def test_probsample_noreplace_ordering(self): probs=array([1, 1, 1, 1, 100, 1, 1, 1, 1, 1]) probsum = float(probs.sum()) first = [] n = 100 #seed(10) for i in range(n): sample = probsample_noreplace(arange(10), 5, prob_array=probs/probsum, return_index=False) # keep the first element sampled first.append(sample[0]) # How many times the fifth element (which has highest probability) came out first. It should be about 90% of the time. freq4 = (array(first) == 4).sum()/float(n) assert freq4 > 0.85, "Error in ordering elements in probsample_noreplace" # check the second sampled element probs=array([1, 1, 100, 1, 1, 1, 1000, 1, 1, 1, 1]) probsum = float(probs.sum()) second=[] while True: sample = probsample_noreplace(arange(11), 5, prob_array=probs/probsum, return_index=False) if sample[0] == 6: second.append(sample[1]) if len(second) >= n: break # How many times the third element came out second given the seventh element came out first. It should be about 90% of the time. freq2 = (array(second) == 2).sum()/float(n) assert freq2 > 0.85, "Error in ordering elements in probsample_noreplace"
def get_movers_from_overfilled_locations(self, agent_set, agents_index, config=None): """Returns an index (relative to agents_index) of agents that should be removed from their locations. """ id_name = self.choice_set.get_id_name()[0] agents_locations = agent_set.get_attribute_by_index(id_name, agents_index) # check if there was an overfilling of locations movers = array([], dtype='int32') if self.compute_capacity_flag: overfilled_string = config.get("is_choice_overfilled_string", None) if overfilled_string: tmp_agent_set = copy.copy(agent_set) overfilled_locations = where(self.choice_set.compute_variables(overfilled_string, self.dataset_pool))[0] current_agents_in_overfilled_locations = intersect1d(agents_locations, overfilled_locations) while current_agents_in_overfilled_locations.size > 0: for location in current_agents_in_overfilled_locations: agents_of_this_location = where(agents_locations == location)[0] if agents_of_this_location.size > 1: sampled_agents = probsample_noreplace(agents_of_this_location, 1) else: sampled_agents = agents_of_this_location movers = concatenate((movers, sampled_agents)) tmp_agent_set.set_values_of_one_attribute(id_name, -1, agents_index[movers]) agents_locations = tmp_agent_set.get_attribute_by_index(id_name, agents_index) self.dataset_pool.replace_dataset(tmp_agent_set.get_dataset_name(), tmp_agent_set) overfilled_locations = where(self.choice_set.compute_variables(overfilled_string, self.dataset_pool))[0] current_agents_in_overfilled_locations = intersect1d(agents_locations, overfilled_locations) self.dataset_pool.replace_dataset(agent_set.get_dataset_name(), agent_set) else: new_locations_vacancy = self.get_locations_vacancy(agent_set) movers = self.choose_agents_to_move_from_overfilled_locations(new_locations_vacancy, agent_set, agents_index, agents_locations) return concatenate((movers, where(agents_locations <= 0)[0]))
def _sample_by_agent_and_stratum(self, index1, index2, stratum, prob_array, chosen_choice_index, strata_sample_setting): """agent by agent and stratum by stratum stratified sampling, suitable for 2d prob_array and/or sample_size varies for agents this method is slower than _sample_by_stratum, for simpler stratified sampling use _sample_by_stratum instead""" rank_of_prob = rank(prob_array) rank_of_strata = rank(strata_sample_setting) J = self.__determine_sampled_index_size(strata_sample_setting, rank_of_strata) sampled_index = zeros((index1.size, J), dtype=DTYPE) - 1 self._sampling_probability = zeros((index1.size, J), dtype=float32) self._stratum_id = ones((index1.size, J), dtype=DTYPE) * NO_STRATUM_ID for i in range(index1.size): if rank_of_strata == 3: strata_sample_pairs = strata_sample_setting[i, :] else: strata_sample_pairs = strata_sample_setting if rank_of_prob == 2: prob = prob_array[i, :] else: prob = prob_array j = 0 for (this_stratum, this_size) in strata_sample_pairs: if this_size <= 0: continue index_not_in_stratum = where(stratum != this_stratum)[0] this_prob = copy.copy(prob) this_prob[index_not_in_stratum] = 0.0 this_prob = normalize(this_prob) if nonzerocounts(this_prob) < this_size: logger.log_warning( "weight array dosen't have enough non-zero counts, use sample with replacement" ) # chosen_index_to_index2 = where(index2 == chosen_choice_index[i])[0] #exclude_index passed to probsample_noreplace needs to be indexed to index2 this_sampled_index = probsample_noreplace( index2, sample_size=this_size, prob_array=this_prob, exclude_index=chosen_choice_index[i], return_index=True) sampled_index[i, j:j + this_size] = this_sampled_index self._sampling_probability[ i, j:j + this_size] = this_prob[this_sampled_index] self._stratum_id[i, j:j + this_size] = ones( (this_sampled_index.size, ), dtype=DTYPE) * this_stratum j += this_size return index2[sampled_index]
def test_probsample_noreplace(self): start_time = time.time() sample = probsample_noreplace(self.all, self.size, self.prob, return_index=True) logger.log_status("probsample_noreplace %s from %s items array in " % (self.size,self.n) + str(time.time() - start_time) + " sec") self.assertEqual(sample.size, self.size, msg ="sample size not equal to size parameter") assert isinstance(sample, ndarray), "sample is not of type ndarray" assert 0 <= sample.min() <= self.n-1, "sampled elements not in between min and max of source array" assert 0 <= sample.max() <= self.n-1, "sampled elements not in between min and max of source array" assert alltrue(not_equal(self.prob[sample], 0.0)), "elements with zero weight in the sample" assert not sometrue(find_duplicates(sample)), "there are duplicates in samples"
def _sample_by_agent_and_stratum( self, index1, index2, stratum, prob_array, chosen_choice_index, strata_sample_setting ): """agent by agent and stratum by stratum stratified sampling, suitable for 2d prob_array and/or sample_size varies for agents this method is slower than _sample_by_stratum, for simpler stratified sampling use _sample_by_stratum instead""" rank_of_prob = rank(prob_array) rank_of_strata = rank(strata_sample_setting) J = self.__determine_sampled_index_size(strata_sample_setting, rank_of_strata) sampled_index = zeros((index1.size, J), dtype="int32") - 1 self._sampling_probability = zeros((index1.size, J), dtype=float32) self._stratum_id = ones((index1.size, J), dtype="int32") * NO_STRATUM_ID for i in range(index1.size): if rank_of_strata == 3: strata_sample_pairs = strata_sample_setting[i, :] else: strata_sample_pairs = strata_sample_setting if rank_of_prob == 2: prob = prob_array[i, :] else: prob = prob_array j = 0 for (this_stratum, this_size) in strata_sample_pairs: if this_size <= 0: continue index_not_in_stratum = where(stratum != this_stratum)[0] this_prob = copy.copy(prob) this_prob[index_not_in_stratum] = 0.0 this_prob = normalize(this_prob) if nonzerocounts(this_prob) < this_size: logger.log_warning("weight array dosen't have enough non-zero counts, use sample with replacement") # chosen_index_to_index2 = where(index2 == chosen_choice_index[i])[0] # exclude_index passed to probsample_noreplace needs to be indexed to index2 this_sampled_index = probsample_noreplace( index2, sample_size=this_size, prob_array=this_prob, exclude_index=chosen_choice_index[i], return_index=True, ) sampled_index[i, j : j + this_size] = this_sampled_index self._sampling_probability[i, j : j + this_size] = this_prob[this_sampled_index] self._stratum_id[i, j : j + this_size] = ones((this_sampled_index.size,), dtype="int32") * this_stratum j += this_size return index2[sampled_index]
def run(self, zones, run_choice_model=True, choose_job_only_in_residence_zone=True, **kwargs): agent_set = kwargs['agent_set'] agents_index = kwargs.get('agents_index', None) if agents_index is None: agents_index = arange(agent_set.size()) cond_array = zeros(agent_set.size(), dtype="bool8") cond_array[agents_index] = True zone_ids = zones.get_id_attribute() agents_zones = agent_set.compute_variables(['urbansim_parcel.%s.%s' % (agent_set.get_dataset_name(), zones.get_id_name()[0])], dataset_pool=self.dataset_pool) if self.filter is not None: jobs_set_index = where( self.job_set.compute_variables(self.filter) )[0] else: jobs_set_index = arange( self.job_set.size() ) #self.job_set.compute_variables("urbansim_parcel.job.zone_id") agent_set.compute_variables("urbansim_parcel.person.zone_id") # remove job links from all workers agent_set.set_values_of_one_attribute(self.choice_attribute_name, -1*ones(agents_index.size, dtype='int32'), index=agents_index) for zone_id in zone_ids: new_index = where(logical_and(cond_array, agents_zones == zone_id))[0] logger.log_status("%s for zone %s" % (self.model_short_name, zone_id)) if run_choice_model: kwargs['agents_index'] = new_index choices = ChoiceModel.run(self, **kwargs) prob_work_at_home = self.upc_sequence.get_probabilities()[:, 1] job_set_in_this_zone = jobs_set_index[self.job_set['zone_id'][jobs_set_index] == zone_id] number_of_hb_jobs = job_set_in_this_zone.size # sample workers for the number of jobs draw = probsample_noreplace(kwargs['agents_index'], min(kwargs['agents_index'].size, number_of_hb_jobs), prob_work_at_home) agent_set.set_values_of_one_attribute(self.choice_attribute_name, ones(draw.size, dtype=agent_set[self.choice_attribute_name].dtype), index=draw) logger.log_status("%s workers choose to work at home, %s workers chose to work out of home." % (where(agent_set.get_attribute_by_index(self.choice_attribute_name, kwargs['agents_index']) == 1)[0].size, where(agent_set.get_attribute_by_index(self.choice_attribute_name, kwargs['agents_index']) == 0)[0].size)) at_home_worker_in_this_zone = kwargs['agents_index'][agent_set[self.choice_attribute_name][kwargs['agents_index']] == 1] assigned_worker_in_this_zone, assigned_job_set_in_this_zone = self._assign_job_to_worker(at_home_worker_in_this_zone, job_set_in_this_zone) agent_set.set_values_of_one_attribute(self.job_set.get_id_name()[0], self.job_set.get_id_attribute()[assigned_job_set_in_this_zone], index=assigned_worker_in_this_zone) agent_set.compute_variables([self.location_id_name], dataset_pool=self.dataset_pool) self.job_set.modify_attribute(name=VariableName(self.location_id_name).get_alias(), data=agent_set.get_attribute_by_index(self.location_id_name, assigned_worker_in_this_zone), index=assigned_job_set_in_this_zone) agent_set.flush_dataset() self.job_set.flush_dataset() logger.log_status("Total: %s workers work at home, %s workers work out of home." % (where(agent_set.get_attribute(self.choice_attribute_name) == 1)[0].size, where(agent_set.get_attribute(self.choice_attribute_name) == 0)[0].size ))
def get_movers_from_overfilled_locations(self, agent_set, agents_index, config=None): """Returns an index (relative to agents_index) of agents that should be removed from their locations. """ id_name = self.choice_set.get_id_name()[0] agents_locations = agent_set.get_attribute_by_index( id_name, agents_index) # check if there was an overfilling of locations movers = array([], dtype='int32') if self.compute_capacity_flag: overfilled_string = config.get("is_choice_overfilled_string", None) if overfilled_string: tmp_agent_set = copy.copy(agent_set) overfilled_locations = where( self.choice_set.compute_variables(overfilled_string, self.dataset_pool))[0] current_agents_in_overfilled_locations = intersect1d( agents_locations, overfilled_locations) while current_agents_in_overfilled_locations.size > 0: for location in current_agents_in_overfilled_locations: agents_of_this_location = where( agents_locations == location)[0] if agents_of_this_location.size > 1: sampled_agents = probsample_noreplace( agents_of_this_location, 1) else: sampled_agents = agents_of_this_location movers = concatenate((movers, sampled_agents)) tmp_agent_set.set_values_of_one_attribute( id_name, -1, agents_index[movers]) agents_locations = tmp_agent_set.get_attribute_by_index( id_name, agents_index) self.dataset_pool.replace_dataset( tmp_agent_set.get_dataset_name(), tmp_agent_set) overfilled_locations = where( self.choice_set.compute_variables( overfilled_string, self.dataset_pool))[0] current_agents_in_overfilled_locations = intersect1d( agents_locations, overfilled_locations) self.dataset_pool.replace_dataset(agent_set.get_dataset_name(), agent_set) else: new_locations_vacancy = self.get_locations_vacancy(agent_set) movers = self.choose_agents_to_move_from_overfilled_locations( new_locations_vacancy, agent_set, agents_index, agents_locations) return concatenate((movers, where(agents_locations <= 0)[0]))
def choose_agents_to_move_from_overfilled_locations(self, capacity, agent_set, agents_index, agents_locations): """Iterates over locations that are overfilled and selects randomly agents placed in those locations to be removed.""" if capacity is None: return array([], dtype='int32') index_valid_agents_locations = where(agents_locations > 0)[0] valid_agents_locations = agents_locations[index_valid_agents_locations] index_consider_capacity = unique(self.choice_set.get_id_index(valid_agents_locations)) capacity_of_affected_locations = capacity[index_consider_capacity] overfilled = where(capacity_of_affected_locations < 0)[0] movers = array([], dtype='int32') choice_ids = self.choice_set.get_id_attribute() for loc in overfilled: agents_to_move = where(valid_agents_locations == choice_ids[index_consider_capacity[loc]])[0] if agents_to_move.size > 0: n = int(-1*capacity_of_affected_locations[loc]) sampled_agents = probsample_noreplace(index_valid_agents_locations[agents_to_move], min(n, agents_to_move.size)) movers = concatenate((movers, sampled_agents)) return movers
def choose_agents_to_move_from_overfilled_locations( self, capacity, agent_set, agents_index, agents_locations): """Iterates over locations that are overfilled and selects randomly agents placed in those locations to be removed.""" if capacity is None: return array([], dtype='int32') index_valid_agents_locations = where(agents_locations > 0)[0] valid_agents_locations = agents_locations[index_valid_agents_locations] index_consider_capacity = unique( self.choice_set.get_id_index(valid_agents_locations)) capacity_of_affected_locations = capacity[index_consider_capacity] overfilled = where(capacity_of_affected_locations < 0)[0] movers = array([], dtype='int32') choice_ids = self.choice_set.get_id_attribute() for loc in overfilled: agents_to_move = where(valid_agents_locations == choice_ids[ index_consider_capacity[loc]])[0] if agents_to_move.size > 0: n = int(-1 * capacity_of_affected_locations[loc]) sampled_agents = probsample_noreplace( index_valid_agents_locations[agents_to_move], min(n, agents_to_move.size)) movers = concatenate((movers, sampled_agents)) return movers
def run(self, in_storage, business_dsname="business"): dataset_pool = DatasetPool(storage=in_storage, package_order=['psrc_parcel', 'urbansim_parcel', 'urbansim', 'opus_core'] ) seed(1) allbusinesses = dataset_pool.get_dataset(business_dsname) parcels = dataset_pool.get_dataset('parcel') buildings = dataset_pool.get_dataset('building') parcels.compute_variables(["urbansim_parcel.parcel.residential_units", "number_of_buildings = parcel.number_of_agents(building)", "non_residential_sqft = (parcel.aggregate(building.non_residential_sqft)).astype(int32)", "number_of_res_buildings = parcel.aggregate(urbansim_parcel.building.is_residential)", "number_of_nonres_buildings = parcel.aggregate(urbansim_parcel.building.is_non_residential)", "number_of_mixed_use_buildings = parcel.aggregate(urbansim_parcel.building.is_generic_building_type_6)" ], dataset_pool=dataset_pool) restypes = [12, 4, 19, 11, 34, 10, 33] reslutypes = [13,14,15,24] is_valid_business = ones(allbusinesses.size(), dtype='bool8') parcels_not_matched = logical_and(in1d(allbusinesses["parcel_id"], parcels.get_id_attribute(), invert=True), allbusinesses["parcel_id"] > 0) if(parcels_not_matched.sum() > 0): is_valid_business[where(parcels_not_matched)] = False logger.log_warning(message="No parcel exists for %s businesses (%s jobs)" % (parcels_not_matched.sum(), allbusinesses[self.number_of_jobs_attr][where(parcels_not_matched)].sum())) zero_parcel = allbusinesses["parcel_id"]<=0 if zero_parcel.sum() > 0: is_valid_business[where(zero_parcel)] = False logger.log_warning(message="%s businesses (%s jobs) located on zero parcel_id" % (zero_parcel.sum(), allbusinesses[self.number_of_jobs_attr][where(zero_parcel)].sum())) zero_size = logical_and(is_valid_business, allbusinesses[self.number_of_jobs_attr].round() == 0) if(sum(zero_size) > 0): is_valid_business[where(zero_size)] = False logger.log_warning(message="%s businesses are of size 0." % sum(zero_size)) businesses = DatasetSubset(allbusinesses, index=where(is_valid_business)[0]) parcels.add_attribute(name="number_of_workplaces", data=parcels.sum_dataset_over_ids(businesses, constant=1)) has_single_res_buildings = logical_and(parcels["number_of_buildings"] == 1, parcels["number_of_res_buildings"] == 1) # 1 (1 residential) parcels.add_attribute(data=has_single_res_buildings.astype("int32"), name="buildings_code") has_mult_res_buildings = logical_and(parcels["number_of_buildings"] > 1, parcels["number_of_nonres_buildings"] == 0) # 2 (mult residential) parcels.modify_attribute("buildings_code", data=2*ones(has_mult_res_buildings.sum()), index=where(has_mult_res_buildings)) has_single_nonres_buildings = logical_and(logical_and(parcels["number_of_buildings"] == 1, parcels["number_of_nonres_buildings"] == 1), parcels["number_of_mixed_use_buildings"] == 0) # 3 (1 non-res) parcels.modify_attribute("buildings_code", data=3*ones(has_single_nonres_buildings.sum()), index=where(has_single_nonres_buildings)) has_mult_nonres_buildings = logical_and(logical_and(parcels["number_of_buildings"] > 1, parcels["number_of_res_buildings"] == 0), parcels["number_of_mixed_use_buildings"] == 0) # 4 (mult non-res) parcels.modify_attribute("buildings_code", data=4*ones(has_mult_nonres_buildings.sum()), index=where(has_mult_nonres_buildings)) has_single_mixed_buildings = logical_and(parcels["number_of_buildings"] == 1, parcels["number_of_mixed_use_buildings"] == 1) # 5 (1 mixed-use) parcels.modify_attribute("buildings_code", data=5*ones(has_single_mixed_buildings.sum()), index=where(has_single_mixed_buildings)) has_mult_mixed_buildings = logical_and(parcels["number_of_buildings"] > 1, logical_or(logical_and(parcels["number_of_res_buildings"] > 0, parcels["number_of_nonres_buildings"] > 0), logical_or(parcels["number_of_mixed_use_buildings"] > 1, logical_and(parcels["number_of_res_buildings"] == 0, parcels["number_of_mixed_use_buildings"] > 0)))) # 6 parcels.modify_attribute("buildings_code", data=6*ones(has_mult_mixed_buildings.sum()), index=where(has_mult_mixed_buildings)) has_no_building_res_lutype = logical_and(parcels["number_of_buildings"] == 0, in1d(parcels["land_use_type_id"], reslutypes)) # 7 (vacant with res LU type) parcels.modify_attribute("buildings_code", data=7*ones(has_no_building_res_lutype.sum()), index=where(has_no_building_res_lutype)) has_no_building_nonres_lutype = logical_and(parcels["number_of_buildings"] == 0, in1d(parcels["land_use_type_id"], reslutypes)==0) # 8 (vacant with non-res LU type) parcels.modify_attribute("buildings_code", data=8*ones(has_no_building_nonres_lutype.sum()), index=where(has_no_building_nonres_lutype)) business_sizes = businesses[self.number_of_jobs_attr].round().astype("int32") business_location = {} business_location1wrkpl = zeros(businesses.size(), dtype="int32") business_location1wrkplres = zeros(businesses.size(), dtype="int32") # sample one building for cases when sampling is required. for ibusid in range(businesses.size()): idx = where(buildings['parcel_id'] == businesses['parcel_id'][ibusid])[0] bldgids = buildings['building_id'][idx] business_location[businesses['business_id'][ibusid]] = bldgids if bldgids.size == 1: business_location1wrkpl[ibusid] = bldgids[0] elif bldgids.size > 1: business_location1wrkpl[ibusid] = bldgids[sample_noreplace(arange(bldgids.size), 1)] if buildings['residential_units'][idx].sum() > 0: # Residential buildings are sampled with probabilities proportional to residential units business_location1wrkplres[ibusid] = bldgids[probsample_noreplace(arange(bldgids.size), 1, prob_array=buildings['residential_units'][idx])] else: business_location1wrkplres[ibusid] = business_location1wrkpl[ibusid] home_based = zeros(business_sizes.sum(), dtype="bool8") job_building_id = zeros(business_sizes.sum(), dtype="int32") job_array_labels = businesses['business_id'].repeat(business_sizes) job_assignment_case = zeros(business_sizes.sum(), dtype="int32") processed_bindicator = zeros(businesses.size(), dtype="bool8") logger.log_status("Total number of jobs: %s" % home_based.size) # 1. up to 5 workers-business in 1 residential building idx_single_worker = where(business_sizes < 6)[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_single_worker]) idx_sngl_wrk_1bld_fit = where(bcode == 1)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_single_worker[idx_sngl_wrk_1bld_fit]]) home_based[jidx] = True job_building_id[jidx] = business_location1wrkpl[idx_single_worker[idx_sngl_wrk_1bld_fit]].repeat(business_sizes[idx_single_worker[idx_sngl_wrk_1bld_fit]]) job_assignment_case[jidx] = 1 processed_bindicator[idx_single_worker[idx_sngl_wrk_1bld_fit]] = True logger.log_status("1. %s jobs (%s businesses) set as home-based due to <6 worker x 1 residential building fit." % ( business_sizes[idx_single_worker[idx_sngl_wrk_1bld_fit]].sum(), idx_sngl_wrk_1bld_fit.size)) # 2. up to 5 workers-business in multiple residential buildings idx_single_worker = where(logical_and(processed_bindicator==0, business_sizes < 6))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_single_worker]) idx_sngl_wrk_multbld_fit = where(bcode == 2)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_single_worker[idx_sngl_wrk_multbld_fit]]) home_based[jidx] = True job_building_id[jidx] = business_location1wrkplres[idx_single_worker[idx_sngl_wrk_multbld_fit]].repeat(business_sizes[idx_single_worker[idx_sngl_wrk_multbld_fit]]) job_assignment_case[jidx] = 2 processed_bindicator[idx_single_worker[idx_sngl_wrk_multbld_fit]] = True logger.log_status("2. %s jobs (%s businesses) set as home-based due to single worker x multiple residential buildings fit." % ( business_sizes[idx_single_worker[idx_sngl_wrk_multbld_fit]].sum(), idx_sngl_wrk_multbld_fit.size)) # 3. single worker in single non-res building (not mixed-use) idx_single_worker = where(logical_and(processed_bindicator==0, business_sizes == 1))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_single_worker]) idx_sngl_wrk_single_nonres_fit = where(bcode == 3)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_single_worker[idx_sngl_wrk_single_nonres_fit]]) job_building_id[jidx] = business_location1wrkpl[idx_single_worker[idx_sngl_wrk_single_nonres_fit]] job_assignment_case[jidx] = 3 processed_bindicator[idx_single_worker[idx_sngl_wrk_single_nonres_fit]] = True logger.log_status("3. %s jobs could be placed due to single worker x single non-res building fit." % idx_sngl_wrk_single_nonres_fit.size) # 4. single worker in multiple non-res building (not mixed-use) idx_single_worker = where(logical_and(processed_bindicator==0, business_sizes == 1))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_single_worker]) idx_sngl_wrk_mult_nonres_fit = where(bcode == 4)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_single_worker[idx_sngl_wrk_mult_nonres_fit]]) job_building_id[jidx] = business_location1wrkpl[idx_single_worker[idx_sngl_wrk_mult_nonres_fit]] job_assignment_case[jidx] = 4 processed_bindicator[idx_single_worker[idx_sngl_wrk_mult_nonres_fit]] = True logger.log_status("4. %s jobs could be placed due to single worker x multiple non-res building fit." % idx_sngl_wrk_mult_nonres_fit.size) # 5. single worker in single mixed-use building idx_single_worker = where(logical_and(processed_bindicator==0, business_sizes == 1))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_single_worker]) idx_sngl_wrk_smu_fit = where(bcode == 5)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_single_worker[idx_sngl_wrk_smu_fit]]) job_building_id[jidx] = business_location1wrkpl[idx_single_worker[idx_sngl_wrk_smu_fit]] job_assignment_case[jidx] = 5 processed_bindicator[idx_single_worker[idx_sngl_wrk_smu_fit]] = True logger.log_status("5. %s jobs in single worker x single mixed-use building." % idx_sngl_wrk_smu_fit.size) # 6. single worker in multiple mixed-type buildings idx_single_worker = where(logical_and(processed_bindicator==0, business_sizes == 1))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_single_worker]) idx_sngl_wrk_mmu_fit = where(bcode == 6)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_single_worker[idx_sngl_wrk_mmu_fit]]) job_building_id[jidx] = business_location1wrkpl[idx_single_worker[idx_sngl_wrk_mmu_fit]] bldtype = buildings.get_attribute_by_id("building_type_id", business_location1wrkpl[idx_single_worker[idx_sngl_wrk_mmu_fit]]) is_bldtype_res = in1d(bldtype, restypes) home_based[in1d(job_array_labels, businesses['business_id'][idx_single_worker[idx_sngl_wrk_mmu_fit]][where(is_bldtype_res)])] = True job_assignment_case[jidx] = 6 processed_bindicator[idx_single_worker[idx_sngl_wrk_mmu_fit]] = True logger.log_status("6. %s jobs in single worker x multiple mixed-type buildings. %s jobs classified as home-based." % (idx_sngl_wrk_mmu_fit.size, is_bldtype_res.sum())) # 7. up to 5 workers-business in residential parcel with no building idx_single_worker = where(logical_and(processed_bindicator==0, business_sizes < 6))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_single_worker]) idx_sngl_wrk_vacant_res = where(bcode == 7)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_single_worker[idx_sngl_wrk_vacant_res]]) job_assignment_case[jidx] = 7 home_based[jidx] = True processed_bindicator[idx_single_worker[idx_sngl_wrk_vacant_res]] = True logger.log_status("7. %s jobs (%s businesses of size <6) could not be placed due to non-existing buildings in parcels with residential LU type." % ( business_sizes[idx_single_worker[idx_sngl_wrk_vacant_res]].sum(), idx_sngl_wrk_vacant_res.size)) # 9. 6+ workers in single residential building: do not place - will go into ELCM idx_more_workers = where(logical_and(processed_bindicator==0, business_sizes > 5))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_more_workers]) idx_sngl_wrk_fit = where(bcode == 1)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_more_workers[idx_sngl_wrk_fit]]) #job_building_id[jidx] = business_location1wrkpl[idx_more_workers[idx_sngl_wrk_fit]].repeat(business_sizes[idx_more_workers[idx_sngl_wrk_fit]]) #home_based[jidx] = True job_assignment_case[jidx] = 9 processed_bindicator[idx_more_workers[idx_sngl_wrk_fit]] = True logger.log_status("9. %s jobs (%s businesses) in 6+ worker x single residential building. Not placed." % ( business_sizes[idx_more_workers[idx_sngl_wrk_fit]].sum(), idx_sngl_wrk_fit.size)) # 10. 6+ workers in multiple residential building: do not place - will go into ELCM idx_more_workers = where(logical_and(processed_bindicator==0, business_sizes > 5))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_more_workers]) idx_sngl_wrk_fit = where(bcode == 2)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_more_workers[idx_sngl_wrk_fit]]) job_assignment_case[jidx] = 10 processed_bindicator[idx_more_workers[idx_sngl_wrk_fit]] = True # sample buildings to businesses by parcels #bpcls = unique(businesses["parcel_id"][idx_more_workers[idx_sngl_wrk_fit]]) #for ipcl in range(bpcls.size): #bidx = where(buildings['parcel_id'] == bpcls[ipcl])[0] #bldgids = buildings['building_id'][bidx] #bussids = businesses['business_id'][businesses["parcel_id"] == bpcls[ipcl]] ## multiply by units for sampling prop. to units rather than buildings #bldgids = bldgids.repeat(maximum(1, buildings['residential_units'][bidx].astype('int32'))) #if bldgids.size < bussids.size: #bldarray = bldgids.repeat(1+ceil((bussids.size - bldgids.size)/float(bldgids.size)) ) #else: #bldarray = bldgids #shuffle(bldarray) # randomly reorder in-place #for ib in range(bussids.size): #jidx = where(job_array_labels == bussids[ib]) #job_building_id[jidx] = bldarray[ib] #home_based[jidx] = True #job_assignment_case[jidx] = 10 logger.log_status("10. %s jobs (%s businesses) in 6+ worker x multiple residential building. Not placed." % ( business_sizes[idx_more_workers[idx_sngl_wrk_fit]].sum(), idx_sngl_wrk_fit.size)) # 11. single workplace, 2+ workers in single non-res or mixed-use building (11.) idx_2plus_workers = where(logical_and(processed_bindicator==0, business_sizes > 1))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_2plus_workers]) workplace_filter = parcels.get_attribute_by_id("number_of_workplaces", businesses["parcel_id"][idx_2plus_workers]) idx_sngl_wrkplace_2plus_workers = where(logical_and(logical_or(bcode==3, bcode==5), workplace_filter==1))[0] which_labels = where(in1d(job_array_labels, businesses['business_id'][idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]]))[0] job_building_id[which_labels] = business_location1wrkpl[idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]].repeat(business_sizes[idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]]) job_assignment_case[which_labels] = 11 processed_bindicator[idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]] = True logger.log_status("11. %s jobs (%s businesses) could be placed due to single workplace x 2+ workers x single non-res/mixed-use building fit." % ( business_sizes[idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]].sum(), idx_sngl_wrkplace_2plus_workers.size)) # 12. single workplace, 2+ workers in multiple mixed-type building idx_2plus_workers = where(logical_and(processed_bindicator==0, business_sizes > 1))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_2plus_workers]) workplace_filter = parcels.get_attribute_by_id("number_of_workplaces", businesses["parcel_id"][idx_2plus_workers]) idx_sngl_wrkplace_2plus_workers = where(logical_and(logical_or(bcode==6, bcode==4), workplace_filter==1))[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]]) job_building_id[jidx] = business_location1wrkpl[idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]].repeat(business_sizes[idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]]) job_assignment_case[jidx] = 12 processed_bindicator[idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]] = True logger.log_status("12. %s jobs (%s businesses) could be placed due to single workplace x 2+ workers x multiple non-res/mixed building fit." % ( business_sizes[idx_2plus_workers[idx_sngl_wrkplace_2plus_workers]].sum(), idx_sngl_wrkplace_2plus_workers.size)) # 13. multiple workplaces, 2+ workers in single non-res or mixed building idx_2plus_workers = where(logical_and(processed_bindicator==0, business_sizes > 1))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_2plus_workers]) workplace_filter = parcels.get_attribute_by_id("number_of_workplaces", businesses["parcel_id"][idx_2plus_workers]) idx_mult_wrkplace_2plus_workers = where(logical_and(logical_or(bcode==3, bcode==5), workplace_filter > 1))[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_2plus_workers[idx_mult_wrkplace_2plus_workers]]) job_building_id[jidx] = business_location1wrkpl[idx_2plus_workers[idx_mult_wrkplace_2plus_workers]].repeat(business_sizes[idx_2plus_workers[idx_mult_wrkplace_2plus_workers]]) job_assignment_case[jidx] = 13 processed_bindicator[idx_2plus_workers[idx_mult_wrkplace_2plus_workers]] = True logger.log_status("13. %s jobs (%s businesses) could be placed due to multiple workplaces x 2+ workers x single non-res/mixed building fit." % ( business_sizes[idx_2plus_workers[idx_mult_wrkplace_2plus_workers]].sum(), idx_mult_wrkplace_2plus_workers.size)) # 14. multiple workplaces, 2+ workers in multiple non-res or mixed building idx_2plus_workers = where(logical_and(processed_bindicator==0, business_sizes > 1))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_2plus_workers]) workplace_filter = parcels.get_attribute_by_id("number_of_workplaces", businesses["parcel_id"][idx_2plus_workers]) idx_mult_wrkplace_2plus_workers = where(logical_and(logical_or(bcode==4, bcode==6), workplace_filter > 1))[0] processed_bindicator[idx_2plus_workers[idx_mult_wrkplace_2plus_workers]] = True # sample buildings to businesses by parcels bpcls = unique(businesses["parcel_id"][idx_2plus_workers[idx_mult_wrkplace_2plus_workers]]) hbasedsum = home_based.sum() for ipcl in range(bpcls.size): bldgids = buildings['building_id'][buildings['parcel_id'] == bpcls[ipcl]] bussids = businesses['business_id'][businesses["parcel_id"] == bpcls[ipcl]] if bldgids.size < bussids.size: bldarray = bldgids.repeat(1+ceil((bussids.size - bldgids.size)/float(bldgids.size))) else: bldarray = bldgids shuffle(bldarray) # randomly reorder in-place is_res = in1d(bldarray, restypes) for ib in range(bussids.size): jidx = where(job_array_labels == bussids[ib]) job_building_id[jidx] = bldarray[ib] home_based[jidx] = is_res job_assignment_case[jidx] = 14 logger.log_status("14. %s jobs (%s businesses) could be placed due to multiple workplaces x 2+ workers x multiple non-res/mixed building fit. Classify %s jobs as home-based." % ( business_sizes[idx_2plus_workers[idx_mult_wrkplace_2plus_workers]].sum(), idx_mult_wrkplace_2plus_workers.size, home_based.sum()-hbasedsum)) # 15. 6+ workers in residential parcel with no building idx_2plus_workers = where(logical_and(processed_bindicator==0, business_sizes > 5))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_2plus_workers]) idx_wrk_vacant_res = where(bcode == 7)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_2plus_workers[idx_wrk_vacant_res]]) job_assignment_case[jidx] = 15 processed_bindicator[idx_2plus_workers[idx_wrk_vacant_res]] = True logger.log_status("15. %s jobs (%s businesses of 6+ workers) could not be placed due to non-existing buildings in parcels with residential LU type." % ( business_sizes[idx_2plus_workers[idx_wrk_vacant_res]].sum(), idx_wrk_vacant_res.size)) # 16. nonresidential parcel with no building idx_any_workers = where(processed_bindicator==0)[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_any_workers]) idx_wrk_vacant_nonres = where(bcode == 8)[0] jidx = in1d(job_array_labels, businesses['business_id'][idx_any_workers[idx_wrk_vacant_nonres]]) job_assignment_case[jidx] = 16 processed_bindicator[idx_any_workers[idx_wrk_vacant_nonres]] = True logger.log_status("16. %s jobs (%s businesses) could not be placed due to non-existing buildings in parcels with rnon-esidential LU type." % ( business_sizes[idx_any_workers[idx_wrk_vacant_nonres]].sum(), idx_wrk_vacant_nonres.size)) # jobs in messy buildings idx_worker = where(logical_and(processed_bindicator==0, business_sizes > 0))[0] bcode = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"][idx_worker]) idx_messy_fit = where(bcode == 0)[0] processed_bindicator[idx_worker[idx_messy_fit]] = True logger.log_status("%s jobs (%s businesses) could not be placed due to messy buildings." % ( business_sizes[idx_worker[idx_messy_fit]].sum(), idx_messy_fit.size)) logger.log_status("So far %s (%s percent) home-based jobs." % (home_based.sum(), round(home_based.sum()/(home_based.size/100.),2))) logger.log_status("So far %s percent (%s) jobs (%s businesses) processed. %s jobs (%s businesses) remain to be processed." % \ (round(business_sizes[processed_bindicator].sum()/(home_based.size/100.),2), business_sizes[processed_bindicator].sum(), processed_bindicator.sum(), business_sizes[logical_not(processed_bindicator)].sum(), business_sizes[logical_not(processed_bindicator)].size)) # create job dataset job_data = {"job_id": arange(job_building_id.size)+1, "home_based" : home_based, "building_id": job_building_id, "business_id": job_array_labels, "sector_id": zeros(job_building_id.size), "parcel_id": zeros(job_building_id.size), "assignment_case": job_assignment_case} for ib in range(businesses.size()): idx = where(job_data['business_id'] == businesses['business_id'][ib]) job_data["sector_id"][idx] = businesses['sector_id'][ib] job_data["parcel_id"][idx] = businesses['parcel_id'][ib] dictstorage = StorageFactory().get_storage('dict_storage') dictstorage.write_table(table_name="jobs", table_data=job_data) return Dataset(in_storage=dictstorage, in_table_name="jobs", dataset_name="job", id_name="job_id")
def run(self, job_dataset, dataset_pool, out_storage=None, jobs_table="jobs"): """ Algorithm: 1. For all non_home_based jobs that have parcel_id assigned but no building_id, try to choose a building from all buildings in that parcel. Draw the building with probabilities given by the sector-building_type distribution. The job sizes are fitted into the available space (the attribute job.sqft is updated). 2. For all non_home_based jobs for which no building was found in step 1, check if the parcel has residential buildings. In such a case, re-assign the jobs to be home-based. Otherwise, if sum of non_residential_sqft over the involved buildings is 0, for all jobs that have impute_building_sqft_flag=True draw a building using the sector-building_type distribution and impute the corresponding sqft to the non_residential_sqft of that building. 3. For all home_based jobs that have parcel_id assigned but no building_id, try to choose a building from all buildings in that parcel. The capacity of a single-family building is determined from sizes of the households living there (for each household the minimum of number of members and 2 is taken). For multi-family buildings the capacity is 50. 4. Assign a building type to jobs that have missing building type. It is sampled from the regional-wide distribution of home based and non-home based jobs. 5. Update the table 'building_sqft_per_job' using the updated job.sqft. 'in_storage' should contain the jobs table and the zone_averages_table. The 'dataset_pool_storage' should contain all other tables needed (buildings, households, building_types). """ parcel_ids = job_dataset.get_attribute("parcel_id") building_ids = job_dataset.get_attribute("building_id") home_base_status = job_dataset.get_attribute("home_based_status") sectors = job_dataset.get_attribute("sector_id") is_considered = logical_and(parcel_ids > 0, building_ids <= 0) # jobs that have assigned parcel but not building job_index_home_based = where(logical_and(is_considered, home_base_status == 0))[0] is_governmental_job = sectors == 18 is_edu_job = sectors == 19 job_index_governmental = where(logical_and(is_considered, is_governmental_job))[0] job_index_edu = where(logical_and(is_considered, is_edu_job))[0] building_dataset = dataset_pool.get_dataset('building') parcel_ids_in_bldgs = building_dataset.get_attribute("parcel_id") bldg_ids_in_bldgs = building_dataset.get_id_attribute() bldg_types_in_bldgs = building_dataset.get_attribute("building_type_id") non_res_sqft = building_dataset.get_attribute("non_residential_sqft") preferred_nhb_btypes = (building_dataset['building.building_type_id'] == 3) + \ (building_dataset['building.building_type_id'] == 8) + \ (building_dataset['building.building_type_id'] == 13) + \ (building_dataset['building.building_type_id'] == 20) + \ (building_dataset['building.building_type_id'] == 21) non_res_sqft_preferred = non_res_sqft * preferred_nhb_btypes is_governmental = building_dataset.compute_variables([ "numpy.logical_and(building.disaggregate(building_type.generic_building_type_id == 7), building.building_type_id <> 18)"], dataset_pool=dataset_pool) idx_gov = where(is_governmental)[0] is_edu = building_dataset['building.building_type_id'] == 18 idx_edu = where(is_edu)[0] bldgs_is_residential = logical_and(logical_not(logical_or(is_governmental, is_edu)), building_dataset.compute_variables(["urbansim_parcel.building.is_residential"], dataset_pool=dataset_pool)) bldgs_isnot_residential = logical_not(bldgs_is_residential) # assign buildings to educational jobs randomly unique_parcels = unique(parcel_ids[job_index_edu]) logger.log_status("Placing educational jobs ...") for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs[idx_edu] == parcel)[0] if idx_in_bldgs.size <= 0: continue idx_in_jobs = where(parcel_ids[job_index_edu] == parcel)[0] draw = sample_replace(idx_in_bldgs, idx_in_jobs.size) building_ids[job_index_edu[idx_in_jobs]] = bldg_ids_in_bldgs[idx_edu[draw]] logger.log_status("%s educational jobs (out of %s edu. jobs) were placed." % ( (building_ids[job_index_edu]>0).sum(), job_index_edu.size)) # assign buildings to governmental jobs randomly unique_parcels = unique(parcel_ids[job_index_governmental]) logger.log_status("Placing governmental jobs ...") for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs[idx_gov] == parcel)[0] if idx_in_bldgs.size <= 0: continue idx_in_jobs = where(parcel_ids[job_index_governmental] == parcel)[0] draw = sample_replace(idx_in_bldgs, idx_in_jobs.size) building_ids[job_index_governmental[idx_in_jobs]] = bldg_ids_in_bldgs[idx_gov[draw]] logger.log_status("%s governmental jobs (out of %s gov. jobs) were placed." % ( (building_ids[job_index_governmental]>0).sum(), job_index_governmental.size)) logger.log_status("The unplaced governmental jobs will be added to the non-home based jobs.") #tmp = unique(parcel_ids[job_index_governmental][building_ids[job_index_governmental]<=0]) #output_dir = "/Users/hana" #write_to_text_file(os.path.join(output_dir, 'parcels_with_no_gov_bldg.txt'), tmp, delimiter='\n') # consider the unplaced governmental jobs together with other non-home-based jobs is_now_considered = logical_and(is_considered, building_ids <= 0) job_index_non_home_based = where(logical_and(is_now_considered, logical_or(home_base_status == 0, is_governmental_job)))[0] # assign buildings to non_home_based jobs based on available space unique_parcels = unique(parcel_ids[job_index_non_home_based]) # iterate over parcels logger.log_status("Placing non-home-based jobs ...") nhb_not_placed = 0 for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs == parcel)[0] if idx_in_bldgs.size <= 0: continue idx_in_jobs = where(parcel_ids[job_index_non_home_based] == parcel)[0] # sample proportionally to the building size weights = non_res_sqft_preferred[idx_in_bldgs] # 1.preference: preferred building types with non-res sqft if weights.sum() <= 0: weights = preferred_nhb_btypes[idx_in_bldgs] # 2.preference: preferred building types if weights.sum() <= 0: weights = non_res_sqft[idx_in_bldgs] # 3.preference: any building with non-res sqft if weights.sum() <= 0: weights = bldgs_isnot_residential[idx_in_bldgs] # 4.preference: any non-res building if weights.sum() <= 0: nhb_not_placed = nhb_not_placed + idx_in_jobs.size continue draw = probsample_replace(idx_in_bldgs, idx_in_jobs.size, weights/float(weights.sum())) building_ids[job_index_non_home_based[idx_in_jobs]] = bldg_ids_in_bldgs[draw] logger.log_status("%s non home based jobs (out of %s nhb jobs) were placed. No capacity in buildings for %s jobs." % ( (building_ids[job_index_non_home_based]>0).sum(), job_index_non_home_based.size, nhb_not_placed)) job_dataset.modify_attribute(name="building_id", data = building_ids) # re-classify unplaced non-home based jobs to home-based if parcels contain residential buildings is_now_considered = logical_and(parcel_ids > 0, building_ids <= 0) job_index_non_home_based_unplaced = where(logical_and(is_now_considered, logical_and(home_base_status == 0, logical_not(is_governmental_job))))[0] unique_parcels = unique(parcel_ids[job_index_non_home_based_unplaced]) logger.log_status("Try to reclassify non-home-based jobs (excluding governmental jobs) ...") nhb_reclass = 0 for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs == parcel)[0] if idx_in_bldgs.size <= 0: continue idx_in_jobs = where(parcel_ids[job_index_non_home_based_unplaced] == parcel)[0] where_residential = where(bldgs_is_residential[idx_in_bldgs])[0] if where_residential.size > 0: #home_base_status[job_index_non_home_based_unplaced[idx_in_jobs]] = 1 # set to home-based jobs nhb_reclass = nhb_reclass + idx_in_jobs.size else: draw = sample_replace(idx_in_bldgs, idx_in_jobs.size) #building_ids[job_index_non_home_based_unplaced[idx_in_jobs]] = bldg_ids_in_bldgs[draw] #job_dataset.modify_attribute(name="home_base_status", data = home_base_status) #job_dataset.modify_attribute(name="building_id", data = building_ids) job_index_home_based = where(logical_and(is_considered, home_base_status == 1))[0] logger.log_status("%s non-home based jobs reclassified as home-based." % nhb_reclass) # home_based jobs unique_parcels = unique(parcel_ids[job_index_home_based]) capacity_in_buildings = building_dataset.compute_variables([ "clip_to_zero(urbansim_parcel.building.total_home_based_job_space-building.aggregate(job.home_based_status==1))"], dataset_pool=dataset_pool) parcels_with_exceeded_capacity = [] # iterate over parcels logger.log_status("Placing home-based jobs ...") for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs == parcel)[0] idx_in_jobs = where(parcel_ids[job_index_home_based] == parcel)[0] capacity = capacity_in_buildings[idx_in_bldgs] if capacity.sum() <= 0: continue probcomb = ones((idx_in_bldgs.size, idx_in_jobs.size)) taken = zeros(capacity.shape, dtype="int32") while True: zero_cap = where((capacity - taken) <= 0)[0] probcomb[zero_cap,:] = 0 if probcomb.sum() <= 0: break req = probcomb.sum(axis=0) wmaxi = where(req==req.max())[0] drawjob = sample_noreplace(arange(wmaxi.size), 1) # draw job from available jobs imax_req = wmaxi[drawjob] weights = probcomb[:,imax_req] # sample building draw = probsample_noreplace(arange(probcomb.shape[0]), 1, resize(weights/weights.sum(), (probcomb.shape[0],))) taken[draw] = taken[draw] + 1 building_ids[job_index_home_based[idx_in_jobs[imax_req]]] = bldg_ids_in_bldgs[idx_in_bldgs[draw]] probcomb[:,imax_req] = 0 if -1 in building_ids[job_index_home_based[idx_in_jobs]]: parcels_with_exceeded_capacity.append(parcel) parcels_with_exceeded_capacity = array(parcels_with_exceeded_capacity) logger.log_status("%s home based jobs (out of %s hb jobs) were placed." % ((building_ids[job_index_home_based]>0).sum(), job_index_home_based.size)) # assign building type where missing # determine regional distribution idx_home_based = where(home_base_status == 1)[0] idx_non_home_based = where(home_base_status == 0)[0] idx_bt_missing = where(home_base_status <= 0)[0] if idx_bt_missing.size > 0: # sample building types sample_bt = probsample_replace(array([1,0]), idx_bt_missing.size, array([idx_home_based.size, idx_non_home_based.size])/float(idx_home_based.size + idx_non_home_based.size)) # coerce to int32 (on a 64 bit machine, sample_bt will be of type int64) home_base_status[idx_bt_missing] = sample_bt.astype(int32) job_dataset.modify_attribute(name="home_based_status", data = home_base_status) if out_storage is not None: job_dataset.write_dataset(out_table_name=jobs_table, out_storage=out_storage, attributes=AttributeType.PRIMARY) logger.log_status("Assigning building_id to jobs done.")
market_ids = m.choice_set.compute_one_variable_with_unknown_package( id_name, dataset_pool=dataset_pool) market_ids_2d = market_ids[m.model_interaction.get_choice_index()] model_data[i].update({'market_id':market_ids_2d, 'market_share':ms}) logger.end_block() training_data.append(model_data) config = xmlconfig.get_run_configuration(options.scenario_name) if not options.agents_index: agent_set = dataset_pool.get_dataset(options.agent_set) agents_size = agent_set.size() if options.agents_filter: is_valid = agent_set.compute_variables(options.agents_filter) options.agents_index = probsample_noreplace(arange(agents_size), options.sample_size, prob_array=is_valid ).tolist() else: options.agents_index = randint(0, agents_size, size=options.sample_size).tolist() ## regularization data population_data = [] for h, hierarchy in enumerate(options.meta_models): model_data = [] for i, model_name in enumerate(hierarchy): logger.start_block('%s' % model_name) config['models_configuration'][model_name]['controller']['run']['arguments']['agents_index'] = options.agents_index config['models'] = [{model_name:["run"]}] config['years'] = [options.year, options.year] config['seed'] = options.seed
def run(self, n=500, realestate_dataset_name='building', current_year=None, occupied_spaces_variable="occupied_spaces", total_spaces_variable="total_spaces", run_config=None, debuglevel=0): """ run method of the Development Project Proposal Sampling Model **Parameters** **n** : int, sample size for each iteration sample n proposals at a time, which are then evaluated one by one until the target vacancies are satisfied or proposals are running out **realestate_dataset_name** : string, name of real estate dataset **current_year**: int, simulation year. If None, get value from SimulationState **occupied_spaces_variable** : string, variable name for calculating how much spaces are currently occupied It can either be a variable for real_estate dataset that returns the amount spaces being occupied or a target_vacancy attribute that contains the name of real_estate variables. **total_spaces_variable** : string, variable name for calculating total existing spaces **Returns** **proposal_set** : indices to proposal_set that are accepted **demolished_buildings** : buildings to be demolished for re-development """ self.accepted_proposals = [] self.demolished_buildings = [] #id of buildings to be demolished if self.proposal_set.n <= 0: logger.log_status( "The size of proposal_set is 0; no proposals to consider, skipping DPPSM." ) return (self.proposal_set, self.demolished_buildings) target_vacancy = self.dataset_pool.get_dataset('target_vacancy') if current_year is None: year = SimulationState().get_current_time() else: year = current_year this_year_index = where(target_vacancy['year'] == year)[0] target_vacancy_for_this_year = DatasetSubset(target_vacancy, this_year_index) if target_vacancy_for_this_year.size() == 0: raise IOError, 'No target vacancy defined for year %s.' % year ## current_target_vacancy.target_attribute_name = 'target_vacancy_rate' ## each column provides a category for which a target vacancy is specified self.column_names = list(set( target_vacancy.get_known_attribute_names() ) - \ set( [ target_vacancy.target_attribute_name, 'year', '_hidden_id_', occupied_spaces_variable, total_spaces_variable ] ) ) self.column_names.sort(reverse=True) ## buildings table provides existing stocks self.realestate_dataset = self.dataset_pool.get_dataset( realestate_dataset_name) occupied_spaces_variables = [occupied_spaces_variable] total_spaces_variables = [total_spaces_variable] if occupied_spaces_variable in target_vacancy_for_this_year.get_known_attribute_names( ): occupied_spaces_variables += unique( target_vacancy_for_this_year[occupied_spaces_variable]).tolist( ) if total_spaces_variable in target_vacancy_for_this_year.get_known_attribute_names( ): total_spaces_variables += unique( target_vacancy_for_this_year[total_spaces_variable]).tolist() self._compute_variables_for_dataset_if_needed( self.realestate_dataset, self.column_names + occupied_spaces_variables + total_spaces_variables) self._compute_variables_for_dataset_if_needed( self.proposal_component_set, self.column_names + total_spaces_variables) self.proposal_set.compute_variables( "urbansim_parcel.development_project_proposal.number_of_components", dataset_pool=self.dataset_pool) n_column = len(self.column_names) target_vacancy_for_this_year.column_values = target_vacancy_for_this_year.get_multiple_attributes( self.column_names).reshape((-1, n_column)) self.realestate_dataset.column_values = self.realestate_dataset.get_multiple_attributes( self.column_names).reshape((-1, n_column)) self.proposal_component_set.column_values = self.proposal_component_set.get_multiple_attributes( self.column_names).reshape((-1, n_column)) #defaults, can be changed later by spaces_variable specified in target_vacancy rates self.realestate_dataset.total_spaces = self.realestate_dataset[ total_spaces_variable] self.proposal_component_set.total_spaces = self.proposal_component_set[ total_spaces_variable] self.realestate_dataset.occupied_spaces = self.realestate_dataset[ occupied_spaces_variable] self.accounting = {} self.logging = {} #has_needed_components = zeros(self.proposal_set.size(), dtype='bool') for index in range(target_vacancy_for_this_year.size()): column_value = tuple( target_vacancy_for_this_year.column_values[index, :].tolist()) accounting = { 'target_vacancy': target_vacancy_for_this_year[ target_vacancy.target_attribute_name][index] } realestate_indexes = self.get_index_by_condition( self.realestate_dataset.column_values, column_value) component_indexes = self.get_index_by_condition( self.proposal_component_set.column_values, column_value) this_total_spaces_variable, this_occupied_spaces_variable = total_spaces_variable, occupied_spaces_variable ## total/occupied_spaces_variable can be specified either as a universal name for all realestate ## or in targe_vacancy_rate dataset for each vacancy category if occupied_spaces_variable in target_vacancy_for_this_year.get_known_attribute_names( ): this_occupied_spaces_variable = target_vacancy_for_this_year[ occupied_spaces_variable][index] self.realestate_dataset.occupied_spaces[realestate_indexes] = ( self.realestate_dataset[this_occupied_spaces_variable] [realestate_indexes]).astype( self.realestate_dataset.occupied_spaces.dtype) if total_spaces_variable in target_vacancy_for_this_year.get_known_attribute_names( ): this_total_spaces_variable = target_vacancy_for_this_year[ total_spaces_variable][index] self.realestate_dataset.total_spaces[realestate_indexes] = ( self.realestate_dataset[this_total_spaces_variable] [realestate_indexes]).astype( self.realestate_dataset.total_spaces.dtype) self.proposal_component_set.total_spaces[component_indexes] = ( self.proposal_component_set[this_total_spaces_variable] [component_indexes]).astype( self.proposal_component_set.total_spaces.dtype) accounting["total_spaces_variable"] = this_total_spaces_variable accounting["total_spaces"] = self.realestate_dataset.total_spaces[ realestate_indexes].sum() accounting[ "occupied_spaces_variable"] = this_occupied_spaces_variable accounting[ "occupied_spaces"] = self.realestate_dataset.occupied_spaces[ realestate_indexes].sum() accounting["target_spaces"] = int( round( accounting["occupied_spaces"] /\ (1 - accounting["target_vacancy"]) ) ) accounting["proposed_spaces"] = 0 accounting["demolished_spaces"] = 0 self.accounting[column_value] = accounting if self._is_target_reached(column_value): proposal_indexes = self.proposal_set.get_id_index( unique(self.proposal_component_set['proposal_id'] [component_indexes])) single_component_indexes = where( self.proposal_set["number_of_components"] == 1)[0] self.weight[intersect1d(proposal_indexes, single_component_indexes)] = 0.0 ## handle planned proposals: all proposals with status_id == is_planned ## and start_year == year are accepted planned_proposal_indexes = where( logical_and( self.proposal_set.get_attribute("status_id") == self.proposal_set.id_planned, self.proposal_set.get_attribute("start_year") == year))[0] self.consider_proposals(planned_proposal_indexes, force_accepting=True) # consider proposals (in this order: proposed, tentative) for status in [ self.proposal_set.id_proposed, self.proposal_set.id_tentative ]: stat = (self.proposal_set.get_attribute("status_id") == status) if stat.sum() == 0: continue logger.log_status( "Sampling from %s eligible proposals of status %s." % (stat.sum(), status)) iteration = 0 while (not self._is_target_reached()): ## prevent proposals from being sampled for vacancy type whose target is reached #for column_value in self.accounting.keys(): if self.weight[stat].sum() == 0.0: logger.log_warning( "Running out of proposals of status %s before vacancy targets are reached; there aren't any proposals with non-zero weight" % status) break available_indexes = where(logical_and(stat, self.weight > 0))[0] sample_size = minimum(available_indexes.size, n) sampled_proposal_indexes = probsample_noreplace( available_indexes, sample_size, prob_array=self.weight[available_indexes], return_index=False) self.consider_proposals(sampled_proposal_indexes) self.weight[sampled_proposal_indexes] = 0 #sample_size = 1 #sampled_proposal_index = probsample_noreplace(available_indexes, sample_size, #prob_array=self.weight[available_indexes], #return_index=False) #self.consider_proposal(sampled_proposal_index) #self.weight[sampled_proposal_index] = 0 iteration += 1 self._log_status() # set status of accepted proposals to 'active' self.proposal_set.modify_attribute(name="status_id", data=self.proposal_set.id_active, index=array(self.accepted_proposals, dtype='int32')) # Code added by Jesse Ayers, MAG, 7/20/2009 # Get the active projects: stat_id = self.proposal_set.get_attribute('status_id') actv = where(stat_id == 1)[0] # Where there are active projects, compute the total_land_area_taken # and store it on the development_project_proposals dataset # so it can be used by the building_construction_model for the proper # computation of units_proposed for those projects with velocity curves if actv.size > 0: total_land_area_taken_computed = self.proposal_set.get_attribute( 'urbansim_parcel.development_project_proposal.land_area_taken') self.proposal_set.modify_attribute( 'total_land_area_taken', total_land_area_taken_computed[actv], actv) return (self.proposal_set, self.realestate_dataset.get_id_attribute()[ self.demolished_buildings])
def run(self, n=500, realestate_dataset_name = 'building', current_year=None, occupied_spaces_variable="occupied_spaces", total_spaces_variable="total_spaces", minimum_spaces_attribute="minimum_spaces", within_parcel_selection_weight_string=None, within_parcel_selection_n=0, within_parcel_selection_compete_among_types=False, within_parcel_selection_threshold=75, within_parcel_selection_MU_same_weight=False, within_parcel_selection_transpose_interpcl_weight=True, run_config=None, debuglevel=0): """ run method of the Development Project Proposal Sampling Model **Parameters** **n** : int, sample size for each iteration sample n proposals at a time, which are then evaluated one by one until the target vacancies are satisfied or proposals are running out **realestate_dataset_name** : string, name of real estate dataset **current_year**: int, simulation year. If None, get value from SimulationState **occupied_spaces_variable** : string, variable name for calculating how much spaces are currently occupied It can either be a variable for real_estate dataset that returns the amount spaces being occupied or a target_vacancy attribute that contains the name of real_estate variables. **total_spaces_variable** : string, variable name for calculating total existing spaces **Returns** **proposal_set** : indices to proposal_set that are accepted **demolished_buildings** : buildings to be demolished for re-development """ self.accepted_proposals = [] self.demolished_buildings = [] #id of buildings to be demolished if self.proposal_set.n <= 0: logger.log_status("The size of proposal_set is 0; no proposals to consider, skipping DPPSM.") return (self.proposal_set, self.demolished_buildings) target_vacancy = self.dataset_pool.get_dataset('target_vacancy') if current_year is None: year = SimulationState().get_current_time() else: year = current_year this_year_index = where(target_vacancy['year']==year)[0] target_vacancy_for_this_year = DatasetSubset(target_vacancy, this_year_index) if target_vacancy_for_this_year.size() == 0: raise IOError, 'No target vacancy defined for year %s.' % year ## current_target_vacancy.target_attribute_name = 'target_vacancy_rate' ## each column provides a category for which a target vacancy is specified self.column_names = list(set( target_vacancy.get_known_attribute_names() ) - \ set( [ target_vacancy.target_attribute_name, 'year', '_hidden_id_', minimum_spaces_attribute, occupied_spaces_variable, total_spaces_variable ] ) ) self.column_names.sort(reverse=True) ## buildings table provides existing stocks self.realestate_dataset = self.dataset_pool.get_dataset(realestate_dataset_name) occupied_spaces_variables = [occupied_spaces_variable] total_spaces_variables = [total_spaces_variable] if occupied_spaces_variable in target_vacancy_for_this_year.get_known_attribute_names(): occupied_spaces_variables += unique(target_vacancy_for_this_year[occupied_spaces_variable]).tolist() if total_spaces_variable in target_vacancy_for_this_year.get_known_attribute_names(): total_spaces_variables += unique(target_vacancy_for_this_year[total_spaces_variable]).tolist() self._compute_variables_for_dataset_if_needed(self.realestate_dataset, self.column_names + occupied_spaces_variables + total_spaces_variables) self._compute_variables_for_dataset_if_needed(self.proposal_component_set, self.column_names + total_spaces_variables) self.proposal_set.compute_variables(["urbansim_parcel.development_project_proposal.number_of_components", "urbansim_parcel.development_project_proposal.land_area_taken"], dataset_pool=self.dataset_pool) n_column = len(self.column_names) self.column_names_index = {} for iname in range(n_column): self.column_names_index[self.column_names[iname]] = iname target_vacancy_for_this_year.column_values = target_vacancy_for_this_year.get_multiple_attributes(self.column_names).reshape((-1, n_column)) self.realestate_dataset.column_values = self.realestate_dataset.get_multiple_attributes(self.column_names).reshape((-1, n_column)) self.proposal_component_set.column_values = self.proposal_component_set.get_multiple_attributes(self.column_names).reshape((-1, n_column)) #defaults, can be changed later by spaces_variable specified in target_vacancy rates self.realestate_dataset.total_spaces = self.realestate_dataset[total_spaces_variable] self.proposal_component_set.total_spaces = self.proposal_component_set[total_spaces_variable] self.realestate_dataset.occupied_spaces = self.realestate_dataset[occupied_spaces_variable] self.accounting = {}; self.logging = {} #has_needed_components = zeros(self.proposal_set.size(), dtype='bool') for index in range(target_vacancy_for_this_year.size()): column_value = tuple(target_vacancy_for_this_year.column_values[index,:].tolist()) accounting = {'target_vacancy': target_vacancy_for_this_year[target_vacancy.target_attribute_name][index]} if minimum_spaces_attribute in target_vacancy_for_this_year.get_known_attribute_names(): accounting['minimum_spaces'] = target_vacancy_for_this_year[minimum_spaces_attribute][index] realestate_indexes = self.get_index_by_condition(self.realestate_dataset.column_values, column_value) component_indexes = self.get_index_by_condition(self.proposal_component_set.column_values, column_value) this_total_spaces_variable, this_occupied_spaces_variable = total_spaces_variable, occupied_spaces_variable ## total/occupied_spaces_variable can be specified either as a universal name for all realestate ## or in targe_vacancy_rate dataset for each vacancy category if occupied_spaces_variable in target_vacancy_for_this_year.get_known_attribute_names(): this_occupied_spaces_variable = target_vacancy_for_this_year[occupied_spaces_variable][index] self.realestate_dataset.occupied_spaces[realestate_indexes] = (self.realestate_dataset[this_occupied_spaces_variable][realestate_indexes] ).astype(self.realestate_dataset.occupied_spaces.dtype) if total_spaces_variable in target_vacancy_for_this_year.get_known_attribute_names(): this_total_spaces_variable = target_vacancy_for_this_year[total_spaces_variable][index] self.realestate_dataset.total_spaces[realestate_indexes] = (self.realestate_dataset[this_total_spaces_variable][realestate_indexes] ).astype(self.realestate_dataset.total_spaces.dtype) self.proposal_component_set.total_spaces[component_indexes] = (self.proposal_component_set[this_total_spaces_variable][component_indexes] ).astype(self.proposal_component_set.total_spaces.dtype) accounting["total_spaces_variable"] = this_total_spaces_variable accounting["total_spaces"] = self.realestate_dataset.total_spaces[realestate_indexes].sum() accounting["occupied_spaces_variable"] = this_occupied_spaces_variable accounting["occupied_spaces"] = self.realestate_dataset.occupied_spaces[realestate_indexes].sum() accounting["target_spaces"] = int( round( accounting["occupied_spaces"] /\ (1 - accounting["target_vacancy"]) ) ) accounting["proposed_spaces"] = 0 accounting["demolished_spaces"] = 0 self.accounting[column_value] = accounting if self._is_target_reached(column_value): proposal_indexes = self.proposal_set.get_id_index(unique(self.proposal_component_set['proposal_id'][component_indexes])) if n_column == 1: comp_indexes = where(ndimage.sum(self.proposal_component_set[self.column_names[0]]==column_value[0], labels=self.proposal_component_set['proposal_id'], index=self.proposal_set.get_id_attribute() ) == self.proposal_set["number_of_components"])[0] else: comp_indexes = where(self.proposal_set["number_of_components"]==1)[0] target_reached_prop_idx = intersect1d(proposal_indexes, comp_indexes) self.weight[target_reached_prop_idx] = 0.0 self.proposal_set["status_id"][intersect1d(target_reached_prop_idx, where(self.proposal_set["status_id"]==self.proposal_set.id_tentative)[0])] = self.proposal_set.id_no_demand ## handle planned proposals: all proposals with status_id == is_planned ## and start_year == year are accepted planned_proposal_indexes = where(logical_and( self.proposal_set.get_attribute("status_id") == self.proposal_set.id_planned, self.proposal_set.get_attribute("start_year") == year ) )[0] logger.start_block("Processing %s planned proposals" % planned_proposal_indexes.size) self.consider_proposals(planned_proposal_indexes, force_accepting=True) logger.end_block() if within_parcel_selection_n > 0: logger.start_block("Selecting proposals within parcels (%s proposals per parcel)" % within_parcel_selection_n) self.select_proposals_within_parcels(nmax=within_parcel_selection_n, weight_string=within_parcel_selection_weight_string, compete_among_types=within_parcel_selection_compete_among_types, filter_threshold=within_parcel_selection_threshold, MU_same_weight=within_parcel_selection_MU_same_weight, transpose_interpcl_weight=within_parcel_selection_transpose_interpcl_weight) logger.end_block() # consider proposals (in this order: proposed, tentative) for status in [self.proposal_set.id_proposed, self.proposal_set.id_tentative]: stat = (self.proposal_set.get_attribute("status_id") == status) if stat.sum() == 0: continue logger.log_status("Sampling from %s eligible proposals of status %s." % (stat.sum(), status)) iteration = 0 while (not self._is_target_reached()): ## prevent proposals from being sampled for vacancy type whose target is reached #for column_value in self.accounting.keys(): if self.weight[stat].sum() == 0.0: logger.log_warning("Running out of proposals of status %s before vacancy targets are reached; there aren't any proposals with non-zero weight" % status) break available_indexes = where(logical_and(stat, self.weight > 0))[0] sample_size = minimum(available_indexes.size, n) sampled_proposal_indexes = probsample_noreplace(available_indexes, sample_size, prob_array=self.weight[available_indexes], return_index=False) #sorted_sampled_indices = argsort(self.weight[sampled_proposal_indexes]) #self.consider_proposals(sampled_proposal_indexes[sorted_sampled_indices][::-1]) self.consider_proposals(sampled_proposal_indexes) self.weight[sampled_proposal_indexes] = 0 iteration += 1 self._log_status() # set status of accepted proposals to 'active' self.proposal_set.modify_attribute(name="status_id", data=self.proposal_set.id_active, index=array(self.accepted_proposals, dtype='int32')) # Code added by Jesse Ayers, MAG, 7/20/2009 # Get the active projects: stat_id = self.proposal_set.get_attribute('status_id') actv = where(stat_id==1)[0] # Where there are active projects, compute the total_land_area_taken # and store it on the development_project_proposals dataset # so it can be used by the building_construction_model for the proper # computation of units_proposed for those projects with velocity curves if actv.size > 0: total_land_area_taken_computed = self.proposal_set['land_area_taken'] self.proposal_set.modify_attribute('total_land_area_taken', total_land_area_taken_computed[actv], actv) return (self.proposal_set, self.realestate_dataset.get_id_attribute()[self.demolished_buildings])
def run(self, run_choice_model=True, choose_job_only_in_residence_zone=False, residence_id='zone_id', *args, **kwargs): agent_set = kwargs['agent_set'] agents_index = kwargs.get('agents_index', None) if agents_index is None: agents_index = arange(agent_set.size()) if agents_index.size <= 0: logger.log_status("Nothing to be done.") return if self.filter is not None: jobs_set_index = where( self.job_set.compute_variables(self.filter) )[0] else: jobs_set_index = arange( self.job_set.size() ) if run_choice_model: choices = ChoiceModel.run(self, *args, **kwargs) if self.match_number_of_jobs: prob_work_at_home = self.upc_sequence.probabilities[:, 1] # sample as many workers as there are jobs draw = probsample_noreplace(arange(agents_index.size), min(agents_index.size, jobs_set_index.size), prob_work_at_home) choices = zeros(agents_index.size, dtype='int32') choices[draw] = 1 agent_set.set_values_of_one_attribute(self.choice_attribute_name, choices, index=agents_index) at_home_worker_index = agents_index[choices==1] logger.log_status("%s workers choose to work at home, %s workers chose to work out of home." % (where(agent_set.get_attribute_by_index(self.choice_attribute_name, agents_index) == 1)[0].size, where(agent_set.get_attribute_by_index(self.choice_attribute_name, agents_index) == 0)[0].size)) else: at_home_worker_index = where(logical_and( agent_set.get_attribute(self.choice_attribute_name) == 1, agent_set.get_attribute('job_id') <= 0 ) )[0] logger.log_status("Total: %s workers work at home, (%s workers work out of home), will try to assign %s workers to %s jobs." % (where(agent_set.get_attribute(self.choice_attribute_name) == 1)[0].size, where(agent_set.get_attribute(self.choice_attribute_name) == 0)[0].size, at_home_worker_index.size, jobs_set_index.size )) if not choose_job_only_in_residence_zone: assigned_worker_index, assigned_job_index = self._assign_job_to_worker(at_home_worker_index, jobs_set_index) else: agent_set.compute_one_variable_with_unknown_package(residence_id, dataset_pool=self.dataset_pool) self.job_set.compute_one_variable_with_unknown_package(residence_id, dataset_pool=self.dataset_pool) agent_zone_ids = agent_set.get_attribute_by_index(residence_id, at_home_worker_index) job_zone_ids = self.job_set.get_attribute_by_index(residence_id, jobs_set_index) unique_zones = unique(job_zone_ids) assigned_worker_index = array([], dtype="int32") assigned_job_index = array([], dtype="int32") for this_zone in unique_zones: logger.log_status("%s: %s" % (residence_id, this_zone)) if this_zone <= 0: continue at_home_worker_in_this_zone = where(agent_zone_ids == this_zone)[0] job_set_in_this_zone = where(job_zone_ids == this_zone)[0] assigned_worker_in_this_zone, assigned_job_set_in_this_zone = self._assign_job_to_worker(at_home_worker_in_this_zone, job_set_in_this_zone) assigned_worker_index = concatenate((assigned_worker_index, at_home_worker_index[assigned_worker_in_this_zone])) assigned_job_index = concatenate((assigned_job_index, jobs_set_index[assigned_job_set_in_this_zone])) ## each worker can only be assigned to 1 job #assert assigned_worker_index.size == unique(assigned_worker_index).size agent_set.set_values_of_one_attribute(self.job_set.get_id_name()[0], self.job_set.get_id_attribute()[assigned_job_index], index=assigned_worker_index) agent_set.compute_variables([self.location_id_name], dataset_pool=self.dataset_pool) self.job_set.modify_attribute(name=VariableName(self.location_id_name).get_alias(), data=agent_set.get_attribute_by_index(self.location_id_name, assigned_worker_index), index=assigned_job_index)
def run(self, dataset1, dataset2, index1=None, index2=None, sample_size=10, weight=None, include_chosen_choice=False, with_replacement=False, resources=None, dataset_pool=None): """this function samples number of sample_size (scalar value) alternatives from dataset2 for agent set specified by dataset1. If index1 is not None, only samples alterantives for agents with indices in index1; if index2 is not None, only samples alternatives from indices in index2. sample_size specifies number of alternatives to be sampled for each agent. weight, to be used as sampling weight, is either an attribute name of dataset2, or a 1d array of the same length as index2 or 2d array of shape (index1.size, index2.size). Also refer to document of interaction_dataset""" if dataset_pool is None: try: sc = SessionConfiguration() dataset_pool = sc.get_dataset_pool() except: dataset_pool = DatasetPool() local_resources = Resources(resources) local_resources.merge_if_not_None({ "dataset1": dataset1, "dataset2": dataset2, "index1": index1, "index2": index2, "sample_size": sample_size, "weight": weight, "with_replacement": with_replacement, "include_chosen_choice": include_chosen_choice }) local_resources.check_obligatory_keys( ['dataset1', 'dataset2', 'sample_size']) agent = local_resources["dataset1"] index1 = local_resources.get("index1", None) if index1 is None: index1 = arange(agent.size()) choice = local_resources["dataset2"] index2 = local_resources.get("index2", None) if index2 is None: index2 = arange(choice.size()) if index1.size == 0 or index2.size == 0: err_msg = "either choice size or agent size is zero, return None" logger.log_warning(err_msg) return None include_chosen_choice = local_resources.get("include_chosen_choice", False) J = local_resources["sample_size"] if include_chosen_choice: J = J - 1 with_replacement = local_resources.get("with_replacement") weight = local_resources.get("weight", None) if isinstance(weight, str): if weight in choice.get_known_attribute_names(): weight = choice.get_attribute(weight) rank_of_weight = 1 else: varname = VariableName(weight) if varname.get_dataset_name() == choice.get_dataset_name(): weight = choice.compute_variables( weight, dataset_pool=dataset_pool) rank_of_weight = 1 elif varname.get_interaction_set_names() is not None: ## weights can be an interaction variable interaction_dataset = InteractionDataset(local_resources) weight = interaction_dataset.compute_variables( weight, dataset_pool=dataset_pool) rank_of_weight = 2 assert (len(weight.shape) >= rank_of_weight) else: err_msg = ("weight is neither a known attribute name " "nor a simple variable from the choice dataset " "nor an interaction variable: '%s'" % weight) logger.log_error(err_msg) raise ValueError, err_msg elif isinstance(weight, ndarray): rank_of_weight = weight.ndim elif not weight: ## weight is None or empty string weight = ones(index2.size) rank_of_weight = 1 else: err_msg = "unkown weight type" logger.log_error(err_msg) raise TypeError, err_msg if (weight.size <> index2.size) and (weight.shape[rank_of_weight - 1] <> index2.size): if weight.shape[rank_of_weight - 1] == choice.size(): if rank_of_weight == 1: weight = take(weight, index2) if rank_of_weight == 2: weight = take(weight, index2, axis=1) else: err_msg = "weight array size doesn't match to size of dataset2 or its index" logger.log_error(err_msg) raise ValueError, err_msg prob = normalize(weight) #chosen_choice = ones(index1.size) * UNPLACED_ID chosen_choice_id = agent.get_attribute(choice.get_id_name()[0])[index1] #index_of_placed_agent = where(greater(chosen_choice_id, UNPLACED_ID))[0] chosen_choice_index = choice.try_get_id_index( chosen_choice_id, return_value_if_not_found=UNPLACED_ID) chosen_choice_index_to_index2 = lookup(chosen_choice_index, index2, index_if_not_found=UNPLACED_ID) if rank_of_weight == 1: # if weight_array is 1d, then each agent shares the same weight for choices replace = with_replacement # sampling with no replacement non_zero_counts = nonzerocounts(weight) if non_zero_counts < J: logger.log_warning( "weight array dosen't have enough non-zero counts, use sample with replacement" ) replace = True if non_zero_counts > 0: sampled_index = prob2dsample( index2, sample_size=(index1.size, J), prob_array=prob, exclude_index=chosen_choice_index_to_index2, replace=replace, return_index=True) else: # all alternatives have a zero weight sampled_index = zeros((index1.size, 0), dtype=DTYPE) #return index2[sampled_index] if rank_of_weight == 2: sampled_index = zeros((index1.size, J), dtype=DTYPE) - 1 for i in range(index1.size): replace = with_replacement # sampling with/without replacement i_prob = prob[i, :] if nonzerocounts(i_prob) < J: logger.log_warning( "weight array dosen't have enough non-zero counts, use sample with replacement" ) replace = True #exclude_index passed to probsample_noreplace needs to be indexed to index2 sampled_index[i, :] = probsample_noreplace( index2, sample_size=J, prob_array=i_prob, exclude_index=chosen_choice_index_to_index2[i], return_index=True) sampling_prob = take(prob, sampled_index) sampled_index_within_prob = sampled_index.copy() sampled_index = index2[sampled_index] is_chosen_choice = zeros(sampled_index.shape, dtype="bool") #chosen_choice = -1 * ones(chosen_choice_index.size, dtype="int32") if include_chosen_choice: sampled_index = column_stack( (chosen_choice_index[:, newaxis], sampled_index)) is_chosen_choice = zeros(sampled_index.shape, dtype="bool") is_chosen_choice[chosen_choice_index != UNPLACED_ID, 0] = 1 #chosen_choice[where(is_chosen_choice)[0]] = where(is_chosen_choice)[1] ## this is necessary because prob is indexed to index2, not to the choice set (as is chosen_choice_index) sampling_prob_for_chosen_choices = take( prob, chosen_choice_index_to_index2[:, newaxis]) ## if chosen choice chosen equals unplaced_id then the sampling prob is 0 sampling_prob_for_chosen_choices[where( chosen_choice_index == UNPLACED_ID)[0], ] = 0.0 sampling_prob = column_stack( [sampling_prob_for_chosen_choices, sampling_prob]) interaction_dataset = self.create_interaction_dataset( dataset1, dataset2, index1, sampled_index) interaction_dataset.add_attribute(sampling_prob, '__sampling_probability') interaction_dataset.add_attribute(is_chosen_choice, 'chosen_choice') if local_resources.get("include_mnl_bias_correction_term", False): if include_chosen_choice: sampled_index_within_prob = column_stack( (chosen_choice_index_to_index2[:, newaxis], sampled_index_within_prob)) interaction_dataset.add_mnl_bias_correction_term( prob, sampled_index_within_prob) ## to get the older returns #sampled_index = interaction_dataset.get_2d_index() #chosen_choices = UNPLACED_ID * ones(index1.size, dtype="int32") #where_chosen = where(interaction_dataset.get_attribute("chosen_choice")) #chosen_choices[where_chosen[0]]=where_chosen[1] #return (sampled_index, chosen_choice) return interaction_dataset
def run(self, in_storage, out_storage=None, business_dsname="business", zone_dsname=None): dataset_pool = DatasetPool(storage=in_storage, package_order=['psrc_parcel', 'urbansim_parcel', 'urbansim', 'opus_core'] ) seed(1) allbusinesses = dataset_pool.get_dataset(business_dsname) parcels = dataset_pool.get_dataset('parcel') buildings = dataset_pool.get_dataset('building') parcels.compute_variables(["urbansim_parcel.parcel.residential_units", "number_of_buildings = parcel.number_of_agents(building)", "non_residential_sqft = (parcel.aggregate(building.non_residential_sqft)).astype(int32)", "number_of_res_buildings = parcel.aggregate(urbansim_parcel.building.is_residential)", "number_of_nonres_buildings = parcel.aggregate(urbansim_parcel.building.is_non_residential)", "number_of_mixed_use_buildings = parcel.aggregate(urbansim_parcel.building.is_generic_building_type_6)" ], dataset_pool=dataset_pool) restypes = [12, 4, 19, 11, 34, 10, 33] reslutypes = [13,14,15,24] is_valid_business = ones(allbusinesses.size(), dtype='bool8') parcels_not_matched = logical_and(in1d(allbusinesses["parcel_id"], parcels.get_id_attribute(), invert=True), allbusinesses["parcel_id"] > 0) if(parcels_not_matched.sum() > 0): is_valid_business[where(parcels_not_matched)] = False logger.log_warning(message="No parcel exists for %s businesses (%s jobs)" % (parcels_not_matched.sum(), allbusinesses[self.number_of_jobs_attr][where(parcels_not_matched)].sum())) zero_parcel = allbusinesses["parcel_id"]<=0 if zero_parcel.sum() > 0: is_valid_business[where(zero_parcel)] = False logger.log_warning(message="%s businesses (%s jobs) located on zero parcel_id" % (zero_parcel.sum(), allbusinesses[self.number_of_jobs_attr][where(zero_parcel)].sum())) zero_size = logical_and(is_valid_business, allbusinesses[self.number_of_jobs_attr].round() == 0) if(sum(zero_size) > 0): is_valid_business[where(zero_size)] = False logger.log_warning(message="%s businesses are of size 0." % sum(zero_size)) businesses = DatasetSubset(allbusinesses, index=where(is_valid_business)[0]) parcels.add_attribute(name="number_of_workplaces", data=parcels.sum_dataset_over_ids(businesses, constant=1)) has_single_res_buildings = logical_and(parcels["number_of_buildings"] == 1, parcels["number_of_res_buildings"] == 1) # 1 (1 residential) parcels.add_attribute(data=has_single_res_buildings.astype("int32"), name="buildings_code") has_mult_res_buildings = logical_and(parcels["number_of_buildings"] > 1, parcels["number_of_nonres_buildings"] == 0) # 2 (mult residential) parcels.modify_attribute("buildings_code", data=2*ones(has_mult_res_buildings.sum()), index=where(has_mult_res_buildings)) has_single_nonres_buildings = logical_and(logical_and(parcels["number_of_buildings"] == 1, parcels["number_of_nonres_buildings"] == 1), parcels["number_of_mixed_use_buildings"] == 0) # 3 (1 non-res) parcels.modify_attribute("buildings_code", data=3*ones(has_single_nonres_buildings.sum()), index=where(has_single_nonres_buildings)) has_mult_nonres_buildings = logical_and(logical_and(parcels["number_of_buildings"] > 1, parcels["number_of_res_buildings"] == 0), parcels["number_of_mixed_use_buildings"] == 0) # 4 (mult non-res) parcels.modify_attribute("buildings_code", data=4*ones(has_mult_nonres_buildings.sum()), index=where(has_mult_nonres_buildings)) has_single_mixed_buildings = logical_and(parcels["number_of_buildings"] == 1, parcels["number_of_mixed_use_buildings"] == 1) # 5 (1 mixed-use) parcels.modify_attribute("buildings_code", data=5*ones(has_single_mixed_buildings.sum()), index=where(has_single_mixed_buildings)) has_mult_mixed_buildings = logical_and(parcels["number_of_buildings"] > 1, logical_or(logical_and(parcels["number_of_res_buildings"] > 0, parcels["number_of_nonres_buildings"] > 0), logical_or(parcels["number_of_mixed_use_buildings"] > 1, logical_and(parcels["number_of_res_buildings"] == 0, parcels["number_of_mixed_use_buildings"] > 0)))) # 6 parcels.modify_attribute("buildings_code", data=6*ones(has_mult_mixed_buildings.sum()), index=where(has_mult_mixed_buildings)) has_no_building_res_lutype = logical_and(parcels["number_of_buildings"] == 0, in1d(parcels["land_use_type_id"], reslutypes)) # 7 (vacant with res LU type) parcels.modify_attribute("buildings_code", data=7*ones(has_no_building_res_lutype.sum()), index=where(has_no_building_res_lutype)) has_no_building_nonres_lutype = logical_and(parcels["number_of_buildings"] == 0, in1d(parcels["land_use_type_id"], reslutypes)==0) # 8 (vacant with non-res LU type) parcels.modify_attribute("buildings_code", data=8*ones(has_no_building_nonres_lutype.sum()), index=where(has_no_building_nonres_lutype)) business_sizes = businesses[self.number_of_jobs_attr].round().astype("int32") business_location = {} business_location1wrkpl = zeros(businesses.size(), dtype="int32") business_location1wrkplres = zeros(businesses.size(), dtype="int32") business_ids = businesses.get_id_attribute() # sample one building for cases when sampling is required. for ibusid in range(businesses.size()): idx = where(buildings['parcel_id'] == businesses['parcel_id'][ibusid])[0] bldgids = buildings['building_id'][idx] business_location[business_ids[ibusid]] = bldgids if bldgids.size == 1: business_location1wrkpl[ibusid] = bldgids[0] elif bldgids.size > 1: business_location1wrkpl[ibusid] = bldgids[sample_noreplace(arange(bldgids.size), 1)] if buildings['residential_units'][idx].sum() > 0: # Residential buildings are sampled with probabilities proportional to residential units business_location1wrkplres[ibusid] = bldgids[probsample_noreplace(arange(bldgids.size), 1, prob_array=buildings['residential_units'][idx])] else: business_location1wrkplres[ibusid] = business_location1wrkpl[ibusid] home_based = zeros(business_sizes.sum(), dtype="bool8") job_building_id = zeros(business_sizes.sum(), dtype="int32") job_array_labels = business_ids.repeat(business_sizes) job_assignment_case = zeros(business_sizes.sum(), dtype="int32") processed_bindicator = zeros(businesses.size(), dtype="bool8") business_codes = parcels.get_attribute_by_id("buildings_code", businesses["parcel_id"]) business_nworkplaces = parcels.get_attribute_by_id("number_of_workplaces", businesses["parcel_id"]) logger.log_status("Total number of jobs: %s" % home_based.size) # 1. 1-2 worker business in 1 residential building idx_sngl_wrk_1bld_fit = where(logical_and(business_sizes < 3, business_codes == 1))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_1bld_fit]) home_based[jidx] = True job_building_id[jidx] = business_location1wrkpl[idx_sngl_wrk_1bld_fit].repeat(business_sizes[idx_sngl_wrk_1bld_fit]) job_assignment_case[jidx] = 1 processed_bindicator[idx_sngl_wrk_1bld_fit] = True logger.log_status("1. %s jobs (%s businesses) set as home-based due to 1-2 worker x 1 residential building fit." % ( business_sizes[idx_sngl_wrk_1bld_fit].sum(), idx_sngl_wrk_1bld_fit.size)) # 2. 1-2 worker business in multiple residential buildings idx_sngl_wrk_multbld_fit = where(logical_and(logical_and(processed_bindicator==0, business_sizes < 3), business_codes == 2))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_multbld_fit]) home_based[jidx] = True job_building_id[jidx] = business_location1wrkplres[idx_sngl_wrk_multbld_fit].repeat(business_sizes[idx_sngl_wrk_multbld_fit]) job_assignment_case[jidx] = 2 processed_bindicator[idx_sngl_wrk_multbld_fit] = True logger.log_status("2. %s jobs (%s businesses) set as home-based due to 1-2 worker x multiple residential buildings fit." % ( business_sizes[idx_sngl_wrk_multbld_fit].sum(), idx_sngl_wrk_multbld_fit.size)) # 3. 1-2 worker in single non-res building (not mixed-use) idx_sngl_wrk_single_nonres_fit = where(logical_and(logical_and(processed_bindicator==0, business_sizes < 3), business_codes == 3))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_single_nonres_fit]) job_building_id[jidx] = business_location1wrkpl[idx_sngl_wrk_single_nonres_fit].repeat(business_sizes[idx_sngl_wrk_single_nonres_fit]) job_assignment_case[jidx] = 3 processed_bindicator[idx_sngl_wrk_single_nonres_fit] = True logger.log_status("3. %s jobs (%s businesses) placed due to 1-2 worker x single non-res building fit." % ( business_sizes[idx_sngl_wrk_single_nonres_fit].sum(), idx_sngl_wrk_single_nonres_fit.size)) # 4. 1-2 worker in multiple non-res building (not mixed-use) idx_sngl_wrk_mult_nonres_fit = where(logical_and(logical_and(processed_bindicator==0, business_sizes < 3), business_codes == 4))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_mult_nonres_fit]) job_building_id[jidx] = business_location1wrkpl[idx_sngl_wrk_mult_nonres_fit].repeat(business_sizes[idx_sngl_wrk_mult_nonres_fit]) job_assignment_case[jidx] = 4 processed_bindicator[idx_sngl_wrk_mult_nonres_fit] = True logger.log_status("4. %s jobs (%s businesses) placed due to 1-2 worker x multiple non-res building fit." % ( business_sizes[idx_sngl_wrk_mult_nonres_fit].sum(), idx_sngl_wrk_mult_nonres_fit.size)) # 5. 1-2 worker in single mixed-use building idx_sngl_wrk_smu_fit = where(logical_and(logical_and(processed_bindicator==0, business_sizes < 3), business_codes == 5))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_smu_fit]) job_building_id[jidx] = business_location1wrkpl[idx_sngl_wrk_smu_fit].repeat(business_sizes[idx_sngl_wrk_smu_fit]) job_assignment_case[jidx] = 5 processed_bindicator[idx_sngl_wrk_smu_fit] = True logger.log_status("5. %s jobs (%s businesses) in 1-2 worker x single mixed-use building." % ( business_sizes[idx_sngl_wrk_smu_fit].sum(), idx_sngl_wrk_smu_fit.size)) # 6. 1-2 worker in multiple mixed-type buildings idx_sngl_wrk_mmu_fit = where(logical_and(logical_and(processed_bindicator==0, business_sizes < 3), business_codes == 6))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_mmu_fit]) job_building_id[jidx] = business_location1wrkpl[idx_sngl_wrk_mmu_fit].repeat(business_sizes[idx_sngl_wrk_mmu_fit]) bldtype = buildings.get_attribute_by_id("building_type_id", business_location1wrkpl[idx_sngl_wrk_mmu_fit]) is_bldtype_res = in1d(bldtype, restypes) home_based[in1d(job_array_labels, business_ids[idx_sngl_wrk_mmu_fit][where(is_bldtype_res)])] = True job_assignment_case[jidx] = 6 processed_bindicator[idx_sngl_wrk_mmu_fit] = True logger.log_status("6. %s jobs (%s businesses) in 1-2 worker x multiple mixed-type buildings. %s jobs classified as home-based." % ( business_sizes[idx_sngl_wrk_mmu_fit].sum(), idx_sngl_wrk_mmu_fit.size, business_sizes[idx_sngl_wrk_mmu_fit][where(is_bldtype_res)].sum())) # 7. 1-2 worker business in residential parcel with no building idx_sngl_wrk_vacant_res = where(logical_and(logical_and(processed_bindicator==0, business_sizes < 3), business_codes == 7))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_vacant_res]) job_assignment_case[jidx] = 7 home_based[jidx] = True processed_bindicator[idx_sngl_wrk_vacant_res] = True logger.log_status("7. %s jobs (%s businesses of size 1-2) could not be placed due to non-existing buildings in parcels with residential LU type." % ( business_sizes[idx_sngl_wrk_vacant_res].sum(), idx_sngl_wrk_vacant_res.size)) # 8. 3+ workers of governmental workplaces in 1+ residential building ind_bussiness_case8 = logical_and(logical_and(processed_bindicator==0, logical_and(business_sizes > 2, in1d(businesses['sector_id'], [18,19]))), in1d(business_codes, [1,2])) idx_wrk_fit = where(ind_bussiness_case8)[0] jidx = in1d(job_array_labels, business_ids[idx_wrk_fit]) job_assignment_case[jidx] = 8 processed_bindicator[idx_wrk_fit] = True logger.log_status("8. %s governmental jobs (%s businesses of size 3+) could not be placed due to residing in residential buildings only." % ( business_sizes[idx_wrk_fit].sum(), idx_wrk_fit.size)) # 9. 3-30 workers in single residential building. Make two of them home based. idx_sngl_wrk_fit = where(logical_and(logical_and(processed_bindicator==0, logical_and(business_sizes > 2, business_sizes <= 30)), business_codes == 1))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_fit]) job_building_id[jidx] = business_location1wrkpl[idx_sngl_wrk_fit].repeat(business_sizes[idx_sngl_wrk_fit]) bsizeminus2 = vstack((2*ones(idx_sngl_wrk_fit.size), business_sizes[idx_sngl_wrk_fit]-2)).ravel("F").astype("int32") # interweaving 2 and remaining business size hbidx = tile(array([True, False]), bsizeminus2.size/2).repeat(bsizeminus2) # set the first two jobs of every business to True, others to False home_based[(where(jidx)[0])[hbidx]] = True job_assignment_case[jidx] = 9 processed_bindicator[idx_sngl_wrk_fit] = True logger.log_status("9. %s jobs (%s businesses) in 3-30 worker x single residential building. %s jobs assigned as home-based." % ( business_sizes[idx_sngl_wrk_fit].sum(), idx_sngl_wrk_fit.size, hbidx.sum())) # 10. 3-30 workers in multiple residential buildings. Make two of them home based. idx_sngl_wrk_fit = where(logical_and(logical_and(processed_bindicator==0, logical_and(business_sizes > 2, business_sizes <= 30)), business_codes == 2))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrk_fit]) job_assignment_case[jidx] = 10 processed_bindicator[idx_sngl_wrk_fit] = True # sample buildings to businesses by parcels bpcls = unique(businesses["parcel_id"][idx_sngl_wrk_fit]) for ipcl in range(bpcls.size): bidx = where(buildings['parcel_id'] == bpcls[ipcl])[0] bldgids = buildings['building_id'][bidx] bussids = intersect1d(business_ids[businesses["parcel_id"] == bpcls[ipcl]], business_ids[idx_sngl_wrk_fit]) # multiply by units for sampling prop. to units rather than buildings bldgids = bldgids.repeat(maximum(1, buildings['residential_units'][bidx].astype('int32'))) if bldgids.size < bussids.size: bldarray = bldgids.repeat(1+ceil((bussids.size - bldgids.size)/float(bldgids.size)) ) else: bldarray = bldgids shuffle(bldarray) # randomly reorder in-place for ib in range(bussids.size): jidx = where(job_array_labels == bussids[ib])[0] job_building_id[jidx] = bldarray[ib] home_based[jidx[0:2]] = True logger.log_status("10. %s jobs (%s businesses) in 3-30 worker x multiple residential building. %s jobs assigned as home-based." % ( business_sizes[idx_sngl_wrk_fit].sum(), idx_sngl_wrk_fit.size, idx_sngl_wrk_fit.size*2)) # 11. single workplace, 3+ workers in single non-res or mixed-use building (11.) idx_sngl_wrkplace_2plus_workers = where(logical_and(logical_and(logical_and(processed_bindicator==0, business_sizes > 2), logical_or(business_codes==3, business_codes==5)), business_nworkplaces==1))[0] which_labels = where(in1d(job_array_labels, business_ids[idx_sngl_wrkplace_2plus_workers]))[0] job_building_id[which_labels] = business_location1wrkpl[idx_sngl_wrkplace_2plus_workers].repeat(business_sizes[idx_sngl_wrkplace_2plus_workers]) job_assignment_case[which_labels] = 11 processed_bindicator[idx_sngl_wrkplace_2plus_workers] = True logger.log_status("11. %s jobs (%s businesses) could be placed due to single workplace x 3+ workers x single non-res/mixed-use building fit." % ( business_sizes[idx_sngl_wrkplace_2plus_workers].sum(), idx_sngl_wrkplace_2plus_workers.size)) # 12. single workplace, 3+ workers in multiple mixed-type building idx_sngl_wrkplace_2plus_workers = where(logical_and(logical_and(logical_and(processed_bindicator==0, business_sizes > 2), logical_or(business_codes==4, business_codes==6)), business_nworkplaces==1))[0] jidx = in1d(job_array_labels, business_ids[idx_sngl_wrkplace_2plus_workers]) job_building_id[jidx] = business_location1wrkpl[idx_sngl_wrkplace_2plus_workers].repeat(business_sizes[idx_sngl_wrkplace_2plus_workers]) job_assignment_case[jidx] = 12 processed_bindicator[idx_sngl_wrkplace_2plus_workers] = True logger.log_status("12. %s jobs (%s businesses) could be placed due to single workplace x 3+ workers x multiple non-res/mixed building fit." % ( business_sizes[idx_sngl_wrkplace_2plus_workers].sum(), idx_sngl_wrkplace_2plus_workers.size)) # 13. multiple workplaces, 3+ workers in single non-res or mixed building idx_mult_wrkplace_2plus_workers = where(logical_and(logical_and(logical_and(processed_bindicator==0, business_sizes > 2), logical_or(business_codes==3, business_codes==5)), business_nworkplaces > 1))[0] jidx = in1d(job_array_labels, business_ids[idx_mult_wrkplace_2plus_workers]) job_building_id[jidx] = business_location1wrkpl[idx_mult_wrkplace_2plus_workers].repeat(business_sizes[idx_mult_wrkplace_2plus_workers]) job_assignment_case[jidx] = 13 processed_bindicator[idx_mult_wrkplace_2plus_workers] = True logger.log_status("13. %s jobs (%s businesses) could be placed due to multiple workplaces x 3+ workers x single non-res/mixed building fit." % ( business_sizes[idx_mult_wrkplace_2plus_workers].sum(), idx_mult_wrkplace_2plus_workers.size)) # 14. multiple workplaces, 3+ workers in multiple non-res or mixed building idx_mult_wrkplace_2plus_workers = where(logical_and(logical_and(logical_and(processed_bindicator==0, business_sizes > 2), logical_or(business_codes==4, business_codes==6)), business_nworkplaces > 1))[0] processed_bindicator[idx_mult_wrkplace_2plus_workers] = True # sample buildings to businesses by parcels bpcls = unique(businesses["parcel_id"][idx_mult_wrkplace_2plus_workers]) #hbasedsum = home_based.sum() for ipcl in range(bpcls.size): bldgids = buildings['building_id'][buildings['parcel_id'] == bpcls[ipcl]] bussids = intersect1d(business_ids[businesses["parcel_id"] == bpcls[ipcl]], business_ids[idx_mult_wrkplace_2plus_workers]) if bldgids.size < bussids.size: bldarray = bldgids.repeat(1+ceil((bussids.size - bldgids.size)/float(bldgids.size))) else: bldarray = bldgids shuffle(bldarray) # randomly reorder in-place is_res = in1d(bldarray, restypes) for ib in range(bussids.size): jidx = where(job_array_labels == bussids[ib]) job_building_id[jidx] = bldarray[ib] #home_based[jidx] = is_res job_assignment_case[jidx] = 14 logger.log_status("14. %s jobs (%s businesses) could be placed due to multiple workplaces x 3+ workers x multiple non-res/mixed building fit." % ( business_sizes[idx_mult_wrkplace_2plus_workers].sum(), idx_mult_wrkplace_2plus_workers.size)) # 15. 3+ workers in residential parcel with no building idx_wrk_vacant_res = where(logical_and(logical_and(processed_bindicator==0, business_sizes > 2), business_codes == 7))[0] jidx = in1d(job_array_labels, business_ids[idx_wrk_vacant_res]) job_assignment_case[jidx] = 15 processed_bindicator[idx_wrk_vacant_res] = True logger.log_status("15. %s jobs (%s businesses of 3+ workers) could not be placed due to non-existing buildings in parcels with residential LU type." % ( business_sizes[idx_wrk_vacant_res].sum(), idx_wrk_vacant_res.size)) # 16. nonresidential parcel with no building idx_wrk_vacant_nonres = where(logical_and(processed_bindicator==0, business_codes == 8))[0] jidx = in1d(job_array_labels, business_ids[idx_wrk_vacant_nonres]) job_assignment_case[jidx] = 16 processed_bindicator[idx_wrk_vacant_nonres] = True logger.log_status("16. %s jobs (%s businesses) could not be placed due to non-existing buildings in parcels with non-esidential LU type." % ( business_sizes[idx_wrk_vacant_nonres].sum(), idx_wrk_vacant_nonres.size)) # 17. 31+ workers in single residential building. Do not place - will go into ELCM. idx_wrk_fit = where(logical_and(logical_and(processed_bindicator==0, business_sizes > 30), business_codes == 1))[0] jidx = in1d(job_array_labels, business_ids[idx_wrk_fit]) job_assignment_case[jidx] = 17 processed_bindicator[idx_wrk_fit] = True logger.log_status("17. %s jobs (%s businesses) in 31+ workers x single residential building." % ( business_sizes[idx_wrk_fit].sum(), idx_wrk_fit.size)) # 18. 31+ workers in multiple residential buildings. idx_wrk_fit = where(logical_and(logical_and(processed_bindicator==0, business_sizes > 30), business_codes == 2))[0] jidx = in1d(job_array_labels, business_ids[idx_wrk_fit]) job_assignment_case[jidx] = 18 processed_bindicator[idx_wrk_fit] = True logger.log_status("18. %s jobs (%s businesses) in 31+ workers x multiple residential building." % ( business_sizes[idx_wrk_fit].sum(), idx_wrk_fit.size)) # jobs in messy buildings idx_messy_fit = where(logical_and(logical_and(processed_bindicator==0, business_sizes > 0), business_codes == 0))[0] processed_bindicator[idx_messy_fit] = True logger.log_status("%s jobs (%s businesses) could not be placed due to messy buildings." % ( business_sizes[idx_messy_fit].sum(), idx_messy_fit.size)) # build new buildings for jobs in cases 7, 8, 15 and 16 jidx_no_bld = where(in1d(job_assignment_case, [7,8,15,16]))[0] bus = unique(job_array_labels[jidx_no_bld]) bsidx = businesses.get_id_index(bus) # first create buildings for single workplaces per parcel single_workplace_idx = where(business_nworkplaces[bsidx] == 1)[0] newbld_parcel_id = businesses['parcel_id'][bsidx][single_workplace_idx] newbld_bt = sector2building_type(businesses['sector_id'][bsidx][single_workplace_idx]) newbids = arange(buildings.get_id_attribute().max()+1, buildings.get_id_attribute().max()+single_workplace_idx.size+1) bbldid = zeros(bsidx.size, dtype='int32') bbldid[single_workplace_idx] = newbids # for parcels with multiple workplaces select the largest business to determine its building type mult_bsidx = bsidx[where(business_nworkplaces[bsidx] > 1)[0]] empty_parcels = businesses['parcel_id'][mult_bsidx] uempty_parcels = unique(empty_parcels) bsize_on_empty_pcl = ndmax(business_sizes[mult_bsidx], labels=empty_parcels, index=uempty_parcels) newbld2_sec = zeros(uempty_parcels.size, dtype='int32') newbids2 = arange(newbids.max()+1, newbids.max()+uempty_parcels.size+1) for ipcl in range(uempty_parcels.size): newbld2_sec[ipcl] = businesses['sector_id'][mult_bsidx][logical_and(businesses['parcel_id'][mult_bsidx] == uempty_parcels[ipcl], business_sizes[mult_bsidx]==bsize_on_empty_pcl[ipcl])][0] this_bidx = where(businesses['parcel_id'][bsidx] == uempty_parcels[ipcl]) bbldid[this_bidx] = newbids2[ipcl] newbld_parcel_id = concatenate((newbld_parcel_id, uempty_parcels)) newbld_bt = concatenate((newbld_bt, sector2building_type(newbld2_sec))) newbldgs = {'building_id': concatenate((newbids, newbids2)), 'parcel_id': newbld_parcel_id, 'building_type_id': newbld_bt, } buildings.add_elements(newbldgs, require_all_attributes=False) jidx = where(in1d(job_array_labels, business_ids[bsidx]))[0] job_building_id[jidx] = bbldid.repeat(business_sizes[bsidx]) logger.log_status("Build %s new buildings to accommodate %s jobs (out of which %s are governmental) from cases 7, 15, 16." % ( newbld_parcel_id.size, jidx.size, business_sizes[bsidx][where(in1d(businesses['sector_id'][bsidx], [18,19]))].sum())) logger.log_status("Assigned %s (%s percent) home-based jobs." % (home_based.sum(), round(home_based.sum()/(home_based.size/100.),2))) logger.log_status("Finished %s percent (%s) jobs (%s businesses) processed. %s jobs (%s businesses) remain to be processed." % \ (round(business_sizes[processed_bindicator].sum()/(home_based.size/100.),2), business_sizes[processed_bindicator].sum(), processed_bindicator.sum(), business_sizes[logical_not(processed_bindicator)].sum(), business_sizes[logical_not(processed_bindicator)].size)) logger.start_block("Storing jobs data.") # create job dataset job_data = {"job_id": (arange(job_building_id.size)+1).astype("int32"), "home_based_status" : home_based, "building_id": job_building_id, "business_id": job_array_labels.astype("int32"), "sector_id": businesses['sector_id'].repeat(business_sizes).astype("int32"), "parcel_id": businesses['parcel_id'].repeat(business_sizes).astype("int32"), "assignment_case": job_assignment_case} # join with zones if zone_dsname is not None: zones = dataset_pool.get_dataset(zone_dsname) idname = zones.get_id_name()[0] #jpcls = buildings.get_attribute_by_id('parcel_id', job_building_id) job_data[idname] = parcels.get_attribute_by_id(idname, job_data["parcel_id"]) dictstorage = StorageFactory().get_storage('dict_storage') dictstorage.write_table(table_name="jobs", table_data=job_data) jobs = Dataset(in_storage=dictstorage, in_table_name="jobs", dataset_name="job", id_name="job_id") if out_storage is not None: jobs.write_dataset(out_storage=out_storage, out_table_name="jobs") buildings.write_dataset(out_storage=out_storage, attributes=AttributeType.PRIMARY) logger.end_block() return jobs
def run(self, dataset1, dataset2, index1=None, index2=None, sample_size=10, weight=None, include_chosen_choice=False, with_replacement=False, resources=None, dataset_pool=None): """this function samples number of sample_size (scalar value) alternatives from dataset2 for agent set specified by dataset1. If index1 is not None, only samples alterantives for agents with indices in index1; if index2 is not None, only samples alternatives from indices in index2. sample_size specifies number of alternatives to be sampled for each agent. weight, to be used as sampling weight, is either an attribute name of dataset2, or a 1d array of the same length as index2 or 2d array of shape (index1.size, index2.size). Also refer to document of interaction_dataset""" if dataset_pool is None: try: sc = SessionConfiguration() dataset_pool=sc.get_dataset_pool() except: dataset_pool = DatasetPool() local_resources = Resources(resources) local_resources.merge_if_not_None( {"dataset1": dataset1, "dataset2": dataset2, "index1":index1, "index2": index2, "sample_size": sample_size, "weight": weight, "with_replacement": with_replacement, "include_chosen_choice": include_chosen_choice}) local_resources.check_obligatory_keys(['dataset1', 'dataset2', 'sample_size']) agent = local_resources["dataset1"] index1 = local_resources.get("index1", None) if index1 is None: index1 = arange(agent.size()) choice = local_resources["dataset2"] index2 = local_resources.get("index2", None) if index2 is None: index2 = arange(choice.size()) if index1.size == 0 or index2.size == 0: err_msg = "either choice size or agent size is zero, return None" logger.log_warning(err_msg) return None include_chosen_choice = local_resources.get("include_chosen_choice", False) J = local_resources["sample_size"] if include_chosen_choice: J = J - 1 with_replacement = local_resources.get("with_replacement") weight = local_resources.get("weight", None) if isinstance(weight, str): if weight in choice.get_known_attribute_names(): weight=choice.get_attribute(weight) rank_of_weight = 1 elif VariableName(weight).get_dataset_name() == choice.get_dataset_name(): weight=choice.compute_variables(weight, dataset_pool=dataset_pool) rank_of_weight = 1 else: ## weights can be an interaction variable interaction_dataset = InteractionDataset(local_resources) weight=interaction_dataset.compute_variables(weight, dataset_pool=dataset_pool) rank_of_weight = 2 elif isinstance(weight, ndarray): rank_of_weight = weight.ndim elif not weight: ## weight is None or empty string weight = ones(index2.size) rank_of_weight = 1 else: err_msg = "unkown weight type" logger.log_error(err_msg) raise TypeError, err_msg if (weight.size <> index2.size) and (weight.shape[rank_of_weight-1] <> index2.size): if weight.shape[rank_of_weight-1] == choice.size(): if rank_of_weight == 1: weight = take(weight, index2) if rank_of_weight == 2: weight = take(weight, index2, axis=1) else: err_msg = "weight array size doesn't match to size of dataset2 or its index" logger.log_error(err_msg) raise ValueError, err_msg prob = normalize(weight) #chosen_choice = ones(index1.size) * UNPLACED_ID chosen_choice_id = agent.get_attribute(choice.get_id_name()[0])[index1] #index_of_placed_agent = where(greater(chosen_choice_id, UNPLACED_ID))[0] chosen_choice_index = choice.try_get_id_index(chosen_choice_id, return_value_if_not_found=UNPLACED_ID) chosen_choice_index_to_index2 = lookup(chosen_choice_index, index2, index_if_not_found=UNPLACED_ID) if rank_of_weight == 1: # if weight_array is 1d, then each agent shares the same weight for choices replace = with_replacement # sampling with no replacement if nonzerocounts(weight) < J: logger.log_warning("weight array dosen't have enough non-zero counts, use sample with replacement") replace = True sampled_index = prob2dsample( index2, sample_size=(index1.size, J), prob_array=prob, exclude_index=chosen_choice_index_to_index2, replace=replace, return_index=True ) #return index2[sampled_index] if rank_of_weight == 2: sampled_index = zeros((index1.size,J), dtype="int32") - 1 for i in range(index1.size): replace = with_replacement # sampling with/without replacement i_prob = prob[i,:] if nonzerocounts(i_prob) < J: logger.log_warning("weight array dosen't have enough non-zero counts, use sample with replacement") replace = True #exclude_index passed to probsample_noreplace needs to be indexed to index2 sampled_index[i,:] = probsample_noreplace( index2, sample_size=J, prob_array=i_prob, exclude_index=chosen_choice_index_to_index2[i], return_index=True ) sampling_prob = take(prob, sampled_index) sampled_index = index2[sampled_index] is_chosen_choice = zeros(sampled_index.shape, dtype="bool") #chosen_choice = -1 * ones(chosen_choice_index.size, dtype="int32") if include_chosen_choice: sampled_index = column_stack((chosen_choice_index[:,newaxis],sampled_index)) is_chosen_choice = zeros(sampled_index.shape, dtype="bool") is_chosen_choice[chosen_choice_index!=UNPLACED_ID, 0] = 1 #chosen_choice[where(is_chosen_choice)[0]] = where(is_chosen_choice)[1] ## this is necessary because prob is indexed to index2, not to the choice set (as is chosen_choice_index) sampling_prob_for_chosen_choices = take(prob, chosen_choice_index_to_index2[:, newaxis]) ## if chosen choice chosen equals unplaced_id then the sampling prob is 0 sampling_prob_for_chosen_choices[where(chosen_choice_index==UNPLACED_ID)[0],] = 0.0 sampling_prob = column_stack([sampling_prob_for_chosen_choices, sampling_prob]) interaction_dataset = self.create_interaction_dataset(dataset1, dataset2, index1, sampled_index) interaction_dataset.add_attribute(sampling_prob, '__sampling_probability') interaction_dataset.add_attribute(is_chosen_choice, 'chosen_choice') ## to get the older returns #sampled_index = interaction_dataset.get_2d_index() #chosen_choices = UNPLACED_ID * ones(index1.size, dtype="int32") #where_chosen = where(interaction_dataset.get_attribute("chosen_choice")) #chosen_choices[where_chosen[0]]=where_chosen[1] #return (sampled_index, chosen_choice) return interaction_dataset
def _add(self, agents_pool, amount, agent_dataset, location_dataset, this_refinement, dataset_pool ): fit_index = self.get_fit_agents_index(agent_dataset, this_refinement.agent_expression, this_refinement.location_expression, dataset_pool) if this_refinement.agent_expression is not None and len(this_refinement.agent_expression) > 0: agents_index = where(agent_dataset.compute_variables(this_refinement.agent_expression, dataset_pool=dataset_pool)>0)[0] else: agents_index = arange(agent_dataset.size()) movers_index = array([],dtype="int32") ar_pool = array(agents_pool) fitted_agents_pool = ar_pool[in1d(ar_pool, agents_index)] amount_from_agents_pool = min( amount, fitted_agents_pool.size ) prob_string = self.probability_attributes.get(agent_dataset.get_dataset_name(),None) if prob_string is not None: probs_values = (agent_dataset.compute_variables([prob_string], dataset_pool=dataset_pool)).astype('int32') uprobs_values = unique(probs_values[fit_index]) if uprobs_values.size > 0: probs_existing = array(ndimage_sum(ones(fit_index.size), labels=probs_values[fit_index], index=uprobs_values)) if amount_from_agents_pool > 0: if prob_string is not None and uprobs_values.size > 0: prob_pool_values = probs_values[fitted_agents_pool] probs_pool=zeros(prob_pool_values.size) for i in range(uprobs_values.size): probpoolidx = where(prob_pool_values == uprobs_values[i])[0] if probpoolidx.size == 0: continue probs_pool[probpoolidx]=probs_existing[i]/float(probpoolidx.size) probs_pool[probs_pool<=0] = (probs_existing.min()/10.0)/float((probs_pool<=0).sum()) else: probs_pool=ones(fitted_agents_pool.size) agents_index_from_agents_pool = probsample_noreplace( fitted_agents_pool, amount_from_agents_pool, prob_array=probs_pool ) [ agents_pool.remove(i) for i in agents_index_from_agents_pool ] if fit_index.size == 0: ##cannot find agents to copy their location or clone them, place agents in agents_pool if amount > amount_from_agents_pool: logger.log_warning("Refinement requests to add %i agents, but there are only %i agents subtracted from previous action(s) and no agents satisfying %s to clone from;" \ "add %i agents instead" % (amount, amount_from_agents_pool, ' and '.join( [this_refinement.agent_expression, this_refinement.location_expression]).strip(' and '), amount_from_agents_pool,) ) amount = amount_from_agents_pool # sample from all suitable locations is_suitable_location = location_dataset.compute_variables( this_refinement.location_expression, dataset_pool=dataset_pool ) location_id_for_agents_pool = sample_replace( location_dataset.get_id_attribute()[is_suitable_location], amount_from_agents_pool ) else: #sample from locations of suitable agents agents_index_for_location = sample_replace( fit_index, amount_from_agents_pool) location_id_for_agents_pool = agent_dataset.get_attribute( location_dataset.get_id_name()[0] )[agents_index_for_location] movers_index = concatenate( (movers_index, agents_index_for_location) ) elif fit_index.size == 0: ## no agents in agents_pool and no agents to clone either, --> fail logger.log_error( "Action 'add' failed: there is no agent subtracted from previous action, and no suitable agents satisfying %s to clone from." % \ ' and '.join( [this_refinement.agent_expression, this_refinement.location_expression] ).strip('and') ) return if amount > amount_from_agents_pool: agents_index_to_clone = sample_replace( fit_index, amount - amount_from_agents_pool) movers_index = concatenate( (movers_index, agents_index_to_clone) ) if movers_index.size > 0 and this_refinement.location_capacity_attribute is not None and len(this_refinement.location_capacity_attribute) > 0: movers_location_id = agent_dataset.get_attribute( location_dataset.get_id_name()[0] )[movers_index] movers_location_index = location_dataset.get_id_index( movers_location_id ) # see previous comment about histogram function num_of_movers_by_location = histogram( movers_location_index, bins=arange(location_dataset.size() +1) )[0] num_of_agents_by_location = location_dataset.compute_variables( "number_of_agents=%s.number_of_agents(%s)" % \ ( location_dataset.dataset_name, agent_dataset.dataset_name ), dataset_pool=dataset_pool) expand_factor = safe_array_divide( (num_of_agents_by_location + num_of_movers_by_location ).astype('float32'), num_of_agents_by_location, return_value_if_denominator_is_zero = 1.0 ) new_values = round_( expand_factor * location_dataset.get_attribute(this_refinement.location_capacity_attribute) ) location_dataset.modify_attribute( this_refinement.location_capacity_attribute, new_values ) self._add_refinement_info_to_dataset(location_dataset, self.id_names, this_refinement, index=movers_location_index) if amount_from_agents_pool > 0: agent_dataset.modify_attribute( 'building_id', -1 * ones( agents_index_from_agents_pool.size, dtype='int32' ), agents_index_from_agents_pool ) agent_dataset.modify_attribute( location_dataset.get_id_name()[0], location_id_for_agents_pool, agents_index_from_agents_pool ) self._add_refinement_info_to_dataset(agent_dataset, self.id_names, this_refinement, index=agents_index_from_agents_pool) self.processed_locations['add'] = concatenate((self.processed_locations.get('add', array([])), unique(location_dataset[self.subarea_id_name][location_dataset.get_id_index(location_id_for_agents_pool)]))) if amount > amount_from_agents_pool: new_agents_index = agent_dataset.duplicate_rows(agents_index_to_clone) self._add_refinement_info_to_dataset(agent_dataset, self.id_names, this_refinement, index=agents_index_to_clone) self._add_refinement_info_to_dataset(agent_dataset, self.id_names, this_refinement, index=new_agents_index) if location_dataset.get_dataset_name() <> 'building': agent_dataset.modify_attribute( 'building_id', -1 * ones( new_agents_index.size, dtype='int32' ), new_agents_index ) self.processed_locations['add'] = concatenate((self.processed_locations.get('add', array([])), unique(agent_dataset[self.subarea_id_name][new_agents_index])))
def run(self, n=500, run_config=None, current_year=None, debuglevel=0): """ n - sample n proposals at a time, evaluate them one by one """ self.demolished_buildings = array( [], dtype='int32') #id of buildings to be demolished if current_year is None: current_year = SimulationState().get_current_time() if not self.positive_proposals: logger.log_status( "Proposal Set size <= 0, no proposals to consider, skipping DPPSM." ) return (self.proposal_set, self.demolished_buildings) self.proposal_component_set.compute_variables([ 'urbansim_parcel.development_project_proposal_component.units_proposed', 'urbansim_parcel.development_project_proposal_component.is_residential' ], dataset_pool=self. dataset_pool) self.proposal_set.compute_variables( [ 'urbansim_parcel.development_project_proposal.number_of_components', 'zone_id=development_project_proposal.disaggregate(parcel.zone_id)', #'occurence_frequency = development_project_proposal.disaggregate(development_template.sample_size)' ], dataset_pool=self.dataset_pool) buildings = self.dataset_pool.get_dataset("building") buildings.compute_variables( [ "occupied_units_for_jobs = urbansim_parcel.building.number_of_non_home_based_jobs", "units_for_jobs = urbansim_parcel.building.total_non_home_based_job_space", "occupied_residential_units = urbansim_parcel.building.number_of_households", # "urbansim_parcel.building.existing_units", "urbansim_parcel.building.is_residential" ], dataset_pool=self.dataset_pool) ## define unit_name by whether a building is residential or not (with is_residential attribute) ## if it is non-residential (0), count units by number of job spaces (units_for_jobs) ## if it is residential (1), count units by residenital units self.unit_name = array(["units_for_jobs", "residential_units"]) target_vacancy = self.dataset_pool.get_dataset('target_vacancy') target_vacancy.compute_variables([ 'is_residential = target_vacancy.disaggregate(building_type.is_residential)' ], dataset_pool=self.dataset_pool) # This try-except block checks to see if the object has a subarea_id_name, # if it does, it calculates the vacancy rates by subarea_id_name try: # Check for subarea_id_name in target_vacancies dataset # if it is present, vacancy rates are specified by subarea_id_name # if it is not, vacancy rates are specified region wide target_vacancy.load_dataset() if self.subarea_id_name in target_vacancy.get_attribute_names(): current_target_vacancy_this_year = DatasetSubset( target_vacancy, index=where( target_vacancy.get_attribute("year") == current_year)[0]) current_target_vacancy = DatasetSubset( current_target_vacancy_this_year, index=where( current_target_vacancy_this_year.get_attribute( self.subarea_id_name) == self.area_id)[0]) else: current_target_vacancy = DatasetSubset( target_vacancy, index=where( target_vacancy.get_attribute("year") == current_year)[0]) except AttributeError: # vacancy rates are specified region wide: current_target_vacancy = DatasetSubset( target_vacancy, index=where( target_vacancy.get_attribute("year") == current_year)[0]) if current_target_vacancy.size() == 0: raise IOError, 'No target vacancy defined for year %s.' % current_year self.existing_units = {} #total existing units by land_use type self.occupied_units = {} #total occupied units by land_use type self.proposed_units = {} #total proposed units by land_use type self.demolished_units = { } #total (to be) demolished units by land_use type components_building_type_ids = self.proposal_component_set.get_attribute( "building_type_id").astype("int32") proposal_ids = self.proposal_set.get_id_attribute() proposal_ids_in_component_set = self.proposal_component_set.get_attribute( "proposal_id") all_units_proposed = self.proposal_component_set.get_attribute( "units_proposed") number_of_components_in_proposals = self.proposal_set.get_attribute( "number_of_components") self.accepting_proposals = zeros( current_target_vacancy.get_attribute("building_type_id").max() + 1, dtype='bool8' ) #whether accepting new proposals, for each building type self.accepted_proposals = [] # index of accepted proposals self.target_vacancies = {} tv_building_types = current_target_vacancy.get_attribute( "building_type_id") tv_rate = current_target_vacancy.get_attribute("target_vacancy_rate") for itype in range(tv_building_types.size): self.target_vacancies[tv_building_types[itype]] = tv_rate[itype] self.check_vacancy_rates( current_target_vacancy ) #initialize self.accepting_proposal based on current vacancy rate sqft_per_job = self.dataset_pool.get_dataset("building_sqft_per_job") zones_of_proposals = self.proposal_set.get_attribute("zone_id") self.building_sqft_per_job_table = sqft_per_job.get_building_sqft_as_table( zones_of_proposals.max(), tv_building_types.max()) # consider only those proposals that have all components of accepted type and sum of proposed units > 0 is_accepted_type = self.accepting_proposals[ components_building_type_ids] sum_is_accepted_type_over_proposals = array( ndimage.sum(is_accepted_type, labels=proposal_ids_in_component_set, index=proposal_ids)) sum_of_units_proposed = array( ndimage.sum(all_units_proposed, labels=proposal_ids_in_component_set, index=proposal_ids)) is_proposal_eligible = logical_and( sum_is_accepted_type_over_proposals == number_of_components_in_proposals, sum_of_units_proposed > 0) is_proposal_eligible = logical_and( is_proposal_eligible, self.proposal_set.get_attribute("start_year") == current_year) ## handle planned proposals: all proposals with status_id == is_planned ## and start_year == current_year are accepted planned_proposal_indexes = where( logical_and( self.proposal_set.get_attribute( "status_id") == self.proposal_set.id_planned, self.proposal_set.get_attribute("start_year") == current_year))[0] self.consider_proposals(planned_proposal_indexes, force_accepting=True) # consider proposals (in this order: planned, proposed, tentative) for status in [ self.proposal_set.id_proposed, self.proposal_set.id_tentative ]: idx = where( logical_and( self.proposal_set.get_attribute("status_id") == status, is_proposal_eligible))[0] if idx.size <= 0: continue logger.log_status( "Sampling from %s eligible proposals with status %s." % (idx.size, status)) while (True in self.accepting_proposals): if self.weight[idx].sum() == 0.0: logger.log_warning( "Running out of proposals; there aren't any proposals with non-zero weight" ) break idx = idx[self.weight[idx] > 0] n = minimum(idx.size, n) sampled_proposal_indexes = probsample_noreplace( proposal_ids[idx], n, prob_array=(self.weight[idx] / float(self.weight[idx].sum())), exclude_index=None, return_index=True) self.consider_proposals( arange(self.proposal_set.size())[ idx[sampled_proposal_indexes]]) self.weight[idx[sampled_proposal_indexes]] = 0 # set status of accepted proposals to 'active' self.proposal_set.modify_attribute(name="status_id", data=self.proposal_set.id_active, index=array(self.accepted_proposals, dtype='int32')) building_types = self.dataset_pool.get_dataset("building_type") logger.log_status("Status of %s development proposals set to active." % len(self.accepted_proposals)) logger.log_status( "Target/existing vacancy rates (reached using eligible proposals) by building type:" ) for type_id in self.existing_units.keys(): units_stock = self._get_units_stock(type_id) vr = self._get_vacancy_rates(type_id) ## units = residential_units if building_type is residential ## units = number of job spaces if building_type is non-residential logger.log_status( """%(type_id)s[%(type_name)s]: %(vr)s = ((existing_units:%(existing_units)s + units_proposed:%(units_proposed)s - units_to_be_demolished:%(units_demolished)s) - units_occupied:%(units_occupied)s) / units_stock:%(units_stock)s""" % \ { 'type_id': type_id, 'type_name': building_types.get_attribute_by_id("building_type_name", type_id), 'vr': vr, 'existing_units': int(self.existing_units[type_id]), 'units_occupied': int(self.occupied_units[type_id]), 'units_proposed': int(self.proposed_units[type_id]), 'units_demolished': int(self.demolished_units[type_id]), 'units_stock': int(units_stock) } ) # Code added by Jesse Ayers, MAG, 7/20/2009 # Get the active projects: stat_id = self.proposal_set.get_attribute('status_id') actv = where(stat_id == 1)[0] # Where there are active projects, compute the total_land_area_taken # and store it on the development_project_proposals dataset # so it can be used by the building_construction_model for the proper # computation of units_proposed for those projects with velocity curves if actv.size > 0: total_land_area_taken_computed = self.proposal_set.get_attribute( 'urbansim_parcel.development_project_proposal.land_area_taken') self.proposal_set.modify_attribute( 'total_land_area_taken', total_land_area_taken_computed[actv], actv) return (self.proposal_set, self.demolished_buildings)
def run(self, n=500, run_config=None, current_year=None, debuglevel=0): """ n - sample n proposals at a time, evaluate them one by one """ self.demolished_buildings = array([], dtype='int32') #id of buildings to be demolished if current_year is None: current_year = SimulationState().get_current_time() if not self.positive_proposals: logger.log_status("Proposal Set size <= 0, no proposals to consider, skipping DPPSM.") return (self.proposal_set, self.demolished_buildings) self.proposal_component_set.compute_variables([ 'urbansim_parcel.development_project_proposal_component.units_proposed', 'urbansim_parcel.development_project_proposal_component.is_residential'], dataset_pool=self.dataset_pool) self.proposal_set.compute_variables([ 'urbansim_parcel.development_project_proposal.number_of_components', 'zone_id=development_project_proposal.disaggregate(parcel.zone_id)', #'occurence_frequency = development_project_proposal.disaggregate(development_template.sample_size)' ], dataset_pool=self.dataset_pool) buildings = self.dataset_pool.get_dataset("building") buildings.compute_variables([ "occupied_units_for_jobs = urbansim_parcel.building.number_of_non_home_based_jobs", "units_for_jobs = urbansim_parcel.building.total_non_home_based_job_space", "occupied_residential_units = urbansim_parcel.building.number_of_households", # "urbansim_parcel.building.existing_units", "urbansim_parcel.building.is_residential" ], dataset_pool=self.dataset_pool) ## define unit_name by whether a building is residential or not (with is_residential attribute) ## if it is non-residential (0), count units by number of job spaces (units_for_jobs) ## if it is residential (1), count units by residenital units self.unit_name = array(["units_for_jobs", "residential_units"]) target_vacancy = self.dataset_pool.get_dataset('target_vacancy') target_vacancy.compute_variables(['is_residential = target_vacancy.disaggregate(building_type.is_residential)'], dataset_pool=self.dataset_pool) # This try-except block checks to see if the object has a subarea_id_name, # if it does, it calculates the vacancy rates by subarea_id_name try: # Check for subarea_id_name in target_vacancies dataset # if it is present, vacancy rates are specified by subarea_id_name # if it is not, vacancy rates are specified region wide target_vacancy.load_dataset() if self.subarea_id_name in target_vacancy.get_attribute_names(): current_target_vacancy_this_year = DatasetSubset(target_vacancy, index=where(target_vacancy.get_attribute("year")==current_year)[0]) current_target_vacancy = DatasetSubset(current_target_vacancy_this_year, index=where(current_target_vacancy_this_year.get_attribute(self.subarea_id_name)==self.area_id)[0]) else: current_target_vacancy = DatasetSubset(target_vacancy, index=where(target_vacancy.get_attribute("year")==current_year)[0]) except AttributeError: # vacancy rates are specified region wide: current_target_vacancy = DatasetSubset(target_vacancy, index=where(target_vacancy.get_attribute("year")==current_year)[0]) if current_target_vacancy.size() == 0: raise IOError, 'No target vacancy defined for year %s.' % current_year self.existing_units = {} #total existing units by land_use type self.occupied_units = {} #total occupied units by land_use type self.proposed_units = {} #total proposed units by land_use type self.demolished_units = {} #total (to be) demolished units by land_use type components_building_type_ids = self.proposal_component_set.get_attribute("building_type_id").astype("int32") proposal_ids = self.proposal_set.get_id_attribute() proposal_ids_in_component_set = self.proposal_component_set.get_attribute("proposal_id") all_units_proposed = self.proposal_component_set.get_attribute("units_proposed") number_of_components_in_proposals = self.proposal_set.get_attribute("number_of_components") self.accepting_proposals = zeros(current_target_vacancy.get_attribute("building_type_id").max()+1, dtype='bool8') #whether accepting new proposals, for each building type self.accepted_proposals = [] # index of accepted proposals self.target_vacancies = {} tv_building_types = current_target_vacancy.get_attribute("building_type_id") tv_rate = current_target_vacancy.get_attribute("target_vacancy_rate") for itype in range(tv_building_types.size): self.target_vacancies[tv_building_types[itype]] = tv_rate[itype] self.check_vacancy_rates(current_target_vacancy) #initialize self.accepting_proposal based on current vacancy rate sqft_per_job = self.dataset_pool.get_dataset("building_sqft_per_job") zones_of_proposals = self.proposal_set.get_attribute("zone_id") self.building_sqft_per_job_table = sqft_per_job.get_building_sqft_as_table(zones_of_proposals.max(), tv_building_types.max()) # consider only those proposals that have all components of accepted type and sum of proposed units > 0 is_accepted_type = self.accepting_proposals[components_building_type_ids] sum_is_accepted_type_over_proposals = array(ndimage.sum(is_accepted_type, labels = proposal_ids_in_component_set, index = proposal_ids)) sum_of_units_proposed = array(ndimage.sum(all_units_proposed, labels = proposal_ids_in_component_set, index = proposal_ids)) is_proposal_eligible = logical_and(sum_is_accepted_type_over_proposals == number_of_components_in_proposals, sum_of_units_proposed > 0) is_proposal_eligible = logical_and(is_proposal_eligible, self.proposal_set.get_attribute("start_year")==current_year ) ## handle planned proposals: all proposals with status_id == is_planned ## and start_year == current_year are accepted planned_proposal_indexes = where(logical_and( self.proposal_set.get_attribute("status_id") == self.proposal_set.id_planned, self.proposal_set.get_attribute("start_year") == current_year ) )[0] self.consider_proposals(planned_proposal_indexes, force_accepting=True) # consider proposals (in this order: planned, proposed, tentative) for status in [self.proposal_set.id_proposed, self.proposal_set.id_tentative]: idx = where(logical_and(self.proposal_set.get_attribute("status_id") == status, is_proposal_eligible))[0] if idx.size <= 0: continue logger.log_status("Sampling from %s eligible proposals with status %s." % (idx.size, status)) while (True in self.accepting_proposals): if self.weight[idx].sum() == 0.0: logger.log_warning("Running out of proposals; there aren't any proposals with non-zero weight") break idx = idx[self.weight[idx] > 0] n = minimum(idx.size, n) sampled_proposal_indexes = probsample_noreplace(proposal_ids[idx], n, prob_array=(self.weight[idx]/float(self.weight[idx].sum())), exclude_index=None, return_index=True) self.consider_proposals(arange(self.proposal_set.size())[idx[sampled_proposal_indexes]]) self.weight[idx[sampled_proposal_indexes]] = 0 # set status of accepted proposals to 'active' self.proposal_set.modify_attribute(name="status_id", data=self.proposal_set.id_active, index=array(self.accepted_proposals, dtype='int32')) building_types = self.dataset_pool.get_dataset("building_type") logger.log_status("Status of %s development proposals set to active." % len(self.accepted_proposals)) logger.log_status("Target/existing vacancy rates (reached using eligible proposals) by building type:") for type_id in self.existing_units.keys(): units_stock = self._get_units_stock(type_id) vr = self._get_vacancy_rates(type_id) ## units = residential_units if building_type is residential ## units = number of job spaces if building_type is non-residential logger.log_status( """%(type_id)s[%(type_name)s]: %(vr)s = ((existing_units:%(existing_units)s + units_proposed:%(units_proposed)s - units_to_be_demolished:%(units_demolished)s) - units_occupied:%(units_occupied)s) / units_stock:%(units_stock)s""" % \ { 'type_id': type_id, 'type_name': building_types.get_attribute_by_id("building_type_name", type_id), 'vr': vr, 'existing_units': int(self.existing_units[type_id]), 'units_occupied': int(self.occupied_units[type_id]), 'units_proposed': int(self.proposed_units[type_id]), 'units_demolished': int(self.demolished_units[type_id]), 'units_stock': int(units_stock) } ) # Code added by Jesse Ayers, MAG, 7/20/2009 # Get the active projects: stat_id = self.proposal_set.get_attribute('status_id') actv = where(stat_id==1)[0] # Where there are active projects, compute the total_land_area_taken # and store it on the development_project_proposals dataset # so it can be used by the building_construction_model for the proper # computation of units_proposed for those projects with velocity curves if actv.size > 0: total_land_area_taken_computed = self.proposal_set.get_attribute('urbansim_parcel.development_project_proposal.land_area_taken') self.proposal_set.modify_attribute('total_land_area_taken', total_land_area_taken_computed[actv], actv) return (self.proposal_set, self.demolished_buildings)
def run(self, job_dataset, dataset_pool, out_storage=None, jobs_table="jobs"): """ Algorithm: 1. For all non_home_based jobs that have parcel_id assigned but no building_id, try to choose a building from all buildings in that parcel. Draw the building with probabilities given by the sector-building_type distribution. The job sizes are fitted into the available space (the attribute job.sqft is updated). 2. For all non_home_based jobs for which no building was found in step 1, check if the parcel has residential buildings. In such a case, re-assign the jobs to be home-based. Otherwise, if sum of non_residential_sqft over the involved buildings is 0, for all jobs that have impute_building_sqft_flag=True draw a building using the sector-building_type distribution and impute the corresponding sqft to the non_residential_sqft of that building. 3. For all home_based jobs that have parcel_id assigned but no building_id, try to choose a building from all buildings in that parcel. The capacity of a single-family building is determined from sizes of the households living there (for each household the minimum of number of members and 2 is taken). For multi-family buildings the capacity is 50. 4. Assign a building type to jobs that have missing building type. It is sampled from the regional-wide distribution of home based and non-home based jobs. 5. Update the table 'building_sqft_per_job' using the updated job.sqft. 'in_storage' should contain the jobs table and the zone_averages_table. The 'dataset_pool_storage' should contain all other tables needed (buildings, households, building_types). """ parcel_ids = job_dataset.get_attribute("parcel_id") building_ids = job_dataset.get_attribute("building_id") building_types = job_dataset.get_attribute("building_type") try: impute_sqft_flags = job_dataset.get_attribute("impute_building_sqft_flag") except: impute_sqft_flags = zeros(job_dataset.size()) is_considered = logical_and(parcel_ids > 0, building_ids <= 0) # jobs that have assigned parcel but not building job_index_home_based = where(logical_and(is_considered, building_types == 1))[0] job_index_governmental = where(logical_and(is_considered, building_types == 3))[0] building_dataset = dataset_pool.get_dataset('building') parcel_ids_in_bldgs = building_dataset.get_attribute("parcel_id") bldg_ids_in_bldgs = building_dataset.get_id_attribute() bldg_types_in_bldgs = building_dataset.get_attribute("building_type_id") non_res_sqft = building_dataset.get_attribute("non_residential_sqft") occupied = building_dataset.compute_variables(["urbansim_parcel.building.occupied_building_sqft_by_jobs"], dataset_pool=dataset_pool) is_governmental = building_dataset.compute_variables(["building.disaggregate(building_type.generic_building_type_id == 7)"], dataset_pool=dataset_pool) # assign buildings to governmental jobs randomly unique_parcels = unique(parcel_ids[job_index_governmental]) logger.log_status("Placing governmental jobs ...") for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs[is_governmental] == parcel)[0] if idx_in_bldgs.size <= 0: continue idx_in_jobs = where(parcel_ids[job_index_governmental] == parcel)[0] draw = sample_replace(idx_in_bldgs, idx_in_jobs.size) building_ids[job_index_governmental[idx_in_jobs]] = bldg_ids_in_bldgs[where(is_governmental)[0][draw]] logger.log_status("%s governmental jobs (out of %s gov. jobs) were placed." % ( (building_ids[job_index_governmental]>0).sum(), job_index_governmental.size)) logger.log_status("The not-placed governmental jobs will be added to the non-home based jobs.") # consider the unplaced governmental jobs together with other non-home-based jobs is_now_considered = logical_and(is_considered, building_ids <= 0) job_index_non_home_based = where(logical_and(is_now_considered, logical_or(building_types == 2, building_types == 3)))[0] # assign buildings to non_home_based jobs based on available space unique_parcels = unique(parcel_ids[job_index_non_home_based]) job_building_types = job_dataset.compute_variables(["bldgs_building_type_id = job.disaggregate(building.building_type_id)"], dataset_pool=dataset_pool) where_valid_jbt = where(logical_and(job_building_types>0, logical_or(building_types == 2, building_types==3)))[0] building_type_dataset = dataset_pool.get_dataset("building_type") available_building_types= building_type_dataset.get_id_attribute() idx_available_bt = building_type_dataset.get_id_index(available_building_types) sectors = job_dataset.get_attribute("sector_id") unique_sectors = unique(sectors) sector_bt_distribution = zeros((unique_sectors.size, building_type_dataset.size()), dtype="float32") jobs_sqft = job_dataset.get_attribute_by_index("sqft", job_index_non_home_based).astype("float32") job_dataset._compute_if_needed("urbansim_parcel.job.zone_id", dataset_pool=dataset_pool) jobs_zones = job_dataset.get_attribute_by_index("zone_id", job_index_non_home_based) new_jobs_sqft = job_dataset.get_attribute("sqft").copy() # find sector -> building_type distribution sector_index_mapping = {} for isector in range(unique_sectors.size): idx = where(sectors[where_valid_jbt]==unique_sectors[isector])[0] if idx.size == 0: continue o = ones(idx.size, dtype="int32") sector_bt_distribution[isector,:] = ndimage_sum(o, labels=job_building_types[where_valid_jbt[idx]], index=available_building_types) sector_bt_distribution[isector,:] = sector_bt_distribution[isector,:]/sector_bt_distribution[isector,:].sum() sector_index_mapping[unique_sectors[isector]] = isector # create a lookup table for zonal average per building type of sqft per employee zone_average_dataset = dataset_pool.get_dataset("building_sqft_per_job") zone_bt_lookup = zone_average_dataset.get_building_sqft_as_table(job_dataset.get_attribute("zone_id").max(), available_building_types.max()) counter_zero_capacity = 0 counter_zero_distr = 0 # iterate over parcels logger.log_status("Placing non-home-based jobs ...") for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs == parcel)[0] if idx_in_bldgs.size <= 0: continue idx_in_jobs = where(parcel_ids[job_index_non_home_based] == parcel)[0] capacity = maximum(non_res_sqft[idx_in_bldgs] - occupied[idx_in_bldgs],0) #capacity = non_res_sqft[idx_in_bldgs] - occupied[idx_in_bldgs] if capacity.sum() <= 0: counter_zero_capacity += idx_in_jobs.size continue this_jobs_sectors = sectors[job_index_non_home_based][idx_in_jobs] this_jobs_sqft_table = resize(jobs_sqft[idx_in_jobs], (idx_in_bldgs.size, idx_in_jobs.size)) wn = jobs_sqft[idx_in_jobs] <= 0 for i in range(idx_in_bldgs.size): this_jobs_sqft_table[i, where(wn)[0]] = zone_bt_lookup[jobs_zones[idx_in_jobs[wn]], bldg_types_in_bldgs[idx_in_bldgs[i]]] supply_demand_ratio = (resize(capacity, (capacity.size, 1))/this_jobs_sqft_table.astype("float32").sum(axis=0))/float(idx_in_jobs.size)*0.9 if any(supply_demand_ratio < 1): # correct only if supply is smaller than demand this_jobs_sqft_table = this_jobs_sqft_table * supply_demand_ratio probcomb = zeros(this_jobs_sqft_table.shape) bt = bldg_types_in_bldgs[idx_in_bldgs] ibt = building_type_dataset.get_id_index(bt) for i in range(probcomb.shape[0]): for j in range(probcomb.shape[1]): probcomb[i,j] = sector_bt_distribution[sector_index_mapping[this_jobs_sectors[j]],ibt[i]] pcs = probcomb.sum(axis=0) probcomb = probcomb/pcs wz = where(pcs<=0)[0] counter_zero_distr += wz.size probcomb[:, wz] = 0 # to avoid nan values taken = zeros(capacity.shape) has_sqft = this_jobs_sqft_table > 0 while True: if (has_sqft * probcomb).sum() <= 0: break req = (this_jobs_sqft_table * probcomb).sum(axis=0) maxi = req.max() wmaxi = where(req==maxi)[0] drawjob = sample_noreplace(arange(wmaxi.size), 1) # draw job from jobs with the maximum size imax_req = wmaxi[drawjob] weights = has_sqft[:,imax_req] * probcomb[:,imax_req] draw = probsample_noreplace(arange(probcomb.shape[0]), 1, resize(weights/weights.sum(), (probcomb.shape[0],))) if (taken[draw] + this_jobs_sqft_table[draw,imax_req]) > capacity[draw]: probcomb[draw,imax_req]=0 continue taken[draw] = taken[draw] + this_jobs_sqft_table[draw,imax_req] building_ids[job_index_non_home_based[idx_in_jobs[imax_req]]] = bldg_ids_in_bldgs[idx_in_bldgs[draw]] probcomb[:,imax_req] = 0 new_jobs_sqft[job_index_non_home_based[idx_in_jobs[imax_req]]] = int(min(self.maximum_sqft, max(round(this_jobs_sqft_table[draw,imax_req]), self.minimum_sqft))) logger.log_status("%s non home based jobs (out of %s nhb jobs) were placed." % ( (building_ids[job_index_non_home_based]>0).sum(), job_index_non_home_based.size)) logger.log_status("Unplaced due to zero capacity: %s" % counter_zero_capacity) logger.log_status("Unplaced due to zero distribution: %s" % counter_zero_distr) job_dataset.modify_attribute(name="building_id", data = building_ids) # re-classify unplaced non-home based jobs to home-based if parcels contain residential buildings bldgs_is_residential = logical_and(logical_not(is_governmental), building_dataset.compute_variables(["urbansim_parcel.building.is_residential"], dataset_pool=dataset_pool)) is_now_considered = logical_and(parcel_ids > 0, building_ids <= 0) job_index_non_home_based_unplaced = where(logical_and(is_now_considered, building_types == 2))[0] unique_parcels = unique(parcel_ids[job_index_non_home_based_unplaced]) imputed_sqft = 0 logger.log_status("Try to reclassify non-home-based jobs (excluding governemtal jobs) ...") for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs == parcel)[0] if idx_in_bldgs.size <= 0: continue idx_in_jobs = where(parcel_ids[job_index_non_home_based_unplaced] == parcel)[0] where_residential = where(bldgs_is_residential[idx_in_bldgs])[0] if where_residential.size > 0: building_types[job_index_non_home_based_unplaced[idx_in_jobs]] = 1 # set to home-based jobs elif non_res_sqft[idx_in_bldgs].sum() <= 0: # impute non_residential_sqft and assign buildings this_jobs_sectors = sectors[job_index_non_home_based_unplaced][idx_in_jobs] this_jobs_sqft_table = resize(jobs_sqft[idx_in_jobs], (idx_in_bldgs.size, idx_in_jobs.size)) wn = jobs_sqft[idx_in_jobs] <= 0 for i in range(idx_in_bldgs.size): this_jobs_sqft_table[i, where(wn)[0]] = zone_bt_lookup[jobs_zones[idx_in_jobs[wn]], bldg_types_in_bldgs[idx_in_bldgs[i]]] probcomb = zeros(this_jobs_sqft_table.shape) bt = bldg_types_in_bldgs[idx_in_bldgs] ibt = building_type_dataset.get_id_index(bt) for i in range(probcomb.shape[0]): for j in range(probcomb.shape[1]): probcomb[i,j] = sector_bt_distribution[sector_index_mapping[this_jobs_sectors[j]],ibt[i]] for ijob in range(probcomb.shape[1]): if (probcomb[:,ijob].sum() <= 0) or (impute_sqft_flags[job_index_non_home_based_unplaced[ijob]] == 0): continue weights = probcomb[:,ijob] draw = probsample_noreplace(arange(probcomb.shape[0]), 1, resize(weights/weights.sum(), (probcomb.shape[0],))) non_res_sqft[idx_in_bldgs[draw]] += this_jobs_sqft_table[draw,ijob] imputed_sqft += this_jobs_sqft_table[draw,ijob] building_ids[job_index_non_home_based_unplaced[idx_in_jobs[ijob]]] = bldg_ids_in_bldgs[idx_in_bldgs[draw]] new_jobs_sqft[job_index_non_home_based[idx_in_jobs[ijob]]] = int(min(self.maximum_sqft, max(round(this_jobs_sqft_table[draw,ijob]), self.minimum_sqft))) building_dataset.modify_attribute(name="non_residential_sqft", data = non_res_sqft) job_dataset.modify_attribute(name="building_id", data = building_ids) job_dataset.modify_attribute(name="building_type", data = building_types) job_dataset.modify_attribute(name="sqft", data = new_jobs_sqft) old_nhb_size = job_index_non_home_based.size job_index_home_based = where(logical_and(is_considered, building_types == 1))[0] job_index_non_home_based = where(logical_and(is_considered, building_types == 2))[0] logger.log_status("%s non-home based jobs reclassified as home-based." % (old_nhb_size-job_index_non_home_based.size)) logger.log_status("%s non-residential sqft imputed." % imputed_sqft) logger.log_status("Additionaly, %s non home based jobs were placed due to imputed sqft." % \ (building_ids[job_index_non_home_based_unplaced]>0).sum()) # home_based jobs unique_parcels = unique(parcel_ids[job_index_home_based]) capacity_in_buildings = building_dataset.compute_variables([ "urbansim_parcel.building.vacant_home_based_job_space"], dataset_pool=dataset_pool) parcels_with_exceeded_capacity = [] # iterate over parcels logger.log_status("Placing home-based jobs ...") for parcel in unique_parcels: idx_in_bldgs = where(parcel_ids_in_bldgs == parcel)[0] idx_in_jobs = where(parcel_ids[job_index_home_based] == parcel)[0] capacity = capacity_in_buildings[idx_in_bldgs] if capacity.sum() <= 0: continue probcomb = ones((idx_in_bldgs.size, idx_in_jobs.size)) taken = zeros(capacity.shape, dtype="int32") while True: zero_cap = where((capacity - taken) <= 0)[0] probcomb[zero_cap,:] = 0 if probcomb.sum() <= 0: break req = probcomb.sum(axis=0) wmaxi = where(req==req.max())[0] drawjob = sample_noreplace(arange(wmaxi.size), 1) # draw job from available jobs imax_req = wmaxi[drawjob] weights = probcomb[:,imax_req] # sample building draw = probsample_noreplace(arange(probcomb.shape[0]), 1, resize(weights/weights.sum(), (probcomb.shape[0],))) taken[draw] = taken[draw] + 1 building_ids[job_index_home_based[idx_in_jobs[imax_req]]] = bldg_ids_in_bldgs[idx_in_bldgs[draw]] probcomb[:,imax_req] = 0 if -1 in building_ids[job_index_home_based[idx_in_jobs]]: parcels_with_exceeded_capacity.append(parcel) parcels_with_exceeded_capacity = array(parcels_with_exceeded_capacity) logger.log_status("%s home based jobs (out of %s hb jobs) were placed." % ((building_ids[job_index_home_based]>0).sum(), job_index_home_based.size)) # assign building type where missing # determine regional distribution idx_home_based = where(building_types == 1)[0] idx_non_home_based = where(building_types == 2)[0] idx_bt_missing = where(building_types <= 0)[0] if idx_bt_missing.size > 0: # sample building types sample_bt = probsample_replace(array([1,2]), idx_bt_missing.size, array([idx_home_based.size, idx_non_home_based.size])/float(idx_home_based.size + idx_non_home_based.size)) # coerce to int32 (on a 64 bit machine, sample_bt will be of type int64) building_types[idx_bt_missing] = sample_bt.astype(int32) job_dataset.modify_attribute(name="building_type", data = building_types) if out_storage is not None: job_dataset.write_dataset(out_table_name=jobs_table, out_storage=out_storage, attributes=AttributeType.PRIMARY) building_dataset.write_dataset(out_table_name='buildings', out_storage=out_storage, attributes=AttributeType.PRIMARY) logger.log_status("Assigning building_id to jobs done.")