diff --git a/.github/workflows/train.yaml b/.github/workflows/train.yaml
index bc1f8001..321325b3 100644
--- a/.github/workflows/train.yaml
+++ b/.github/workflows/train.yaml
@@ -12,7 +12,8 @@ jobs:
         run: |
           pip install -r requirements.txt
           dvc repro 
-
+          
+          # This is needed to compare the differences of the various ML approaches
           git fetch --prune
           dvc metrics diff --show-md master > report.md
 
diff --git a/.vscode/launch.json b/.vscode/launch.json
new file mode 100644
index 00000000..17e15f27
--- /dev/null
+++ b/.vscode/launch.json
@@ -0,0 +1,15 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Current File",
+            "type": "python",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal"
+        }
+    ]
+}
\ No newline at end of file
diff --git a/dvc.lock b/dvc.lock
index 64c1df08..82ef3799 100644
--- a/dvc.lock
+++ b/dvc.lock
@@ -1,30 +1,41 @@
-get_data:
-  cmd: python get_data.py
-  deps:
-  - path: get_data.py
-    md5: 1db5f442403042e0403c75132fe59af4
-  outs:
-  - path: data_raw.csv
-    md5: a6aec8da63a5fa2619af025a76746f29
-process:
-  cmd: python process_data.py
-  deps:
-  - path: data_raw.csv
-    md5: a6aec8da63a5fa2619af025a76746f29
-  - path: process_data.py
-    md5: 79b357c12f171f3d07c76780815b651c
-  outs:
-  - path: data_processed.csv
-    md5: 3b20a3a6ac0570f3de28b77d1e88f932
-train:
-  cmd: python train.py
-  deps:
-  - path: data_processed.csv
-    md5: 3b20a3a6ac0570f3de28b77d1e88f932
-  - path: train.py
-    md5: 80ad33d8caf823fc1d5cdefcb5b9490a
-  outs:
-  - path: by_region.png
-    md5: e7f3818fac35589b0c46dd65f8293e74
-  - path: metrics.json
-    md5: f4844c28505568f336c5f91db3f1beb3
+schema: '2.0'
+stages:
+  get_data:
+    cmd: python get_data.py
+    deps:
+    - path: get_data.py
+      md5: 1db5f442403042e0403c75132fe59af4
+      size: 516
+    outs:
+    - path: data_raw.csv
+      md5: a6aec8da63a5fa2619af025a76746f29
+      size: 68868
+  process:
+    cmd: python process_data.py
+    deps:
+    - path: data_raw.csv
+      md5: a6aec8da63a5fa2619af025a76746f29
+      size: 68868
+    - path: process_data.py
+      md5: 79b357c12f171f3d07c76780815b651c
+      size: 928
+    outs:
+    - path: data_processed.csv
+      md5: 03269b6c0a766dc80e090326008765b3
+      size: 24333
+  train:
+    cmd: python train.py
+    deps:
+    - path: data_processed.csv
+      md5: 03269b6c0a766dc80e090326008765b3
+      size: 24333
+    - path: train.py
+      md5: 80ad33d8caf823fc1d5cdefcb5b9490a
+      size: 1524
+    outs:
+    - path: by_region.png
+      md5: a789d2d4025a7b0750e17088fe032d1f
+      size: 7914
+    - path: metrics.json
+      md5: f4844c28505568f336c5f91db3f1beb3
+      size: 89