From f4d2a3075e2dd93b9fa96fede8d58abb9e5abf84 Mon Sep 17 00:00:00 2001 From: Valentin LE BESCOND Date: Tue, 12 Nov 2024 16:22:28 +0100 Subject: [PATCH 1/2] add a full config with all possible entries --- full_config.yml | 200 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 200 insertions(+) create mode 100644 full_config.yml diff --git a/full_config.yml b/full_config.yml new file mode 100644 index 0000000..efdddf6 --- /dev/null +++ b/full_config.yml @@ -0,0 +1,200 @@ +## Synthetic population pipeline for Île-de-France +## based on the synpp package + +# This is the path to a directory where the pipeline can store temporary data +working_directory: cache + +# This section defines which parts of the pipeline should be run +run: + - synthesis.output # To create the output population in the output_path (see below) + #- matsim.output # Uncomment, if you want to run the full simulation (you'll need Java for that) + +# Here the configuraiton of the pipeline starts +config: + + ### Some general configuration + + ## Number of CPUs to use + processes: 4 + + ### Random seeds + + ## global random seed for the output population + random_seed: 1234 + + ## bpe specific random seed when impute missing coordinates for known IRIS + # bpe_random_seed: 0 + + ### Define sampling rate for the output population + sampling_rate: 0.001 + + ### household travel survey (HTS) + + ## Define whether to use ENTD or EGT as the HTS + hts: entd # entd, egt, edgt_lyon, edgt_44 + + ## Whether to filter people going outside of the area and other filters + # filter_hts: true + + ## if selected, chose the source for edgt_lyon + # edgt_lyon_source: unchosen # unchosen, adisp, cerema + + ### Zone selection + + ## select regions by region_id + # regions: [11] + + ## select departments by department_id + # departments: [] + + ### Output paths + + ## output folder + output_path: output + + ## output prefix, appended to file names + # output_prefix: ile_de_france_ + + ## file formats that should be exported + # output_formats: ["csv", "gpkg"] # ["csv", "gpkg", "parquet", "geoparquet"] + + ### Algorithms configurations + + ## Use the bhepop2 package for attributing income + # income_assignation_method: bhepop2 # uniform, bhepop2 + + ## Activate if you want to run mode choice, will assign a mode to output trips + mode_choice: true + + ## Statistical matching configuration + + ## Minimum number of observation to sample from + # matching_minimum_observations: 20 + + ## list of attributes to use for matching + # matching_attributes: ["sex", "any_cars", "age_class", "socioprofessional_class", "departement_id"] + + ## Use INSEE's urban type in statistical matching + # use_urban_type: true + # urban_type_path: urban_type/UU2020_au_01-01-2023.zip + # matching_attributes: ["urban_type", "*default*"] + + ## Exclude entreprise without any employee (trancheEffectifsEtablissement is NA, "NN" or "00") + # exclude_no_employee: true + + ## source for the education locations + # education_location_source: bpe # bpe, addresses + + ## max iterations for the secondary location selection algorithm + # secloc_maximum_iterations: np.inf + + ## Buffer arround buildings to capture adresses in their vicinity + # home_address_buffer: 5.0 + + ## How sample homes, using weights or not + # home_location_weight: housing # "uniform", "housing" + + # home_location_source: addresses # "addresses", "buildings", "tiles" + + ## When running matsim + + ## performing one run of the matsim simulation or not + # run_matsim: true + + ## creating the far or not + # write_jar: true + + ### Analysis configuration + + ## Whether to use previously generated files or not + # analysis_from_file: false + + ## prefix of the files to compare to + # comparison_file_prefix: other_ + + ### Tools configuration + + ## Mostly interesting if you run the simulation, or you activate the `mode_choice` option, + + ## Binaries paths + # git_binary: git + # osmosis_binary: osmosis + # java_binary: java + # maven_binary: mvn + + ## Binaries parameters + # java_memory: 14G + # maven_skip_tests: false + + ## eqasim-java parameters + # eqasim_version: 1.5.0 + # eqasim_branch: develop + # eqasim_commit: ece4932 + # eqasim_repository: https://github.com/eqasim-org/eqasim-java.git + # eqasim_path: "" + + ## pt2matsim parameters + # pt2matsim_version: 22.3 + # pt2matsim_branch: v22.3 + + ## Strategy to use in pt2matsim gtfs processing + # gtfs_date: dayWithMostServices + ## Export the detailed geometry of the network before simplification in pt2matsim + # export_detailed_network: true + + ### Input paths + + ## Absolute root path of all input data + data_path: /path/to/my/data + + # census_path: rp_2019/RP2019_INDCVI_csv.zip + # census_csv: FD_INDCVI_2019.csv + + # ban_path: ban_idf + + # bdtopo_path: bdtopo_idf + + # bpe_path: bpe_2021/bpe21_ensemble_xy_csv.zip + # bpe_csv: bpe21_ensemble_xy.csv + + # gtfs_path: gtfs_idf + + # income_com_path: filosofi_2019/indic-struct-distrib-revenu-2019-COMMUNES.zip + # income_com_xlsx: FILO2019_DISP_COM.xlsx + # income_reg_path: filosofi_2019/indic-struct-distrib-revenu-2019-SUPRA.zip + # income_reg_xlsx: FILO2019_DISP_REG.xlsx + # income_year: 19 + + # tiles_path: tiles_2019/Filosofi2019_carreaux_200m_gpkg.zip + # tiles_file: carreaux_200m_met.gpkg + + # od_pro_path: rp_2019/RP2019_MOBPRO_csv.zip + # od_sco_path: rp_2019/RP2019_MOBSCO_csv.zip + # od_pro_csv: FD_MOBPRO_2019.csv + # od_sco_csv: FD_MOBSCO_2019.csv + + # ## external education locations file + # education_file: education/education_addresses.geojson + + # osm_path: osm_idf + # osm_highways: "*" + # osm_railways: "*" + + # siren_path: sirene/StockUniteLegale_utf8.zip + # siret_path: sirene/StockEtablissement_utf8.zip + # siret_geo_path: sirene/GeolocalisationEtablissement_Sirene_pour_etudes_statistiques_utf8.zip + + # iris_path: iris_2021 + + # population_path: rp_2019/base-ic-evol-struct-pop-2019.zip + # population_xlsx: base-ic-evol-struct-pop-2019.xlsx + # population_year: 19 + + # # population projections + # projection_path: projection_2021 + # projection_scenario: 00_central + # projection_year: 2030 + + # vehicles_method: default # fleet_sample, default + # vehicles_path: vehicles + # vehicles_year: 2021 \ No newline at end of file From 0b13eb08a0c001791e4e163ae7c0d84c35ee9c1e Mon Sep 17 00:00:00 2001 From: Valentin LE BESCOND Date: Thu, 14 Nov 2024 10:44:46 +0100 Subject: [PATCH 2/2] chore: change name and dceorate more --- full_config.yml => config_full.yml | 46 ++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 12 deletions(-) rename full_config.yml => config_full.yml (84%) diff --git a/full_config.yml b/config_full.yml similarity index 84% rename from full_config.yml rename to config_full.yml index efdddf6..2bc6593 100644 --- a/full_config.yml +++ b/config_full.yml @@ -12,12 +12,16 @@ run: # Here the configuraiton of the pipeline starts config: - ### Some general configuration + ############################## + # Some general configuration # + ############################## ## Number of CPUs to use processes: 4 - ### Random seeds + ################ + # Random seeds # + ################ ## global random seed for the output population random_seed: 1234 @@ -25,10 +29,15 @@ config: ## bpe specific random seed when impute missing coordinates for known IRIS # bpe_random_seed: 0 - ### Define sampling rate for the output population + ################################################## + # Define sampling rate for the output population # + ################################################## + sampling_rate: 0.001 - ### household travel survey (HTS) + ################################# + # household travel survey (HTS) # + ################################# ## Define whether to use ENTD or EGT as the HTS hts: entd # entd, egt, edgt_lyon, edgt_44 @@ -39,7 +48,9 @@ config: ## if selected, chose the source for edgt_lyon # edgt_lyon_source: unchosen # unchosen, adisp, cerema - ### Zone selection + ################## + # Zone selection # + ################## ## select regions by region_id # regions: [11] @@ -47,7 +58,9 @@ config: ## select departments by department_id # departments: [] - ### Output paths + ####################### + # Output paths # + ####################### ## output folder output_path: output @@ -58,7 +71,9 @@ config: ## file formats that should be exported # output_formats: ["csv", "gpkg"] # ["csv", "gpkg", "parquet", "geoparquet"] - ### Algorithms configurations + ############################## + # Algorithms configurations # + ############################## ## Use the bhepop2 package for attributing income # income_assignation_method: bhepop2 # uniform, bhepop2 @@ -104,7 +119,9 @@ config: ## creating the far or not # write_jar: true - ### Analysis configuration + ############################ + # Analysis configuration # + ############################ ## Whether to use previously generated files or not # analysis_from_file: false @@ -112,7 +129,9 @@ config: ## prefix of the files to compare to # comparison_file_prefix: other_ - ### Tools configuration + ########################## + # Tools configuration # + ########################## ## Mostly interesting if you run the simulation, or you activate the `mode_choice` option, @@ -139,10 +158,13 @@ config: ## Strategy to use in pt2matsim gtfs processing # gtfs_date: dayWithMostServices + ## Export the detailed geometry of the network before simplification in pt2matsim # export_detailed_network: true - ### Input paths + ################# + # Input paths # + ################# ## Absolute root path of all input data data_path: /path/to/my/data @@ -173,7 +195,7 @@ config: # od_pro_csv: FD_MOBPRO_2019.csv # od_sco_csv: FD_MOBSCO_2019.csv - # ## external education locations file + ## external education locations file # education_file: education/education_addresses.geojson # osm_path: osm_idf @@ -190,7 +212,7 @@ config: # population_xlsx: base-ic-evol-struct-pop-2019.xlsx # population_year: 19 - # # population projections + ## population projections # projection_path: projection_2021 # projection_scenario: 00_central # projection_year: 2030