def calibration_objectives(cali_obj, ind):
"""Evaluate the objectives of given individual.
"""
cali_obj.ID = ind.id
model_args = cali_obj.model.ConfigDict
model_args.setdefault('calibration_id', -1)
model_args['calibration_id'] = ind.id
model_obj = MainSEIMS(args_dict=model_args)
# Set observation data to model_obj, no need to query database
model_obj.SetOutletObservations(ind.obs.vars, ind.obs.data)
# Execute model
model_obj.SetMongoClient()
model_obj.run()
time.sleep(0.1) # Wait a moment in case of unpredictable file system error
# read simulation data of the entire simulation period (include calibration and validation)
if model_obj.ReadTimeseriesSimulations():
ind.sim.vars = model_obj.sim_vars[:]
ind.sim.data = deepcopy(model_obj.sim_value)
else:
model_obj.clean(calibration_id=ind.id)
model_obj.UnsetMongoClient()
return ind
# Calculate NSE, R2, RMSE, PBIAS, and RSR, etc. of calibration period
ind.cali.vars, ind.cali.data = model_obj.ExtractSimData(
cali_obj.cfg.cali_stime, cali_obj.cfg.cali_etime)
ind.cali.sim_obs_data = model_obj.ExtractSimObsData(
cali_obj.cfg.cali_stime, cali_obj.cfg.cali_etime)
ind.cali.objnames, \
ind.cali.objvalues = model_obj.CalcTimeseriesStatistics(ind.cali.sim_obs_data,
cali_obj.cfg.cali_stime,
cali_obj.cfg.cali_etime)
if ind.cali.objnames and ind.cali.objvalues:
ind.cali.valid = True
# Calculate NSE, R2, RMSE, PBIAS, and RSR, etc. of validation period
if cali_obj.cfg.calc_validation:
ind.vali.vars, ind.vali.data = model_obj.ExtractSimData(
cali_obj.cfg.vali_stime, cali_obj.cfg.vali_etime)
ind.vali.sim_obs_data = model_obj.ExtractSimObsData(
cali_obj.cfg.vali_stime, cali_obj.cfg.vali_etime)
ind.vali.objnames, \
ind.vali.objvalues = model_obj.CalcTimeseriesStatistics(ind.vali.sim_obs_data,
cali_obj.cfg.vali_stime,
cali_obj.cfg.vali_etime)
if ind.vali.objnames and ind.vali.objvalues:
ind.vali.valid = True
# Get timespan
ind.io_time, ind.comp_time, ind.simu_time, ind.runtime = model_obj.GetTimespan(
)
# delete model output directory for saving storage
model_obj.clean(calibration_id=ind.id)
model_obj.UnsetMongoClient()
return ind
def main(cfg):
"""Main workflow of NSGA-II based Scenario analysis."""
random.seed()
scoop_log('Population: %d, Generation: %d' % (cfg.opt.npop, cfg.opt.ngens))
# Initial timespan variables
stime = time.time()
plot_time = 0.
allmodels_exect = list() # execute time of all model runs
# create reference point for hypervolume
ref_pt = numpy.array(worse_objects) * multi_weight * -1
stats = tools.Statistics(lambda sind: sind.fitness.values)
stats.register('min', numpy.min, axis=0)
stats.register('max', numpy.max, axis=0)
stats.register('avg', numpy.mean, axis=0)
stats.register('std', numpy.std, axis=0)
logbook = tools.Logbook()
logbook.header = 'gen', 'evals', 'min', 'max', 'avg', 'std'
# read observation data from MongoDB
cali_obj = Calibration(cfg)
# Read observation data just once
model_cfg_dict = cali_obj.model.ConfigDict
model_obj = MainSEIMS(args_dict=model_cfg_dict)
model_obj.SetMongoClient()
obs_vars, obs_data_dict = model_obj.ReadOutletObservations(object_vars)
model_obj.UnsetMongoClient()
# Initialize population
param_values = cali_obj.initialize(cfg.opt.npop)
pop = list()
for i in range(cfg.opt.npop):
ind = creator.Individual(param_values[i])
ind.gen = 0
ind.id = i
ind.obs.vars = obs_vars[:]
ind.obs.data = deepcopy(obs_data_dict)
pop.append(ind)
param_values = numpy.array(param_values)
# Write calibrated values to MongoDB
# TODO, extract this function, which is same with `Sensitivity::write_param_values_to_mongodb`.
write_param_values_to_mongodb(cfg.model.db_name, cali_obj.ParamDefs,
param_values)
# get the low and up bound of calibrated parameters
bounds = numpy.array(cali_obj.ParamDefs['bounds'])
low = bounds[:, 0]
up = bounds[:, 1]
low = low.tolist()
up = up.tolist()
pop_select_num = int(cfg.opt.npop * cfg.opt.rsel)
init_time = time.time() - stime
def check_validation(fitvalues):
"""Check the validation of the fitness values of an individual."""
flag = True
for condidx, condstr in enumerate(conditions):
if condstr is None:
continue
if not eval('%f%s' % (fitvalues[condidx], condstr)):
flag = False
return flag
def evaluate_parallel(invalid_pops):
"""Evaluate model by SCOOP or map, and set fitness of individuals
according to calibration step."""
popnum = len(invalid_pops)
labels = list()
try: # parallel on multi-processors or clusters using SCOOP
from scoop import futures
invalid_pops = list(
futures.map(toolbox.evaluate, [cali_obj] * popnum,
invalid_pops))
except ImportError or ImportWarning: # Python build-in map (serial)
invalid_pops = list(
map(toolbox.evaluate, [cali_obj] * popnum, invalid_pops))
for tmpind in invalid_pops:
labels = list() # TODO, find an elegant way to get labels.
tmpfitnessv = list()
for k, v in list(multiobj.items()):
tmpvalues, tmplabel = tmpind.cali.efficiency_values(
k, object_names[k])
tmpfitnessv += tmpvalues[:]
labels += tmplabel[:]
tmpind.fitness.values = tuple(tmpfitnessv)
# Filter for a valid solution
if filter_ind:
invalid_pops = [
tmpind for tmpind in invalid_pops
if check_validation(tmpind.fitness.values)
]
if len(invalid_pops) < 2:
print(
'The initial population should be greater or equal than 2. '
'Please check the parameters ranges or change the sampling strategy!'
)
exit(2)
return invalid_pops, labels # Currently, `invalid_pops` contains evaluated individuals
# Record the count and execute timespan of model runs during the optimization
modelruns_count = {0: len(pop)}
modelruns_time = {
0: 0.
} # Total time counted according to evaluate_parallel()
modelruns_time_sum = {
0: 0.
} # Summarize time of every model runs according to pop
# Generation 0 before optimization
stime = time.time()
pop, plotlables = evaluate_parallel(pop)
modelruns_time[0] = time.time() - stime
for ind in pop:
allmodels_exect.append(
[ind.io_time, ind.comp_time, ind.simu_time, ind.runtime])
modelruns_time_sum[0] += ind.runtime
# currently, len(pop) may less than pop_select_num
pop = toolbox.select(pop, pop_select_num)
# Output simulated data to json or pickle files for future use.
output_population_details(pop,
cfg.opt.simdata_dir,
0,
plot_cfg=cali_obj.cfg.plot_cfg)
record = stats.compile(pop)
logbook.record(gen=0, evals=len(pop), **record)
scoop_log(logbook.stream)
# Begin the generational process
output_str = '### Generation number: %d, Population size: %d ###\n' % (
cfg.opt.ngens, cfg.opt.npop)
scoop_log(output_str)
UtilClass.writelog(cfg.opt.logfile, output_str, mode='replace')
modelsel_count = {
0: len(pop)
} # type: Dict[int, int] # newly added Pareto fronts
for gen in range(1, cfg.opt.ngens + 1):
output_str = '###### Generation: %d ######\n' % gen
scoop_log(output_str)
offspring = [toolbox.clone(ind) for ind in pop]
# method1: use crowding distance (normalized as 0~1) as eta
# tools.emo.assignCrowdingDist(offspring)
# method2: use the index of individual at the sorted offspring list as eta
if len(offspring
) >= 2: # when offspring size greater than 2, mate can be done
for i, ind1, ind2 in zip(range(len(offspring) // 2),
offspring[::2], offspring[1::2]):
if random.random() > cfg.opt.rcross:
continue
eta = i
toolbox.mate(ind1, ind2, eta, low, up)
toolbox.mutate(ind1, eta, low, up, cfg.opt.rmut)
toolbox.mutate(ind2, eta, low, up, cfg.opt.rmut)
del ind1.fitness.values, ind2.fitness.values
else:
toolbox.mutate(offspring[0], 1., low, up, cfg.opt.rmut)
del offspring[0].fitness.values
# Evaluate the individuals with an invalid fitness
invalid_inds = [ind for ind in offspring if not ind.fitness.valid]
valid_inds = [ind for ind in offspring if ind.fitness.valid]
if len(invalid_inds) == 0: # No need to continue
scoop_log(
'Note: No invalid individuals available, the NSGA2 will be terminated!'
)
break
# Write new calibrated parameters to MongoDB
param_values = list()
for idx, ind in enumerate(invalid_inds):
ind.gen = gen
ind.id = idx
param_values.append(ind[:])
param_values = numpy.array(param_values)
write_param_values_to_mongodb(cfg.model.db_name, cali_obj.ParamDefs,
param_values)
# Count the model runs, and execute models
invalid_ind_size = len(invalid_inds)
modelruns_count.setdefault(gen, invalid_ind_size)
stime = time.time()
invalid_inds, plotlables = evaluate_parallel(invalid_inds)
curtimespan = time.time() - stime
modelruns_time.setdefault(gen, curtimespan)
modelruns_time_sum.setdefault(gen, 0.)
for ind in invalid_inds:
allmodels_exect.append(
[ind.io_time, ind.comp_time, ind.simu_time, ind.runtime])
modelruns_time_sum[gen] += ind.runtime
# Select the next generation population
# Previous version may result in duplications of the same scenario in one Pareto front,
# thus, I decided to check and remove the duplications first.
# pop = toolbox.select(pop + valid_inds + invalid_inds, pop_select_num)
tmppop = pop + valid_inds + invalid_inds
pop = list()
unique_sces = dict()
for tmpind in tmppop:
if tmpind.gen in unique_sces and tmpind.id in unique_sces[
tmpind.gen]:
continue
if tmpind.gen not in unique_sces:
unique_sces.setdefault(tmpind.gen, [tmpind.id])
elif tmpind.id not in unique_sces[tmpind.gen]:
unique_sces[tmpind.gen].append(tmpind.id)
pop.append(tmpind)
pop = toolbox.select(pop, pop_select_num)
output_population_details(pop,
cfg.opt.simdata_dir,
gen,
plot_cfg=cali_obj.cfg.plot_cfg)
hyper_str = 'Gen: %d, New model runs: %d, ' \
'Execute timespan: %.4f, Sum of model run timespan: %.4f, ' \
'Hypervolume: %.4f\n' % (gen, invalid_ind_size,
curtimespan, modelruns_time_sum[gen],
hypervolume(pop, ref_pt))
scoop_log(hyper_str)
UtilClass.writelog(cfg.opt.hypervlog, hyper_str, mode='append')
record = stats.compile(pop)
logbook.record(gen=gen, evals=len(invalid_inds), **record)
scoop_log(logbook.stream)
# Count the newly generated near Pareto fronts
new_count = 0
for ind in pop:
if ind.gen == gen:
new_count += 1
modelsel_count.setdefault(gen, new_count)
# Plot 2D near optimal pareto front graphs,
# i.e., (NSE, RSR), (NSE, PBIAS), and (RSR,PBIAS)
# And 3D near optimal pareto front graphs, i.e., (NSE, RSR, PBIAS)
stime = time.time()
front = numpy.array([ind.fitness.values for ind in pop])
title = (u'近似最优Pareto解集' if cali_obj.cfg.plot_cfg.plot_cn else
'Near Pareto optimal solutions')
plot_pareto_front_single(front,
plotlables,
cfg.opt.out_dir,
gen,
title,
plot_cfg=cali_obj.cfg.plot_cfg)
plot_time += time.time() - stime
# save in file
# Header information
output_str += 'generation\tcalibrationID\t'
for kk, vv in list(object_names.items()):
output_str += pop[0].cali.output_header(kk, vv, 'Cali')
if cali_obj.cfg.calc_validation:
for kkk, vvv in list(object_names.items()):
output_str += pop[0].vali.output_header(kkk, vvv, 'Vali')
output_str += 'gene_values\n'
for ind in pop:
output_str += '%d\t%d\t' % (ind.gen, ind.id)
for kk, vv in list(object_names.items()):
output_str += ind.cali.output_efficiency(kk, vv)
if cali_obj.cfg.calc_validation:
for kkk, vvv in list(object_names.items()):
output_str += ind.vali.output_efficiency(kkk, vvv)
output_str += str(ind)
output_str += '\n'
UtilClass.writelog(cfg.opt.logfile, output_str, mode='append')
# TODO: Figure out if we should terminate the evolution
# Plot hypervolume and newly executed model count
plot_hypervolume_single(cfg.opt.hypervlog,
cfg.opt.out_dir,
plot_cfg=cali_obj.cfg.plot_cfg)
# Save newly added Pareto fronts of each generations
new_fronts_count = numpy.array(list(modelsel_count.items()))
numpy.savetxt('%s/new_pareto_fronts_count.txt' % cfg.opt.out_dir,
new_fronts_count,
delimiter=str(','),
fmt=str('%d'))
# Save and print timespan information
allmodels_exect = numpy.array(allmodels_exect)
numpy.savetxt('%s/exec_time_allmodelruns.txt' % cfg.opt.out_dir,
allmodels_exect,
delimiter=str(' '),
fmt=str('%.4f'))
scoop_log('Running time of all SEIMS models:\n'
'\tIO\tCOMP\tSIMU\tRUNTIME\n'
'MAX\t%s\n'
'MIN\t%s\n'
'AVG\t%s\n'
'SUM\t%s\n' %
('\t'.join('%.3f' % t for t in allmodels_exect.max(0)),
'\t'.join('%.3f' % t
for t in allmodels_exect.min(0)), '\t'.join(
'%.3f' % t
for t in allmodels_exect.mean(0)), '\t'.join(
'%.3f' % t for t in allmodels_exect.sum(0))))
exec_time = 0.
for genid, tmptime in list(modelruns_time.items()):
exec_time += tmptime
exec_time_sum = 0.
for genid, tmptime in list(modelruns_time_sum.items()):
exec_time_sum += tmptime
allcount = 0
for genid, tmpcount in list(modelruns_count.items()):
allcount += tmpcount
scoop_log('Initialization timespan: %.4f\n'
'Model execution timespan: %.4f\n'
'Sum of model runs timespan: %.4f\n'
'Plot Pareto graphs timespan: %.4f' %
(init_time, exec_time, exec_time_sum, plot_time))
return pop, logbook
class Scenario(object):
"""Base class of Scenario Analysis.
Attributes:
ID(integer): Unique ID in BMPScenario database -> BMP_SCENARIOS collection
eval_timerange(float): Simulation time range, read from MongoDB, the unit is year.
economy(float): Economical effectiveness, e.g., income minus expenses
environment(float): Environmental effectiveness, e.g., reduction rate of soil erosion
gene_num(integer): The number of genes of one chromosome, i.e., an individual
gene_values(list): BMP identifiers on each location of gene. The length is gen_num.
bmp_items(dict): BMP configuration items that can be imported to MongoDB directly.
The key is `bson.objectid.ObjectId`, the value is scenario item dict.
rules(boolean): Config BMPs randomly or rule-based.
modelrun(boolean): Has SEIMS model run successfully?
"""
def __init__(self, cfg):
# type: (SAConfig) -> None
"""Initialize."""
self.ID = -1
self.eval_timerange = 1. # unit: year
self.economy = 0.
self.environment = 0.
self.worst_econ = cfg.worst_econ
self.worst_env = cfg.worst_env
self.gene_num = 0
self.gene_values = list() # type: List[int]
self.bmp_items = dict()
self.rule_mtd = cfg.bmps_cfg_method
self.bmps_info = cfg.bmps_info
self.bmps_retain = cfg.bmps_retain
self.eval_info = cfg.eval_info
self.export_sce_txt = cfg.export_sce_txt
self.export_sce_tif = cfg.export_sce_tif
self.scenario_dir = cfg.scenario_dir # predefined directories to store scenarios related
# SEIMS-based model related
self.modelcfg = cfg.model
self.modelcfg_dict = self.modelcfg.ConfigDict
self.model = MainSEIMS(args_dict=self.modelcfg_dict)
self.model.SetMongoClient()
self.model.ReadMongoDBData()
self.scenario_db = self.model.ScenarioDBName
self.model.ResetSimulationPeriod() # Reset the simulation period
# Reset the starttime and endtime of the desired outputs according to evaluation period
if ModelCfgFields.output_id in self.eval_info:
self.model.ResetOutputsPeriod(
self.eval_info[ModelCfgFields.output_id], cfg.eval_stime,
cfg.eval_etime)
else:
print(
'Warning: No OUTPUTID is defined in BMPs_info. Please make sure the '
'STARTTIME and ENDTIME of ENVEVAL are consistent with Evaluation period!'
)
self.model.UnsetMongoClient() # Unset in time!
# (Re)Calculate timerange in the unit of year
dlt = cfg.eval_etime - cfg.eval_stime + timedelta(seconds=1)
self.eval_timerange = (dlt.days * 86400. + dlt.seconds) / 86400. / 365.
self.modelout_dir = None # determined in `execute_seims_model` based on unique scenario ID
self.modelrun = False # indicate whether the model has been executed
def set_unique_id(self, given_id=None):
# type: (Optional[int]) -> int
"""Set unique ID."""
if given_id is None:
self.ID = next(generate_uniqueid())
else:
self.ID = given_id
# Update scenario ID for self.modelcfg and self.model
self.model.scenario_id = self.ID
self.modelcfg.scenario_id = self.ID
self.modelcfg_dict[
'scenario_id'] = self.ID if self.modelcfg_dict else 0
return self.ID
def rule_based_config(self, method, conf_rate):
# type: (float, str) -> None
"""Config available BMPs to each gene of the chromosome by rule-based method.
Virtual function that should be overridden in inherited Scenario class.
"""
pass
def random_based_config(self, conf_rate):
# type: (float) -> None
"""Config available BMPs to each gene of the chromosome by random-based method.
Virtual function that should be overridden in inherited Scenario class.
"""
pass
def decoding(self):
"""Decoding gene_values to bmp_items
This function should be overridden.
"""
pass
def export_to_mongodb(self):
"""Export current scenario to MongoDB.
Delete the same ScenarioID if existed.
"""
# client = ConnectMongoDB(self.modelcfg.host, self.modelcfg.port)
# conn = client.get_conn()
conn = MongoDBObj.client
db = conn[self.scenario_db]
collection = db[DBTableNames.scenarios]
try:
# find ScenarioID, remove if existed.
if collection.find({
'ID': self.ID
}, no_cursor_timeout=True).count():
collection.remove({'ID': self.ID})
except NetworkTimeout or Exception:
# In case of unexpected raise
pass
for objid, bmp_item in viewitems(self.bmp_items):
bmp_item['_id'] = ObjectId()
collection.insert_one(bmp_item)
# client.close()
def export_scenario_to_txt(self):
"""Export current scenario information to text file.
This function is better be called after `calculate_environment` and `calculate_environment`
or in static method, e.g., `scenario_effectiveness`.
"""
if not self.export_sce_txt:
return
ofile = self.scenario_dir + os.path.sep + 'Scenario_%d.txt' % self.ID
with open(ofile, 'w', encoding='utf-8') as outfile:
outfile.write('Scenario ID: %d\n' % self.ID)
outfile.write('Gene number: %d\n' % self.gene_num)
outfile.write('Gene values: %s\n' % ', '.join(
(repr(v) for v in self.gene_values)))
outfile.write('Scenario items:\n')
if len(self.bmp_items) > 0:
header = list()
for obj, item in viewitems(self.bmp_items):
header = list(item.keys())
break
outfile.write('\t'.join(header))
outfile.write('\n')
for obj, item in viewitems(self.bmp_items):
outfile.write('\t'.join(
str(v) for v in list(item.values())))
outfile.write('\n')
outfile.write(
'Effectiveness:\n\teconomy: %f\n\tenvironment: %f\n' %
(self.economy, self.environment))
def export_scenario_to_gtiff(self):
"""Export the areal BMPs to gtiff for further analysis.
This function should be overridden in inherited class.
"""
pass
def import_from_mongodb(self, sid):
"""Import a specified Scenario (`sid`) from MongoDB.
This function should be overridden in inherited class.
Returns:
True if succeed, otherwise False.
"""
pass
def import_from_txt(self, sid):
"""Import a specified Scenario (`sid`) from text file.
This function should be overridden in inherited class.
Returns:
True if succeed, otherwise False.
"""
pass
def calculate_economy(self):
"""Calculate economical effectiveness, which is application specified."""
pass
def calculate_environment(self):
"""Calculate environment effectiveness, which is application specified."""
pass
def clean(self,
scenario_id=None,
calibration_id=None,
delete_scenario=False,
delete_spatial_gfs=False):
"""Clean the intermediate data."""
# model clean
self.model.SetMongoClient()
self.model.clean(scenario_id=scenario_id,
calibration_id=calibration_id,
delete_scenario=delete_scenario,
delete_spatial_gfs=delete_spatial_gfs)
self.model.UnsetMongoClient()
def execute_seims_model(self):
"""Run SEIMS for evaluating environmental effectiveness.
If execution fails, the `self.economy` and `self.environment` will be set the worst values.
"""
scoop_log('Scenario ID: %d, running SEIMS model...' % self.ID)
self.model.scenario_id = self.ID
self.modelout_dir = self.model.OutputDirectory
self.model.SetMongoClient()
self.model.run()
self.model.UnsetMongoClient()
self.modelrun = True
return self.model.run_success
def initialize(self, input_genes=None):
# type: (Optional[List]) -> List
"""Initialize a scenario.
Returns:
A list contains BMPs identifier of each gene location.
"""
pass