1
0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-01 01:51:18 +08:00
Files
qlib/scripts/data_collector/crypto/README.md
Arthur Cui 3e79a088ef Add Crypto dataset from coingecko (#733)
* add crypto symbols collectors

* add crypto data collector

* add crypto symbols collectors

* add crypto data collector

* solver region and source problem

* fix merge

* fix merge

* clean all cn information

Co-authored-by: DefangCui <170007807@pku.edu.cn>
2021-12-31 22:24:26 +08:00

55 lines
1.6 KiB
Markdown

# Collect Crypto Data
> *Please pay **ATTENTION** that the data is collected from [Coingecko](https://www.coingecko.com/en/api) and the data might not be perfect. We recommend users to prepare their own data if they have high-quality dataset. For more information, users can refer to the [related document](https://qlib.readthedocs.io/en/latest/component/data.html#converting-csv-format-into-qlib-format)*
## Requirements
```bash
pip install -r requirements.txt
```
## Usage of the dataset
> *Crypto dateset only support Data retrieval function but not support backtest function due to the lack of OHLC data.*
## Collector Data
### Crypto Data
#### 1d from Coingecko
```bash
# download from https://api.coingecko.com/api/v3/
python collector.py download_data --source_dir ~/.qlib/crypto_data/source/1d --start 2015-01-01 --end 2021-11-30 --delay 1 --interval 1d
# normalize
python collector.py normalize_data --source_dir ~/.qlib/crypto_data/source/1d --normalize_dir ~/.qlib/crypto_data/source/1d_nor --interval 1d --date_field_name date
# dump data
cd qlib/scripts
python dump_bin.py dump_all --csv_path ~/.qlib/crypto_data/source/1d_nor --qlib_dir ~/.qlib/qlib_data/crypto_data --freq day --date_field_name date --include_fields prices,total_volumes,market_caps
```
### using data
```python
import qlib
from qlib.data import D
qlib.init(provider_uri="~/.qlib/qlib_data/crypto_data")
df = D.features(D.instruments(market="all"), ["$prices", "$total_volumes","$market_caps"], freq="day")
```
### Help
```bash
python collector.py collector_data --help
```
## Parameters
- interval: 1d
- delay: 1