From 43ac0c98d00926dc6d32de4502f9204f88d14e24 Mon Sep 17 00:00:00 2001
From: Michael Duong <michael123ster@gmail.com>
Date: Thu, 28 Sep 2023 19:33:41 +0000
Subject: [PATCH] correct logic

---
 .../src/pipeline/configs/build_model.yaml     |  2 +-
 .../pipeline/configs/post_prediction_logic.py |  2 +-
 modules/ml-pipeline/src/pipeline/dvc.lock     | 50 +++++++++----------
 3 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
index e0cc3d3..08108fb 100644
--- a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
+++ b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
@@ -11,6 +11,6 @@ AutogluonAutoML:
   output_filepath: ./data/model/autogluonmodel/
   problem_type: regression
   eval_metric: mean_absolute_error
-  time_limit: 600
+  time_limit: 800
   presets: medium_quality
   excluded_model_types: ['KNN']
diff --git a/modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py b/modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py
index 95cb293..903da7d 100644
--- a/modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py
+++ b/modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py
@@ -11,7 +11,7 @@ def clip_predictions_to_minimum_value(
     series_name = predictions.name
     predictions.name = "predictions"
     predictions_df = pd.concat([data, predictions], axis=1)
-    replace_index = predictions_df["SAP_STARTING"] > predictions_df["predictions"]
+    replace_index = predictions_df["SAP_STARTING"] + 1 > predictions_df["predictions"]
     predictions_df.loc[replace_index, "predictions"] = (
         predictions_df.loc[replace_index, "SAP_STARTING"] + minimum_value
     )
diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock
index 6197fe7..d205374 100644
--- a/modules/ml-pipeline/src/pipeline/dvc.lock
+++ b/modules/ml-pipeline/src/pipeline/dvc.lock
@@ -15,20 +15,20 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 2f00c92bf2fff7ed8006f4036f8f7d06.dir
-      size: 21102167
+      md5: 7bcbf81a82015276e25749d1bc249a57.dir
+      size: 21076961
       nfiles: 2
   build_model:
     cmd: python build_model.py
     deps:
     - path: build_model.py
       hash: md5
-      md5: 84b86e829cb164fb2a202033f39e66e8
-      size: 5243
+      md5: 3eb1a5110df6e25a23d8e8a92bb27823
+      size: 5257
     - path: data/prepared_data
       hash: md5
-      md5: 2f00c92bf2fff7ed8006f4036f8f7d06.dir
-      size: 21102167
+      md5: 7bcbf81a82015276e25749d1bc249a57.dir
+      size: 21076961
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -36,7 +36,7 @@ stages:
           output_filepath: ./data/model/autogluonmodel/
           problem_type: regression
           eval_metric: mean_absolute_error
-          time_limit: 600
+          time_limit: 800
           presets: medium_quality
           excluded_model_types:
           - KNN
@@ -49,30 +49,30 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: d9b051bb9cc626b4fc4b77873838f029.dir
-      size: 242877007
+      md5: 397c46c062b51034b6f8f3f229345de3.dir
+      size: 334481421
       nfiles: 18
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: bbf8a1bb90cd8d9fea447ca97fe8eea3
-      size: 180
+      md5: f6e7e21d4229d4a229ea0a11f3023637
+      size: 184
   generate_predictions:
     cmd: python generate_predictions.py
     deps:
     - path: data/model
       hash: md5
-      md5: d9b051bb9cc626b4fc4b77873838f029.dir
-      size: 242877007
+      md5: 397c46c062b51034b6f8f3f229345de3.dir
+      size: 334481421
       nfiles: 18
     - path: data/prepared_data
       hash: md5
-      md5: 2f00c92bf2fff7ed8006f4036f8f7d06.dir
-      size: 21102167
+      md5: 7bcbf81a82015276e25749d1bc249a57.dir
+      size: 21076961
       nfiles: 2
     - path: generate_predictions.py
       hash: md5
-      md5: 20c4657f5872cb8b60b69344600251b8
-      size: 4420
+      md5: 874da2443ef0d92731e4c127f3ce4acb
+      size: 4434
     params:
       configs/generate_predictions.yaml:
         input_dataclient_type: local
@@ -83,21 +83,21 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 81f707df70bc0d9f7b305427e0034ed1.dir
-      size: 383598
+      md5: 9c18005e722f0e428f4b83c3f974f206.dir
+      size: 381870
       nfiles: 1
   generate_metrics:
     cmd: python generate_metrics.py
     deps:
     - path: data/predictions
       hash: md5
-      md5: 81f707df70bc0d9f7b305427e0034ed1.dir
-      size: 383598
+      md5: 9c18005e722f0e428f4b83c3f974f206.dir
+      size: 381870
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 2f00c92bf2fff7ed8006f4036f8f7d06.dir
-      size: 21102167
+      md5: 7bcbf81a82015276e25749d1bc249a57.dir
+      size: 21076961
       nfiles: 2
     - path: generate_metrics.py
       hash: md5
@@ -111,8 +111,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 75baa77d94386c9a567afdac48384435
-      size: 185
+      md5: 93d9b69d6cd951ae2c14b29ba92a2a38
+      size: 186
   startup_cleanup:
     cmd: python startup_cleanup.py
     deps: