junte/ML
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/ML.git synced 2026-06-08 11:17:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'sap-dev' of github.com:Hestia-Homes/ML into sap-dev-revert

Browse source
This commit is contained in:
Michael Duong 2024-02-16 16:25:57 +00:00
commit e060aeb4c0
5 changed files with 31 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
MODEL_REGISTRY.md
View file

@ -8,9 +8,9 @@
"active": true
},
"sap": {
"version": "v0.6.0",
"version": "v0.9.0",
"stage": {
"dev": "v0.6.0"
"dev": "v0.9.0"
},
"registered": true,
"active": true

BIN
modules/ml-pipeline/src/pipeline/analysis/feature_importance.parquet
View file

Binary file not shown.

2
modules/ml-pipeline/src/pipeline/configs/build_model.yaml
View file

@ -16,6 +16,6 @@ default:
eval_metric: mean_squared_error #mean_absolute_error
time_limit: 4000
presets: medium_quality
excluded_model_types: ['RF', 'FASTAI', 'CAT', 'NN_TORCH', 'KNN', 'XT']
excluded_model_types: ['RF', 'NN_TORCH', 'KNN', 'XT', 'CAT', 'FASTAI']
infer_limit: 0.05
infer_limit_batch_size: 10000

3
modules/ml-pipeline/src/pipeline/configs/settings.yaml
View file

@ -22,7 +22,8 @@ default:
# 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_test.parquet
data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
# data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_rooms.parquet
# data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
train_proportion: 1
output_train_filepath: ./data/prepared_data/train.parquet

52
modules/ml-pipeline/src/pipeline/dvc.lock
View file

@ -22,7 +22,7 @@ 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_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
@ -31,8 +31,8 @@ stages:
outs:
- path: data/prepared_data/
hash: md5
md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
size: 42626894
md5: 8f0f5481075094460ab852ace2fa9b7a.dir
size: 43692138
nfiles: 2
build_model:
cmd: python 2_build_model.py
@ -43,8 +43,8 @@ stages:
size: 4820
- path: data/prepared_data
hash: md5
md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
size: 42626894
md5: 8f0f5481075094460ab852ace2fa9b7a.dir
size: 43692138
nfiles: 2
params:
configs/build_model.yaml:
@ -65,28 +65,28 @@ stages:
presets: medium_quality
excluded_model_types:
- RF
- FASTAI
- CAT
- NN_TORCH
- KNN
- XT
- CAT
- FASTAI
infer_limit: 0.05
infer_limit_batch_size: 10000
outs:
- path: data/fit_predictions/
hash: md5
md5: e0a11ac6e4adf69d6180c0217c639a0e.dir
size: 3680908
md5: e2a05a84a14d35516a6cda8e0a1e963c.dir
size: 3681005
nfiles: 1
- path: data/model/
hash: md5
md5: bdaaf823857f9dc7b6ee2d4b88927cc1.dir
size: 805896324
nfiles: 31
md5: 7b0382d001ed2bd7aec5c8112f69d129.dir
size: 793365790
nfiles: 30
- path: metrics/fit_metrics.json
hash: md5
md5: 0ed5b1141bbb8bc3156e7c056b29f3cd
size: 225
md5: bcfd8d3bd3af858fa3dc26433bc8cd9e
size: 224
generate_predictions:
cmd: python 3_generate_predictions.py
deps:
@ -96,13 +96,13 @@ stages:
size: 2464
- path: data/model
hash: md5
md5: bdaaf823857f9dc7b6ee2d4b88927cc1.dir
size: 805896324
nfiles: 31
md5: 7b0382d001ed2bd7aec5c8112f69d129.dir
size: 793365790
nfiles: 30
- path: data/prepared_data
hash: md5
md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
size: 42626894
md5: 8f0f5481075094460ab852ace2fa9b7a.dir
size: 43692138
nfiles: 2
params:
configs/settings.yaml:
@ -114,8 +114,8 @@ stages:
outs:
- path: data/predictions/
hash: md5
md5: 38707d16ae1e2330cc03f524db9cdd60.dir
size: 648730
md5: 90b5275b5d9829a42573ade3f5a025d2.dir
size: 648526
nfiles: 1
generate_metrics:
cmd: python 4_generate_metrics.py
@ -126,13 +126,13 @@ stages:
size: 3484
- path: data/predictions
hash: md5
md5: 38707d16ae1e2330cc03f524db9cdd60.dir
size: 648730
md5: 90b5275b5d9829a42573ade3f5a025d2.dir
size: 648526
nfiles: 1
- path: data/prepared_data
hash: md5
md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
size: 42626894
md5: 8f0f5481075094460ab852ace2fa9b7a.dir
size: 43692138
nfiles: 2
params:
configs/settings.yaml:
@ -142,7 +142,7 @@ stages:
outs:
- path: metrics/metrics.json
hash: md5
md5: 145e7ac84ab4a4407b23695a632b4d91
md5: be48389ba2755e6c18e41243aaa9bb81
size: 226
startup_cleanup:
cmd: python 0_startup_cleanup.py