From eeb653c0415e8c6a24144c5a98af76fb16f8f525 Mon Sep 17 00:00:00 2001
From: Michael Duong <michael123ster@gmail.com>
Date: Sat, 10 Feb 2024 11:03:38 +0000
Subject: [PATCH] new model

---
 .../src/pipeline/configs/settings.yaml        |  4 +-
 modules/ml-pipeline/src/pipeline/dvc.lock     | 44 +++++++++----------
 2 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/modules/ml-pipeline/src/pipeline/configs/settings.yaml b/modules/ml-pipeline/src/pipeline/configs/settings.yaml
index 98cf6dc..19b0a5b 100644
--- a/modules/ml-pipeline/src/pipeline/configs/settings.yaml
+++ b/modules/ml-pipeline/src/pipeline/configs/settings.yaml
@@ -22,8 +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-datalake-dev/dataset_with0perm_all.parquet
+    data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
+    # data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
     train_proportion: 1
     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 69729e0..826e654 100644
--- a/modules/ml-pipeline/src/pipeline/dvc.lock
+++ b/modules/ml-pipeline/src/pipeline/dvc.lock
@@ -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-datalake-dev/dataset_with0perm_all.parquet
+        default.prepare_data.data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.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: cfaebbb77306750fcc9a39adbb40015b.dir
-      size: 41367957
+      md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
+      size: 42626894
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -43,8 +43,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: cfaebbb77306750fcc9a39adbb40015b.dir
-      size: 41367957
+      md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
+      size: 42626894
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -75,17 +75,17 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: f15cbb7486924de81c5bf032b5ca962d.dir
-      size: 3572461
+      md5: e0a11ac6e4adf69d6180c0217c639a0e.dir
+      size: 3680908
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 5d41efafd16cda31e10a0ca1a0a19759.dir
-      size: 798325885
+      md5: bdaaf823857f9dc7b6ee2d4b88927cc1.dir
+      size: 805896324
       nfiles: 31
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 7790bc6b081a2c933547f67c843fef10
+      md5: 0ed5b1141bbb8bc3156e7c056b29f3cd
       size: 225
   generate_predictions:
     cmd: python 3_generate_predictions.py
@@ -96,13 +96,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 5d41efafd16cda31e10a0ca1a0a19759.dir
-      size: 798325885
+      md5: bdaaf823857f9dc7b6ee2d4b88927cc1.dir
+      size: 805896324
       nfiles: 31
     - path: data/prepared_data
       hash: md5
-      md5: cfaebbb77306750fcc9a39adbb40015b.dir
-      size: 41367957
+      md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
+      size: 42626894
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -114,8 +114,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 0f476eaeaca81fbc7fac9400c77f653a.dir
-      size: 626833
+      md5: 38707d16ae1e2330cc03f524db9cdd60.dir
+      size: 648730
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -126,13 +126,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 0f476eaeaca81fbc7fac9400c77f653a.dir
-      size: 626833
+      md5: 38707d16ae1e2330cc03f524db9cdd60.dir
+      size: 648730
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: cfaebbb77306750fcc9a39adbb40015b.dir
-      size: 41367957
+      md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
+      size: 42626894
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -142,8 +142,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: e000a99df92dc0c7ca86b020cbcd6b5b
-      size: 224
+      md5: 145e7ac84ab4a4407b23695a632b4d91
+      size: 226
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps: