new make file

modules/ml-pipeline/Makefile

@@ -1,9 +1,25 @@
 export PYENV_ROOT=$(HOME)/.pyenv
 export PATH := $(PYENV_ROOT)/bin:$(PATH)
 PYTHON_VERSION ?= 3.10.12
+CONDA_ENV=dev_env_pipeline
 
 .PHONY: init
-init: dev-pyenv
+init: dev-conda
+
+.PHONY: dev-conda
+dev-conda:
+	# conda deactivate || echo "Not in conda environment"
+	# conda remove --name $CONDA_ENV --all -y || echo "No environment created previously"
+	conda create --name $CONDA_ENV python=$(PYTHON_VERSION) -y
+	conda init bash
+	conda run -vvvv -n $CONDA_ENV pip install --upgrade pip
+	conda run -vvvv -n $CONDA_ENV pip install -r src/pipeline/requirements/training/requirements-dev.txt
+	conda run -vvvv -n $CONDA_ENV pip install -r src/pipeline/requirements/version_control/requirements.txt
+	conda run -vvvv -n $CONDA_ENV pre-commit install
+	conda run -vvvv -n $CONDA_ENV pip install ipykernel
+	echo "TO ACTIVATE ENVIRONMENT, USE THE FOLLOWING COMMAND"
+	echo "conda activate $CONDA_ENV"
+
 
 .PHONY: dev-pyenv
 dev-pyenv:

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

@@ -15,8 +15,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: ec064b0274e2e6a0864580a748e6bb6a.dir
-      size: 24067192
+      md5: c183712d22ab739e0be016724f44ee1c.dir
+      size: 12203729
       nfiles: 2
   build_model:
     cmd: python build_model.py
@@ -27,8 +27,8 @@ stages:
       size: 5134
     - path: data/prepared_data
       hash: md5
-      md5: ec064b0274e2e6a0864580a748e6bb6a.dir
-      size: 24067192
+      md5: c183712d22ab739e0be016724f44ee1c.dir
+      size: 12203729
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -49,25 +49,25 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: dc73587056f07735719bfee464a5f898.dir
-      size: 285397707
-      nfiles: 16
+      md5: cb03448b572cb167bf281ee8d43dccd9.dir
+      size: 99423757
+      nfiles: 14
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: f6d03cb197a3d78e61f6fef023ed8d7f
-      size: 184
+      md5: 48d9cc86c22c1ac0da8903a32a7d10c3
+      size: 183
   generate_predictions:
     cmd: python generate_predictions.py
     deps:
     - path: data/model
       hash: md5
-      md5: dc73587056f07735719bfee464a5f898.dir
-      size: 285397707
-      nfiles: 16
+      md5: cb03448b572cb167bf281ee8d43dccd9.dir
+      size: 99423757
+      nfiles: 14
     - path: data/prepared_data
       hash: md5
-      md5: ec064b0274e2e6a0864580a748e6bb6a.dir
-      size: 24067192
+      md5: c183712d22ab739e0be016724f44ee1c.dir
+      size: 12203729
       nfiles: 2
     - path: generate_predictions.py
       hash: md5
@@ -83,21 +83,21 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 3d70862c00e38f383a06c3e4df5ebb38.dir
-      size: 386958
+      md5: 3d5002f0eecd2374a0ef2fd6f711503e.dir
+      size: 383878
       nfiles: 1
   generate_metrics:
     cmd: python generate_metrics.py
     deps:
     - path: data/predictions
       hash: md5
-      md5: 3d70862c00e38f383a06c3e4df5ebb38.dir
-      size: 386958
+      md5: 3d5002f0eecd2374a0ef2fd6f711503e.dir
+      size: 383878
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: ec064b0274e2e6a0864580a748e6bb6a.dir
-      size: 24067192
+      md5: c183712d22ab739e0be016724f44ee1c.dir
+      size: 12203729
       nfiles: 2
     - path: generate_metrics.py
       hash: md5
@@ -111,7 +111,7 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 2507f756ea68768185ebeaf66db2ebbd
+      md5: 08a81d2e5cecf360043498526bc98314
       size: 183
   startup_cleanup:
     cmd: python startup_cleanup.py