}/subbasin_catchments'.format(self.hydrography)
climatedata = '{}/{}/climate'.format(self.output, HUC8)
# make a directory for the climate data and time series
if not os.path.isdir(climatedata): os.mkdir(climatedata)
# use the Climateprocessor to get the data
climateprocessor = ClimateProcessor()
climateprocessor.download_shapefile(subbasinfile, s, e, climatedata,
space = 0.5)
# make directories for hourly and daily aggregated timeseries
hourly = '{}/hourly'.format(climatedata)
daily = '{}/daily'.format(climatedata)
if not os.path.isdir(hourly): os.mkdir(hourly)
if not os.path.isdir(daily): os.mkdir(daily)
# aggregate the daily GSOD tmin, tmax, dewpoint, and wind data
tmin = '{}/tmin'.format(daily)
tmax = '{}/tmax'.format(daily)
dewt = '{}/dewpoint'.format(daily)
wind = '{}/wind'.format(daily)
if not os.path.isfile(tmin):
ts = s, 1440, climateprocessor.aggregate('GSOD', 'tmin', s, e)
with open(tmin, 'wb') as f: pickle.dump(ts, f)
if not os.path.isfile(tmax):
ts = s, 1440, climateprocessor.aggregate('GSOD', 'tmax', s, e)
with open(tmax, 'wb') as f: pickle.dump(ts, f)
if not os.path.isfile(dewt):
ts = s, 1440, climateprocessor.aggregate('GSOD','dewpoint', s,e)
with open(dewt, 'wb') as f: pickle.dump(ts, f)
if not os.path.isfile(wind):
ts = s, 1440, climateprocessor.aggregate('GSOD', 'wind', s, e)
with open(wind, 'wb') as f: pickle.dump(ts, f)
# aggregate the daily GHCND snowfall and snowdepth data
snowfall = '{}/snowfall'.format(daily)
snowdepth = '{}/snowdepth'.format(daily)
if not os.path.isfile(snowfall):
ts = s, 1440, climateprocessor.aggregate('GHCND','snowfall', s, e)
with open(snowfall, 'wb') as f: pickle.dump(ts, f)
if not os.path.isfile(snowdepth):
ts = s, 1440,climateprocessor.aggregate('GHCND','snowdepth', s, e)
with open(snowdepth, 'wb') as f: pickle.dump(ts, f)
# find stations with pan evaporation data from GHCND
evapstations = []
for k, v in climateprocessor.metadata.ghcndstations.items():
# check if the station has any evaporation data
if v['evap'] > 0:
# open up the file and get the data
with open(k, 'rb') as f: station = pickle.load(f)
data = station.make_timeseries('evaporation', s, e)
# ignore datasets with no observations during the period
observations = [v for v in data if v is not None]
if len(observations) > 0: evapstations.append(k)
# aggregate the hourly NSRDB metstat data
hsolar = '{}/solar'.format(hourly)
if not os.path.isfile(hsolar):
ts = s, 60, climateprocessor.aggregate('NSRDB', 'metstat', s, e)
with open(hsolar, 'wb') as f: pickle.dump(ts, f)
# aggregate the hourly solar to daily
dsolar = '{}/solar'.format(daily)
if not os.path.isfile(dsolar):
with open(hsolar, 'rb') as f: t, tstep, data = pickle.load(f)
ts = s, 1440, [sum(data[i:i+24]) / 24
for i in range(0, 24 * (e-s).days, 24)]
with open(dsolar, 'wb') as f: pickle.dump(ts, f)
# aggregate the hourly precipitation for each subbasin using IDWA
precip = '{}/hourlyprecipitation'.format(climatedata)
if not os.path.isdir(precip): os.mkdir(precip)
# use the subbasin shapefile to get the location of the centroids
sf = Reader(subbasinfile)
# index of the comid, latitude, and longitude records
comid_index = [f[0] for f in sf.fields].index('ComID') - 1
lon_index = [f[0] for f in sf.fields].index('CenX') - 1
lat_index = [f[0] for f in sf.fields].index('CenY') - 1
elev_index = [f[0] for f in sf.fields].index('AvgElevM') - 1
area_index = [f[0] for f in sf.fields].index('AreaSqKm') - 1
# iterate through the shapefile records and aggregate the timeseries
for i in range(len(sf.records())):
record = sf.record(i)
comid = record[comid_index]
lon = record[lon_index]
lat = record[lat_index]
# check if the aggregated time series exists or calculate it
subbasinprecip = '{}/{}'.format(precip, comid)
if not os.path.isfile(subbasinprecip):
if verbose:
i = comid, lon, lat
print('aggregating timeseries for comid ' +
'{} at {}, {}\n'.format(*i))
p = climateprocessor.aggregate('precip3240', 'precip', s, e,
method = 'IDWA',
longitude = lon,
latitude = lat)
ts = s, 60, p
with open(subbasinprecip, 'wb') as f: pickle.dump(ts, f)
# make a directory for the evapotranspiration time series
evapotranspiration = '{}/evapotranspiration'.format(climatedata)
if not os.path.isdir(evapotranspiration):
os.mkdir(evapotranspiration)
# use the ETCalculator to calculate the ET time series
etcalculator = ETCalculator()
# get the centroid of the watershed from the subbasin shapefile
areas = [r[area_index] for r in sf.records()]
xs = [r[lon_index] for r in sf.records()]
ys = [r[lat_index] for r in sf.records()]
zs = [r[elev_index] for r in sf.records()]
# get the areal-weighted averages
lon = sum([a * x for a, x in zip(areas, xs)]) / sum(areas)
lat = sum([a * y for a, y in zip(areas, ys)]) / sum(areas)
elev = sum([a * z for a, z in zip(areas, zs)]) / sum(areas)
# add them to the ETCalculator
etcalculator.add_location(lon, lat, elev)
# check if the daily RET exists; otherwise calculate it
dRET = '{}/dailyRET'.format(evapotranspiration)
if not os.path.isfile(dRET):
# add the daily time series to the calculator
with open(tmin, 'rb') as f: t, tstep, data = pickle.load(f)
etcalculator.add_timeseries('tmin', tstep, t, data)
with open(tmax, 'rb') as f: t, tstep, data = pickle.load(f)
etcalculator.add_timeseries('tmax', tstep, t, data)
with open(dewt, 'rb') as f: t, tstep, data = pickle.load(f)
etcalculator.add_timeseries('dewpoint', tstep, t, data)
with open(wind, 'rb') as f: t, tstep, data = pickle.load(f)
etcalculator.add_timeseries('wind', tstep, t, data)
with open(dsolar, 'rb') as f: t, tstep, data = pickle.load(f)
etcalculator.add_timeseries('solar', tstep, t, data)
# calculate the daily RET
etcalculator.penman_daily(s, e)
ts = s, 1440, etcalculator.daily['RET'][1]
with open(dRET, 'wb') as f: pickle.dump(ts, f)
# disaggregate the daily temperature time series to hourly
hourlytemp = '{}/temperature'.format(hourly)
if not os.path.isfile(hourlytemp):
if etcalculator.daily['tmin'] is None:
with open(tmin, 'rb') as f: t, tstep, data = pickle.load(f)
etcalculator.add_timeseries('tmin', tstep, t, data)
if etcalculator.daily['tmax'] is None:
with open(tmax, 'rb') as f: t, tstep, data = pickle.load(f)
etcalculator.add_timeseries('tmax', tstep, t, data)
data = etcalculator.interpolate_temperatures(s, e)
tstep = 60
ts = t, tstep, data
with open(hourlytemp, 'wb') as f: pickle.dump(ts, f)
etcalculator.add_timeseries('temperature', tstep, t, data)
# disaggregate the dewpoint and wind speed time series to hourly
hourlydewt = '{}/dewpoint'.format(hourly)
if not os.path.isfile(hourlydewt):
if etcalculator.daily['dewpoint'] is None:
with open(dewt, 'rb') as f: t, tstep, data = pickle.load(f)
else:
t, data = etcalculator.daily['dewpoint']
tstep = 60
data = [v for v in data for i in range(24)]
ts = t, tstep, data
with open(hourlydewt, 'wb') as f: pickle.dump(ts, f)
etcalculator.add_timeseries('dewpoint', tstep, t, data)
hourlywind = '{}/wind'.format(hourly)
if not os.path.isfile(hourlywind):
if etcalculator.daily['wind'] is None:
with open(wind, 'rb') as f: t, tstep, data = pickle.load(f)
else:
t, data = etcalculator.daily['wind']
tstep = 60
data = [v for v in data for i in range(24)]
ts = t, tstep, data
with open(hourlywind, 'wb') as f: pickle.dump(ts, f)
etcalculator.add_timeseries('wind', tstep, t, data)
# check if the hourly RET exists; otherwise calculate it
hRET = '{}/hourlyRET'.format(evapotranspiration)
if not os.path.isfile(hRET):
required = 'temperature', 'solar', 'dewpoint', 'wind'
for tstype in required:
if etcalculator.hourly[tstype] is None:
name = '{}/{}'.format(hourly, tstype)
with open(name, 'rb') as f:
t, tstep, data = pickle.load(f)
etcalculator.add_timeseries(tstype, tstep, t, data)
# calculate and save the hourly RET
etcalculator.penman_hourly(s, e)
ts = s, 60, etcalculator.hourly['RET'][1]
with open(hRET, 'wb') as f: pickle.dump(ts, f)
# add the daily time series for the plot
required = 'tmin', 'tmax', 'dewpoint', 'wind', 'solar'
for tstype in required:
if etcalculator.daily[tstype] is None:
name = '{}/{}'.format(daily, tstype)
with open(name, 'rb') as f:
t, tstep, data = pickle.load(f)
etcalculator.add_timeseries(tstype, tstep, t, data)
# aggregate the hourly to daily for plotting
hRET = etcalculator.hourly['RET'][1]
dRET = [sum(hRET[i:i+24]) for i in range(0, len(hRET), 24)]
etcalculator.add_timeseries('RET', 'daily', s, dRET)
name = '{}/referenceET'.format(evapotranspiration)
etcalculator.plotET(stations = evapstations, output = name,
show = False)
name = '{}/dayofyearET'.format(evapotranspiration)
etcalculator.plotdayofyear(stations = evapstations,
output = name,
show = False)
# calculate hourly PET for different land use categories
lucs = ('corn',
'soybeans',
'grains',
'alfalfa',
'fallow',
'pasture',
'wetlands',
'others',
)
colors = ('yellow',
'green',
'brown',
'lime',
'gray',
'orange',
'blue',
'black',
)
pdates = (datetime.datetime(2000, 4, 15),
datetime.datetime(2000, 5, 15),
datetime.datetime(2000, 4, 15),
datetime.datetime(2000, 5, 15),
datetime.datetime(2000, 3, 1),
datetime.datetime(2000, 3, 1),
datetime.datetime(2000, 3, 1),
datetime.datetime(2000, 3, 1),
)
ems = (30,
20,
20,
10,
10,
10,
10,
10,
)
gs = (50,
30,
30,
10,
10,
10,
10,
10,
)
fs = (60,
60,
60,
120,
240,
240,
240,
240,
)
ls = (40,
30,
40,
10,
10,
10,
10,
10,
)
Kis = (0.30,
0.40,
0.30,
0.30,
0.30,
0.30,
1.00,
1.00,
)
Kms = (1.15,
1.15,
1.15,
0.95,
0.30,
0.85,
1.20,
1.00,
)
Kls = (0.40,
0.55,
0.40,
0.90,
0.30,
0.30,
1.00,
1.00,
)
# add the hourly RET time series if it isn't present
if etcalculator.hourly['RET'] is None:
with open(hRET, 'rb') as f: t, tstep, data = pickle.load(f)
etcalculator.add_timeseries('RET', tstep, t, data)
# iterate through the land use categories and calculate PET
for i in zip(lucs, colors, pdates, ems, gs, fs, ls, Kis, Kms, Kls):
crop, c, plant, emergence, growth, full, late, Ki, Km, Kl = i
# add the information and calculate the PET time series
etcalculator.add_crop(crop,
plant,
emergence,
growth,
full,
late,
Ki,
Km,
Kl,
)
etcalculator.hourly_PET(crop, s, e)
# get the PET time series
t, PET = etcalculator.hourlyPETs[crop]
ts = t, 60, PET
# save it
name = '{}/{}'.format(evapotranspiration, crop)
with open(name, 'wb') as f: pickle.dump(ts, f)
def build_watershed(self,
subbasinfile,
flowfile,
outletfile,
damfile,
gagefile,
landfiles,
VAAfile,
years,
HUC8,
filename,
plotname = None,
):
# create a dictionary to store subbasin data
subbasins = {}
# create a dictionary to keep track of subbasin inlets
inlets = {}
# read in the flow plane data into an instance of the FlowPlane class
sf = Reader(subbasinfile, shapeType = 5)
comid_index = sf.fields.index(['ComID', 'N', 9, 0]) - 1
len_index = sf.fields.index(['PlaneLenM', 'N', 8, 2]) - 1
slope_index = sf.fields.index(['PlaneSlope', 'N', 9, 6]) - 1
area_index = sf.fields.index(['AreaSqKm', 'N', 10, 2]) - 1
cx_index = sf.fields.index(['CenX', 'N', 12, 6]) - 1
cy_index = sf.fields.index(['CenY', 'N', 12, 6]) - 1
elev_index = sf.fields.index(['AvgElevM', 'N', 8, 2]) - 1
for record in sf.records():
comid = '{}'.format(record[comid_index])
length = record[len_index]
slope = record[slope_index]
tot_area = record[area_index]
centroid = [record[cx_index], record[cy_index]]
elevation = record[elev_index]
subbasin = Subbasin(comid)
subbasin.add_flowplane(length, slope, centroid, elevation)
subbasins[comid] = subbasin
# read in the flowline data to an instance of the Reach class
sf = Reader(flowfile)
outcomid_index = sf.fields.index(['OutComID', 'N', 9, 0]) - 1
gnis_index = sf.fields.index(['GNIS_NAME', 'C', 65, 0]) - 1
reach_index = sf.fields.index(['REACHCODE', 'C', 8, 0]) - 1
incomid_index = sf.fields.index(['InletComID', 'N', 9, 0]) - 1
maxelev_index = sf.fields.index(['MaxElev', 'N', 9, 2]) - 1
minelev_index = sf.fields.index(['MinElev', 'N', 9, 2]) - 1
slopelen_index = sf.fields.index(['SlopeLenKM', 'N', 6, 2]) - 1
slope_index = sf.fields.index(['Slope', 'N', 8, 5]) - 1
inflow_index = sf.fields.index(['InFlowCFS', 'N', 8, 3]) - 1
outflow_index = sf.fields.index(['OutFlowCFS', 'N', 8, 3]) - 1
velocity_index = sf.fields.index(['VelFPS', 'N', 7, 4]) - 1
traveltime_index = sf.fields.index(['TravTimeHR', 'N', 8, 2]) - 1
for record in sf.records():
outcomid = '{}'.format(record[outcomid_index])
gnis = record[gnis_index]
reach = record[reach_index]
incomid = '{}'.format(record[incomid_index])
maxelev = record[maxelev_index] / 100
minelev = record[minelev_index] / 100
slopelen = record[slopelen_index]
slope = record[slope_index]
inflow = record[inflow_index]
outflow = record[outflow_index]
velocity = record[velocity_index]
traveltime = record[traveltime_index]
if isinstance(gnis, bytes): gnis = ''
subbasin = subbasins[outcomid]
flow = (inflow + outflow) / 2
subbasin.add_reach(gnis, maxelev, minelev, slopelen, flow = flow,
velocity = velocity, traveltime = traveltime)
inlets[outcomid] = incomid
# open up the outlet file and see if the subbasin has a gage or dam
sf = Reader(outletfile)
records = sf.records()
comid_index = sf.fields.index(['COMID', 'N', 9, 0]) - 1
nid_index = sf.fields.index(['NIDID', 'C', 7, 0]) - 1
nwis_index = sf.fields.index(['SITE_NO', 'C', 15, 0]) - 1
nids = {'{}'.format(r[comid_index]):r[nid_index] for r in records
if isinstance(r[nid_index], str)}
nwiss = {'{}'.format(r[comid_index]):r[nwis_index] for r in records
if r[nwis_index] is not None}
# open up the dam file and read in the information for the dams
sf = Reader(damfile)
records = sf.records()
name_index = sf.fields.index(['DAM_NAME', 'C', 65, 0]) - 1
nid_index = sf.fields.index(['NIDID', 'C', 7, 0]) - 1
long_index = sf.fields.index(['LONGITUDE', 'N', 19, 11]) - 1
lat_index = sf.fields.index(['LATITUDE', 'N', 19, 11]) - 1
river_index = sf.fields.index(['RIVER', 'C', 65, 0]) - 1
owner_index = sf.fields.index(['OWN_NAME', 'C', 65, 0]) - 1
type_index = sf.fields.index(['DAM_TYPE', 'C', 10, 0]) - 1
purp_index = sf.fields.index(['PURPOSES', 'C', 254, 0]) - 1
year_index = sf.fields.index(['YR_COMPL', 'C', 10, 0]) - 1
high_index = sf.fields.index(['NID_HEIGHT', 'N', 19, 11]) - 1
mstor_index = sf.fields.index(['MAX_STOR', 'N', 19, 11]) - 1
nstor_index = sf.fields.index(['NORMAL_STO', 'N', 19, 11]) - 1
area_index = sf.fields.index(['SURF_AREA', 'N', 19, 11]) - 1
# iterate through the subbasins and see if they have a dam
for comid, subbasin in subbasins.items():
if comid in nids:
# if the subbasin has a dam, find the data info in the file
nid = nids[comid]
r = records[[r[nid_index] for r in records].index(nid)]
subbasin.add_dam(nid,
r[name_index],
r[long_index],
r[lat_index],
r[river_index],
r[owner_index],
r[type_index],
r[purp_index],
r[year_index],
r[high_index],
r[mstor_index],
r[nstor_index],
r[area_index],
)
# read in the landuse data from the csv files
for year in years:
csvfile = '{}/{}landuse.csv'.format(landfiles, year)
with open(csvfile, 'r') as f:
reader = csv.reader(f)
rows = [r for r in reader]
# organize the data
comids = [r[0] for r in rows[3:]]
categories = rows[2][2:]
emptys = [r[1] for r in rows[3:]]
data = [r[2:] for r in rows[3:]]
for comid, subbasin in subbasins.items():
i = comids.index(comid)
subbasin.add_landuse(year, categories, data[i])
# create an instance of the Watershed class
watershed = Watershed(HUC8, subbasins)
# open up the flowline VAA file to use to establish mass linkages
with open(VAAfile, 'rb') as f: flowlines = pickle.load(f)
# create a dictionary to connect the comids to hydroseqs
hydroseqs = {'{}'.format(flowlines[f].comid):
flowlines[f].hydroseq for f in flowlines}
# establish the mass linkages using a dictionary "updown" and a list of
# head water subbasins
updown = {}
for comid, subbasin in watershed.subbasins.items():
# get the flowline instance for the outlet comid
flowline = flowlines[hydroseqs[comid]]
# check if the subbasin is a watershed inlet or a headwater source
inlet = hydroseqs[inlets[comid]]
if flowlines[inlet].up in flowlines:
i = '{}'.format(flowlines[flowlines[inlet].up].comid)
subbasin.add_inlet(i)
elif flowlines[inlet].up != 0:
watershed.add_inlet(comid)
else:
watershed.add_headwater(comid)
# check if the subbasin is a watershed outlet, and if it is not
# then find the downstream reach
if flowline.down in flowlines:
flowline = flowlines[flowline.down]
while '{}'.format(flowline.comid) not in subbasins:
flowline = flowlines[flowline.down]
updown[comid] = '{}'.format(flowline.comid)
else:
updown[comid] = 0
watershed.add_outlet('{}'.format(comid))
# add the updown dictionary to show mass linkage in the reaches
watershed.add_mass_linkage(updown)
with open(filename, 'wb') as f: pickle.dump(watershed, f)
if plotname is not None and not os.path.isfile(plotname + '.png'):
self.plot_mass_flow(watershed, plotname)
careas[c] = f.variables["area_" + c][:]
# find valid fpus
tarea = 100 * (111.2 / 2) ** 2 * cos(pi * lats / 180)
tarea = resize(tarea, (nlons, nlats)).T
validfpus = []
for i in range(nfpu):
hareafpu = harea[fpumap == fpu[i]].sum()
tareafpu = tarea[fpumap == fpu[i]].sum()
if hareafpu / tareafpu > percent / 100.0:
validfpus.append(fpu[i])
# load shape file
r = Reader(shapefile)
shapes = r.shapes()
records = r.records()
models = ["epic", "gepic", "lpj-guess", "lpjml", "pdssat", "pegasus"] # exclude image
gcms = ["gfdl-esm2m", "hadgem2-es", "ipsl-cm5a-lr", "miroc-esm-chem", "noresm1-m"]
crops = ["maize", "wheat", "soy", "rice"] if crop == "all" else [crop]
co2s = ["co2", "noco2"]
hadgemidx = gcms.index("hadgem2-es")
nm, ng, ncr, nco2 = len(models), len(gcms), len(crops), len(co2s)
# variables
sh = (nm, ng, ncr, 3, nfpu, nco2)
dy26arr = masked_array(zeros(sh), mask=ones(sh))
dy85arr = masked_array(zeros(sh), mask=ones(sh))
with nc(infile) as f:
def calculate_landuse(self,
rasterfile,
shapefile,
aggregatefile,
attribute,
csvfile = None,
):
"""
Calculates the land use for the given year for the "attribute"
feature attribute in the polygon shapefile using the aggregate
mapping provided in the "aggregatefile."
"""
# make sure the files exist
for f in rasterfile, shapefile + '.shp', aggregatefile:
if not os.path.isfile(f):
print('error, {} does not exist\n'.format(f))
raise
# read the aggregate file
self.read_aggregatefile(aggregatefile)
# open the shapefile
sf = Reader(shapefile, shapeType = 5)
attributes = [f[0] for f in sf.fields]
try: index = attributes.index(attribute) - 1
except:
print('error: attribute ' +
'{} is not in the shapefile fields'.format(attribute))
raise
# iterate through the shapes, get the fractions and save them
for i in range(len(sf.records())):
points = numpy.array(sf.shape(i).points)
record = sf.record(i)
k = record[index]
# store the results
self.landuse[k] = {r:0 for r in self.order}
try:
values, origin = get_raster_in_poly(rasterfile, points,
verbose = False)
values = values.flatten()
values = values[values.nonzero()]
tot_pixels = len(values)
# count the number of pixels of each land use type
for v in numpy.unique(values):
# find all the indices for each pixel value
pixels = numpy.argwhere(values == v)
# normalize by the total # of pixels
f = len(values[pixels]) / tot_pixels
# add the landuse to the aggregated value
self.landuse[k][self.groups[v]] += f
# work around for small shapes
except: self.landuse[k][self.groups[0]] = 1
if csvfile is not None: self.make_csv(attribute, csvfile)
return self.landuse
def plot_landuse(self,
landuse,
catchments,
attribute,
categoryfile,
output = None,
datatype = 'raw',
overwrite = False,
pixels = 1000,
border = 0.02,
lw = 0.5,
show = False,
verbose = True,
vverbose = False
):
"""
Makes a plot of the landuse of a catchment shapefile on top of a
raster landuse file.
"""
if self.order is None:
print('error: no landuse aggregation file information provided\n')
raise
self.read_categoryfile(categoryfile)
if verbose: print('generating a {} land use plot\n'.format(datatype))
# make the figure
fig = pyplot.figure()
subplot = fig.add_subplot(111, aspect = 'equal')
subplot.tick_params(axis = 'both', which = 'major', labelsize = 11)
# add the title
if datatype == 'results': title = 'Land Use Fractions'
else: title = 'Raw Land Use Data'
subplot.set_title(title, size = 14)
# open the shapefile and get the bounding box
s = Reader(catchments, shapeType = 5)
xmin, ymin, xmax, ymax = s.bbox
# get the index of the field for the attribute matching
index = [f[0] for f in s.fields].index(attribute) - 1
# set up a custom colormap using the rgbs supplied in the aggregate file
color_table = [(self.reds[g] / 255, self.greens[g] / 255,
self.blues[g] / 255) for g in self.order]
cmap = colors.ListedColormap(color_table)
# provide the cutoff boundaries for the mapping of values to the table
bounds = [i-0.5 for i in range(len(self.order)+1)]
# create a norm to map the bounds to the colors
norm = colors.BoundaryNorm(bounds, cmap.N)
# get the pixel width and origin
w = (xmax - xmin) / pixels
# calculate the image array height and the height of a pixel
height = int(numpy.ceil((ymax - ymin) / (xmax - xmin)) * pixels)
h = (ymax - ymin) / height
# set up the image array
image_array = numpy.zeros((height, pixels), dtype = 'uint8')
# get the land use fraction for each category
if datatype == 'results':
# iterate through the shapes and make patches
for i in range(len(s.records())):
comid = s.record(i)[index]
points = numpy.array(s.shape(i).points)
# convert the shape to pixel coordinates
pixel_polygon = [(get_pixel(x, xmin, w), get_pixel(y, ymin, h))
for x, y in points]
# make a PIL image to use as a mask
rasterpoly = Image.new('L', (pixels, height), 1)
rasterize = ImageDraw.Draw(rasterpoly)
# rasterize the polygon
rasterize.polygon(pixel_polygon, 0)
# convert the PIL array to numpy boolean to use as a mask
mask = 1 - numpy.array(rasterpoly)
# get the total number of pixels in the shape
tot = mask.sum()
# iterate from left to right and get the fraction of the total
# area inside the shape as a function of x (takes into account
# the depth)
fractions = [column.sum() / tot for column in mask.transpose()]
area_cdf = [sum(fractions[:i+1])
for i in range(len(fractions))]
# convert the land use fractions into a land use cdf
fractions = [self.landuse[comid][g] for g in self.order]
land_cdf = [sum(fractions[:i+1]) for i in range(len(fractions))]
# use the area cdf to determine the break points for the land
# use patches. note this array does not account for the masking
# of the patch. thus there are n+1 vertical bands. the first
# and last are the "empty" (first in the aggregate file). in
# between the break points are determined from the area cdf.
color_array = numpy.zeros(len(mask[0]), dtype = 'uint8')
# find the break point for each band by looping through the land
# ues cdf and filling from left to right
i = 0
for p, n in zip(land_cdf, range(len(self.order))):
# move from left to right nuntil the area_cdf exceeds
# the land area cdf
while area_cdf[i] <= p:
color_array[i] = n
if i < len(area_cdf) - 1: i += 1
else: break
# multiply the color band array by the mask to get the img
sub_img = mask * color_array
# add the new mask to the watershed image
image_array = image_array + sub_img
# add a patch for the shape boundary
subplot.add_patch(self.make_patch(points, (1,0,0,0), width=lw))
# show the bands
bbox = s.bbox[0], s.bbox[2], s.bbox[1], s.bbox[3]
im = subplot.imshow(image_array, extent = bbox,
origin = 'upper left',
interpolation = 'nearest',
cmap = cmap, norm = norm)
# adjust the plot bounding box
xmin, xmax = xmin-border * (xmax-xmin), xmax + border * (xmax-xmin)
ymin, ymax = ymin-border * (ymax-ymin), ymax + border * (ymax-ymin)
else:
# adjust the plot bounding box
xmin, xmax = xmin-border * (xmax-xmin), xmax + border * (xmax-xmin)
ymin, ymax = ymin-border * (ymax-ymin), ymax + border * (ymax-ymin)
# pixel width in latitude
pw = (xmax - xmin) / pixels
# calculate the image height in pixels
ny = int(numpy.ceil((ymax - ymin) / (xmax - xmin) * pixels))
# note the height of pixels = width of pixels
# and image width in pixels is "pixels"
xs = numpy.array([xmin + (i + 0.5) * pw for i in range(pixels)])
ys = numpy.array([ymin + (i + 0.5) * pw for i in range(ny)])
# set up an array of values for the image
zs = numpy.zeros((ny, pixels))
for i in range(len(ys)):
ps = [(x, ys[i]) for x in xs]
zs[i, :] = numpy.array(get_raster(landuse, ps, quiet = True))
zs = zs.astype(int)
tot = zs.size
for v in numpy.unique(zs):
group = self.groups[v]
i = self.order.index(group)
zs[numpy.where(zs == v)] = i
# plot the grid
im = subplot.imshow(zs,
interpolation = 'nearest',
origin = 'upper left',
extent = [xmin, xmax, ymin, ymax],
norm = norm,
cmap = cmap,
)
# add patch for the shape boundary
for shape in s.shapes():
points = numpy.array(shape.points)
subplot.add_patch(self.make_patch(points, (1,0,0,0), width=0.5))
# add the legend using a dummy box to make patches for the legend
dummybox = [[0,0], [0,1], [1,1], [1,0], [0,0]]
handles, labels = [], []
for group, color in zip(self.order[1:], color_table[1:]):
p = self.make_patch(dummybox, facecolor = color, width = 0)
handles.append(subplot.add_patch(p))
labels.append(group)
leg = subplot.legend(handles, labels, bbox_to_anchor = (1.0, 0.5),
loc = 'center left', title = 'Land Use Categories')
legtext = leg.get_texts()
pyplot.setp(legtext, fontsize = 10)
subplot.set_position([0.125, 0.1, 0.6, 0.8])
# add the labels and set the limits
subplot.set_xlabel('Longitude, Decimal Degrees', size = 13)
subplot.set_ylabel('Latitude, Decimal Degrees', size = 13)
subplot.set_xlim([xmin, xmax])
subplot.set_ylim([ymin, ymax])
subplot.xaxis.set_major_locator(ticker.MaxNLocator(8))
subplot.yaxis.set_major_locator(ticker.MaxNLocator(8))
subplot.xaxis.set_major_formatter(ticker.FormatStrFormatter('%.2f'))
subplot.yaxis.set_major_formatter(ticker.FormatStrFormatter('%.2f'))
# show it
if output is not None: pyplot.savefig(output)
if show: pyplot.show()
pyplot.clf()
pyplot.close()
def plot_landuse(self,
landuse,
catchments,
attribute,
output=None,
datatype='raw',
overwrite=False,
pixels=1000,
border=0.02,
lw=0.5,
show=False,
verbose=True,
vverbose=False):
"""
Makes a plot of the landuse of a catchment shapefile on top of a
raster landuse file.
"""
if verbose: print('generating land use plot\n')
# make the figure
fig = pyplot.figure()
subplot = fig.add_subplot(111, aspect='equal')
subplot.tick_params(axis='both', which='major', labelsize=11)
# add the title
if datatype == 'results': title = 'Land Use Fractions'
else: title = 'Raw Land Use Data'
subplot.set_title(title, size=14)
# open the shapefile and get the bounding box
s = Reader(catchments, shapeType=5)
xmin, ymin, xmax, ymax = s.bbox
# get the index of the field for the attribute matching
index = [f[0] for f in s.fields].index(attribute) - 1
# set up a custom colormap using the rgbs supplied in the aggregate file
color_table = [(self.reds[g] / 255, self.greens[g] / 255,
self.blues[g] / 255) for g in self.order]
cmap = colors.ListedColormap(color_table)
# provide the cutoff boundaries for the mapping of values to the table
bounds = [i - 0.5 for i in range(len(self.order) + 1)]
# create a norm to map the bounds to the colors
norm = colors.BoundaryNorm(bounds, cmap.N)
# get the pixel width and origin
w = (xmax - xmin) / pixels
# calculate the image array height and the height of a pixel
height = int(numpy.ceil((ymax - ymin) / (xmax - xmin)) * pixels)
h = (ymax - ymin) / height
# set up the image array
image_array = numpy.zeros((height, pixels), dtype='uint8')
# get the land use fraction for each category
if datatype == 'results':
# iterate through the shapes and make patches
for i in range(len(s.records())):
comid = s.record(i)[index]
points = numpy.array(s.shape(i).points)
# convert the shape to pixel coordinates
pixel_polygon = [(get_pixel(x, xmin, w), get_pixel(y, ymin, h))
for x, y in points]
# make a PIL image to use as a mask
rasterpoly = Image.new('L', (pixels, height), 1)
rasterize = ImageDraw.Draw(rasterpoly)
# rasterize the polygon
rasterize.polygon(pixel_polygon, 0)
# convert the PIL array to numpy boolean to use as a mask
mask = 1 - numpy.array(rasterpoly)
# get the total number of pixels in the shape
tot = mask.sum()
# iterate from left to right and get the fraction of the total
# area inside the shape as a function of x (takes into account
# the depth)
fractions = [column.sum() / tot for column in mask.transpose()]
area_cdf = [
sum(fractions[:i + 1]) for i in range(len(fractions))
]
# convert the land use fractions into a land use cdf
fractions = [self.landuse[comid][g] for g in self.order]
land_cdf = [
sum(fractions[:i + 1]) for i in range(len(fractions))
]
# use the area cdf to determine the break points for the land
# use patches. note this array does not account for the masking
# of the patch. thus there are n+1 vertical bands. the first
# and last are the "empty" (first in the aggregate file). in
# between the break points are determined from the area cdf.
color_array = numpy.zeros(len(mask[0]), dtype='uint8')
# find the break point for each band by looping through the land
# ues cdf and filling from left to right
i = 0
for p, n in zip(land_cdf, range(len(self.order))):
# move from left to right nuntil the area_cdf exceeds
# the land area cdf
while area_cdf[i] <= p:
color_array[i] = n
if i < len(area_cdf) - 1: i += 1
else: break
# multiply the color band array by the mask to get the img
sub_img = mask * color_array
# add the new mask to the watershed image
image_array = image_array + sub_img
# add a patch for the shape boundary
subplot.add_patch(
self.make_patch(points, (1, 0, 0, 0), width=lw))
# show the bands
bbox = s.bbox[0], s.bbox[2], s.bbox[1], s.bbox[3]
im = subplot.imshow(image_array,
extent=bbox,
origin='upper left',
interpolation='nearest',
cmap=cmap,
norm=norm)
# adjust the plot bounding box
xmin, xmax = xmin - border * (xmax - xmin), xmax + border * (xmax -
xmin)
ymin, ymax = ymin - border * (ymax - ymin), ymax + border * (ymax -
ymin)
else:
# adjust the plot bounding box
xmin, xmax = xmin - border * (xmax - xmin), xmax + border * (xmax -
xmin)
ymin, ymax = ymin - border * (ymax - ymin), ymax + border * (ymax -
ymin)
# pixel width in latitude
pw = (xmax - xmin) / pixels
# calculate the image height in pixels
ny = int(numpy.ceil((ymax - ymin) / (xmax - xmin) * pixels))
# note the height of pixels = width of pixels
# and image width in pixels is "pixels"
xs = numpy.array([xmin + (i + 0.5) * pw for i in range(pixels)])
ys = numpy.array([ymin + (i + 0.5) * pw for i in range(ny)])
# set up an array of values for the image
zs = numpy.zeros((ny, pixels))
for i in range(len(ys)):
ps = [(x, ys[i]) for x in xs]
zs[i, :] = numpy.array(get_raster(landuse, ps, quiet=True))
zs = zs.astype(int)
tot = zs.size
for v in numpy.unique(zs):
group = self.groups[v]
i = self.order.index(group)
zs[numpy.where(zs == v)] = i
# plot the grid
im = subplot.imshow(
zs,
interpolation='nearest',
origin='upper left',
extent=[xmin, xmax, ymin, ymax],
norm=norm,
cmap=cmap,
)
# add patch for the shape boundary
for shape in s.shapes():
points = numpy.array(shape.points)
subplot.add_patch(
self.make_patch(points, (1, 0, 0, 0), width=0.5))
# add the legend using a dummy box to make patches for the legend
dummybox = [[0, 0], [0, 1], [1, 1], [1, 0], [0, 0]]
handles, labels = [], []
for group, color in zip(self.order[1:], color_table[1:]):
p = self.make_patch(dummybox, facecolor=color, width=0)
handles.append(subplot.add_patch(p))
labels.append(group)
leg = subplot.legend(handles,
labels,
bbox_to_anchor=(1.0, 0.5),
loc='center left',
title='Land Use Categories')
legtext = leg.get_texts()
pyplot.setp(legtext, fontsize=10)
subplot.set_position([0.125, 0.1, 0.6, 0.8])
# add the labels and set the limits
subplot.set_xlabel('Longitude, Decimal Degrees', size=13)
subplot.set_ylabel('Latitude, Decimal Degrees', size=13)
subplot.set_xlim([xmin, xmax])
subplot.set_ylim([ymin, ymax])
subplot.xaxis.set_major_locator(ticker.MaxNLocator(8))
subplot.yaxis.set_major_locator(ticker.MaxNLocator(8))
subplot.xaxis.set_major_formatter(ticker.FormatStrFormatter('%.2f'))
subplot.yaxis.set_major_formatter(ticker.FormatStrFormatter('%.2f'))
# show it
if output is not None: pyplot.savefig(output)
if show: pyplot.show()
pyplot.clf()
pyplot.close()
def plot_HUC8(self,
flowfile,
cfile,
bfile,
VAAfile,
elevfile,
patchcolor = None,
resolution = 400,
colormap = 'gist_earth',
grid = False,
title = None,
verbose = True,
output = None,
show = False,
):
"""Makes a plot of the raw NHDPlus data."""
if verbose: print('generating plot of the watershed\n')
fig = pyplot.figure()
subplot = fig.add_subplot(111, aspect = 'equal')
subplot.tick_params(axis = 'both', which = 'major', labelsize = 10)
# add the title
if title is not None: subplot.set_title(title, fontsize = 14)
if patchcolor is None: facecolor = (1,0,0,0.)
else: facecolor = patchcolor
# open up and show the boundary
b = Reader(bfile, shapeType = 5)
boundary = b.shape(0)
points = numpy.array(boundary.points)
subplot.add_patch(self.make_patch(points, facecolor, width = 0.5))
# open up and show the catchments
c = Reader(cfile, shapeType = 5)
extent = self.get_boundaries(c.shapes(), space = 0.02)
xmin, ymin, xmax, ymax = extent
# figure out how far one foot is on the map
points_per_width = 72 * 8
ft_per_km = 3280.84
scale_factor = (points_per_width /
self.get_distance([xmin, ymin], [xmax, ymin]) /
ft_per_km)
# make patches of the catchment area
for i in range(len(c.records())):
catchment = c.shape(i)
points = numpy.array(catchment.points)
subplot.add_patch(self.make_patch(points, facecolor, width = 0.1))
# get the flowline attributes, make an "updown" dictionary to follow
# flow, and change the keys to comids
with open(VAAfile, 'rb') as f: flowlineVAAs = pickle.load(f)
updown = {}
for f in flowlineVAAs:
if flowlineVAAs[f].down in flowlineVAAs:
updown[flowlineVAAs[f].comid] = \
flowlineVAAs[flowlineVAAs[f].down].comid
flowlineVAAs = {flowlineVAAs[f].comid:flowlineVAAs[f]
for f in flowlineVAAs}
# open up and show the flowfiles
f = Reader(flowfile, shapeType = 3)
comid_index = f.fields.index(['COMID', 'N', 9, 0]) - 1
all_comids = [r[comid_index] for r in f.records()]
# get the flows and velocities from the dictionary
widths = []
comids = []
for comid in all_comids:
if comid in flowlineVAAs:
flow = flowlineVAAs[comid].flow
velocity = flowlineVAAs[comid].velocity
# estimate flow width (ft) assuming triangular 90 d channel
comids.append(comid)
widths.append(numpy.sqrt(4 * flow / velocity))
# convert widths in feet to points on the figure; exaggerated by 10
widths = [w * scale_factor * 20 for w in widths]
# get the flowline and the corresponding catchment
for comid, w in zip(comids, widths):
i = all_comids.index(comid)
flowline = numpy.array(f.shape(i).points)
# plot it
subplot.plot(flowline[:, 0], flowline[:, 1], 'b', lw = w)
subplot.set_xlabel('Longitude, Decimal Degrees', size = 13)
subplot.set_ylabel('Latitude, Decimal Degrees', size = 13)
# add the NED raster
im = self.add_raster(subplot, elevfile, resolution, extent,
colormap, 100)
divider = make_axes_locatable(subplot)
cax = divider.append_axes('right', size = 0.16, pad = 0.16)
colorbar = fig.colorbar(im, cax = cax, orientation = 'vertical')
colorbar.set_label('Elevation, m', size = 12)
cbax = pyplot.axes(colorbar.ax)
for t in cbax.get_yaxis().get_majorticklabels(): t.set_fontsize(10)
subplot.xaxis.set_major_locator(ticker.MultipleLocator(0.2))
subplot.yaxis.set_major_locator(ticker.MultipleLocator(0.2))
if grid:
subplot.xaxis.grid(True, 'minor', linestyle = '-', linewidth = 0.5)
subplot.yaxis.grid(True, 'minor', linestyle = '-', linewidth = 0.5)
# show it
pyplot.tight_layout()
if output is not None: pyplot.savefig(output)
if show: pyplot.show()
pyplot.close()
pyplot.clf()
# weighted average (IDWA) to interpolate between the stations at a given point
# using the "method," "latitude," and "longitude" keyword arguments. the
# result is the same as the previous example. as before, the subbasin_catchments
# shapefile will be used that contains the centroid for each aggregation.
sf = Reader(filename)
# index of the comid, latitude, and longitude records
comid_index = [f[0] for f in sf.fields].index('ComID') - 1
lon_index = [f[0] for f in sf.fields].index('CenX') - 1
lat_index = [f[0] for f in sf.fields].index('CenY') - 1
# iterate through the shapefile records and aggregate the timeseries
for i in range(len(sf.records())):
record = sf.record(i)
comid = record[comid_index]
lon = record[lon_index]
lat = record[lat_index]
i = comid, lon, lat
print('aggregating timeseries for comid {} at {}, {}\n'.format(*i))
precipitation = processor.aggregate('precip3240', 'precip', start, end,
method = 'IDWA', longitude = lon,
latitude = lat)
mean = sum(precipitation) / (end - start).days * 365.25
name_index = sf.fields.index(['DAM_NAME', 'C', 65, 0]) - 1
nid_index = sf.fields.index(['NIDID', 'C', 7, 0]) - 1
lon_index = sf.fields.index(['LONGITUDE', 'N', 19, 11]) - 1
lat_index = sf.fields.index(['LATITUDE', 'N', 19, 11]) - 1
river_index = sf.fields.index(['RIVER', 'C', 65, 0]) - 1
owner_index = sf.fields.index(['OWN_NAME', 'C', 65, 0]) - 1
type_index = sf.fields.index(['DAM_TYPE', 'C', 10, 0]) - 1
purp_index = sf.fields.index(['PURPOSES', 'C', 254, 0]) - 1
year_index = sf.fields.index(['YR_COMPL', 'C', 10, 0]) - 1
high_index = sf.fields.index(['NID_HEIGHT', 'N', 19, 11]) - 1
mstor_index = sf.fields.index(['MAX_STOR', 'N', 19, 11]) - 1
nstor_index = sf.fields.index(['NORMAL_STO', 'N', 19, 11]) - 1
area_index = sf.fields.index(['SURF_AREA', 'N', 19, 11]) - 1
# iterate through the records and get whatever information is needed
for r in sf.records():
name = r[name_index]
nidid = r[nid_index]
lon = r[lon_index]
lat = r[lat_index]
pur = r[purp_index]
print('Dam name: ', name)
print('NID ID: ', nidid)
print('Longitude: ', lon)
print('Latitude: ', lat)
print('Primary Purpose:', pur)
print('')
def plot_climate(HUC8, sfile, bfile, pfile = None, efile = None, tfile = None,
snowfile = None, centroids = True, radius = None,
patchcolor = None, solarfile = None, windfile = None,
output = None, show = False, verbose = True):
"""Makes a plot of all the hourly precipitation stations of a watershed
defined by "bfile" with subbasin defined by "sfile" from the source
precipitation shapefile "pfile"."""
if verbose:
print('generating plot of watershed %s NCDC stations\n' % HUC8)
fig = pyplot.figure()
subplot = fig.add_subplot(111, aspect = 'equal')
subplot.tick_params(axis = 'both', which = 'major', labelsize = 10)
# add the title
description = 'Climate Data Stations'
title = 'Cataloging Unit %s\n%s' % (HUC8, description)
subplot.set_title(title, fontsize = 14)
# open up and show the catchments
if patchcolor is None: facecolor = (1,0,0,0.)
else: facecolor = patchcolor
b = Reader(bfile, shapeType = 5)
points = np.array(b.shape(0).points)
subplot.add_patch(make_patch(points, facecolor = facecolor, width = 1.))
extent = get_boundaries(b.shapes(), space = 0.02)
xmin, ymin, xmax, ymax = extent
# add the subbasin file
s = Reader(sfile, shapeType = 5)
# make patches of the subbasins
for i in range(len(s.records())):
shape = s.shape(i)
points = np.array(shape.points)
subplot.add_patch(make_patch(points, facecolor, width = 0.15))
plots = [] # keep track of the scatterplots
names = [] # keep track of names for the legend
# add the subbasin centroids
if centroids:
cx_index = s.fields.index(['CenX', 'N', 12, 6]) - 1
cy_index = s.fields.index(['CenY', 'N', 12, 6]) - 1
centroids = [[r[cx_index], r[cy_index]] for r in s.records()]
xs, ys = zip(*centroids)
cplot = subplot.scatter(xs, ys, marker = '+', c = 'pink', s = 15)
plots.append(cplot)
names.append('Centroids')
# add a circle showing around subbasin "radius" showing the gages within
# the radius for a given subbasin
if radius is not None:
comid_index = s.fields.index(['ComID', 'N', 9, 0]) - 1
cx_index = s.fields.index(['CenX', 'N', 12, 6]) - 1
cy_index = s.fields.index(['CenY', 'N', 12, 6]) - 1
area_index = s.fields.index(['AreaSqKm', 'N', 10, 2]) - 1
comids = ['{}'.format(r[comid_index]) for r in s.records()]
cxs = [r[cx_index] for r in s.records()]
cys = [r[cy_index] for r in s.records()]
areas = [r[area_index] for r in s.records()]
try: i = comids.index(radius)
except: i = 0
c = [cxs[i], cys[i]]
radii = [math.sqrt(a / math.pi) for a in areas]
# scale kms to degrees
km = get_distance([xmin, ymin], [xmax, ymax])
deg = math.sqrt((xmin - xmax)**2 + (ymax - ymin)**2)
r = sum(radii) / len(radii) * deg / km * 5
circle = pyplot.Circle(c, radius = r, edgecolor = 'black',
facecolor = 'yellow', alpha = 0.5)
subplot.add_patch(circle)
subplot.scatter(c[0], c[1], marker = '+', c = 'black')
# add the precipitation gage points
if pfile is not None:
with open(pfile, 'rb') as f: precips = pickle.load(f)
gage_points = [(p.longitude, p.latitude) for p in precips.values()]
x1, y1 = zip(*gage_points)
plots.append(subplot.scatter(x1, y1, marker = 'o', c = 'b'))
names.append('Precipitation')
# add the pan evaporation points
if efile is not None:
with open(efile, 'rb') as f: evaps = pickle.load(f)
gage_points = [(e.longitude, e.latitude) for e in evaps.values()]
x2, y2 = zip(*gage_points)
eplot = subplot.scatter(x2, y2, s = evaps, marker = 'o', c = 'g')
plots.append(eplot)
names.append('Pan Evaporation')
# add the temperature station points
if tfile is not None:
with open(tfile, 'rb') as f: temps = pickle.load(f)
gage_points = [(t.longitude, t.latitude) for t in temps.values()]
x2, y2 = zip(*gage_points)
plots.append(subplot.scatter(x2, y2, marker = 's', c = 'red'))
names.append('Temperature')
# add the snowdepth station points
if snowfile is not None:
with open(snowfile, 'rb') as f: snows = pickle.load(f)
snow_points = [(s.longitude, s.latitude) for s in snows.values()]
x2, y2 = zip(*snow_points)
plots.append(subplot.scatter(x2, y2, marker = 'o', c = 'gray',
alpha = 0.5))
names.append('Snow')
# add the solar radiation files
if solarfile is not None:
with open(solarfile, 'rb') as f: solar = pickle.load(f)
points = [(s.longitude, s.latitude) for s in solar.values()]
x2, y2 = zip(*points)
plots.append(subplot.scatter(x2, y2, marker = 'o', c = 'orange'))
names.append('Solar')
# add the wind files
if windfile is not None:
with open(windfile, 'rb') as f: wind = pickle.load(f)
points = [(w.longitude, w.latitude) for w in wind.values()]
x2, y2 = zip(*points)
plots.append(subplot.scatter(x2, y2, marker = 'o', c = 'pink'))
names.append('Wind')
# add a legend
leg = subplot.legend(plots, names, loc = 'upper center',
ncol = 3, bbox_to_anchor = (0.5, -0.15))
legtext = leg.get_texts()
pyplot.setp(legtext, fontsize = 10)
#subplot.set_position([0.125, 0.1, 0.6, 0.8])
# set the labels
subplot.set_xlabel('Longitude, Decimal Degrees', size = 13)
subplot.set_ylabel('Latitude, Decimal Degrees', size = 13)
# show it
if output is not None: pyplot.savefig(output)
if show: pyplot.show()
pyplot.clf()
pyplot.close()
def merge_shapes(inputfile, outputfile = None, overwrite = False,
verbose = True, vverbose = False):
"""Merges all the shapes in a shapefile into a single shape."""
if outputfile is None: output = '{}/merged'.format(os.getcwd())
if os.path.isfile(outputfile + '.shp') and not overwrite:
if verbose: print('combined watershed shapefile %s exists' % outputfile)
return
if verbose: print('combining shapes from {}\n'.format(inputfile) +
'this may take a while...\n')
# start by copying the projection files
shutil.copy(inputfile + '.prj', outputfile + '.prj')
# load the catchment and flowline shapefiles
r = Reader(inputfile, shapeType = 5)
n = len(r.records())
try:
shapes = []
records = []
bboxes = []
for i in range(n):
shape = r.shape(i)
record = r.record(i)
shape_list = format_shape(shape.points)
for sh in shape_list:
shapes.append(sh)
records.append(record)
bboxes.append(shape.bbox)
try: combined = combine_shapes(shapes, bboxes,
verbose = vverbose)
except:
if verbose: print('trying alternate trace method')
combined = combine_shapes(shapes, bboxes, skip = True,
verbose = vverbose)
except:
if verbose: print('trying alternate trace method')
shapes = []
records = []
bboxes = []
for i in range(n):
shape = r.shape(i)
record = r.record(i)
shape_list = format_shape(shape.points, omit = True)
for sh in shape_list:
shapes.append(sh)
records.append(record)
bboxes.append(shape.bbox)
try: combined = combine_shapes(shapes, bboxes, verbose = vverbose)
except:
if verbose: print('trying alternate trace method')
combined = combine_shapes(shapes, bboxes, skip = True,
verbose = vverbose)
# create the new file with the merged shapes
w = Writer(shapeType = 5)
w.poly(shapeType = 5, parts = [combined])
# copy the fields from the original and then the first record; note this
# can be adapted as needed
for field in r.fields: w.field(*field)
w.record(*r.record(0))
w.save(outputfile)
if verbose:
print('successfully combined shapes from %s to %s\n' %
(inputfile, outputfile))
import csv, pandas
from shapefile import Reader
sf = 'C:/HSPF_data/07080106/hydrography/subbasin_catchments'
# read the areas from the shapefile into a lookup dictionary
r = Reader(sf)
comid_index = [f[0] for f in r.fields].index('ComID') - 1
area_index = [f[0] for f in r.fields].index('AreaSqKm') - 1
areas = {row[comid_index]: row[area_index] for row in r.records()}
# directory to the land use data
p = 'C:/HSPF_new/07080106/landuse'
# store the results in a data structure
rows = [['Year']]
for y in range(2000,2011):
# expand the structure for the next file
rows.append([y])
# land use csv file for the year (contains the fractions for each comid)
def calculate_landuse(
self,
rasterfile,
shapefile,
aggregatefile,
attribute,
csvfile=None,
):
"""
Calculates the land use for the given year for the "attribute"
feature attribute in the polygon shapefile using the aggregate
mapping provided in the "aggregatefile."
"""
# make sure the files exist
for f in rasterfile, shapefile + '.shp', aggregatefile:
if not os.path.isfile(f):
print('error, {} does not exist\n'.format(f))
raise
# read the aggregate file
self.read_aggregatefile(aggregatefile)
# open the shapefile
sf = Reader(shapefile, shapeType=5)
attributes = [f[0] for f in sf.fields]
try:
index = attributes.index(attribute) - 1
except:
print('error: attribute ' +
'{} is not in the shapefile fields'.format(attribute))
raise
# iterate through the shapes, get the fractions and save them
for i in range(len(sf.records())):
points = numpy.array(sf.shape(i).points)
record = sf.record(i)
k = record[index]
# store the results
self.landuse[k] = {r: 0 for r in self.order}
try:
values, origin = get_raster_in_poly(rasterfile,
points,
verbose=False)
values = values.flatten()
values = values[values.nonzero()]
tot_pixels = len(values)
# count the number of pixels of each land use type
for v in numpy.unique(values):
# find all the indices for each pixel value
pixels = numpy.argwhere(values == v)
# normalize by the total # of pixels
f = len(values[pixels]) / tot_pixels
# add the landuse to the aggregated value
self.landuse[k][self.groups[v]] += f
# work around for small shapes
except:
self.landuse[k][self.groups[0]] = 1
if csvfile is not None: self.make_csv(attribute, csvfile)
return self.landuse
def extract_HUC8(self, HUC8, output, gagefile = 'gagestations',
verbose = True):
"""Extracts the USGS gage stations for a watershed from the gage
station shapefile into a shapefile for the 8-digit hydrologic unit
code of interest.
"""
# make sure the metadata exist locally
self.download_metadata()
# make sure the output destination exists
if not os.path.isdir(output): os.mkdir(output)
sfile = '{}/{}'.format(output, gagefile)
if not os.path.isfile(sfile + '.shp'):
# copy the projection
shutil.copy(self.NWIS + '.prj', sfile + '.prj')
# read the file
gagereader = Reader(self.NWIS, shapeType = 1)
gagerecords = gagereader.records()
# pull out the HUC8 record to parse the dataset
HUC8_index = gagereader.fields.index(['HUC', 'C', 8, 0]) - 1
# iterate through the field and find gages in the watershed
its = HUC8, sfile
print('extracting gage stations in {} to {}\n'.format(*its))
gage_indices = []
i = 0
for record in gagerecords:
if record[HUC8_index] == HUC8: gage_indices.append(i)
i+=1
# write the data from the HUC8 to a new shapefile
w = Writer(shapeType = 1)
for field in gagereader.fields: w.field(*field)
for i in gage_indices:
point = gagereader.shape(i).points[0]
w.point(*point)
w.record(*gagerecords[i])
w.save(sfile)
if verbose:
print('successfully extracted NWIS gage stations\n')
elif verbose:
print('gage station file {} exists\n'.format(sfile))
self.set_metadata(sfile)
# use the ETCalculator to estimate the evapotranspiration time series
calculator = ETCalculator()
# some of the parameters in the Penman-Monteith Equation depend on the
# geographic location so get the average longitude, latitude, and elevation
sf = Reader(filename)
# make a list of the fields for each shape
fields = [f[0] for f in sf.fields]
# get the area, centroid and elevation of each shape
areas = [r[fields.index("AreaSqKm") - 1] for r in sf.records()]
xs = [r[fields.index("CenX") - 1] for r in sf.records()]
ys = [r[fields.index("CenY") - 1] for r in sf.records()]
zs = [r[fields.index("AvgElevM") - 1] for r in sf.records()]
# get the areal-weighted averages
lon = sum([a * x for a, x in zip(areas, xs)]) / sum(areas)
lat = sum([a * y for a, y in zip(areas, ys)]) / sum(areas)
elev = sum([a * z for a, z in zip(areas, zs)]) / sum(areas)
# add the information to the calculator
calculator.add_location(lon, lat, elev)
# use the daily tmin and tmax time series to the calculator to get hourly temps
# solar radiation in W/m2; these are the units supplied by the other classes
# in PyHSPF already so no manipulation is needed
# some of the parameters in the Penman-Monteith Equation depend on the
# geographic location so let's use the information in the shapefile to
# provide the average longitude, latitude, and elevation
sf = Reader(filename)
# make a list of the fields for each shape
fields = [f[0] for f in sf.fields]
# get the area, centroid and elevation of each shape
areas = [r[fields.index('AreaSqKm') - 1] for r in sf.records()]
xs = [r[fields.index('CenX') - 1] for r in sf.records()]
ys = [r[fields.index('CenY') - 1] for r in sf.records()]
zs = [r[fields.index('AvgElevM') - 1] for r in sf.records()]
# get the areal-weighted averages
lon = sum([a * x for a, x in zip(areas, xs)]) / sum(areas)
lat = sum([a * y for a, y in zip(areas, ys)]) / sum(areas)
elev = sum([a * z for a, z in zip(areas, zs)]) / sum(areas)
# add the information to the calculator
calculator.add_location(lon, lat, elev)
# it is pretty trivial to get the corresponding reference evapotranspiration
extractor.download_gagedata(gageid, start, end, output = gageid)
# need to know the reach length; so find the location of the gage, then find
# the flowline in the shapefile and use the record info to get the length
# first use the NWIS metadata file to get the latitude and longitude of the gage
reader = Reader('{}/USGS_Streamgages-NHD_Locations.shp'.format(NWIS))
# find the record index for the NWIS gage ids
i = [f[0] for f in reader.fields].index('SITE_NO') - 1
# find the index of the gage
j = [r[i] for r in reader.records()].index(gageid)
# use the index to get the latitude and longitude of the station
x, y = reader.shape(j).points[0]
print('location of gage {}: {:.4f}, {:.4f}\n'.format(gageid, x, y))
# open the flowline shapefile to supply reach length (miles or kilometers
# depending on the unit system)
reader = Reader(flowfile)
# find shapes with a bounding box encompassing the gage to narrow the search
print('searching for the closest flowline to the gage\n')
def plot_gage_subbasin(self, hspfmodel, folder):
"""Makes a plot of the subbasin area."""
subbasinfile = '{}/subbasins'.format(folder)
boundaryfile = '{}/boundary'.format(folder)
flowfile = '{}/flowlines'.format(folder)
combinedfile = '{}/combined'.format(folder)
watershedplot = '{}/watershed.png'.format(folder)
# make a shapefile of the subbasins for the watershed
f = '{0}/{1}/{1}subbasins'.format(self.directory, self.HUC8)
for out in (subbasinfile, boundaryfile, flowfile, combinedfile):
if not os.path.isfile(out + '.prj'):
shutil.copy(f + '.prj', out + '.prj')
if not os.path.isfile(subbasinfile + '.shp'):
subshapes = []
subrecords = []
for subbasin in hspfmodel.subbasins:
f = '{0}/{1}/{2}/combined'.format(self.directory, self.HUC8,
subbasin)
s = Reader(f, shapeType = 5)
subshapes.append(s.shape(0).points)
subrecords.append(s.record(0))
w = Writer(shapeType = 5)
for field in s.fields: w.field(*field)
for record in subrecords: w.record(*record)
for shape in subshapes: w.poly(shapeType = 5, parts = [shape])
w.save(subbasinfile)
if not os.path.isfile(combinedfile + '.shp'):
fshapes = []
frecords = []
for subbasin in hspfmodel.subbasins:
f = '{0}/{1}/{2}/combined_flowline'.format(self.directory,
self.HUC8,
subbasin)
r = Reader(f, shapeType = 3)
fshapes.append(r.shape(0).points)
frecords.append(r.record(0))
w = Writer(shapeType = 3)
for field in r.fields: w.field(*field)
for record in frecords: w.record(*record)
for shape in fshapes: w.poly(shapeType = 3, parts = [shape])
w.save(combinedfile)
# merge the shapes into a watershed
if not os.path.exists(boundaryfile + '.shp'):
merge_shapes(subbasinfile, outputfile = boundaryfile)
# make a flowline file for the subbasins for the watershed
if not os.path.isfile(flowfile + '.shp'):
shapes = []
records = []
for subbasin in hspfmodel.subbasins:
f = '{0}/{1}/{2}/flowlines'.format(self.directory,
self.HUC8, subbasin)
r = Reader(f, shapeType = 3)
for shape in r.shapes(): shapes.append(shape.points)
for record in r.records(): records.append(record)
w = Writer(shapeType = 3)
for field in r.fields: w.field(*field)
for record in records: w.record(*record)
for shape in shapes: w.poly(shapeType = 3, parts = [shape])
w.save(flowfile)
if not os.path.isfile(watershedplot):
plot_gage_subbasin(folder, self.HUC8, self.gageid, hspfmodel,
output = watershedplot)
# use the ETCalculator to estimate the evapotranspiration time series
calculator = ETCalculator()
# some of the parameters in the Penman-Monteith Equation depend on the
# geographic location so get the average longitude, latitude, and elevation
sf = Reader(filename)
# make a list of the fields for each shape
fields = [f[0] for f in sf.fields]
# get the area, centroid and elevation of each shape
areas = [r[fields.index('AreaSqKm') - 1] for r in sf.records()]
xs = [r[fields.index('CenX') - 1] for r in sf.records()]
ys = [r[fields.index('CenY') - 1] for r in sf.records()]
zs = [r[fields.index('AvgElevM') - 1] for r in sf.records()]
# get the areal-weighted averages
lon = sum([a * x for a, x in zip(areas, xs)]) / sum(areas)
lat = sum([a * y for a, y in zip(areas, ys)]) / sum(areas)
elev = sum([a * z for a, z in zip(areas, zs)]) / sum(areas)
# add the information to the calculator
calculator.add_location(lon, lat, elev)
# use the daily tmin and tmax time series to the calculator to get hourly temps
