From f92c97f6cfb832feff1fee4a77a484251bf3f81f Mon Sep 17 00:00:00 2001
From: Michael Duong <michael123ster@gmail.com>
Date: Fri, 9 Feb 2024 16:19:47 +0000
Subject: [PATCH] drop days_starting and days_ending

---
 .../src/pipeline/configs/build_model.yaml     |  2 +-
 .../src/pipeline/configs/settings.yaml        |  2 +-
 modules/ml-pipeline/src/pipeline/dvc.lock     | 56 ++++++++++---------
 3 files changed, 31 insertions(+), 29 deletions(-)

diff --git a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
index fcec7f7..f4770a7 100644
--- a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
+++ b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
@@ -14,7 +14,7 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 4000
+      time_limit: 400
       presets: medium_quality
       excluded_model_types: ['RF', 'FASTAI', 'CAT', 'NN_TORCH', 'KNN', 'XT']
       infer_limit: 0.05
diff --git a/modules/ml-pipeline/src/pipeline/configs/settings.yaml b/modules/ml-pipeline/src/pipeline/configs/settings.yaml
index 4327e64..98cf6dc 100644
--- a/modules/ml-pipeline/src/pipeline/configs/settings.yaml
+++ b/modules/ml-pipeline/src/pipeline/configs/settings.yaml
@@ -35,7 +35,7 @@ default:
       subsample_seed: 0
       target: sap_ending
       identifier_columns: ["uprn"]
-      drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending"]
+      drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", "days_to_starting", "days_to_ending"]
       # retain_features: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
       retain_features: null
 
diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock
index f15978f..9bb73b8 100644
--- a/modules/ml-pipeline/src/pipeline/dvc.lock
+++ b/modules/ml-pipeline/src/pipeline/dvc.lock
@@ -5,8 +5,8 @@ stages:
     deps:
     - path: 1_prepare_data.py
       hash: md5
-      md5: 1793a35e71751d3c84f9affc67ecb9a8
-      size: 4296
+      md5: 11a3b8bfdfe199ab7ecc39ccc5652649
+      size: 4298
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
@@ -15,6 +15,8 @@ stages:
         - rdsap_change
         - heat_demand_ending
         - carbon_ending
+        - days_to_starting
+        - days_to_ending
         default.feature_processor.feature_processor_config.retain_features:
         default.feature_processor.feature_processor_config.subsample_amount:
         default.feature_processor.feature_processor_config.subsample_seed: 0
@@ -29,8 +31,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 84fa631bd02686b052d6a7144eafd38e.dir
-      size: 43859225
+      md5: f85c36a5dfd31a897538b3934d5fb997.dir
+      size: 41375196
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -41,8 +43,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 84fa631bd02686b052d6a7144eafd38e.dir
-      size: 43859225
+      md5: f85c36a5dfd31a897538b3934d5fb997.dir
+      size: 41375196
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -59,7 +61,7 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 4000
+              time_limit: 400
               presets: medium_quality
               excluded_model_types:
               - RF
@@ -73,18 +75,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: ede187e9d0bffdef054f573f3c2bd222.dir
-      size: 3578590
+      md5: 991e6c55826953aa7c2be573369ec96f.dir
+      size: 3574047
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: b2ad0b538dc4aef0de3d431fc9c40c4f.dir
-      size: 814720415
-      nfiles: 31
+      md5: f8a8b7462831bd46b1e2df47d73bb69d.dir
+      size: 391430703
+      nfiles: 23
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: c45b84f12971a0156e4f3d85d3e725f5
-      size: 218
+      md5: 35a66a845854cc6fee9dd10860e216bb
+      size: 225
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -94,13 +96,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: b2ad0b538dc4aef0de3d431fc9c40c4f.dir
-      size: 814720415
-      nfiles: 31
+      md5: f8a8b7462831bd46b1e2df47d73bb69d.dir
+      size: 391430703
+      nfiles: 23
     - path: data/prepared_data
       hash: md5
-      md5: 84fa631bd02686b052d6a7144eafd38e.dir
-      size: 43859225
+      md5: f85c36a5dfd31a897538b3934d5fb997.dir
+      size: 41375196
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -112,8 +114,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 5e60ca251af51de6fef3d0c659f8bb27.dir
-      size: 627416
+      md5: 94b7381ac318b1ca18e0bc086778f7ce.dir
+      size: 626160
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -124,13 +126,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 5e60ca251af51de6fef3d0c659f8bb27.dir
-      size: 627416
+      md5: 94b7381ac318b1ca18e0bc086778f7ce.dir
+      size: 626160
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 84fa631bd02686b052d6a7144eafd38e.dir
-      size: 43859225
+      md5: f85c36a5dfd31a897538b3934d5fb997.dir
+      size: 41375196
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -140,8 +142,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 033efa4d4044b6b6fc92dd37194727fa
-      size: 225
+      md5: 4d8681f7c0f41f97be52d6b1ae039c5b
+      size: 224
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps: