From d5f40a8eb294924e0525904d6ee1864999d77c23 Mon Sep 17 00:00:00 2001 From: Michael Duong Date: Sat, 17 Feb 2024 21:17:34 +0000 Subject: [PATCH] only ending --- .../src/pipeline/configs/settings.yaml | 29 ++++---- modules/ml-pipeline/src/pipeline/dvc.lock | 67 +++++++------------ 2 files changed, 36 insertions(+), 60 deletions(-) diff --git a/modules/ml-pipeline/src/pipeline/configs/settings.yaml b/modules/ml-pipeline/src/pipeline/configs/settings.yaml index dc28a9a..a85d3ab 100644 --- a/modules/ml-pipeline/src/pipeline/configs/settings.yaml +++ b/modules/ml-pipeline/src/pipeline/configs/settings.yaml @@ -24,7 +24,7 @@ default: # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_test.parquet data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet # data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet - train_proportion: 0.95 + train_proportion: 0.98 output_train_filepath: ./data/prepared_data/train.parquet output_test_filepath: ./data/prepared_data/test.parquet @@ -41,29 +41,24 @@ default: 'walls_energy_eff_ending', 'secondheat_description_ending', 'property_type', 'mainheatc_energy_eff_ending', 'built_form', 'walls_insulation_thickness_ending', 'potential_energy_efficiency', - 'transaction_type_ending', 'mainheat_energy_eff_starting', - 'floor_thermal_transmittance_ending', 'hot_water_energy_eff_starting', + 'transaction_type_ending', + 'floor_thermal_transmittance_ending', 'low_energy_lighting_ending', 'heat_demand_starting', 'photo_supply_ending', 'carbon_starting', - 'walls_thermal_transmittance_ending', 'fuel_type_ending', - 'roof_insulation_thickness_ending', 'transaction_type_starting', + 'walls_thermal_transmittance_ending', + 'roof_insulation_thickness_ending', 'total_floor_area_ending', 'number_open_fireplaces_ending', - 'roof_insulation_thickness', 'windows_energy_eff_ending', - 'walls_insulation_thickness', 'floor_height_ending', - 'secondheat_description_starting', 'floor_thermal_transmittance', - 'mainheatc_energy_eff_starting', 'extension_count_ending', - 'has_air_source_heat_pump_ending', 'walls_energy_eff_starting', + 'windows_energy_eff_ending', + 'floor_height_ending', + 'extension_count_ending', + 'has_air_source_heat_pump_ending', 'charging_system_ending', 'construction_age_band', 'glazed_type_ending', 'roof_thermal_transmittance_ending', 'floor_insulation_thickness_ending', 'has_mains_gas_ending', 'estimated_perimeter_starting', 'energy_consumption_potential', - 'environment_impact_potential', 'roof_energy_eff_starting', - 'another_property_below', 'heater_type_ending', - 'walls_thermal_transmittance', 'total_floor_area_starting', - 'multi_glaze_proportion_ending', 'is_suspended', - 'floor_height_starting', 'lighting_energy_eff_ending', - 'energy_tariff_ending', 'fixed_lighting_outlets_count', - 'low_energy_lighting_starting', 'mechanical_ventilation_ending'] + 'environment_impact_potential', 'heater_type_ending', + 'multi_glaze_proportion_ending', + 'lighting_energy_eff_ending', 'fixed_lighting_outlets_count'] # retain_features: null generate_predictions: diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock index 05844e3..71a9c44 100644 --- a/modules/ml-pipeline/src/pipeline/dvc.lock +++ b/modules/ml-pipeline/src/pipeline/dvc.lock @@ -32,29 +32,19 @@ stages: - walls_insulation_thickness_ending - potential_energy_efficiency - transaction_type_ending - - mainheat_energy_eff_starting - floor_thermal_transmittance_ending - - hot_water_energy_eff_starting - low_energy_lighting_ending - heat_demand_starting - photo_supply_ending - carbon_starting - walls_thermal_transmittance_ending - - fuel_type_ending - roof_insulation_thickness_ending - - transaction_type_starting - total_floor_area_ending - number_open_fireplaces_ending - - roof_insulation_thickness - windows_energy_eff_ending - - walls_insulation_thickness - floor_height_ending - - secondheat_description_starting - - floor_thermal_transmittance - - mainheatc_energy_eff_starting - extension_count_ending - has_air_source_heat_pump_ending - - walls_energy_eff_starting - charging_system_ending - construction_age_band - glazed_type_ending @@ -64,19 +54,10 @@ stages: - estimated_perimeter_starting - energy_consumption_potential - environment_impact_potential - - roof_energy_eff_starting - - another_property_below - heater_type_ending - - walls_thermal_transmittance - - total_floor_area_starting - multi_glaze_proportion_ending - - is_suspended - - floor_height_starting - lighting_energy_eff_ending - - energy_tariff_ending - fixed_lighting_outlets_count - - low_energy_lighting_starting - - mechanical_ventilation_ending default.feature_processor.feature_processor_config.subsample_amount: default.feature_processor.feature_processor_config.subsample_seed: 0 default.feature_processor.feature_processor_config.target: sap_ending @@ -86,12 +67,12 @@ stages: default.prepare_data.output_dataclient_type: local default.prepare_data.output_test_filepath: ./data/prepared_data/test.parquet default.prepare_data.output_train_filepath: ./data/prepared_data/train.parquet - default.prepare_data.train_proportion: 0.95 + default.prepare_data.train_proportion: 0.98 outs: - path: data/prepared_data/ hash: md5 - md5: 59f8ea78ec225f5a05de451c6145e2d5.dir - size: 34059502 + md5: 544427230544c2cc526334e246db4845.dir + size: 26132493 nfiles: 2 build_model: cmd: python 2_build_model.py @@ -102,8 +83,8 @@ stages: size: 4820 - path: data/prepared_data hash: md5 - md5: 59f8ea78ec225f5a05de451c6145e2d5.dir - size: 34059502 + md5: 544427230544c2cc526334e246db4845.dir + size: 26132493 nfiles: 2 params: configs/build_model.yaml: @@ -134,18 +115,18 @@ stages: outs: - path: data/fit_predictions/ hash: md5 - md5: bb74626ff3d33581efe750955cdff860.dir - size: 3539589 + md5: 8f9e2059782dd55d3ecdad54b4551f6a.dir + size: 3630849 nfiles: 1 - path: data/model/ hash: md5 - md5: e100d4dcccc1c7d30367b0ca0672e3af.dir - size: 654714285 + md5: e031eb3c3fdb63917aabfea745b56ac6.dir + size: 618445494 nfiles: 31 - path: metrics/fit_metrics.json hash: md5 - md5: d074f5aa588d3405be65a9684f192465 - size: 226 + md5: e68009f5b66230b3ee4cd2ffc9a2d697 + size: 222 generate_predictions: cmd: python 3_generate_predictions.py deps: @@ -155,13 +136,13 @@ stages: size: 2464 - path: data/model hash: md5 - md5: e100d4dcccc1c7d30367b0ca0672e3af.dir - size: 654714285 + md5: e031eb3c3fdb63917aabfea745b56ac6.dir + size: 618445494 nfiles: 31 - path: data/prepared_data hash: md5 - md5: 59f8ea78ec225f5a05de451c6145e2d5.dir - size: 34059502 + md5: 544427230544c2cc526334e246db4845.dir + size: 26132493 nfiles: 2 params: configs/settings.yaml: @@ -173,8 +154,8 @@ stages: outs: - path: data/predictions/ hash: md5 - md5: 36e26c509176caae6290f75ad486810d.dir - size: 232044 + md5: 1c14c9ac9711f5d33a60890e3ca72454.dir + size: 90361 nfiles: 1 generate_metrics: cmd: python 4_generate_metrics.py @@ -185,13 +166,13 @@ stages: size: 3484 - path: data/predictions hash: md5 - md5: 36e26c509176caae6290f75ad486810d.dir - size: 232044 + md5: 1c14c9ac9711f5d33a60890e3ca72454.dir + size: 90361 nfiles: 1 - path: data/prepared_data hash: md5 - md5: 59f8ea78ec225f5a05de451c6145e2d5.dir - size: 34059502 + md5: 544427230544c2cc526334e246db4845.dir + size: 26132493 nfiles: 2 params: configs/settings.yaml: @@ -201,8 +182,8 @@ stages: outs: - path: metrics/metrics.json hash: md5 - md5: 7b71931c5857358ca2603889de6abb3a - size: 223 + md5: 98e59ea9569522a8665c4e6c1bea7473 + size: 222 startup_cleanup: cmd: python 0_startup_cleanup.py deps: @@ -232,5 +213,5 @@ stages: outs: - path: metrics/scenario_table.md hash: md5 - md5: 72db7530c9ca42470ee8bd1a1e7b52b4 + md5: 3ee1966a06c1e5b9c37797597be94797 size: 1648