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

PROJECT_NAME = lnp-ml
PYTHON_VERSION = 3.8
PYTHON_INTERPRETER = python

# --- CLI flag 变量 ---
MPNN_FLAG = $(if $(USE_MPNN),--use-mpnn,)
FREEZE_FLAG = $(if $(FREEZE_BACKBONE),--freeze-backbone,)
DEVICE_FLAG = $(if $(DEVICE),--device $(DEVICE),)
SCAFFOLD_SPLIT_FLAG = $(if $(filter 1,$(SCAFFOLD_SPLIT)),--scaffold-split,)
SEED_FLAG = $(if $(SEED),--seed $(SEED),)
N_TRIALS_FLAG = $(if $(N_TRIALS),--n-trials $(N_TRIALS),)
EPOCHS_PER_TRIAL_FLAG = $(if $(EPOCHS_PER_TRIAL),--epochs-per-trial $(EPOCHS_PER_TRIAL),)
MIN_STRATUM_FLAG = $(if $(MIN_STRATUM_COUNT),--min-stratum-count $(MIN_STRATUM_COUNT),)
OUTPUT_DIR_FLAG = $(if $(OUTPUT_DIR),--output-dir $(OUTPUT_DIR),)
USE_SWA_FLAG = $(if $(USE_SWA),--use-swa,)
INIT_PRETRAIN_FLAG = $(if $(NO_PRETRAIN),,--init-from-pretrain $(or $(INIT_PRETRAIN),models/pretrain_delivery.pt))

#################################################################################
# ENVIRONMENT & CODE QUALITY                                                    #
#################################################################################

## Install Python dependencies
.PHONY: requirements
requirements:
	pixi install

## Set up Python interpreter environment
.PHONY: create_environment
create_environment:
	@echo ">>> Pixi environment will be created when running 'make requirements'"
	@echo ">>> Activate with:\npixi shell"

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

## Lint using ruff (use `make format` to do formatting)
.PHONY: lint
lint:
	ruff format --check
	ruff check

## Format source code with ruff
.PHONY: format
format:
	ruff check --fix
	ruff format

#################################################################################
# DATA PROCESSING                                                              #
#################################################################################

## Preprocess internal data (raw -> interim)
.PHONY: preprocess
preprocess: requirements
	$(PYTHON_INTERPRETER) scripts/preprocess_internal.py

## Process dataset (interim -> processed)
.PHONY: data
data: requirements
	$(PYTHON_INTERPRETER) scripts/process_data.py

## Process dataset for final training (interim -> processed/final, train:val=9:1, no test)
.PHONY: data_final
data_final: requirements
	$(PYTHON_INTERPRETER) scripts/process_data_final.py

## Process external data for pretrain (external -> processed)
.PHONY: data_pretrain
data_pretrain: requirements
	$(PYTHON_INTERPRETER) scripts/process_external.py

## Process baseline CV data for benchmark (external/all_amine_split_for_LiON -> processed/benchmark)
.PHONY: data_benchmark
data_benchmark: requirements
	$(PYTHON_INTERPRETER) scripts/process_benchmark_data.py

## Process internal data with CV splitting (interim -> processed/cv)
## Use SCAFFOLD_SPLIT=1 to enable amine-based scaffold splitting (default: random shuffle)
.PHONY: data_cv
data_cv: requirements
	$(PYTHON_INTERPRETER) scripts/process_data_cv.py $(SCAFFOLD_SPLIT_FLAG)

#################################################################################
# TRAINING                                                                      #
#################################################################################

## Pretrain on external data (delivery only)
.PHONY: pretrain
pretrain: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.pretrain main $(MPNN_FLAG) $(DEVICE_FLAG)

## Benchmark on baseline CV data: 5-fold train + test (delivery only)
.PHONY: benchmark
benchmark: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.benchmark main $(MPNN_FLAG) $(DEVICE_FLAG)
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.benchmark test $(DEVICE_FLAG)

## Train model (multi-task, from scratch)
.PHONY: train
train: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.train $(MPNN_FLAG) $(DEVICE_FLAG)

## Finetune from pretrained checkpoint (use FREEZE_BACKBONE=1 to freeze backbone)
.PHONY: finetune
finetune: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.train --init-from-pretrain models/pretrain_delivery.pt $(FREEZE_FLAG) $(MPNN_FLAG) $(DEVICE_FLAG)

## Final training using all data (train:val=9:1, no test set), with pretrained weights
.PHONY: train_final
train_final: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.train \
		--train-path data/processed/final/train.parquet \
		--val-path data/processed/final/val.parquet \
		--output-dir models/final \
		--init-from-pretrain models/pretrain_delivery.pt \
		$(FREEZE_FLAG) $(MPNN_FLAG) $(DEVICE_FLAG)

## Train with cross-validation on internal data only (5-fold, amine-based split)
.PHONY: train_cv
train_cv: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.train_cv main $(FREEZE_FLAG) $(MPNN_FLAG) $(DEVICE_FLAG)

## Finetune with cross-validation on internal data (5-fold) with pretrained weights
.PHONY: finetune_cv
finetune_cv: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.train_cv main --init-from-pretrain models/pretrain_delivery.pt $(FREEZE_FLAG) $(MPNN_FLAG) $(DEVICE_FLAG)

#################################################################################
# EVALUATION                                                                    #
#################################################################################

## Evaluate pretrain model (delivery metrics)
.PHONY: test_pretrain
test_pretrain: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.pretrain test $(MPNN_FLAG) $(DEVICE_FLAG)

## Evaluate CV finetuned models on test sets (auto-detects MPNN from checkpoint)
.PHONY: test_cv
test_cv: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.train_cv test $(DEVICE_FLAG)

## Test model on test set (with detailed metrics, auto-detects MPNN from checkpoint)
.PHONY: test
test: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.predict test $(DEVICE_FLAG)

## Run predictions
.PHONY: predict
predict: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.predict $(DEVICE_FLAG)

#################################################################################
# HYPERPARAMETER TUNING                                                         #
#################################################################################
# 通用参数：
#   SEED            随机种子 (默认: 42)
#   N_TRIALS        Optuna 试验数 (默认: 20)
#   EPOCHS_PER_TRIAL 每个试验的最大 epoch (默认: 30)
#   MIN_STRATUM_COUNT 复合分层标签的最小样本数 (默认: 5)
#   OUTPUT_DIR      输出目录 (根据命令有不同默认值)
#   INIT_PRETRAIN   预训练权重路径 (默认: models/pretrain_delivery.pt)
#   NO_PRETRAIN=1   禁用预训练权重

## Train with hyperparameter tuning
.PHONY: tune
tune: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.train --tune $(MPNN_FLAG) $(DEVICE_FLAG)

## Nested CV with Optuna: outer 5-fold (test) + inner 3-fold (tune)
## 用于模型评估：外层 5-fold 产生无偏性能估计，内层 3-fold 做超参搜索
## 使用示例: make nested_cv_tune DEVICE=cuda N_TRIALS=30
.PHONY: nested_cv_tune
nested_cv_tune: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.nested_cv_optuna \
		$(DEVICE_FLAG) $(MPNN_FLAG) $(SEED_FLAG) $(INIT_PRETRAIN_FLAG) \
		$(N_TRIALS_FLAG) $(EPOCHS_PER_TRIAL_FLAG) $(MIN_STRATUM_FLAG) $(OUTPUT_DIR_FLAG)

## Final training with Optuna: 3-fold CV tune + full data train
## 用于最终模型训练：3-fold 调参后用全量数据训练（无 early-stop）
## 使用示例: make final_optuna DEVICE=cuda N_TRIALS=30 USE_SWA=1
.PHONY: final_optuna
final_optuna: requirements
	$(PYTHON_INTERPRETER) -m lnp_ml.modeling.final_train_optuna_cv \
		$(DEVICE_FLAG) $(MPNN_FLAG) $(SEED_FLAG) $(INIT_PRETRAIN_FLAG) \
		$(N_TRIALS_FLAG) $(EPOCHS_PER_TRIAL_FLAG) $(MIN_STRATUM_FLAG) $(OUTPUT_DIR_FLAG) $(USE_SWA_FLAG)

#################################################################################
# SERVING & DEPLOYMENT                                                          #
#################################################################################

## Formulation optimization: find optimal LNP formulation for target organ
## Usage: make optimize SMILES="CC(C)..." ORGAN=liver
.PHONY: optimize
optimize: requirements
	$(PYTHON_INTERPRETER) -m app.optimize --smiles "$(SMILES)" --organ $(ORGAN) $(DEVICE_FLAG)

## Start FastAPI backend server (port 8000)
.PHONY: api
api: requirements
	uvicorn app.api:app --host 0.0.0.0 --port 8000 --reload

## Start Streamlit frontend app (port 8501)
.PHONY: webapp
webapp: requirements
	streamlit run app/app.py --server.port 8501

## Start both API and webapp (run in separate terminals)
.PHONY: serve
serve:
	@echo "请在两个终端分别运行:"
	@echo "  终端 1: make api"
	@echo "  终端 2: make webapp"
	@echo ""
	@echo "然后访问: http://localhost:8501"

#################################################################################
# DOCKER                                                                        #
#################################################################################

## Build Docker images
.PHONY: docker-build
docker-build:
	docker compose build

## Start all services with Docker Compose
.PHONY: docker-up
docker-up:
	docker compose up -d

## Stop all Docker services
.PHONY: docker-down
docker-down:
	docker compose down

## View Docker logs
.PHONY: docker-logs
docker-logs:
	docker compose logs -f

## Build and start all services
.PHONY: docker-serve
docker-serve: docker-build docker-up
	@echo ""
	@echo "🚀 服务已启动!"
	@echo "   - API:       http://localhost:8000"
	@echo "   - Web 应用:  http://localhost:8501"
	@echo ""
	@echo "查看日志: make docker-logs"
	@echo "停止服务: make docker-down"

## Clean Docker resources (images, volumes, etc.)
.PHONY: docker-clean
docker-clean:
	docker compose down -v --rmi local
	docker system prune -f

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

.DEFAULT_GOAL := help

define PRINT_HELP_PYSCRIPT
import re, sys; \
lines = '\n'.join([line for line in sys.stdin]); \
matches = re.findall(r'\n## (.*)\n[\s\S]+?\n([a-zA-Z_-]+):', lines); \
print('Available rules:\n'); \
print('\n'.join(['{:25}{}'.format(*reversed(match)) for match in matches]))
endef
export PRINT_HELP_PYSCRIPT

help:
	@$(PYTHON_INTERPRETER) -c "${PRINT_HELP_PYSCRIPT}" < $(MAKEFILE_LIST)