From 680e879503c5b4dafb4702a1ad9cb2391cb500fa Mon Sep 17 00:00:00 2001
From: Michael Duong <michael123ster@gmail.com>
Date: Wed, 11 Oct 2023 15:38:55 +0000
Subject: [PATCH] 400 second model

---
 .../src/pipeline/configs/build_model.yaml     |  2 +-
 .../pipeline/configs/post_prediction_logic.py | 13 +++---
 modules/ml-pipeline/src/pipeline/dvc.lock     | 46 +++++++++----------
 3 files changed, 30 insertions(+), 31 deletions(-)

diff --git a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
index ee7394e..7e409bf 100644
--- a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
+++ b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml
@@ -13,6 +13,6 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 60
+      time_limit: 400
       presets: medium_quality
       excluded_model_types: ['KNN', 'RF']
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 bb36713..1ffab90 100644
--- a/modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py
+++ b/modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py
@@ -5,19 +5,18 @@ import pandas as pd
 
 
 def clip_predictions_to_minimum_value(
-    data: pd.DataFrame, predictions: pd.Series, minimum_value: int = 1
+    data: pd.DataFrame,
+    predictions: pd.Series,
 ) -> pd.Series:
 
     series_name = predictions.name
     predictions.name = "predictions"
     predictions_df = pd.concat([data, predictions], axis=1)
     # We expect all prediction to be atleast one point improvement
-    replace_index = (
-        predictions_df["predictions"] > predictions_df["CARBON_STARTING"] - 1
-    )
-    predictions_df.loc[replace_index, "predictions"] = (
-        predictions_df.loc[replace_index, "CARBON_STARTING"] - minimum_value
-    )
+    replace_index = predictions_df["predictions"] > predictions_df["CARBON_STARTING"]
+    predictions_df.loc[replace_index, "predictions"] = predictions_df.loc[
+        replace_index, "CARBON_STARTING"
+    ]
 
     predictions_new = predictions_df["predictions"]
     predictions_new.name = series_name
diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock
index d2291d8..2056834 100644
--- a/modules/ml-pipeline/src/pipeline/dvc.lock
+++ b/modules/ml-pipeline/src/pipeline/dvc.lock
@@ -29,8 +29,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: cd9a3d5e6208c1fd5de513b4d5c51b5b.dir
-      size: 30121189
+      md5: 5fd3c01804ee2994ee77fc501d178be4.dir
+      size: 30137355
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -41,8 +41,8 @@ stages:
       size: 5359
     - path: data/prepared_data
       hash: md5
-      md5: cd9a3d5e6208c1fd5de513b4d5c51b5b.dir
-      size: 30121189
+      md5: 5fd3c01804ee2994ee77fc501d178be4.dir
+      size: 30137355
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -58,7 +58,7 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 60
+              time_limit: 400
               presets: medium_quality
               excluded_model_types:
               - KNN
@@ -66,13 +66,13 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: 0d43e4ac3985da215dadf5fed8e68200.dir
-      size: 210841782
-      nfiles: 21
+      md5: 4b49c12395a645e35e50a9de8840f08d.dir
+      size: 282024140
+      nfiles: 24
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 06f8bb0d004b91c33493dbee9a8763e7
-      size: 206
+      md5: a6d139fa59f5ddf75023bb7d3364f6d2
+      size: 225
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -82,13 +82,13 @@ stages:
       size: 3028
     - path: data/model
       hash: md5
-      md5: 0d43e4ac3985da215dadf5fed8e68200.dir
-      size: 210841782
-      nfiles: 21
+      md5: 4b49c12395a645e35e50a9de8840f08d.dir
+      size: 282024140
+      nfiles: 24
     - path: data/prepared_data
       hash: md5
-      md5: cd9a3d5e6208c1fd5de513b4d5c51b5b.dir
-      size: 30121189
+      md5: 5fd3c01804ee2994ee77fc501d178be4.dir
+      size: 30137355
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -100,8 +100,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: acdcb06ee7574672b1148c10c37a868b.dir
-      size: 275959
+      md5: 8f724261b3d17bf87067e91a1ff99077.dir
+      size: 441423
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -112,13 +112,13 @@ stages:
       size: 4487
     - path: data/predictions
       hash: md5
-      md5: acdcb06ee7574672b1148c10c37a868b.dir
-      size: 275959
+      md5: 8f724261b3d17bf87067e91a1ff99077.dir
+      size: 441423
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: cd9a3d5e6208c1fd5de513b4d5c51b5b.dir
-      size: 30121189
+      md5: 5fd3c01804ee2994ee77fc501d178be4.dir
+      size: 30137355
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -128,8 +128,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: e3bdc173023a7d909704f0313aa1609f
-      size: 219
+      md5: 38787835f838f65c6cc75654843eb311
+      size: 223
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps: