add dockerfile for developement

modules/ml-pipeline/src/pipeline/.devcontainer/devcontainer.json

@@ -0,0 +1,29 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/docker-existing-dockerfile
+{
+	"name": "Existing Dockerfile",
+	"build": {
+		// Sets the run context to one level up instead of the .devcontainer folder.
+		"context": "..",
+		// Update the 'dockerFile' property if you aren't using the standard 'Dockerfile' filename.
+		"dockerfile": "../Dockerfile"
+	},
+	"features": {
+		"ghcr.io/devcontainers/features/git:1": {}
+	}
+
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Uncomment the next line to run commands after the container is created.
+	// "postCreateCommand": "cat /etc/os-release",
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as an existing user other than the container default. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "devcontainer"
+}

modules/ml-pipeline/src/pipeline/Dockerfile

@@ -1,4 +1,9 @@
 # Dockerfile that grabs the current dvc hashed model
-FROM python:3.9-slim
+FROM python:3.10.12-slim
+
+COPY training/requirements/requirements-dev.txt requirements.txt
+
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+
 
-RUN pip install -r experimentation/requirements/training.txt

modules/ml-pipeline/src/pipeline/training/.dvc/config

@@ -0,0 +1,2 @@
+['remote "myremote"']
+    url = /tmp/dvcstore

modules/ml-pipeline/src/pipeline/training/configs/prepare_data.yaml

@@ -1,6 +1,6 @@
 dataclient_type: minio
 data_location: s3://dev_bucket
-train_proportion: 0.8
+train_proportion: 0.75
 output_train_filepath: ./data/prepared_data/train.parquet
 output_test_filepath: ./data/prepared_data/test.parquet
 

modules/ml-pipeline/src/pipeline/training/dvc.lock

@@ -11,24 +11,24 @@ stages:
       configs/prepare_data.yaml:
         output_test_filepath: ./data/prepared_data/test.parquet
         output_train_filepath: ./data/prepared_data/train.parquet
-        train_proportion: 0.8
+        train_proportion: 0.75
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 9afb06007a6da3cef1619e937e9c413e.dir
-      size: 36344
+      md5: 5cededc181e2b86c8ff63498a3e79462.dir
+      size: 36481
       nfiles: 2
   build_model:
     cmd: python build_model.py
     deps:
     - path: build_model.py
       hash: md5
-      md5: 43ff6a4781efacff4234fe261022a5dd
+      md5: 152d52b7754b4c6f96f3481dc26562fc
       size: 3576
     - path: data/prepared_data
       hash: md5
-      md5: 9afb06007a6da3cef1619e937e9c413e.dir
-      size: 36344
+      md5: 5cededc181e2b86c8ff63498a3e79462.dir
+      size: 36481
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -41,7 +41,7 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: e0f58c7c4e12fa92b29d973dd5f3f565.dir
+      md5: e4904765c79b0139ccb80d56ef044383.dir
       size: 1096
       nfiles: 1
   generate_predictions:
@@ -49,18 +49,18 @@ stages:
     deps:
     - path: data/model
       hash: md5
-      md5: e0f58c7c4e12fa92b29d973dd5f3f565.dir
+      md5: e4904765c79b0139ccb80d56ef044383.dir
       size: 1096
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 9afb06007a6da3cef1619e937e9c413e.dir
-      size: 36344
+      md5: 5cededc181e2b86c8ff63498a3e79462.dir
+      size: 36481
       nfiles: 2
     - path: generate_predictions.py
       hash: md5
-      md5: 209fe6efbebfd3d7aa1a1bb27885d3c1
-      size: 3114
+      md5: b3250f5b597fe33bf57e8bc225606be7
+      size: 3268
     params:
       configs/generate_predictions.yaml:
         predictions_output_filepath: ./data/predictions/predictions.parquet
@@ -68,26 +68,26 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 28ad87e9a47ea8815a0b8ba5808e750c.dir
-      size: 2531
+      md5: d78af354c4ecb0b0296ac093e515a01b.dir
+      size: 2734
       nfiles: 1
   generate_metrics:
     cmd: python generate_metrics.py
     deps:
     - path: data/predictions
       hash: md5
-      md5: 28ad87e9a47ea8815a0b8ba5808e750c.dir
-      size: 2531
+      md5: d78af354c4ecb0b0296ac093e515a01b.dir
+      size: 2734
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 9afb06007a6da3cef1619e937e9c413e.dir
-      size: 36344
+      md5: 5cededc181e2b86c8ff63498a3e79462.dir
+      size: 36481
       nfiles: 2
     - path: generate_metrics.py
       hash: md5
-      md5: 4c1379bf37f5e5ad5843eb5b5a22ebc5
-      size: 3407
+      md5: 8c78578a8c45edf4b93a85c42c2b2192
+      size: 3561
     params:
       configs/generate_metrics.yaml:
         metrics_output_filepath: ./metrics/metrics.json
@@ -95,5 +95,5 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 82e90d3f00bfd7c5a3fb83c2c14f4cff
+      md5: a32cd5e65ca89db0920297a7c6ca39bf
       size: 182