def write_asc_file(filename, data, xsize, ysize, geotransform,
nodata_value):
"""Output Raster to ASCII file.
Args:
filename: output ASCII filename.
data: 2D array data.
xsize: Col count.
ysize: Row count.
geotransform: geographic transformation.
nodata_value: nodata_flow value.
"""
UtilClass.mkdir(os.path.dirname(FileClass.get_file_fullpath(filename)))
header = 'NCOLS %d\n' \
'NROWS %d\n' \
'XLLCENTER %f\n' \
'YLLCENTER %f\n' \
'CELLSIZE %f\n' \
'NODATA_VALUE %f' % (xsize, ysize, geotransform[0] + 0.5 * geotransform[1],
geotransform[3] - (ysize - 0.5) * geotransform[1],
geotransform[1], nodata_value)
with open(filename, 'w', encoding='utf-8') as f:
f.write(header)
for i in range(0, ysize):
for j in range(0, xsize):
f.write('%s\t' % repr(data[i][j]))
f.write('\n')
f.close()
def write_autofuzslppos_config_file(ini_name, bin, wp, data_path, dem_name):
UtilClass.mkdir(wp)
org_ini_file = data_path + os.sep + ini_name
demf = data_path + os.sep + 'inputs' + os.sep + dem_name
if not os.path.isfile(org_ini_file):
print('%s file is not existed!' % org_ini_file)
exit(-1)
dst_int_file = wp + os.sep + ini_name
cfg_items = list()
with open(org_ini_file, 'r') as f:
for line in f.readlines():
cfg_items.append(line.strip())
# print cfg_items
cfg_items.append('[REQUIRED]')
cfg_items.append('exeDir = %s' % bin)
cfg_items.append('rootDir = %s' % wp)
cfg_items.append('rawdem = %s' % demf)
with open(dst_int_file, 'w') as f:
for item in cfg_items:
f.write(item + '\n')
cf = ConfigParser()
cf.read(dst_int_file)
return AutoFuzSlpPosConfig(cf)
def write_gtiff_file(f_name, n_rows, n_cols, data, geotransform, srs, nodata_value,
gdal_type=GDT_Float32):
"""Output Raster to GeoTiff format file.
Args:
f_name: output gtiff file name.
n_rows: Row count.
n_cols: Col count.
data: 2D array data.
geotransform: geographic transformation.
srs: coordinate system.
nodata_value: nodata value.
gdal_type (:obj:`pygeoc.raster.GDALDataType`): output raster data type,
GDT_Float32 as default.
"""
UtilClass.mkdir(os.path.dirname(FileClass.get_file_fullpath(f_name)))
driver = gdal_GetDriverByName(str('GTiff'))
try:
ds = driver.Create(f_name, n_cols, n_rows, 1, gdal_type)
except Exception:
print('Cannot create output file %s' % f_name)
return
ds.SetGeoTransform(geotransform)
try:
ds.SetProjection(srs.ExportToWkt())
except AttributeError or Exception:
ds.SetProjection(srs)
ds.GetRasterBand(1).SetNoDataValue(nodata_value)
# if data contains numpy.nan, then replaced by nodata_value
if isinstance(data, numpy.ndarray) and data.dtype in [numpy.dtype('int'),
numpy.dtype('float')]:
data = numpy.where(numpy.isnan(data), nodata_value, data)
ds.GetRasterBand(1).WriteArray(data)
ds = None
def write_asc_file(filename, data, xsize, ysize, geotransform, nodata_value):
"""Output Raster to ASCII file.
Args:
filename: output ASCII filename.
data: 2D array data.
xsize: Col count.
ysize: Row count.
geotransform: geographic transformation.
nodata_value: nodata_flow value.
"""
UtilClass.mkdir(os.path.dirname(FileClass.get_file_fullpath(filename)))
header = 'NCOLS %d\n' \
'NROWS %d\n' \
'XLLCENTER %f\n' \
'YLLCENTER %f\n' \
'CELLSIZE %f\n' \
'NODATA_VALUE %f' % (xsize, ysize, geotransform[0] + 0.5 * geotransform[1],
geotransform[3] - (ysize - 0.5) * geotransform[1],
geotransform[1], nodata_value)
with open(filename, 'w', encoding='utf-8') as f:
f.write(header)
for i in range(0, ysize):
for j in range(0, xsize):
f.write('%s\t' % repr(data[i][j]))
f.write('\n')
f.close()
def mask_origin_delineated_data(cfg):
"""Mask the original delineated data by Subbasin raster."""
subbasin_tau_file = cfg.taudems.subbsn
geodata2dbdir = cfg.dirs.geodata2db
UtilClass.mkdir(geodata2dbdir)
mask_file = cfg.spatials.mask
RasterUtilClass.get_mask_from_raster(subbasin_tau_file, mask_file)
# Total 12 raster files
original_files = [
cfg.taudems.subbsn, cfg.taudems.d8flow, cfg.taudems.stream_raster,
cfg.taudems.slp, cfg.taudems.filldem, cfg.taudems.d8acc,
cfg.taudems.stream_order, cfg.taudems.dinf, cfg.taudems.dinf_d8dir,
cfg.taudems.dinf_slp, cfg.taudems.dinf_weight,
cfg.taudems.dist2stream_d8
]
# output masked files
output_files = [
cfg.taudems.subbsn_m, cfg.taudems.d8flow_m, cfg.taudems.stream_m,
cfg.spatials.slope, cfg.spatials.filldem, cfg.spatials.d8acc,
cfg.spatials.stream_order, cfg.spatials.dinf,
cfg.spatials.dinf_d8dir, cfg.spatials.dinf_slp,
cfg.spatials.dinf_weight, cfg.spatials.dist2stream_d8
]
default_values = list()
for i in range(len(original_files)):
default_values.append(DEFAULT_NODATA)
# other input rasters need to be masked
# soil and landuse
FileClass.check_file_exists(cfg.soil)
FileClass.check_file_exists(cfg.landuse)
original_files.append(cfg.soil)
output_files.append(cfg.spatials.soil_type)
default_values.append(cfg.default_soil)
original_files.append(cfg.landuse)
output_files.append(cfg.spatials.landuse)
default_values.append(cfg.default_landuse)
# Additional raster file
for k, v in cfg.additional_rs.items():
org_v = v
if not FileClass.is_file_exists(org_v):
v = cfg.spatial_dir + os.path.sep + org_v
if not FileClass.is_file_exists(v):
print('WARNING: The additional file %s MUST be located in '
'SPATIAL_DATA_DIR, or provided as full file path!' %
k)
continue
original_files.append(v)
output_files.append(cfg.dirs.geodata2db + os.path.sep + k + '.tif')
default_values.append(DEFAULT_NODATA)
config_file = cfg.logs.mask_cfg
# run mask operation
print('Mask original delineated data by Subbasin raster...')
SpatialDelineation.mask_raster_cpp(cfg.seims_bin, mask_file,
original_files, output_files,
default_values, config_file)
def __init__(self, wp):
"""Initialization."""
self.param_defs_json = wp + os.path.sep + 'param_defs.json'
self.param_values_txt = wp + os.path.sep + 'param_values.txt'
self.output_values_dir = wp + os.path.sep + 'temp_output_values'
self.output_values_txt = wp + os.path.sep + 'output_values.txt'
self.psa_si_json = wp + os.path.sep + 'psa_si.json'
self.psa_si_sort_txt = wp + os.path.sep + 'psa_si_sorted.csv'
UtilClass.mkdir(self.output_values_dir)
def __init__(self, cf, method='morris'):
"""Initialization."""
self.method = method
# 1. SEIMS model related
self.model = ParseSEIMSConfig(cf)
# 2. Common settings of parameters sensitivity analysis
if 'PSA_Settings' not in cf.sections():
raise ValueError(
"[PSA_Settings] section MUST be existed in *.ini file.")
self.evaluate_params = list()
if cf.has_option('PSA_Settings', 'evaluateparam'):
eva_str = cf.get('PSA_Settings', 'evaluateparam')
self.evaluate_params = StringClass.split_string(eva_str, ',')
else:
self.evaluate_params = ['Q'] # Default
self.param_range_def = 'morris_param_rng.def' # Default
if cf.has_option('PSA_Settings', 'paramrngdef'):
self.param_range_def = cf.get('PSA_Settings', 'paramrngdef')
self.param_range_def = self.model.model_dir + os.path.sep + self.param_range_def
if not FileClass.is_file_exists(self.param_range_def):
raise IOError('Ranges of parameters MUST be provided!')
if not (cf.has_option('PSA_Settings', 'psa_time_start')
and cf.has_option('PSA_Settings', 'psa_time_end')):
raise ValueError(
"Start and end time of PSA MUST be specified in [PSA_Settings]."
)
try:
# UTCTIME
tstart = cf.get('PSA_Settings', 'psa_time_start')
tend = cf.get('PSA_Settings', 'psa_time_end')
self.psa_stime = StringClass.get_datetime(tstart)
self.psa_etime = StringClass.get_datetime(tend)
except ValueError:
raise ValueError('The time format MUST be"YYYY-MM-DD HH:MM:SS".')
if self.psa_stime >= self.psa_etime:
raise ValueError("Wrong time settings in [PSA_Settings]!")
# 3. Parameters settings for specific sensitivity analysis methods
self.morris = None
self.fast = None
if self.method == 'fast':
self.fast = FASTConfig(cf)
self.psa_outpath = '%s/PSA_FAST_N%dM%d' % (
self.model.model_dir, self.fast.N, self.fast.M)
elif self.method == 'morris':
self.morris = MorrisConfig(cf)
self.psa_outpath = '%s/PSA_Morris_N%dL%d' % (
self.model.model_dir, self.morris.N, self.morris.num_levels)
# 4. (Optional) Plot settings for matplotlib
self.plot_cfg = PlotConfig(cf)
# Do not remove psa_outpath if already existed
UtilClass.mkdir(self.psa_outpath)
self.outfiles = PSAOutputs(self.psa_outpath)
def __init__(self, wp):
"""Initialization."""
self.param_defs_json = wp + os.path.sep + 'param_defs.json'
self.param_values_txt = wp + os.path.sep + 'param_values.txt'
self.output_values_dir = wp + os.path.sep + 'temp_output_values'
self.output_values_txt = wp + os.path.sep + 'output_values.txt'
self.psa_si_json = wp + os.path.sep + 'psa_si.json'
self.psa_si_sort_txt = wp + os.path.sep + 'psa_si_sorted.csv'
UtilClass.mkdir(self.output_values_dir)
def save_png_eps(plot, wp, name):
"""Save figures, both png and eps formats"""
eps_dir = wp + os.path.sep + 'eps'
pdf_dir = wp + os.path.sep + 'pdf'
UtilClass.mkdir(eps_dir)
UtilClass.mkdir(pdf_dir)
for figpath in [wp + os.path.sep + name + '.png',
eps_dir + os.path.sep + name + '.eps',
pdf_dir + os.path.sep + name + '.pdf']:
plot.savefig(figpath, dpi=300)
def __init__(self, cf, method='morris'):
"""Initialization."""
self.method = method
# 1. SEIMS model related
self.model = ParseSEIMSConfig(cf)
# 2. Common settings of parameters sensitivity analysis
if 'PSA_Settings' not in cf.sections():
raise ValueError("[PSA_Settings] section MUST be existed in *.ini file.")
self.evaluate_params = list()
if cf.has_option('PSA_Settings', 'evaluateparam'):
eva_str = cf.get('PSA_Settings', 'evaluateparam')
self.evaluate_params = StringClass.split_string(eva_str, ',')
else:
self.evaluate_params = ['Q'] # Default
self.param_range_def = 'morris_param_rng.def' # Default
if cf.has_option('PSA_Settings', 'paramrngdef'):
self.param_range_def = cf.get('PSA_Settings', 'paramrngdef')
self.param_range_def = self.model.model_dir + os.path.sep + self.param_range_def
if not FileClass.is_file_exists(self.param_range_def):
raise IOError('Ranges of parameters MUST be provided!')
if not (cf.has_option('PSA_Settings', 'psa_time_start') and
cf.has_option('PSA_Settings', 'psa_time_end')):
raise ValueError("Start and end time of PSA MUST be specified in [PSA_Settings].")
try:
# UTCTIME
tstart = cf.get('PSA_Settings', 'psa_time_start')
tend = cf.get('PSA_Settings', 'psa_time_end')
self.psa_stime = StringClass.get_datetime(tstart)
self.psa_etime = StringClass.get_datetime(tend)
except ValueError:
raise ValueError('The time format MUST be"YYYY-MM-DD HH:MM:SS".')
if self.psa_stime >= self.psa_etime:
raise ValueError("Wrong time settings in [PSA_Settings]!")
# 3. Parameters settings for specific sensitivity analysis methods
self.morris = None
self.fast = None
if self.method == 'fast':
self.fast = FASTConfig(cf)
self.psa_outpath = '%s/PSA-FAST-N%dM%d' % (self.model.model_dir,
self.fast.N, self.fast.M)
elif self.method == 'morris':
self.morris = MorrisConfig(cf)
self.psa_outpath = '%s/PSA-Morris-N%dL%dJ%d' % (self.model.model_dir,
self.morris.N,
self.morris.num_levels,
self.morris.grid_jump)
# Do not remove psa_outpath if already existed
UtilClass.mkdir(self.psa_outpath)
self.outfiles = PSAOutputs(self.psa_outpath)
def mask_origin_delineated_data(cfg):
"""Mask the original delineated data by Subbasin raster."""
subbasin_tau_file = cfg.taudems.subbsn
geodata2dbdir = cfg.dirs.geodata2db
UtilClass.mkdir(geodata2dbdir)
mask_file = cfg.spatials.mask
RasterUtilClass.get_mask_from_raster(subbasin_tau_file, mask_file)
# Total 12 raster files
original_files = [cfg.taudems.subbsn, cfg.taudems.d8flow, cfg.taudems.stream_raster,
cfg.taudems.slp, cfg.taudems.filldem, cfg.taudems.d8acc,
cfg.taudems.stream_order, cfg.taudems.dinf, cfg.taudems.dinf_d8dir,
cfg.taudems.dinf_slp, cfg.taudems.dinf_weight,
cfg.taudems.dist2stream_d8]
# output masked files
output_files = [cfg.taudems.subbsn_m, cfg.taudems.d8flow_m, cfg.taudems.stream_m,
cfg.spatials.slope, cfg.spatials.filldem, cfg.spatials.d8acc,
cfg.spatials.stream_order, cfg.spatials.dinf, cfg.spatials.dinf_d8dir,
cfg.spatials.dinf_slp, cfg.spatials.dinf_weight,
cfg.spatials.dist2stream_d8]
default_values = list()
for i in range(len(original_files)):
default_values.append(DEFAULT_NODATA)
# other input rasters need to be masked
# soil and landuse
FileClass.check_file_exists(cfg.soil)
FileClass.check_file_exists(cfg.landuse)
original_files.append(cfg.soil)
output_files.append(cfg.spatials.soil_type)
default_values.append(cfg.default_soil)
original_files.append(cfg.landuse)
output_files.append(cfg.spatials.landuse)
default_values.append(cfg.default_landuse)
# Additional raster file
for k, v in cfg.additional_rs.items():
org_v = v
if not FileClass.is_file_exists(org_v):
v = cfg.spatial_dir + os.path.sep + org_v
if not FileClass.is_file_exists(v):
print('WARNING: The additional file %s MUST be located in '
'SPATIAL_DATA_DIR, or provided as full file path!' % k)
continue
original_files.append(v)
output_files.append(cfg.dirs.geodata2db + os.path.sep + k + '.tif')
default_values.append(DEFAULT_NODATA)
config_file = cfg.logs.mask_cfg
# run mask operation
print('Mask original delineated data by Subbasin raster...')
SpatialDelineation.mask_raster_cpp(cfg.seims_bin, mask_file, original_files,
output_files, default_values, config_file)
def original_delineation(cfg):
"""Original Delineation by calling TauDEM functions"""
# Check directories
UtilClass.mkdir(cfg.workspace)
UtilClass.mkdir(cfg.dirs.log)
bin_dir = cfg.seims_bin
mpi_bin = cfg.mpi_bin
np = cfg.np
TauDEMWorkflow.watershed_delineation(np, cfg.dem, cfg.outlet_file, cfg.d8acc_threshold,
True,
cfg.dirs.taudem, mpi_bin, bin_dir,
cfg.logs.delineation)
def original_delineation(cfg):
"""Original Delineation by calling TauDEM functions"""
# Check directories
UtilClass.mkdir(cfg.workspace)
UtilClass.mkdir(cfg.dirs.log)
bin_dir = cfg.seims_bin
mpi_bin = cfg.mpi_bin
np = cfg.np
TauDEMWorkflow.watershed_delineation(np, cfg.dem, cfg.outlet_file, cfg.d8acc_threshold,
True,
cfg.dirs.taudem, mpi_bin, bin_dir,
cfg.logs.delineation)
def save_png_eps(plot, wp, name, plot_cfg=None):
# type: (plt, AnyStr, AnyStr, Optional[PlotConfig]) -> None
"""Save figures, both png and eps formats"""
# plot.tight_layout()
if plot_cfg is None:
plot_cfg = PlotConfig()
if plot_cfg.plot_cn:
wp = wp + os.path.sep + 'cn'
UtilClass.mkdir(wp)
for fmt in plot_cfg.fmts:
fmt_dir = wp + os.path.sep + fmt
UtilClass.mkdir(fmt_dir)
figpath = fmt_dir + os.path.sep + name + '.' + fmt
plot.savefig(figpath, dpi=plot_cfg.dpi)
def post_process_of_delineated_data(cfg):
"""Do some necessary transfer for subbasin, stream, and flow direction raster."""
# inputs
stream_net_file = cfg.taudems.streamnet_shp
subbasin_file = cfg.taudems.subbsn_m
flow_dir_file_tau = cfg.taudems.d8flow_m
stream_raster_file = cfg.taudems.stream_m
# outputs
# -- shapefile
shp_dir = cfg.dirs.geoshp
UtilClass.mkdir(shp_dir)
# ---- outlet, copy from DirNameUtils.TauDEM
FileClass.copy_files(cfg.taudems.outlet_m, cfg.vecs.outlet)
# ---- reaches
output_reach_file = cfg.vecs.reach
# ---- subbasins
subbasin_vector_file = cfg.vecs.subbsn
# -- raster file
output_subbasin_file = cfg.spatials.subbsn
output_flow_dir_file = cfg.spatials.d8flow
output_stream_link_file = cfg.spatials.stream_link
output_hillslope_file = cfg.spatials.hillslope
id_map = StreamnetUtil.serialize_streamnet(stream_net_file,
output_reach_file)
RasterUtilClass.raster_reclassify(subbasin_file, id_map,
output_subbasin_file, GDT_Int32)
StreamnetUtil.assign_stream_id_raster(stream_raster_file,
output_subbasin_file,
output_stream_link_file)
# Convert D8 encoding rule to ArcGIS
D8Util.convert_code(flow_dir_file_tau, output_flow_dir_file)
# convert raster to shapefile (for subbasin and basin)
print('Generating subbasin vector...')
VectorUtilClass.raster2shp(output_subbasin_file, subbasin_vector_file,
'subbasin', FieldNames.subbasin_id)
mask_file = cfg.spatials.mask
basin_vector = cfg.vecs.bsn
print('Generating basin vector...')
VectorUtilClass.raster2shp(mask_file, basin_vector, 'basin',
FieldNames.basin)
# delineate hillslope
DelineateHillslope.downstream_method_whitebox(output_stream_link_file,
flow_dir_file_tau,
output_hillslope_file)
def __init__(self, bpath, data_dir_name, model_dir_name):
self.mpi_bin = None
self.bin_dir = bpath + os.path.sep + 'bin'
self.prescript_dir = bpath + os.path.sep + 'seims' + os.path.sep + 'preprocess'
self.base_dir = bpath + os.path.sep + 'data' + os.path.sep + data_dir_name
self.cfg_dir = self.base_dir + os.path.sep + 'model_configs'
self.model_dir = self.base_dir + os.path.sep + model_dir_name
self.data_dir = self.base_dir + os.path.sep + 'data_prepare'
self.clim_dir = self.data_dir + os.path.sep + 'climate'
self.spatial_dir = self.data_dir + os.path.sep + 'spatial'
self.observe_dir = self.data_dir + os.path.sep + 'observed'
self.scenario_dir = self.data_dir + os.path.sep + 'scenario'
self.lookup_dir = self.data_dir + os.path.sep + 'lookup'
self.workspace = self.base_dir + os.path.sep + 'workspace'
UtilClass.mkdir(self.workspace)
print('SEIMS binary location: %s' % self.bin_dir)
print('Demo data location: %s' % self.base_dir)
print('Data preprocess location: %s' % self.workspace)
def __init__(self, bpath, data_dir_name, model_dir_name):
self.mpi_bin = None
self.bin_dir = bpath + os.path.sep + 'bin'
self.prescript_dir = bpath + os.path.sep + 'seims' + os.path.sep + 'preprocess'
self.base_dir = bpath + os.path.sep + 'data' + os.path.sep + data_dir_name
self.cfg_dir = self.base_dir + os.path.sep + 'model_configs'
self.model_dir = self.base_dir + os.path.sep + model_dir_name
self.data_dir = self.base_dir + os.path.sep + 'data_prepare'
self.clim_dir = self.data_dir + os.path.sep + 'climate'
self.spatial_dir = self.data_dir + os.path.sep + 'spatial'
self.observe_dir = self.data_dir + os.path.sep + 'observed'
self.scenario_dir = self.data_dir + os.path.sep + 'scenario'
self.lookup_dir = self.data_dir + os.path.sep + 'lookup'
self.workspace = self.base_dir + os.path.sep + 'workspace'
UtilClass.mkdir(self.workspace)
print('SEIMS binary location: %s' % self.bin_dir)
print('Demo data location: %s' % self.base_dir)
print('Data preprocessing location: %s' % self.workspace)
def prepare_node_with_weight_for_metis(graph, weight, wp):
# construct the METIS input file
UtilClass.mkdir(wp)
metis_input = r'%s/metis.txt' % wp
ns = graph.nodes()
with open(metis_input, 'w') as f:
f.write(str(len(ns)) + '\t' + str(len(graph.edges())) + '\t' + '010\t1\n')
for node in ns:
if node <= 0:
continue
f.write(str(weight[node][ImportReaches2Mongo._NUMCELLS]) + '\t')
for e in graph.out_edges(node):
if e[1] > 0:
f.write(str(e[1]) + '\t')
for e in graph.in_edges(node):
if e[0] > 0:
f.write(str(e[0]) + '\t')
f.write('\n')
return metis_input
def post_process_of_delineated_data(cfg):
"""Do some necessary transfer for subbasin, stream, and flow direction raster."""
# inputs
stream_net_file = cfg.taudems.streamnet_shp
subbasin_file = cfg.taudems.subbsn_m
flow_dir_file_tau = cfg.taudems.d8flow_m
stream_raster_file = cfg.taudems.stream_m
# outputs
# -- shapefile
shp_dir = cfg.dirs.geoshp
UtilClass.mkdir(shp_dir)
# ---- outlet, copy from DirNameUtils.TauDEM
FileClass.copy_files(cfg.taudems.outlet_m, cfg.vecs.outlet)
# ---- reaches
output_reach_file = cfg.vecs.reach
# ---- subbasins
subbasin_vector_file = cfg.vecs.subbsn
# -- raster file
output_subbasin_file = cfg.spatials.subbsn
output_flow_dir_file = cfg.spatials.d8flow
output_stream_link_file = cfg.spatials.stream_link
output_hillslope_file = cfg.spatials.hillslope
id_map = StreamnetUtil.serialize_streamnet(stream_net_file, output_reach_file)
RasterUtilClass.raster_reclassify(subbasin_file, id_map, output_subbasin_file, GDT_Int32)
StreamnetUtil.assign_stream_id_raster(stream_raster_file, output_subbasin_file,
output_stream_link_file)
# Convert D8 encoding rule to ArcGIS
D8Util.convert_code(flow_dir_file_tau, output_flow_dir_file)
# convert raster to shapefile (for subbasin and basin)
print('Generating subbasin vector...')
VectorUtilClass.raster2shp(output_subbasin_file, subbasin_vector_file, 'subbasin',
FieldNames.subbasin_id)
mask_file = cfg.spatials.mask
basin_vector = cfg.vecs.bsn
print('Generating basin vector...')
VectorUtilClass.raster2shp(mask_file, basin_vector, 'basin', FieldNames.basin)
# delineate hillslope
DelineateHillslope.downstream_method_whitebox(output_stream_link_file, flow_dir_file_tau,
output_hillslope_file)
def write_gtiff_file(f_name,
n_rows,
n_cols,
data,
geotransform,
srs,
nodata_value,
gdal_type=GDT_Float32):
"""Output Raster to GeoTiff format file.
Args:
f_name: output gtiff file name.
n_rows: Row count.
n_cols: Col count.
data: 2D array data.
geotransform: geographic transformation.
srs: coordinate system.
nodata_value: nodata value.
gdal_type (:obj:`pygeoc.raster.GDALDataType`): output raster data type,
GDT_Float32 as default.
"""
UtilClass.mkdir(os.path.dirname(FileClass.get_file_fullpath(f_name)))
driver = gdal_GetDriverByName(str('GTiff'))
try:
ds = driver.Create(f_name, n_cols, n_rows, 1, gdal_type)
except Exception:
print('Cannot create output file %s' % f_name)
return
ds.SetGeoTransform(geotransform)
try:
ds.SetProjection(srs.ExportToWkt())
except AttributeError or Exception:
ds.SetProjection(srs)
ds.GetRasterBand(1).SetNoDataValue(nodata_value)
# if data contains numpy.nan, then replaced by nodata_value
if isinstance(data, numpy.ndarray) and data.dtype in [
numpy.dtype('int'), numpy.dtype('float')
]:
data = numpy.where(numpy.isnan(data), nodata_value, data)
ds.GetRasterBand(1).WriteArray(data)
ds = None
def prepare_node_with_weight_for_metis(graph, weight, wp):
# construct the METIS input file
UtilClass.mkdir(wp)
metis_input = r'%s/metis.txt' % wp
ns = graph.nodes()
with open(metis_input, 'w') as f:
f.write(
str(len(ns)) + '\t' + str(len(graph.edges())) + '\t' +
'010\t1\n')
for node in ns:
if node <= 0:
continue
f.write(
str(weight[node][ImportReaches2Mongo._NUMCELLS]) + '\t')
for e in graph.out_edges(node):
if e[1] > 0:
f.write(str(e[1]) + '\t')
for e in graph.in_edges(node):
if e[0] > 0:
f.write(str(e[0]) + '\t')
f.write('\n')
return metis_input
def prepare_node_with_weight_for_metis(graph, weight, wp):
# construct the METIS input file
UtilClass.mkdir(wp)
metis_input = '%s/metis.txt' % wp
ns = list(graph.nodes())
ns.sort()
with open(metis_input, 'w', encoding='utf-8') as f:
f.write('%s\t%s\t010\t1\n' %
(repr(len(ns)), repr(len(graph.edges()))))
for node in ns:
if node <= 0:
continue
tmp_line = '%s\t' % repr(
weight[node][ImportReaches2Mongo._NUMCELLS])
for e in graph.out_edges(node):
if e[1] > 0:
tmp_line += '%s\t' % repr(e[1])
for e in graph.in_edges(node):
if e[0] > 0:
tmp_line += '%s\t' % repr(e[0])
f.write('%s\n' % tmp_line)
return metis_input
def __init__(self, root_dir):
"""Create workspace directories for outputs.
Args:
root_dir: Root directory
"""
if not os.path.isdir(root_dir):
try:
os.makedirs(root_dir)
except Exception: # failed of any types
root_dir = UtilClass.current_path(
lambda: 0) + os.sep + "FuzzySlpPos"
os.mkdir(root_dir)
self.root_dir = root_dir
self.pre_dir = self.root_dir + os.sep + "PreDir"
self.param_dir = self.root_dir + os.sep + "Params"
self.log_dir = self.root_dir + os.sep + "Log"
self.output_dir = self.root_dir + os.sep + "FuzzySlpPos"
self.typloc_dir = self.root_dir + os.sep + "TypLoc"
self.conf_dir = self.root_dir + os.sep + "Config"
UtilClass.mkdir(self.pre_dir)
UtilClass.mkdir(self.param_dir)
UtilClass.mkdir(self.output_dir)
UtilClass.mkdir(self.log_dir)
UtilClass.mkdir(self.typloc_dir)
UtilClass.mkdir(self.conf_dir)
def watershed_delineation(np, dem, outlet_file=None, thresh=0, singlebasin=False,
workingdir=None, mpi_bin=None, bin_dir=None,
logfile=None, runtime_file=None, hostfile=None,
avoid_redo=False):
"""Watershed Delineation based on D8 flow direction.
Args:
np: process number for MPI
dem: DEM path
outlet_file: predefined outlet shapefile path
thresh: predefined threshold for extracting stream from accumulated flow direction
singlebasin: when set True, only extract subbasins that drains into predefined outlets
workingdir: directory that store outputs
mpi_bin: directory of MPI executable binary, e.g., mpiexec, mpirun
bin_dir: directory of TauDEM and other executable binaries
logfile: log file path
runtime_file: runtime file path
hostfile: host list file path for MPI
avoid_redo: avoid executing some functions that do not depend on input arguments
when repeatedly invoke this function
"""
# 1. Check directories
if not os.path.exists(dem):
TauDEM.error('DEM: %s is not existed!' % dem)
dem = os.path.abspath(dem)
if workingdir is None or workingdir is '':
workingdir = os.path.dirname(dem)
nc = TauDEMFilesUtils(workingdir) # predefined names
workingdir = nc.workspace
UtilClass.mkdir(workingdir)
# 2. Check log file
if logfile is not None and FileClass.is_file_exists(logfile):
os.remove(logfile)
# 3. perform calculation
# Filling DEM
if not (avoid_redo and FileClass.is_file_exists(nc.filldem)):
UtilClass.writelog(logfile, '[Output] %s' % 'remove pit...', 'a')
TauDEM.pitremove(np, dem, nc.filldem, workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
# Flow direction based on D8 algorithm
if not (avoid_redo and FileClass.is_file_exists(nc.d8flow)):
UtilClass.writelog(logfile, '[Output] %s' % 'D8 flow direction...', 'a')
TauDEM.d8flowdir(np, nc.filldem, nc.d8flow, nc.slp, workingdir,
mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
# Flow accumulation without stream skeleton as weight
if not (avoid_redo and FileClass.is_file_exists(nc.d8acc)):
UtilClass.writelog(logfile, '[Output] %s' % 'D8 flow accumulation...', 'a')
TauDEM.aread8(np, nc.d8flow, nc.d8acc, None, None, False, workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
# Initial stream network using mean accumulation as threshold
UtilClass.writelog(logfile, '[Output] %s' % 'Generating stream raster initially...', 'a')
min_accum, max_accum, mean_accum, std_accum = RasterUtilClass.raster_statistics(nc.d8acc)
TauDEM.threshold(np, nc.d8acc, nc.stream_raster, mean_accum, workingdir,
mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
# Outlets position initialization and adjustment
UtilClass.writelog(logfile, '[Output] %s' % 'Moving outlet to stream...', 'a')
if outlet_file is None: # if not given, take cell with maximum accumulation as outlet
outlet_file = nc.outlet_pre
TauDEM.connectdown(np, nc.d8flow, nc.d8acc, outlet_file, nc.outlet_m, wtsd=None,
workingdir=workingdir, mpiexedir=mpi_bin, exedir=bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
TauDEM.moveoutletstostrm(np, nc.d8flow, nc.stream_raster, outlet_file,
nc.outlet_m, workingdir=workingdir,
mpiexedir=mpi_bin, exedir=bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
# Stream skeleton by peuker-douglas algorithm
UtilClass.writelog(logfile, '[Output] %s' % 'Generating stream skeleton ...', 'a')
TauDEM.peukerdouglas(np, nc.filldem, nc.stream_pd, workingdir,
mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
# Weighted flow acculation with outlet
UtilClass.writelog(logfile, '[Output] %s' % 'Flow accumulation with outlet...', 'a')
tmp_outlet = None
if singlebasin:
tmp_outlet = nc.outlet_m
TauDEM.aread8(np, nc.d8flow, nc.d8acc_weight, tmp_outlet, nc.stream_pd, False,
workingdir, mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
# Determine threshold by input argument or dropanalysis function
if thresh <= 0: # find the optimal threshold using dropanalysis function
UtilClass.writelog(logfile, '[Output] %s' %
'Drop analysis to select optimal threshold...', 'a')
min_accum, max_accum, mean_accum, std_accum = \
RasterUtilClass.raster_statistics(nc.d8acc_weight)
if mean_accum - std_accum < 0:
minthresh = mean_accum
else:
minthresh = mean_accum - std_accum
maxthresh = mean_accum + std_accum
TauDEM.dropanalysis(np, nc.filldem, nc.d8flow, nc.d8acc_weight,
nc.d8acc_weight, nc.outlet_m, minthresh, maxthresh,
20, 'true', nc.drptxt, workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
if not FileClass.is_file_exists(nc.drptxt):
# raise RuntimeError('Dropanalysis failed and drp.txt was not created!')
UtilClass.writelog(logfile, '[Output] %s' %
'dropanalysis failed!', 'a')
thresh = 0.5 * (maxthresh - minthresh) + minthresh
else:
with open(nc.drptxt, 'r', encoding='utf-8') as drpf:
temp_contents = drpf.read()
(beg, thresh) = temp_contents.rsplit(' ', 1)
thresh = float(thresh)
UtilClass.writelog(logfile, '[Output] %s: %f' %
('Selected optimal threshold: ', thresh), 'a')
# Final stream network
UtilClass.writelog(logfile, '[Output] %s' % 'Generating stream raster...', 'a')
TauDEM.threshold(np, nc.d8acc_weight, nc.stream_raster, thresh,
workingdir, mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %s' % 'Generating stream net...', 'a')
TauDEM.streamnet(np, nc.filldem, nc.d8flow, nc.d8acc_weight, nc.stream_raster,
nc.outlet_m, nc.stream_order, nc.channel_net,
nc.channel_coord, nc.streamnet_shp, nc.subbsn,
workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
# Serialize IDs of subbasins and the corresponding streams
UtilClass.writelog(logfile, '[Output] %s' % 'Serialize subbasin&stream IDs...', 'a')
id_map = StreamnetUtil.serialize_streamnet(nc.streamnet_shp, nc.streamnet_m)
RasterUtilClass.raster_reclassify(nc.subbsn, id_map, nc.subbsn_m, GDT_Int32)
StreamnetUtil.assign_stream_id_raster(nc.stream_raster, nc.subbsn_m, nc.stream_m)
# convert raster to shapefile (for subbasin and basin)
UtilClass.writelog(logfile, '[Output] %s' % 'Generating subbasin vector...', 'a')
VectorUtilClass.raster2shp(nc.subbsn_m, nc.subbsn_shp, 'subbasin', 'SUBBASINID')
# Finish the workflow
UtilClass.writelog(logfile, '[Output] %s' %
'Original subbasin delineation is finished!', 'a')
def watershed_delineation(np, dem, outlet_file=None, thresh=0, singlebasin=False,
workingdir=None, mpi_bin=None, bin_dir=None,
logfile=None, runtime_file=None, hostfile=None):
"""Watershed Delineation."""
# 1. Check directories
if not os.path.exists(dem):
TauDEM.error('DEM: %s is not existed!' % dem)
dem = os.path.abspath(dem)
if workingdir is None:
workingdir = os.path.dirname(dem)
namecfg = TauDEMFilesUtils(workingdir)
workingdir = namecfg.workspace
UtilClass.mkdir(workingdir)
# 2. Check log file
if logfile is not None and FileClass.is_file_exists(logfile):
os.remove(logfile)
# 3. Get predefined intermediate file names
filled_dem = namecfg.filldem
flow_dir = namecfg.d8flow
slope = namecfg.slp
flow_dir_dinf = namecfg.dinf
slope_dinf = namecfg.dinf_slp
dir_code_dinf = namecfg.dinf_d8dir
weight_dinf = namecfg.dinf_weight
acc = namecfg.d8acc
stream_raster = namecfg.stream_raster
default_outlet = namecfg.outlet_pre
modified_outlet = namecfg.outlet_m
stream_skeleton = namecfg.stream_pd
acc_with_weight = namecfg.d8acc_weight
stream_order = namecfg.stream_order
ch_network = namecfg.channel_net
ch_coord = namecfg.channel_coord
stream_net = namecfg.streamnet_shp
subbasin = namecfg.subbsn
dist2_stream_d8 = namecfg.dist2stream_d8
# 4. perform calculation
UtilClass.writelog(logfile, '[Output] %d..., %s' % (10, 'pitremove DEM...'), 'a')
TauDEM.pitremove(np, dem, filled_dem, workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %d..., %s' %
(20, 'Calculating D8 and Dinf flow direction...'), 'a')
TauDEM.d8flowdir(np, filled_dem, flow_dir, slope, workingdir,
mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
TauDEM.dinfflowdir(np, filled_dem, flow_dir_dinf, slope_dinf, workingdir,
mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
DinfUtil.output_compressed_dinf(flow_dir_dinf, dir_code_dinf, weight_dinf)
UtilClass.writelog(logfile, '[Output] %d..., %s' % (30, 'D8 flow accumulation...'), 'a')
TauDEM.aread8(np, flow_dir, acc, None, None, False, workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %d..., %s' %
(40, 'Generating stream raster initially...'), 'a')
min_accum, max_accum, mean_accum, std_accum = RasterUtilClass.raster_statistics(acc)
TauDEM.threshold(np, acc, stream_raster, mean_accum, workingdir,
mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %d..., %s' % (50, 'Moving outlet to stream...'), 'a')
if outlet_file is None:
outlet_file = default_outlet
TauDEM.connectdown(np, flow_dir, acc, outlet_file, wtsd=None,
workingdir=workingdir, mpiexedir=mpi_bin, exedir=bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
TauDEM.moveoutletstostrm(np, flow_dir, stream_raster, outlet_file,
modified_outlet, workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %d..., %s' %
(60, 'Generating stream skeleton...'), 'a')
TauDEM.peukerdouglas(np, filled_dem, stream_skeleton, workingdir,
mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %d..., %s' %
(70, 'Flow accumulation with outlet...'), 'a')
tmp_outlet = None
if singlebasin:
tmp_outlet = modified_outlet
TauDEM.aread8(np, flow_dir, acc_with_weight, tmp_outlet, stream_skeleton, False,
workingdir, mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
if thresh <= 0: # find the optimal threshold using dropanalysis function
UtilClass.writelog(logfile, '[Output] %d..., %s' %
(75, 'Drop analysis to select optimal threshold...'), 'a')
min_accum, max_accum, mean_accum, std_accum = \
RasterUtilClass.raster_statistics(acc_with_weight)
if mean_accum - std_accum < 0:
minthresh = mean_accum
else:
minthresh = mean_accum - std_accum
maxthresh = mean_accum + std_accum
numthresh = 20
logspace = 'true'
drp_file = namecfg.drptxt
TauDEM.dropanalysis(np, filled_dem, flow_dir, acc_with_weight,
acc_with_weight, modified_outlet, minthresh, maxthresh,
numthresh, logspace, drp_file, workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
if not FileClass.is_file_exists(drp_file):
raise RuntimeError('Dropanalysis failed and drp.txt was not created!')
with open(drp_file, 'r', encoding='utf-8') as drpf:
temp_contents = drpf.read()
(beg, thresh) = temp_contents.rsplit(' ', 1)
print(thresh)
UtilClass.writelog(logfile, '[Output] %d..., %s' % (80, 'Generating stream raster...'), 'a')
TauDEM.threshold(np, acc_with_weight, stream_raster, float(thresh),
workingdir, mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %d..., %s' % (90, 'Generating stream net...'), 'a')
TauDEM.streamnet(np, filled_dem, flow_dir, acc_with_weight, stream_raster,
modified_outlet, stream_order, ch_network,
ch_coord, stream_net, subbasin, workingdir, mpi_bin, bin_dir,
log_file=logfile, runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %d..., %s' %
(95, 'Calculating distance to stream (D8)...'), 'a')
TauDEM.d8hdisttostrm(np, flow_dir, stream_raster, dist2_stream_d8, 1,
workingdir, mpi_bin, bin_dir, log_file=logfile,
runtime_file=runtime_file, hostfile=hostfile)
UtilClass.writelog(logfile, '[Output] %d.., %s' %
(100, 'Original subbasin delineation is finished!'), 'a')
def run(function_name, in_files, wp=None, in_params=None, out_files=None, mpi_params=None,
log_params=None):
"""
Run TauDEM function.
- 1. The command will not execute if any input file does not exist.
- 2. An error will be detected after running the TauDEM command if
any output file does not exist;
Args:
function_name (str): Full path of TauDEM function.
in_files (dict, required): Dict of pairs of parameter id (string) and file path
(string or list) for input files, e.g.::
{'-z': '/full/path/to/dem.tif'}
wp (str, optional): Workspace for outputs. If not specified, the directory of the
first input file in ``in_files`` will be used.
in_params (dict, optional): Dict of pairs of parameter id (string) and value
(or None for a flag parameter without a value) for input parameters, e.g.::
{'-nc': None}
{'-thresh': threshold}
{'-m': 'ave' 's', '-nc': None}
out_files (dict, optional): Dict of pairs of parameter id (string) and file
path (string or list) for output files, e.g.::
{'-fel': 'filleddem.tif'}
{'-maxS': ['harden.tif', 'maxsimi.tif']}
mpi_params (dict, optional): Dict of pairs of parameter id (string) and value or
path for MPI setting, e.g.::
{'mpipath':'/soft/bin','hostfile':'/soft/bin/cluster.node','n':4}
{'mpipath':'/soft/bin', 'n':4}
{'n':4}
log_params (dict, optional): Dict of pairs of parameter id (string) and value or
path for runtime and log output parameters. e.g.::
{'logfile': '/home/user/log.txt',
'runtimefile': '/home/user/runtime.txt'}
Returns:
True if TauDEM run successfully, otherwise False.
"""
# Check input files
if in_files is None:
TauDEM.error('Input files parameter is required!')
if not isinstance(in_files, dict):
TauDEM.error('The input files parameter must be a dict!')
for (pid, infile) in iteritems(in_files):
if infile is None:
continue
if isinstance(infile, list) or isinstance(infile, tuple):
for idx, inf in enumerate(infile):
if inf is None:
continue
inf, wp = TauDEM.check_infile_and_wp(inf, wp)
in_files[pid][idx] = inf
continue
if os.path.exists(infile):
infile, wp = TauDEM.check_infile_and_wp(infile, wp)
in_files[pid] = os.path.abspath(infile)
else:
# For more flexible input files extension.
# e.g., -inputtags 1 <path/to/tag1.tif> 2 <path/to/tag2.tif> ...
# in such unpredictable circumstance, we cannot check the existance of
# input files, so the developer will check it in other place.
if len(StringClass.split_string(infile, ' ')) > 1:
continue
else: # the infile still should be a existing file, so check in workspace
if wp is None:
TauDEM.error('Workspace should not be None!')
infile = wp + os.sep + infile
if not os.path.exists(infile):
TauDEM.error('Input files parameter %s: %s is not existed!' %
(pid, infile))
in_files[pid] = os.path.abspath(infile)
# Make workspace dir if not existed
UtilClass.mkdir(wp)
# Check the log parameter
log_file = None
runtime_file = None
if log_params is not None:
if not isinstance(log_params, dict):
TauDEM.error('The log parameter must be a dict!')
if 'logfile' in log_params and log_params['logfile'] is not None:
log_file = log_params['logfile']
# If log_file is just a file name, then save it in the default workspace.
if os.sep not in log_file:
log_file = wp + os.sep + log_file
log_file = os.path.abspath(log_file)
if 'runtimefile' in log_params and log_params['runtimefile'] is not None:
runtime_file = log_params['runtimefile']
# If log_file is just a file name, then save it in the default workspace.
if os.sep not in runtime_file:
runtime_file = wp + os.sep + runtime_file
runtime_file = os.path.abspath(runtime_file)
# remove out_files to avoid any file IO related error
new_out_files = list()
if out_files is not None:
if not isinstance(out_files, dict):
TauDEM.error('The output files parameter must be a dict!')
for (pid, out_file) in iteritems(out_files):
if out_file is None:
continue
if isinstance(out_file, list) or isinstance(out_file, tuple):
for idx, outf in enumerate(out_file):
if outf is None:
continue
outf = FileClass.get_file_fullpath(outf, wp)
FileClass.remove_files(outf)
out_files[pid][idx] = outf
new_out_files.append(outf)
else:
out_file = FileClass.get_file_fullpath(out_file, wp)
FileClass.remove_files(out_file)
out_files[pid] = out_file
new_out_files.append(out_file)
# concatenate command line
commands = list()
# MPI header
if mpi_params is not None:
if not isinstance(mpi_params, dict):
TauDEM.error('The MPI settings parameter must be a dict!')
if 'mpipath' in mpi_params and mpi_params['mpipath'] is not None:
commands.append(mpi_params['mpipath'] + os.sep + 'mpiexec')
else:
commands.append('mpiexec')
if 'hostfile' in mpi_params and mpi_params['hostfile'] is not None \
and not StringClass.string_match(mpi_params['hostfile'], 'none') \
and os.path.isfile(mpi_params['hostfile']):
commands.append('-f')
commands.append(mpi_params['hostfile'])
if 'n' in mpi_params and mpi_params['n'] > 1:
commands.append('-n')
commands.append(str(mpi_params['n']))
else: # If number of processor is less equal than 1, then do not call mpiexec.
commands = []
# append TauDEM function name, which can be full path or just one name
commands.append(function_name)
# append input files
for (pid, infile) in iteritems(in_files):
if infile is None:
continue
if pid[0] != '-':
pid = '-' + pid
commands.append(pid)
if isinstance(infile, list) or isinstance(infile, tuple):
commands.append(' '.join(tmpf for tmpf in infile))
else:
commands.append(infile)
# append input parameters
if in_params is not None:
if not isinstance(in_params, dict):
TauDEM.error('The input parameters must be a dict!')
for (pid, v) in iteritems(in_params):
if pid[0] != '-':
pid = '-' + pid
commands.append(pid)
# allow for parameter which is an flag without value
if v != '' and v is not None:
if MathClass.isnumerical(v):
commands.append(str(v))
else:
commands.append(v)
# append output parameters
if out_files is not None:
for (pid, outfile) in iteritems(out_files):
if outfile is None:
continue
if pid[0] != '-':
pid = '-' + pid
commands.append(pid)
if isinstance(outfile, list) or isinstance(outfile, tuple):
commands.append(' '.join(tmpf for tmpf in outfile))
else:
commands.append(outfile)
# run command
runmsg = UtilClass.run_command(commands)
TauDEM.log(runmsg, log_file)
TauDEM.output_runtime_to_log(function_name, runmsg, runtime_file)
# Check out_files, raise RuntimeError if not exist.
for of in new_out_files:
if not os.path.exists(of):
TauDEM.error('%s failed, and the %s was not generated!' % (function_name, of))
return False
return True
def __init__(self, cf):
"""Initialization."""
# 1. Directories
self.base_dir = None
self.clim_dir = None
self.spatial_dir = None
self.observe_dir = None
self.scenario_dir = None
self.model_dir = None
self.txt_db_dir = None
self.preproc_script_dir = None
self.seims_bin = None
self.mpi_bin = None
self.workspace = None
# 1.1. Directory determined flags
self.use_observed = True
self.use_scernario = True
# 2. MongoDB configuration and database, collation, GridFS names
self.hostname = '127.0.0.1' # localhost by default
self.port = 27017
self.climate_db = ''
self.bmp_scenario_db = ''
self.spatial_db = ''
# 3. Climate inputs
self.hydro_climate_vars = None
self.prec_sites = None
self.prec_data = None
self.Meteo_sites = None
self.Meteo_data = None
self.thiessen_field = 'ID'
# 4. Spatial inputs
self.prec_sites_thiessen = None
self.meteo_sites_thiessen = None
self.dem = None
self.outlet_file = None
self.landuse = None
self.landcover_init_param = None
self.soil = None
self.soil_property = None
self.fields_partition = False
self.fields_partition_thresh = list()
self.additional_rs = dict()
# 5. Option parameters
self.d8acc_threshold = 0
self.np = 4
self.d8down_method = 's'
self.dorm_hr = -1.
self.temp_base = 0.
self.imper_perc_in_urban = 0.
self.default_landuse = -1
self.default_soil = -1
# 1. Directories
if 'PATH' in cf.sections():
self.base_dir = cf.get('PATH', 'base_data_dir')
self.clim_dir = cf.get('PATH', 'climate_data_dir')
self.spatial_dir = cf.get('PATH', 'spatial_data_dir')
self.observe_dir = cf.get('PATH', 'measurement_data_dir')
self.scenario_dir = cf.get('PATH', 'bmp_data_dir')
self.model_dir = cf.get('PATH', 'model_dir')
self.txt_db_dir = cf.get('PATH', 'txt_db_dir')
self.preproc_script_dir = cf.get('PATH', 'preproc_script_dir')
self.seims_bin = cf.get('PATH', 'cpp_program_dir')
self.mpi_bin = cf.get('PATH', 'mpiexec_dir')
self.workspace = cf.get('PATH', 'working_dir')
else:
raise ValueError('[PATH] section MUST be existed in *.ini file.')
if not (FileClass.is_dir_exists(self.base_dir)
and FileClass.is_dir_exists(self.model_dir)
and FileClass.is_dir_exists(self.txt_db_dir)
and FileClass.is_dir_exists(self.preproc_script_dir)
and FileClass.is_dir_exists(self.seims_bin)):
raise IOError(
'Please Check Directories defined in [PATH]. '
'BASE_DATA_DIR, MODEL_DIR, TXT_DB_DIR, PREPROC_SCRIPT_DIR, '
'and CPP_PROGRAM_DIR are required!')
if not FileClass.is_dir_exists(self.mpi_bin):
self.mpi_bin = None
if not FileClass.is_dir_exists(self.workspace):
try: # first try to make dirs
UtilClass.mkdir(self.workspace)
# os.mkdir(self.workspace)
except OSError as exc:
self.workspace = self.model_dir + os.path.sep + 'preprocess_output'
print('WARNING: Make WORKING_DIR failed! Use the default: %s' %
self.workspace)
if not os.path.exists(self.workspace):
UtilClass.mkdir(self.workspace)
self.dirs = DirNameUtils(self.workspace)
self.logs = LogNameUtils(self.dirs.log)
self.vecs = VectorNameUtils(self.dirs.geoshp)
self.taudems = TauDEMFilesUtils(self.dirs.taudem)
self.spatials = SpatialNamesUtils(self.dirs.geodata2db)
self.modelcfgs = ModelCfgUtils(self.model_dir)
self.paramcfgs = ModelParamDataUtils(self.preproc_script_dir +
os.path.sep + 'database')
if not FileClass.is_dir_exists(self.clim_dir):
print(
'The CLIMATE_DATA_DIR is not existed, try the default folder name "climate".'
)
self.clim_dir = self.base_dir + os.path.sep + 'climate'
if not FileClass.is_dir_exists(self.clim_dir):
raise IOError(
'Directories named "climate" MUST BE located in [base_dir]!'
)
if not FileClass.is_dir_exists(self.spatial_dir):
print(
'The SPATIAL_DATA_DIR is not existed, try the default folder name "spatial".'
)
self.spatial_dir = self.base_dir + os.path.sep + 'spatial'
raise IOError(
'Directories named "spatial" MUST BE located in [base_dir]!')
if not FileClass.is_dir_exists(self.observe_dir):
self.observe_dir = None
self.use_observed = False
if not FileClass.is_dir_exists(self.scenario_dir):
self.scenario_dir = None
self.use_scernario = False
# 2. MongoDB related
if 'MONGODB' in cf.sections():
self.hostname = cf.get('MONGODB', 'hostname')
self.port = cf.getint('MONGODB', 'port')
self.climate_db = cf.get('MONGODB', 'climatedbname')
self.bmp_scenario_db = cf.get('MONGODB', 'bmpscenariodbname')
self.spatial_db = cf.get('MONGODB', 'spatialdbname')
else:
raise ValueError(
'[MONGODB] section MUST be existed in *.ini file.')
if not StringClass.is_valid_ip_addr(self.hostname):
raise ValueError('HOSTNAME illegal defined in [MONGODB]!')
# 3. Climate Input
if 'CLIMATE' in cf.sections():
self.hydro_climate_vars = self.clim_dir + os.path.sep + cf.get(
'CLIMATE', 'hydroclimatevarfile')
self.prec_sites = self.clim_dir + os.path.sep + cf.get(
'CLIMATE', 'precsitefile')
self.prec_data = self.clim_dir + os.path.sep + cf.get(
'CLIMATE', 'precdatafile')
self.Meteo_sites = self.clim_dir + os.path.sep + cf.get(
'CLIMATE', 'meteositefile')
self.Meteo_data = self.clim_dir + os.path.sep + cf.get(
'CLIMATE', 'meteodatafile')
self.thiessen_field = cf.get('CLIMATE', 'thiessenidfield')
else:
raise ValueError(
'Climate input file names MUST be provided in [CLIMATE]!')
# 4. Spatial Input
if 'SPATIAL' in cf.sections():
self.prec_sites_thiessen = self.spatial_dir + os.path.sep + cf.get(
'SPATIAL', 'precsitesthiessen')
self.meteo_sites_thiessen = self.spatial_dir + os.path.sep + cf.get(
'SPATIAL', 'meteositesthiessen')
self.dem = self.spatial_dir + os.path.sep + cf.get(
'SPATIAL', 'dem')
self.outlet_file = self.spatial_dir + os.path.sep + cf.get(
'SPATIAL', 'outlet_file')
if not os.path.exists(self.outlet_file):
self.outlet_file = None
self.landuse = self.spatial_dir + os.path.sep + cf.get(
'SPATIAL', 'landusefile')
self.landcover_init_param = self.txt_db_dir + os.path.sep + cf.get(
'SPATIAL', 'landcoverinitfile')
self.soil = self.spatial_dir + os.path.sep + cf.get(
'SPATIAL', 'soilseqnfile')
self.soil_property = self.txt_db_dir + os.path.sep + cf.get(
'SPATIAL', 'soilseqntext')
if cf.has_option('SPATIAL', 'additionalfile'):
additional_dict_str = cf.get('SPATIAL', 'additionalfile')
tmpdict = json.loads(additional_dict_str)
tmpdict = {
str(k): (str(v) if is_string(v) else v)
for k, v in list(tmpdict.items())
}
for k, v in list(tmpdict.items()):
# Existence check has been moved to mask_origin_delineated_data()
# in sp_delineation.py
self.additional_rs[k] = v
# Field partition
if cf.has_option('SPATIAL', 'field_partition_thresh'):
ths = cf.get('SPATIAL', 'field_partition_thresh')
thsv = StringClass.extract_numeric_values_from_string(ths)
if thsv is not None:
self.fields_partition_thresh = [int(v) for v in thsv]
self.fields_partition = True
else:
raise ValueError(
'Spatial input file names MUST be provided in [SPATIAL]!')
# 5. Optional parameters
if 'OPTIONAL_PARAMETERS' in cf.sections():
self.d8acc_threshold = cf.getfloat('OPTIONAL_PARAMETERS',
'd8accthreshold')
self.np = cf.getint('OPTIONAL_PARAMETERS', 'np')
self.d8down_method = cf.get('OPTIONAL_PARAMETERS', 'd8downmethod')
if StringClass.string_match(self.d8down_method, 'surface'):
self.d8down_method = 's'
elif StringClass.string_match(self.d8down_method, 'horizontal'):
self.d8down_method = 'h'
elif StringClass.string_match(self.d8down_method, 'pythagoras'):
self.d8down_method = 'p'
elif StringClass.string_match(self.d8down_method, 'vertical'):
self.d8down_method = 'v'
else:
self.d8down_method = self.d8down_method.lower()
if self.d8down_method not in ['s', 'h', 'p', 'v']:
self.d8down_method = 's'
self.dorm_hr = cf.getfloat('OPTIONAL_PARAMETERS', 'dorm_hr')
self.temp_base = cf.getfloat('OPTIONAL_PARAMETERS', 't_base')
self.imper_perc_in_urban = cf.getfloat(
'OPTIONAL_PARAMETERS', 'imperviouspercinurbancell')
self.default_landuse = cf.getint('OPTIONAL_PARAMETERS',
'defaultlanduse')
self.default_soil = cf.getint('OPTIONAL_PARAMETERS', 'defaultsoil')
def metis_partition(g, weight, wp, bin_dir):
"""Partition subbasins into multiple groups by METIS
Args:
g: `NetworkX.DiGraph` object
weight: weight of each node, e.g., area of subbasin, {subbasinID: weight}
wp: output directory
bin_dir: directory of METIS package
Returns:
group_dict: {subbasinID: {'group': group_number_list,
'kmetis': group_ids_list_by_kmetis,
'pmetis': group_ids_list_by_pmetis}
}
"""
group_dict = dict()
for subbsn_id in g.nodes():
group_dict[subbsn_id] = {
'group': list(),
'kmetis': list(),
'pmetis': list()
}
metis_input = ImportReaches2Mongo.prepare_node_with_weight_for_metis(
g, weight, wp)
# Creating group divided numbers
nlist = list(range(1, 129))
nlist.extend([192, 256, 384, 512, 768, 1536])
# nlist should be less than the number of subbasin, otherwise it will make nonsense.
ns = g.nodes()
nlist = [x for x in nlist if x <= max(ns)]
# Make directories for KMETIS and PMETIS
UtilClass.mkdir(wp + os.path.sep + 'kmetis')
UtilClass.mkdir(wp + os.path.sep + 'pmetis')
for n in nlist:
print('divide number: %d' % n)
if n <= 1:
for subbsn_id in g.nodes():
group_dict[subbsn_id]['group'].append(1)
group_dict[subbsn_id]['kmetis'].append(0)
group_dict[subbsn_id]['pmetis'].append(0)
continue
# kmetis, -ptype=kway, direct k-way partitioning (default)
str_command = '"%s/gpmetis" %s %d' % (bin_dir, metis_input, n)
result = UtilClass.run_command(str_command)
with open('%s/kmetis/kmetisResult%d.txt' % (wp, n),
'w') as f_metis_output:
for line in result:
f_metis_output.write(line)
metis_output = '%s.part.%d' % (metis_input, n)
with open(metis_output, 'r') as f:
lines = f.readlines()
group_kmetis = [int(item) for item in lines]
adjust_group_result(weight, group_kmetis, n)
shutil.move(metis_output, '%s/kmetis/metis.part.%d' % (wp, n))
# pmetis, -ptype=rb, recursive bisectioning
str_command = '"%s/gpmetis" -ptype=rb %s %d' % (bin_dir,
metis_input, n)
result = UtilClass.run_command(str_command)
with open('%s/pmetis/pmetisResult%d.txt' % (wp, n),
'w') as f_metis_output:
for line in result:
f_metis_output.write(line)
with open(metis_output, 'r') as f:
lines = f.readlines()
group_pmetis = [int(item) for item in lines]
adjust_group_result(weight, group_pmetis, n)
shutil.move(metis_output, '%s/pmetis/metis.part.%d' % (wp, n))
for i, (gk, gp) in enumerate(zip(group_kmetis, group_pmetis)):
group_dict[i + 1]['group'].append(n)
group_dict[i + 1]['kmetis'].append(gk)
group_dict[i + 1]['pmetis'].append(gp)
return group_dict
def __init__(self, cf):
"""Initialization."""
# 1. Directories
self.base_dir = None
self.clim_dir = None
self.spatial_dir = None
self.observe_dir = None
self.scenario_dir = None
self.model_dir = None
self.txt_db_dir = None
self.preproc_script_dir = None
self.seims_bin = None
self.mpi_bin = None
self.workspace = None
# 1.1. Directory determined flags
self.use_observed = True
self.use_scernario = True
# 2. MongoDB configuration and database, collation, GridFS names
self.hostname = '127.0.0.1' # localhost by default
self.port = 27017
self.climate_db = ''
self.bmp_scenario_db = ''
self.spatial_db = ''
# 3. Switch for building SEIMS. These switches should be removed! By lj.
# self.gen_cn = True
# self.gen_runoff_coef = True
# self.gen_crop = True
# self.gen_iuh = True
# 4. Climate inputs
self.hydro_climate_vars = None
self.prec_sites = None
self.prec_data = None
self.Meteo_sites = None
self.Meteo_data = None
self.thiessen_field = 'ID'
# 5. Spatial inputs
self.prec_sites_thiessen = None
self.meteo_sites_thiessen = None
self.dem = None
self.outlet_file = None
self.landuse = None
self.landcover_init_param = None
self.soil = None
self.soil_property = None
self.fields_partition = False
self.fields_partition_thresh = list()
self.additional_rs = dict()
# 6. Option parameters
self.d8acc_threshold = 0
self.np = 4
self.d8down_method = 's'
self.dorm_hr = -1.
self.temp_base = 0.
self.imper_perc_in_urban = 0.
self.default_landuse = -1
self.default_soil = -1
# 1. Directories
if 'PATH' in cf.sections():
self.base_dir = cf.get('PATH', 'base_data_dir')
self.clim_dir = cf.get('PATH', 'climate_data_dir')
self.spatial_dir = cf.get('PATH', 'spatial_data_dir')
self.observe_dir = cf.get('PATH', 'measurement_data_dir')
self.scenario_dir = cf.get('PATH', 'bmp_data_dir')
self.model_dir = cf.get('PATH', 'model_dir')
self.txt_db_dir = cf.get('PATH', 'txt_db_dir')
self.preproc_script_dir = cf.get('PATH', 'preproc_script_dir')
self.seims_bin = cf.get('PATH', 'cpp_program_dir')
self.mpi_bin = cf.get('PATH', 'mpiexec_dir')
self.workspace = cf.get('PATH', 'working_dir')
else:
raise ValueError('[PATH] section MUST be existed in *.ini file.')
if not (FileClass.is_dir_exists(self.base_dir)
and FileClass.is_dir_exists(self.model_dir)
and FileClass.is_dir_exists(self.txt_db_dir)
and FileClass.is_dir_exists(self.preproc_script_dir)
and FileClass.is_dir_exists(self.seims_bin)):
raise IOError('Please Check Directories defined in [PATH]. '
'BASE_DATA_DIR, MODEL_DIR, TXT_DB_DIR, PREPROC_SCRIPT_DIR, '
'and CPP_PROGRAM_DIR are required!')
if not FileClass.is_dir_exists(self.mpi_bin):
self.mpi_bin = None
if not FileClass.is_dir_exists(self.workspace):
try: # first try to make dirs
UtilClass.mkdir(self.workspace)
# os.mkdir(self.workspace)
except OSError as exc:
self.workspace = self.model_dir + os.path.sep + 'preprocess_output'
print('WARNING: Make WORKING_DIR failed: %s. '
'Use the default: %s' % (exc.message, self.workspace))
if not os.path.exists(self.workspace):
UtilClass.mkdir(self.workspace)
self.dirs = DirNameUtils(self.workspace)
self.logs = LogNameUtils(self.dirs.log)
self.vecs = VectorNameUtils(self.dirs.geoshp)
self.taudems = TauDEMFilesUtils(self.dirs.taudem)
self.spatials = SpatialNamesUtils(self.dirs.geodata2db)
self.modelcfgs = ModelCfgUtils(self.model_dir)
self.paramcfgs = ModelParamDataUtils(self.preproc_script_dir + os.path.sep + 'database')
if not FileClass.is_dir_exists(self.clim_dir):
print('The CLIMATE_DATA_DIR is not existed, try the default folder name "climate".')
self.clim_dir = self.base_dir + os.path.sep + 'climate'
if not FileClass.is_dir_exists(self.clim_dir):
raise IOError('Directories named "climate" MUST BE located in [base_dir]!')
if not FileClass.is_dir_exists(self.spatial_dir):
print('The SPATIAL_DATA_DIR is not existed, try the default folder name "spatial".')
self.spatial_dir = self.base_dir + os.path.sep + 'spatial'
raise IOError('Directories named "spatial" MUST BE located in [base_dir]!')
if not FileClass.is_dir_exists(self.observe_dir):
self.observe_dir = None
self.use_observed = False
if not FileClass.is_dir_exists(self.scenario_dir):
self.scenario_dir = None
self.use_scernario = False
# 2. MongoDB related
if 'MONGODB' in cf.sections():
self.hostname = cf.get('MONGODB', 'hostname')
self.port = cf.getint('MONGODB', 'port')
self.climate_db = cf.get('MONGODB', 'climatedbname')
self.bmp_scenario_db = cf.get('MONGODB', 'bmpscenariodbname')
self.spatial_db = cf.get('MONGODB', 'spatialdbname')
else:
raise ValueError('[MONGODB] section MUST be existed in *.ini file.')
if not StringClass.is_valid_ip_addr(self.hostname):
raise ValueError('HOSTNAME illegal defined in [MONGODB]!')
# 3. Model related switch. The SWITCH section should be removed! By lj.
# by default, OpenMP version and daily (longterm) mode will be built
# if 'SWITCH' in cf.sections():
# self.gen_cn = cf.getboolean('SWITCH', 'gencn')
# self.gen_runoff_coef = cf.getboolean('SWITCH', 'genrunoffcoef')
# self.gen_crop = cf.getboolean('SWITCH', 'gencrop')
#
# if self.storm_mode:
# self.gen_iuh = False
# self.climate_db = ModelNameUtils.standardize_climate_dbname(self.climate_db)
# 4. Climate Input
if 'CLIMATE' in cf.sections():
self.hydro_climate_vars = self.clim_dir + os.path.sep + cf.get('CLIMATE',
'hydroclimatevarfile')
self.prec_sites = self.clim_dir + os.path.sep + cf.get('CLIMATE', 'precsitefile')
self.prec_data = self.clim_dir + os.path.sep + cf.get('CLIMATE', 'precdatafile')
self.Meteo_sites = self.clim_dir + os.path.sep + cf.get('CLIMATE', 'meteositefile')
self.Meteo_data = self.clim_dir + os.path.sep + cf.get('CLIMATE', 'meteodatafile')
self.thiessen_field = cf.get('CLIMATE', 'thiessenidfield')
else:
raise ValueError('Climate input file names MUST be provided in [CLIMATE]!')
# 5. Spatial Input
if 'SPATIAL' in cf.sections():
self.prec_sites_thiessen = self.spatial_dir + os.path.sep + cf.get('SPATIAL',
'precsitesthiessen')
self.meteo_sites_thiessen = self.spatial_dir + os.path.sep + cf.get('SPATIAL',
'meteositesthiessen')
self.dem = self.spatial_dir + os.path.sep + cf.get('SPATIAL', 'dem')
self.outlet_file = self.spatial_dir + os.path.sep + cf.get('SPATIAL', 'outlet_file')
if not os.path.exists(self.outlet_file):
self.outlet_file = None
self.landuse = self.spatial_dir + os.path.sep + cf.get('SPATIAL', 'landusefile')
self.landcover_init_param = self.txt_db_dir + os.path.sep + cf.get('SPATIAL',
'landcoverinitfile')
self.soil = self.spatial_dir + os.path.sep + cf.get('SPATIAL', 'soilseqnfile')
self.soil_property = self.txt_db_dir + os.path.sep + cf.get('SPATIAL', 'soilseqntext')
if cf.has_option('SPATIAL', 'additionalfile'):
additional_dict_str = cf.get('SPATIAL', 'additionalfile')
tmpdict = json.loads(additional_dict_str)
tmpdict = {str(k): (str(v) if isinstance(v, str) else v) for k, v in
list(tmpdict.items())}
for k, v in list(tmpdict.items()):
# Existence check has been moved to mask_origin_delineated_data()
# in sp_delineation.py
self.additional_rs[k] = v
# Field partition
if cf.has_option('SPATIAL', 'field_partition_thresh'):
ths = cf.get('SPATIAL', 'field_partition_thresh')
thsv = StringClass.extract_numeric_values_from_string(ths)
if thsv is not None:
self.fields_partition_thresh = [int(v) for v in thsv]
self.fields_partition = True
else:
raise ValueError('Spatial input file names MUST be provided in [SPATIAL]!')
# 6. Option parameters
if 'OPTIONAL_PARAMETERS' in cf.sections():
self.d8acc_threshold = cf.getfloat('OPTIONAL_PARAMETERS', 'd8accthreshold')
self.np = cf.getint('OPTIONAL_PARAMETERS', 'np')
self.d8down_method = cf.get('OPTIONAL_PARAMETERS', 'd8downmethod')
if StringClass.string_match(self.d8down_method, 'surface'):
self.d8down_method = 's'
elif StringClass.string_match(self.d8down_method, 'horizontal'):
self.d8down_method = 'h'
elif StringClass.string_match(self.d8down_method, 'pythagoras'):
self.d8down_method = 'p'
elif StringClass.string_match(self.d8down_method, 'vertical'):
self.d8down_method = 'v'
else:
self.d8down_method = self.d8down_method.lower()
if self.d8down_method not in ['s', 'h', 'p', 'v']:
self.d8down_method = 'h'
self.dorm_hr = cf.getfloat('OPTIONAL_PARAMETERS', 'dorm_hr')
self.temp_base = cf.getfloat('OPTIONAL_PARAMETERS', 't_base')
self.imper_perc_in_urban = cf.getfloat('OPTIONAL_PARAMETERS',
'imperviouspercinurbancell')
self.default_landuse = cf.getint('OPTIONAL_PARAMETERS', 'defaultlanduse')
self.default_soil = cf.getint('OPTIONAL_PARAMETERS', 'defaultsoil')
def run(function_name,
in_files,
wp=None,
in_params=None,
out_files=None,
mpi_params=None,
log_params=None):
"""
Run TauDEM function.
1. The command will not execute if any input file does not exist.
2. An error will be detected after running the TauDEM command if
any output file does not exist;
Args:
function_name (str): Full path of TauDEM function.
in_files (dict, required): Dict of pairs of parameter id (string) and file path
(string or list) for input files, e.g.::
{'-z': '/full/path/to/dem.tif'}
wp (str, optional): Workspace for outputs. If not specified, the directory of the
first input file in ``in_files`` will be used.
in_params (dict, optional): Dict of pairs of parameter id (string) and value
(or None for a flag parameter without a value) for input parameters, e.g.::
{'-nc': None}
{'-thresh': threshold}
{'-m': 'ave' 's', '-nc': None}
out_files (dict, optional): Dict of pairs of parameter id (string) and file
path (string or list) for output files, e.g.::
{'-fel': 'filleddem.tif'}
{'-maxS': ['harden.tif', 'maxsimi.tif']}
mpi_params (dict, optional): Dict of pairs of parameter id (string) and value or
path for MPI setting, e.g.::
{'mpipath':'/soft/bin','hostfile':'/soft/bin/cluster.node','n':4}
{'mpipath':'/soft/bin', 'n':4}
{'n':4}
log_params (dict, optional): Dict of pairs of parameter id (string) and value or
path for runtime and log output parameters. e.g.::
{'logfile': '/home/user/log.txt',
'runtimefile': '/home/user/runtime.txt'}
Returns:
True if TauDEM run successfully, otherwise False.
"""
# Check input files
if in_files is None:
TauDEM.error('Input files parameter is required!')
if not isinstance(in_files, dict):
TauDEM.error('The input files parameter must be a dict!')
for (pid, infile) in list(in_files.items()):
if infile is None:
continue
if isinstance(infile, list) or isinstance(infile, tuple):
for idx, inf in enumerate(infile):
if inf is None:
continue
inf, wp = TauDEM.check_infile_and_wp(inf, wp)
in_files[pid][idx] = inf
continue
if os.path.exists(infile):
infile, wp = TauDEM.check_infile_and_wp(infile, wp)
in_files[pid] = os.path.abspath(infile)
else:
# For more flexible input files extension.
# e.g., -inputtags 1 <path/to/tag1.tif> 2 <path/to/tag2.tif> ...
# in such unpredictable circumstance, we cannot check the existance of
# input files, so the developer will check it in other place.
if len(StringClass.split_string(infile, ' ')) > 1:
continue
else: # the infile still should be a existing file, so check in workspace
if wp is None:
TauDEM.error('Workspace should not be None!')
infile = wp + os.sep + infile
if not os.path.exists(infile):
TauDEM.error(
'Input files parameter %s: %s is not existed!' %
(pid, infile))
in_files[pid] = os.path.abspath(infile)
# Make workspace dir if not existed
UtilClass.mkdir(wp)
# Check the log parameter
log_file = None
runtime_file = None
if log_params is not None:
if not isinstance(log_params, dict):
TauDEM.error('The log parameter must be a dict!')
if 'logfile' in log_params and log_params['logfile'] is not None:
log_file = log_params['logfile']
# If log_file is just a file name, then save it in the default workspace.
if os.sep not in log_file:
log_file = wp + os.sep + log_file
log_file = os.path.abspath(log_file)
if 'runtimefile' in log_params and log_params[
'runtimefile'] is not None:
runtime_file = log_params['runtimefile']
# If log_file is just a file name, then save it in the default workspace.
if os.sep not in runtime_file:
runtime_file = wp + os.sep + runtime_file
runtime_file = os.path.abspath(runtime_file)
# remove out_files to avoid any file IO related error
new_out_files = list()
if out_files is not None:
if not isinstance(out_files, dict):
TauDEM.error('The output files parameter must be a dict!')
for (pid, out_file) in list(out_files.items()):
if out_file is None:
continue
if isinstance(out_file, list) or isinstance(out_file, tuple):
for idx, outf in enumerate(out_file):
if outf is None:
continue
outf = FileClass.get_file_fullpath(outf, wp)
FileClass.remove_files(outf)
out_files[pid][idx] = outf
new_out_files.append(outf)
else:
out_file = FileClass.get_file_fullpath(out_file, wp)
FileClass.remove_files(out_file)
out_files[pid] = out_file
new_out_files.append(out_file)
# concatenate command line
commands = list()
# MPI header
if mpi_params is not None:
if not isinstance(mpi_params, dict):
TauDEM.error('The MPI settings parameter must be a dict!')
if 'mpipath' in mpi_params and mpi_params['mpipath'] is not None:
commands.append(mpi_params['mpipath'] + os.sep + 'mpiexec')
else:
commands.append('mpiexec')
if 'hostfile' in mpi_params and mpi_params['hostfile'] is not None \
and not StringClass.string_match(mpi_params['hostfile'], 'none') \
and os.path.isfile(mpi_params['hostfile']):
commands.append('-f')
commands.append(mpi_params['hostfile'])
if 'n' in mpi_params and mpi_params['n'] > 1:
commands.append('-n')
commands.append(str(mpi_params['n']))
else: # If number of processor is less equal than 1, then do not call mpiexec.
commands = []
# append TauDEM function name, which can be full path or just one name
commands.append(function_name)
# append input files
for (pid, infile) in list(in_files.items()):
if infile is None:
continue
if pid[0] != '-':
pid = '-' + pid
commands.append(pid)
if isinstance(infile, list) or isinstance(infile, tuple):
commands.append(' '.join(tmpf for tmpf in infile))
else:
commands.append(infile)
# append input parameters
if in_params is not None:
if not isinstance(in_params, dict):
TauDEM.error('The input parameters must be a dict!')
for (pid, v) in list(in_params.items()):
if pid[0] != '-':
pid = '-' + pid
commands.append(pid)
# allow for parameter which is an flag without value
if v != '' and v is not None:
if MathClass.isnumerical(v):
commands.append(str(v))
else:
commands.append(v)
# append output parameters
if out_files is not None:
for (pid, outfile) in list(out_files.items()):
if outfile is None:
continue
if pid[0] != '-':
pid = '-' + pid
commands.append(pid)
if isinstance(outfile, list) or isinstance(outfile, tuple):
commands.append(' '.join(tmpf for tmpf in outfile))
else:
commands.append(outfile)
# run command
runmsg = UtilClass.run_command(commands)
TauDEM.log(runmsg, log_file)
TauDEM.output_runtime_to_log(function_name, runmsg, runtime_file)
# Check out_files, raise RuntimeError if not exist.
for of in new_out_files:
if not os.path.exists(of):
TauDEM.error('%s failed, and the %s was not generated!' %
(function_name, of))
return False
return True
def watershed_delineation(np,
dem,
outlet_file=None,
thresh=0,
singlebasin=False,
workingdir=None,
mpi_bin=None,
bin_dir=None,
logfile=None,
runtime_file=None,
hostfile=None):
"""Watershed Delineation."""
# 1. Check directories
if not os.path.exists(dem):
TauDEM.error('DEM: %s is not existed!' % dem)
dem = os.path.abspath(dem)
if workingdir is None:
workingdir = os.path.dirname(dem)
namecfg = TauDEMFilesUtils(workingdir)
workingdir = namecfg.workspace
UtilClass.mkdir(workingdir)
# 2. Check log file
if logfile is not None and FileClass.is_file_exists(logfile):
os.remove(logfile)
# 3. Get predefined intermediate file names
filled_dem = namecfg.filldem
flow_dir = namecfg.d8flow
slope = namecfg.slp
flow_dir_dinf = namecfg.dinf
slope_dinf = namecfg.dinf_slp
dir_code_dinf = namecfg.dinf_d8dir
weight_dinf = namecfg.dinf_weight
acc = namecfg.d8acc
stream_raster = namecfg.stream_raster
default_outlet = namecfg.outlet_pre
modified_outlet = namecfg.outlet_m
stream_skeleton = namecfg.stream_pd
acc_with_weight = namecfg.d8acc_weight
stream_order = namecfg.stream_order
ch_network = namecfg.channel_net
ch_coord = namecfg.channel_coord
stream_net = namecfg.streamnet_shp
subbasin = namecfg.subbsn
dist2_stream_d8 = namecfg.dist2stream_d8
# 4. perform calculation
UtilClass.writelog(logfile,
"[Output] %d..., %s" % (10, "pitremove DEM..."),
'a')
TauDEM.pitremove(np,
dem,
filled_dem,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
UtilClass.writelog(
logfile, "[Output] %d..., %s" %
(20, "Calculating D8 and Dinf flow direction..."), 'a')
TauDEM.d8flowdir(np,
filled_dem,
flow_dir,
slope,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
TauDEM.dinfflowdir(np,
filled_dem,
flow_dir_dinf,
slope_dinf,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
DinfUtil.output_compressed_dinf(flow_dir_dinf, dir_code_dinf,
weight_dinf)
UtilClass.writelog(
logfile, "[Output] %d..., %s" % (30, "D8 flow accumulation..."),
'a')
TauDEM.aread8(np,
flow_dir,
acc,
None,
None,
False,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
UtilClass.writelog(
logfile, "[Output] %d..., %s" %
(40, "Generating stream raster initially..."), 'a')
min_accum, max_accum, mean_accum, std_accum = RasterUtilClass.raster_statistics(
acc)
TauDEM.threshold(np,
acc,
stream_raster,
mean_accum,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
UtilClass.writelog(
logfile, "[Output] %d..., %s" % (50, "Moving outlet to stream..."),
'a')
if outlet_file is None:
outlet_file = default_outlet
TauDEM.connectdown(np,
flow_dir,
acc,
outlet_file,
wtsd=None,
workingdir=workingdir,
mpiexedir=mpi_bin,
exedir=bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
TauDEM.moveoutletstostrm(np,
flow_dir,
stream_raster,
outlet_file,
modified_outlet,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
UtilClass.writelog(
logfile,
"[Output] %d..., %s" % (60, "Generating stream skeleton..."), 'a')
TauDEM.peukerdouglas(np,
filled_dem,
stream_skeleton,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
UtilClass.writelog(
logfile,
"[Output] %d..., %s" % (70, "Flow accumulation with outlet..."),
'a')
tmp_outlet = None
if singlebasin:
tmp_outlet = modified_outlet
TauDEM.aread8(np,
flow_dir,
acc_with_weight,
tmp_outlet,
stream_skeleton,
False,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
if thresh <= 0: # find the optimal threshold using dropanalysis function
UtilClass.writelog(
logfile, "[Output] %d..., %s" %
(75, "Drop analysis to select optimal threshold..."), 'a')
min_accum, max_accum, mean_accum, std_accum = \
RasterUtilClass.raster_statistics(acc_with_weight)
if mean_accum - std_accum < 0:
minthresh = mean_accum
else:
minthresh = mean_accum - std_accum
maxthresh = mean_accum + std_accum
numthresh = 20
logspace = 'true'
drp_file = namecfg.drptxt
TauDEM.dropanalysis(np,
filled_dem,
flow_dir,
acc_with_weight,
acc_with_weight,
modified_outlet,
minthresh,
maxthresh,
numthresh,
logspace,
drp_file,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
if not FileClass.is_file_exists(drp_file):
raise RuntimeError(
"Dropanalysis failed and drp.txt was not created!")
drpf = open(drp_file, "r")
temp_contents = drpf.read()
(beg, thresh) = temp_contents.rsplit(' ', 1)
print(thresh)
drpf.close()
UtilClass.writelog(
logfile,
"[Output] %d..., %s" % (80, "Generating stream raster..."), 'a')
TauDEM.threshold(np,
acc_with_weight,
stream_raster,
float(thresh),
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
UtilClass.writelog(
logfile, "[Output] %d..., %s" % (90, "Generating stream net..."),
'a')
TauDEM.streamnet(np,
filled_dem,
flow_dir,
acc_with_weight,
stream_raster,
modified_outlet,
stream_order,
ch_network,
ch_coord,
stream_net,
subbasin,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
UtilClass.writelog(
logfile, "[Output] %d..., %s" %
(95, "Calculating distance to stream (D8)..."), 'a')
TauDEM.d8hdisttostrm(np,
flow_dir,
stream_raster,
dist2_stream_d8,
1,
workingdir,
mpi_bin,
bin_dir,
log_file=logfile,
runtime_file=runtime_file,
hostfile=hostfile)
UtilClass.writelog(
logfile, "[Output] %d.., %s" %
(100, "Original subbasin delineation is finished!"), 'a')
def metis_partition(g, weight, wp, bin_dir):
"""Partition subbasins into multiple groups by METIS
Args:
g: `NetworkX.DiGraph` object
weight: weight of each node, e.g., area of subbasin, {subbasinID: weight}
wp: output directory
bin_dir: directory of METIS package
Returns:
group_dict: {subbasinID: {'group': group_number_list,
'kmetis': group_ids_list_by_kmetis,
'pmetis': group_ids_list_by_pmetis}
}
"""
group_dict = dict()
for subbsn_id in g.nodes():
group_dict[subbsn_id] = {'group': list(), 'kmetis': list(), 'pmetis': list()}
metis_input = ImportReaches2Mongo.prepare_node_with_weight_for_metis(g, weight, wp)
# Creating group divided numbers
nlist = list(range(1, 129))
nlist.extend([192, 256, 384, 512, 768, 1536])
# nlist should be less than the number of subbasin, otherwise it will make nonsense.
ns = g.nodes()
nlist = [x for x in nlist if x <= max(ns)]
# Make directories for KMETIS and PMETIS
UtilClass.mkdir(wp + os.path.sep + 'kmetis')
UtilClass.mkdir(wp + os.path.sep + 'pmetis')
for n in nlist:
print('divide number: %d' % n)
if n <= 1:
for subbsn_id in g.nodes():
group_dict[subbsn_id]['group'].append(1)
group_dict[subbsn_id]['kmetis'].append(0)
group_dict[subbsn_id]['pmetis'].append(0)
continue
# kmetis, -ptype=kway, direct k-way partitioning (default)
str_command = '"%s/gpmetis" %s %d' % (bin_dir, metis_input, n)
result = UtilClass.run_command(str_command)
with open('%s/kmetis/kmetisResult%d.txt' % (wp, n), 'w') as f_metis_output:
for line in result:
f_metis_output.write(line)
metis_output = '%s.part.%d' % (metis_input, n)
with open(metis_output, 'r') as f:
lines = f.readlines()
group_kmetis = [int(item) for item in lines]
adjust_group_result(weight, group_kmetis, n)
shutil.move(metis_output, '%s/kmetis/metis.part.%d' % (wp, n))
# pmetis, -ptype=rb, recursive bisectioning
str_command = '"%s/gpmetis" -ptype=rb %s %d' % (bin_dir, metis_input, n)
result = UtilClass.run_command(str_command)
with open('%s/pmetis/pmetisResult%d.txt' % (wp, n), 'w') as f_metis_output:
for line in result:
f_metis_output.write(line)
with open(metis_output, 'r') as f:
lines = f.readlines()
group_pmetis = [int(item) for item in lines]
adjust_group_result(weight, group_pmetis, n)
shutil.move(metis_output, '%s/pmetis/metis.part.%d' % (wp, n))
for i, (gk, gp) in enumerate(zip(group_kmetis, group_pmetis)):
group_dict[i + 1]['group'].append(n)
group_dict[i + 1]['kmetis'].append(gk)
group_dict[i + 1]['pmetis'].append(gp)
return group_dict