From 37c6824f5f3f785b792cc5fe5d216df03081efde Mon Sep 17 00:00:00 2001 From: Michael Duong Date: Wed, 5 Nov 2025 14:05:06 +0000 Subject: [PATCH] alternate build --- .../src/pipeline/configs/build_model.yaml | 2 +- modules/ml-pipeline/src/pipeline/dvc.lock | 51 ++++++++++--------- 2 files changed, 28 insertions(+), 25 deletions(-) diff --git a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml index d0d3806..a4d4c31 100644 --- a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml +++ b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml @@ -28,7 +28,7 @@ default: 'GBM': [{'extra_trees': True, 'ag_args': {'name_suffix': 'XT'}}, {}, {'learning_rate': 0.03, 'num_leaves': 128, 'feature_fraction': 0.9, 'min_data_in_leaf': 3, 'ag_args': {'name_suffix': 'Large', 'priority': 0,}}], # 'GBM': [{}], 'CAT': [{}], - 'XGB': [{}], + 'XGB': [{}, {'max_depth': 10, 'ag_args': {'name_suffix': 'Deep'}}], 'FASTAI': [{}], 'RF': [{'criterion': 'gini', 'ag_args': {'name_suffix': 'Gini', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'entropy', 'ag_args': {'name_suffix': 'Entr', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'squared_error', 'ag_args': {'name_suffix': 'MSE', 'problem_types': ['regression', 'quantile']}}], 'XT': [{'criterion': 'gini', 'ag_args': {'name_suffix': 'Gini', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'entropy', 'ag_args': {'name_suffix': 'Entr', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'squared_error', 'ag_args': {'name_suffix': 'MSE', 'problem_types': ['regression', 'quantile']}}], diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock index e914805..4f24327 100644 --- a/modules/ml-pipeline/src/pipeline/dvc.lock +++ b/modules/ml-pipeline/src/pipeline/dvc.lock @@ -84,8 +84,8 @@ stages: outs: - path: data/prepared_data/ hash: md5 - md5: 93be1608a3ac26ad1cc61e03e9eda405.dir - size: 9623159 + md5: d74d92498c1641cffe971f6b0634ccb0.dir + size: 9623332 nfiles: 3 build_model: cmd: python 2_build_model.py @@ -96,8 +96,8 @@ stages: size: 4820 - path: data/prepared_data hash: md5 - md5: 93be1608a3ac26ad1cc61e03e9eda405.dir - size: 9623159 + md5: d74d92498c1641cffe971f6b0634ccb0.dir + size: 9623332 nfiles: 3 params: configs/build_model.yaml: @@ -148,6 +148,9 @@ stages: - {} XGB: - {} + - max_depth: 10 + ag_args: + name_suffix: Deep FASTAI: - {} RF: @@ -198,18 +201,18 @@ stages: outs: - path: data/fit_predictions/ hash: md5 - md5: 19815d7a7ce972b3fedd470f2166f748.dir - size: 1545546 + md5: c9c8140e5a9fe111e5670810a36cd2ef.dir + size: 1545780 nfiles: 1 - path: data/model/ hash: md5 - md5: af81d84cb9ec873c8a613c74cbd43259.dir - size: 210837341 - nfiles: 31 + md5: d9f63a57f146409734cd8f84f707b3d9.dir + size: 233231379 + nfiles: 34 - path: metrics/fit_metrics.json hash: md5 - md5: 4ab313ac1c4194dd411aae48a0133805 - size: 211 + md5: a3d0eefbd5bd873fa0cd42390ac9575a + size: 214 generate_predictions: cmd: python 3_generate_predictions.py deps: @@ -219,13 +222,13 @@ stages: size: 2464 - path: data/model hash: md5 - md5: af81d84cb9ec873c8a613c74cbd43259.dir - size: 210837341 - nfiles: 31 + md5: d9f63a57f146409734cd8f84f707b3d9.dir + size: 233231379 + nfiles: 34 - path: data/prepared_data hash: md5 - md5: 93be1608a3ac26ad1cc61e03e9eda405.dir - size: 9623159 + md5: d74d92498c1641cffe971f6b0634ccb0.dir + size: 9623332 nfiles: 3 params: configs/settings.yaml: @@ -239,8 +242,8 @@ stages: outs: - path: data/predictions/ hash: md5 - md5: 216bd74b3a26af7201e7cb60822bec30.dir - size: 163454 + md5: 95172b679bf045e30fde8b6326780e15.dir + size: 163474 nfiles: 1 generate_metrics: cmd: python 4_generate_metrics.py @@ -251,13 +254,13 @@ stages: size: 3484 - path: data/predictions hash: md5 - md5: 216bd74b3a26af7201e7cb60822bec30.dir - size: 163454 + md5: 95172b679bf045e30fde8b6326780e15.dir + size: 163474 nfiles: 1 - path: data/prepared_data hash: md5 - md5: 93be1608a3ac26ad1cc61e03e9eda405.dir - size: 9623159 + md5: d74d92498c1641cffe971f6b0634ccb0.dir + size: 9623332 nfiles: 3 params: configs/settings.yaml: @@ -267,8 +270,8 @@ stages: outs: - path: metrics/metrics.json hash: md5 - md5: f60c70d023919a9d1e5c0da1b0ec2af5 - size: 209 + md5: c079b41b1a0033b666f27f99be4e12ef + size: 212 generate_scenerio_metrics: cmd: python 5_generate_scenarios.py deps: