add dvc and gto

modules/ml-pipeline/.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

modules/ml-pipeline/.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

modules/ml-pipeline/.gto

@@ -0,0 +1 @@
+stages = ["dev", "staging", "prod"]

modules/ml-pipeline/Makefile

@@ -0,0 +1,20 @@
+export PYENV_ROOT=$(HOME)/.pyenv
+export PATH := $(PYENV_ROOT)/bin:$(PATH)
+PYTHON_VERSION ?= 3.10.12
+
+.PHONY: init
+init: dev-pyenv dvc-init
+
+.PHONY: dev-pyenv
+dev-pyenv:
+	curl https://pyenv.run | bash || echo "Pyenv - Already installed"
+	pyenv install ${PYTHON_VERSION} || echo "Python version already installed"
+	pyenv global ${PYTHON_VERSION}
+	python3 -m venv .dev_env
+	. .dev_env/bin/activate && pip install --upgrade pip && pip install -r src/training/requirements/requirements-dev.txt && pre-commit install
+	echo "TO ACTIVATE ENVIRONMENT, USE THE FOLLOWING COMMAND"
+	echo "source .dev_env/bin/activate"
+
+.PHONY: dvc-init
+dvc-init:
+	. .dev_env/bin/activate && dvc init --subdir

modules/ml-pipeline/docs/README.md

@@ -0,0 +1,4 @@
+# Docs generation
+
+This will be done via a sphinx pre-commit hook
+Only file to adjust is probably the conf.py file if needed

modules/ml-pipeline/tests/README.md

@@ -0,0 +1,3 @@
+# Tests
+
+This is the testing folder for pipeline components and end to end testing