use test dataset

This commit is contained in:
Michael Duong 2023-10-18 13:27:25 +00:00
parent a60a3bd285
commit 790c3a9456
3 changed files with 23 additions and 23 deletions

View file

@ -13,6 +13,6 @@ default:
output_filepath: ./data/model/allmodels/
problem_type: regression
eval_metric: mean_squared_error #mean_absolute_error
time_limit: 180
time_limit: 4000
presets: medium_quality
excluded_model_types: ['KNN', 'RF']

View file

@ -21,7 +21,7 @@ default:
# data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_with_differencing.parquet
# data_filepath: s3://retrofit-data-dev/sap_change_model/floor_area_clean_test.parquet
# data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_without_differencing.parquet
data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_test.parquet
train_proportion: 0.9
output_train_filepath: ./data/prepared_data/train.parquet
output_test_filepath: ./data/prepared_data/test.parquet

View file

@ -20,7 +20,7 @@ stages:
default.feature_processor.feature_processor_config.subsample_seed: 0
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/dataset.parquet
default.prepare_data.data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_test.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
@ -29,8 +29,8 @@ stages:
outs:
- path: data/prepared_data/
hash: md5
md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
size: 33881619
md5: cd75be9fecff0c647792dd2db648085c.dir
size: 37056053
nfiles: 2
build_model:
cmd: python 2_build_model.py
@ -41,8 +41,8 @@ stages:
size: 5359
- path: data/prepared_data
hash: md5
md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
size: 33881619
md5: cd75be9fecff0c647792dd2db648085c.dir
size: 37056053
nfiles: 2
params:
configs/build_model.yaml:
@ -66,13 +66,13 @@ stages:
outs:
- path: data/model/
hash: md5
md5: 7bb5156243b4db39349e80a01ffecde4.dir
size: 473398662
md5: 7a5527f779efcb1a7db068148b6bcc45.dir
size: 422448184
nfiles: 27
- path: metrics/fit_metrics.json
hash: md5
md5: 2bb16ac67de8778fbc08171d562b34d5
size: 184
md5: 77790bb9485c04c77125e361921c3774
size: 225
generate_predictions:
cmd: python 3_generate_predictions.py
deps:
@ -82,13 +82,13 @@ stages:
size: 3028
- path: data/model
hash: md5
md5: 7bb5156243b4db39349e80a01ffecde4.dir
size: 473398662
md5: 7a5527f779efcb1a7db068148b6bcc45.dir
size: 422448184
nfiles: 27
- path: data/prepared_data
hash: md5
md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
size: 33881619
md5: cd75be9fecff0c647792dd2db648085c.dir
size: 37056053
nfiles: 2
params:
configs/settings.yaml:
@ -100,8 +100,8 @@ stages:
outs:
- path: data/predictions/
hash: md5
md5: 0bb3cf991906953def81c8204cdcfaf0.dir
size: 374532
md5: 28d2876e6c6d5cc64844ecc1d6ac40b2.dir
size: 346687
nfiles: 1
generate_metrics:
cmd: python 4_generate_metrics.py
@ -112,13 +112,13 @@ stages:
size: 4487
- path: data/predictions
hash: md5
md5: 0bb3cf991906953def81c8204cdcfaf0.dir
size: 374532
md5: 28d2876e6c6d5cc64844ecc1d6ac40b2.dir
size: 346687
nfiles: 1
- path: data/prepared_data
hash: md5
md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
size: 33881619
md5: cd75be9fecff0c647792dd2db648085c.dir
size: 37056053
nfiles: 2
params:
configs/settings.yaml:
@ -128,8 +128,8 @@ stages:
outs:
- path: metrics/metrics.json
hash: md5
md5: 2e13ae67759a64261d03224f1c0d4bf4
size: 185
md5: 7afd04d656dc83ad6aa942d9c63f5b4e
size: 224
startup_cleanup:
cmd: python 0_startup_cleanup.py
deps: