summarization/Makefile

.PHONY: clean dirs virtualenv lint requirements push pull run clone upload

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

PROJECT_DIR := $(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
PYTHON_INTERPRETER = python

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

## Create virtualenv.
## Activate with the command:
## source env/bin/activate
virtualenv:
	virtualenv -p $(PYTHON_INTERPRETER) env

## Install Python Dependencies.
## Make sure you activate the virtualenv first!
requirements: 
	$(PYTHON_INTERPRETER) -m pip install -U pip setuptools wheel
	$(PYTHON_INTERPRETER) -m pip install -r requirements.txt

## Create directories that are ignored by git but required for the project
dirs:
	mkdir -p data/raw data/processed models

## Delete all compiled Python files
clean:
	find . -type f -name "*.py[co]" -delete
	find . -type d -name "__pycache__" -delete

## Lint using flake8
lint:
	flake8 src
	black src

## Upload Data to default DVC remote
push:
	dvc push -r origin


## Download Data from default DVC remote
pull:
	dvc pull -r origin

## run the DVC pipeline - recompute any modified outputs such as processed data or trained models
run:
	dvc repro eval

## run the visualization using Streamlit
visualize:
	dvc repro visualize

## push the trained model to HF model hub
upload:
	dvc repro push_to_hf_hub

## Clone the T5 summarisation repo
clone:
	git clone https://dagshub.com/gagan3012/summarization.git

## Update python package
update:
	python setup.py sdist bdist_wheel
	python -m twine upload dist/*

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



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

.DEFAULT_GOAL := 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: help
help:
	@echo "$$(tput bold)Available rules:$$(tput sgr0)"
	@echo
	@sed -n -e "/^## / Missing" $Missing \
	| 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)" \
	'Missing \
			printf "%s ", words[i]; \
		} \
		printf "\n"; \
	}' \
	| more $(shell test $(shell uname) = Darwin && echo '--no-init --raw-control-chars')