[Qlib] CH3. 플랫폼 구성-(2)Train

Microsoft Qlib Framework

Contents

• Installation
• Framework Overview
• Main Component
  • Data
  • Train
  • Backtest
• Examples

CH3. Main Components - (2)Train

Introduction

• Data Layer에서는 user-friendly APIs를 통해 high-performance data infrastructure를 제공함
• 즉, 쉽게 데이터를 다운로드하고 변경할 수 있도록 Data Loader, Handler 등 다양한 기능을 제공함 
• 이번 장에서는 주식 데이터를 쉽게 변경하고 가공하는 Data Layer에 대해서 알아보고자 함

Data Layer: Data Framework & Usage — QLib 0.9.3.99 documentation

---

1. Data Preparation

• Dataset Download

# download 1d China/USA
python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/us_data --region us

# download 1min China
python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/qlib_cn_1min --region cn --interval 1min

Download results

• Automatic update of daily frequency data
  • <user data dir>
  • <trading_date>: start of trading day
  • <end_date>: end of trading day(not included)

python scripts/data_collector/yahoo/collector.py update_data_to_bin --qlib_data_1d_dir <user data dir> --trading_date <start date> --end_date <end date>

 

• Converting CSV format into Qlib .bin Format

# Converting 1d
python scripts/get_data.py download_data --file_name csv_data_cn.zip --target_dir ~/.qlib/csv_data/cn_data
python scripts/get_data.py download_data --file_name csv_data_us.zip --target_dir ~/.qlib/csv_data/us_data

# Converting 1min
python scripts/data_collector/yahoo/collector.py download_data --source_dir ~/.qlib/stock_data/source/cn_1min --region CN --start 2021-05-20 --end 2021-05-23 --delay 0.1 --interval 1min --limit_nums 10

 

2. Data API

 

 

3. Data Loader

 

 

4. Data Handler

 

 

5. Dataset

 

 

6. Cache

 

 

7. Data and Cache File Structure