#####################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.01 #
#####################################################
# Refer to:
# - https://github.com/microsoft/qlib/blob/main/examples/workflow_by_code.ipynb
# - https://github.com/microsoft/qlib/blob/main/examples/workflow_by_code.py
# python exps/trading/workflow_test.py
#####################################################
import sys, site
from pathlib import Path

lib_dir = (Path(__file__).parent / '..' / '..' / 'lib').resolve()
if str(lib_dir) not in sys.path: sys.path.insert(0, str(lib_dir))

import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.model.gbdt import LGBModel
from qlib.contrib.data.handler import Alpha158
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
    backtest as normal_backtest,
    risk_analysis,
)
from qlib.utils import exists_qlib_data, init_instance_by_config
from qlib.workflow import R
from qlib.workflow.record_temp import SignalRecord, PortAnaRecord
from qlib.utils import flatten_dict


# use default data
# NOTE: need to download data from remote: python scripts/get_data.py qlib_data_cn --target_dir ~/.qlib/qlib_data/cn_data
provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
if not exists_qlib_data(provider_uri):
    print(f"Qlib data is not found in {provider_uri}")
    sys.path.append(str(scripts_dir))
    from get_data import GetData
    GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)


market = "csi300"
benchmark = "SH000300"


###################################
# train model
###################################
data_handler_config = {
    "start_time": "2008-01-01",
    "end_time": "2020-08-01",
    "fit_start_time": "2008-01-01",
    "fit_end_time": "2014-12-31",
    "instruments": market,
}

task = {
    "model": {
        "class": "QuantTransformer",
        "module_path": "trade_models",
        "kwargs": {
            "loss": "mse",
            "GPU": "0",
            "metric": "loss",
        },
    },
    "dataset": {
        "class": "DatasetH",
        "module_path": "qlib.data.dataset",
        "kwargs": {
            "handler": {
                "class": "Alpha158",
                "module_path": "qlib.contrib.data.handler",
                "kwargs": data_handler_config,
            },
            "segments": {
                "train": ("2008-01-01", "2014-12-31"),
                "valid": ("2015-01-01", "2016-12-31"),
                "test": ("2017-01-01", "2020-08-01"),
            },
        },
    },
}

# model initiaiton
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])

# start exp to train model
with R.start(experiment_name="train_model"):
    R.log_params(**flatten_dict(task))
    model.fit(dataset)
    R.save_objects(trained_model=model)
    rid = R.get_recorder().id