diff --git a/modules/ml-pipeline/src/pipeline/configs/settings.yaml b/modules/ml-pipeline/src/pipeline/configs/settings.yaml index 838e9a9..a3db1ce 100644 --- a/modules/ml-pipeline/src/pipeline/configs/settings.yaml +++ b/modules/ml-pipeline/src/pipeline/configs/settings.yaml @@ -21,7 +21,8 @@ default: # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/dataset_rooms.parquet # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-25-08-36-36/dataset_rooms.parquet # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-26-10-31-39/dataset_rooms.parquet - data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet + # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet + data_filepath: s3://retrofit-data-dev/sap_change_model/2024-06-11-20-47-16/dataset_rooms.parquet train_proportion: 0.9 output_train_filepath: ./data/prepared_data/train.parquet output_test_filepath: ./data/prepared_data/test.parquet diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock index 31315db..41dde01 100644 --- a/modules/ml-pipeline/src/pipeline/dvc.lock +++ b/modules/ml-pipeline/src/pipeline/dvc.lock @@ -40,7 +40,7 @@ stages: default.feature_processor.feature_processor_config.target: sap_ending default.feature_processor.feature_processor_type: dataframe default.prepare_data.data_filepath: - s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet + s3://retrofit-data-dev/sap_change_model/2024-06-11-20-47-16/dataset_rooms.parquet default.prepare_data.input_dataclient_type: aws-s3 default.prepare_data.output_dataclient_type: local default.prepare_data.output_test_filepath: ./data/prepared_data/test.parquet @@ -49,8 +49,8 @@ stages: outs: - path: data/prepared_data/ hash: md5 - md5: 80c9e138146a1d96b9d16091c207e2e8.dir - size: 45056059 + md5: 2f170af5775ef9d73a6b0ed3179fe6bd.dir + size: 43067740 nfiles: 2 build_model: cmd: python 2_build_model.py @@ -61,8 +61,8 @@ stages: size: 4820 - path: data/prepared_data hash: md5 - md5: 80c9e138146a1d96b9d16091c207e2e8.dir - size: 45056059 + md5: 2f170af5775ef9d73a6b0ed3179fe6bd.dir + size: 43067740 nfiles: 2 params: configs/build_model.yaml: @@ -94,18 +94,18 @@ stages: outs: - path: data/fit_predictions/ hash: md5 - md5: d9c9afc05e8780db47c0548b19bf7d19.dir - size: 3349989 + md5: 1e064ffabd4d8d0b24a15a9fedc0f758.dir + size: 3429320 nfiles: 1 - path: data/model/ hash: md5 - md5: 13c3100e1486c27a83a8a47491077842.dir - size: 773523079 - nfiles: 36 + md5: 2267316ee27bdd5d0033e6185dac0ad7.dir + size: 717150406 + nfiles: 35 - path: metrics/fit_metrics.json hash: md5 - md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a - size: 224 + md5: de776a14048f7c144e88f4e09580cf9b + size: 225 generate_predictions: cmd: python 3_generate_predictions.py deps: @@ -115,13 +115,13 @@ stages: size: 2464 - path: data/model hash: md5 - md5: 13c3100e1486c27a83a8a47491077842.dir - size: 773523079 - nfiles: 36 + md5: 2267316ee27bdd5d0033e6185dac0ad7.dir + size: 717150406 + nfiles: 35 - path: data/prepared_data hash: md5 - md5: 80c9e138146a1d96b9d16091c207e2e8.dir - size: 45056059 + md5: 2f170af5775ef9d73a6b0ed3179fe6bd.dir + size: 43067740 nfiles: 2 params: configs/settings.yaml: @@ -133,8 +133,8 @@ stages: outs: - path: data/predictions/ hash: md5 - md5: 5d07bcebf3160a72bb18dfd79106e85c.dir - size: 463197 + md5: 37e288e451605b067876040f968c075f.dir + size: 476983 nfiles: 1 generate_metrics: cmd: python 4_generate_metrics.py @@ -145,13 +145,13 @@ stages: size: 3484 - path: data/predictions hash: md5 - md5: 5d07bcebf3160a72bb18dfd79106e85c.dir - size: 463197 + md5: 37e288e451605b067876040f968c075f.dir + size: 476983 nfiles: 1 - path: data/prepared_data hash: md5 - md5: 80c9e138146a1d96b9d16091c207e2e8.dir - size: 45056059 + md5: 2f170af5775ef9d73a6b0ed3179fe6bd.dir + size: 43067740 nfiles: 2 params: configs/settings.yaml: @@ -161,8 +161,8 @@ stages: outs: - path: metrics/metrics.json hash: md5 - md5: 3e08df02fd5c5d094bcf936e1338d596 - size: 223 + md5: 382fcdcdb0d449eec63644be8dba5205 + size: 224 generate_scenerio_metrics: cmd: python 5_generate_scenarios.py deps: @@ -182,9 +182,9 @@ stages: outs: - path: metrics/scenario_metrics.md hash: md5 - md5: fa4d6d7bbd7818613800da5f8f37ea96 + md5: 067f6f16752c789013178fa1d9c179c1 size: 363 - path: metrics/scenario_table.md hash: md5 - md5: d6baf100a1623cc2467c2f8221d314c9 + md5: 48c6c39108c27fb37016754ad44723ee size: 2133