Makefile

.PHONY: all all_kenza_docker all_kenza_venv create_environment clean data delete_environment features lint requirements test_environment train

#################################################################################
# GLOBALS                                                                       #
#################################################################################

PROJECT_DIR := $(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
PROFILE = default
PROJECT_NAME = the-wise-ml-example
PYTHON_INTERPRETER = python3


#################################################################################
# COMMANDS                                                                      #
#################################################################################

## Install Python Dependencies
requirements: test_environment
	pip install -r requirements.txt --extra-index-url https://repo.fury.io/kenza

## Make Dataset
data: requirements
	$(PYTHON_INTERPRETER) src/data/make_dataset.py

## Make Features (Depends on data)
features: requirements
	$(PYTHON_INTERPRETER) src/features/build_features.py

## Train model (Depends on features)
train: requirements
	$(PYTHON_INTERPRETER) src/models/train_model.py

## Clean Data, Prepare Features and Train Model
all: requirements data features train

## Clean Data, Prepare Fetures and Train Model (Kenza - virtualenv mode)
all_kenza_venv: requirements data features
	kenza local train "$(job_name)" --main=src/models/train_model.py --project-id=$(project_id)

## Clean Data, Prepare Fetures and Train Model (Kenza - Docker mode)
all_kenza_docker: requirements data features 
	kenza local train "$(job_name)" --main=src/models/train_model.py --project-id=$(project_id) --docker


## Delete all compiled Python files
clean:
	find . -name "*.pyc" -exec rm {} \;

## Lint using flake8
lint:
	flake8 --exclude=lib/,bin/,docs/conf.py .

## Set up python interpreter environment
create_environment:
	@pip install -q virtualenv virtualenvwrapper
	@echo ">>> Installing virtualenvwrapper if not already intalled.\nMake sure the following lines are in shell startup file\n\
	export WORKON_HOME=$$HOME/.virtualenvs\nexport PROJECT_HOME=$$HOME/Devel\nsource $(shell which virtualenvwrapper.sh)\n"
	@bash -c "source `which virtualenvwrapper.sh`;mkvirtualenv $(PROJECT_NAME) --python=$(PYTHON_INTERPRETER)"
	@echo ">>> New virtualenv created. Activate with:\nworkon $(PROJECT_NAME)"

## Delete python interpreter environment
delete_environment:
	@bash -c "source `which virtualenvwrapper.sh`;rmvirtualenv $(PROJECT_NAME)"
	@echo ">>>virtualenv $(PROJECT_NAME) is deleted"

## Test python environment is setup correctly
test_environment:
	$(PYTHON_INTERPRETER) test_environment.py

#################################################################################
# PROJECT RULES                                                                 #
#################################################################################



#################################################################################
# Self Documenting Commands                                                     #
#################################################################################

.DEFAULT_GOAL := show-help

# Inspired by <http://marmelab.com/blog/2016/02/29/auto-documented-makefile.html>
# sed script explained:
# /^##/:
# 	* save line in hold space
# 	* purge line
# 	* Loop:
# 		* append newline + line to hold space
# 		* go to next line
# 		* if line starts with doc comment, strip comment character off and loop
# 	* remove target prerequisites
# 	* append hold space (+ newline) to line
# 	* replace newline plus comments by `---`
# 	* print line
# Separate expressions are necessary because labels cannot be delimited by
# semicolon; see <http://stackoverflow.com/a/11799865/1968>
.PHONY: show-help
show-help:
	@echo "$$(tput bold)Available rules:$$(tput sgr0)"
	@echo
	@sed -n -e "/^## / { \
		h; \
		s/.*//; \
		:doc" \
		-e "H; \
		n; \
		s/^## //; \
		t doc" \
		-e "s/:.*//; \
		G; \
		s/\\n## /---/; \
		s/\\n/ /g; \
		p; \
	}" ${MAKEFILE_LIST} \
	| LC_ALL='C' sort --ignore-case \
	| awk -F '---' \
		-v ncol=$$(tput cols) \
		-v indent=19 \
		-v col_on="$$(tput setaf 6)" \
		-v col_off="$$(tput sgr0)" \
	'{ \
		printf "%s%*s%s ", col_on, -indent, $$1, col_off; \
		n = split($$2, words, " "); \
		line_length = ncol - indent; \
		for (i = 1; i <= n; i++) { \
			line_length -= length(words[i]) + 1; \
			if (line_length <= 0) { \
				line_length = ncol - indent - length(words[i]) - 1; \
				printf "\n%*s ", -indent, " "; \
			} \
			printf "%s ", words[i]; \
		} \
		printf "\n"; \
	}' \
	| more $(shell test $(shell uname) = Darwin && echo '--no-init --raw-control-chars')