FreqAI

FreqAI: generalizing adaptive modeling for chaotic time-series market forecasts - Published in JOSS (2022)

https://github.com/freqtrade/freqtrade

Science Score: 95.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 4 DOI reference(s) in README and JOSS metadata
  • Academic publication links
    Links to: joss.theoj.org
  • Committers with academic emails
    4 of 354 committers (1.1%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
    Published in Journal of Open Source Software

Keywords

algorithmic-trading bitcoin cryptocurrencies cryptocurrency freqtrade python telegram-bot trade trading-bot

Keywords from Contributors

mathematics mesh deeplearning matrix multiclass-classification statistical-analysis chemistry chainer end-to-end kaldi

Scientific Fields

Artificial Intelligence and Machine Learning Computer Science - 62% confidence
Engineering Computer Science - 41% confidence
Earth and Environmental Sciences Physical Sciences - 40% confidence
Last synced: 4 months ago · JSON representation

Repository

Free, open source crypto trading bot

Basic Info
  • Host: GitHub
  • Owner: freqtrade
  • License: gpl-3.0
  • Language: Python
  • Default Branch: develop
  • Homepage: https://www.freqtrade.io
  • Size: 596 MB
Statistics
  • Stars: 41,740
  • Watchers: 707
  • Forks: 8,498
  • Open Issues: 39
  • Releases: 100
Topics
algorithmic-trading bitcoin cryptocurrencies cryptocurrency freqtrade python telegram-bot trade trading-bot
Created over 8 years ago · Last pushed 4 months ago
Metadata Files
Readme Contributing Funding License

README.md

freqtrade

Freqtrade CI DOI Coverage Status Documentation

Freqtrade is a free and open source crypto trading bot written in Python. It is designed to support all major exchanges and be controlled via Telegram or webUI. It contains backtesting, plotting and money management tools as well as strategy optimization by machine learning.

freqtrade

Disclaimer

This software is for educational purposes only. Do not risk money which you are afraid to lose. USE THE SOFTWARE AT YOUR OWN RISK. THE AUTHORS AND ALL AFFILIATES ASSUME NO RESPONSIBILITY FOR YOUR TRADING RESULTS.

Always start by running a trading bot in Dry-run and do not engage money before you understand how it works and what profit/loss you should expect.

We strongly recommend you to have coding and Python knowledge. Do not hesitate to read the source code and understand the mechanism of this bot.

Supported Exchange marketplaces

Please read the exchange specific notes to learn about eventual, special configurations needed for each exchange.

Supported Futures Exchanges (experimental)

Please make sure to read the exchange specific notes, as well as the trading with leverage documentation before diving in.

Community tested

Exchanges confirmed working by the community:

Documentation

We invite you to read the bot documentation to ensure you understand how the bot is working.

Please find the complete documentation on the freqtrade website.

Features

  • [x] Based on Python 3.11+: For botting on any operating system - Windows, macOS and Linux.
  • [x] Persistence: Persistence is achieved through sqlite.
  • [x] Dry-run: Run the bot without paying money.
  • [x] Backtesting: Run a simulation of your buy/sell strategy.
  • [x] Strategy Optimization by machine learning: Use machine learning to optimize your buy/sell strategy parameters with real exchange data.
  • [X] Adaptive prediction modeling: Build a smart strategy with FreqAI that self-trains to the market via adaptive machine learning methods. Learn more
  • [x] Whitelist crypto-currencies: Select which crypto-currency you want to trade or use dynamic whitelists.
  • [x] Blacklist crypto-currencies: Select which crypto-currency you want to avoid.
  • [x] Builtin WebUI: Builtin web UI to manage your bot.
  • [x] Manageable via Telegram: Manage the bot with Telegram.
  • [x] Display profit/loss in fiat: Display your profit/loss in fiat currency.
  • [x] Performance status report: Provide a performance status of your current trades.

Quick start

Please refer to the Docker Quickstart documentation on how to get started quickly.

For further (native) installation methods, please refer to the Installation documentation page.

Basic Usage

Bot commands

``` usage: freqtrade [-h] [-V] {trade,create-userdir,new-config,show-config,new-strategy,download-data,convert-data,convert-trade-data,trades-to-ohlcv,list-data,backtesting,backtesting-show,backtesting-analysis,edge,hyperopt,hyperopt-list,hyperopt-show,list-exchanges,list-markets,list-pairs,list-strategies,list-hyperoptloss,list-freqaimodels,list-timeframes,show-trades,test-pairlist,convert-db,install-ui,plot-dataframe,plot-profit,webserver,strategy-updater,lookahead-analysis,recursive-analysis} ...

Free, open source crypto trading bot

positional arguments: {trade,create-userdir,new-config,show-config,new-strategy,download-data,convert-data,convert-trade-data,trades-to-ohlcv,list-data,backtesting,backtesting-show,backtesting-analysis,edge,hyperopt,hyperopt-list,hyperopt-show,list-exchanges,list-markets,list-pairs,list-strategies,list-hyperoptloss,list-freqaimodels,list-timeframes,show-trades,test-pairlist,convert-db,install-ui,plot-dataframe,plot-profit,webserver,strategy-updater,lookahead-analysis,recursive-analysis} trade Trade module. create-userdir Create user-data directory. new-config Create new config show-config Show resolved config new-strategy Create new strategy download-data Download backtesting data. convert-data Convert candle (OHLCV) data from one format to another. convert-trade-data Convert trade data from one format to another. trades-to-ohlcv Convert trade data to OHLCV data. list-data List downloaded data. backtesting Backtesting module. backtesting-show Show past Backtest results backtesting-analysis Backtest Analysis module. hyperopt Hyperopt module. hyperopt-list List Hyperopt results hyperopt-show Show details of Hyperopt results list-exchanges Print available exchanges. list-markets Print markets on exchange. list-pairs Print pairs on exchange. list-strategies Print available strategies. list-hyperoptloss Print available hyperopt loss functions. list-freqaimodels Print available freqAI models. list-timeframes Print available timeframes for the exchange. show-trades Show trades. test-pairlist Test your pairlist configuration. convert-db Migrate database to different system install-ui Install FreqUI plot-dataframe Plot candles with indicators. plot-profit Generate plot showing profits. webserver Webserver module. strategy-updater updates outdated strategy files to the current version lookahead-analysis Check for potential look ahead bias. recursive-analysis Check for potential recursive formula issue.

options: -h, --help show this help message and exit -V, --version show program's version number and exit ```

Telegram RPC commands

Telegram is not mandatory. However, this is a great way to control your bot. More details and the full command list on the documentation

  • /start: Starts the trader.
  • /stop: Stops the trader.
  • /stopentry: Stop entering new trades.
  • /status <trade_id>|[table]: Lists all or specific open trades.
  • /profit [<n>]: Lists cumulative profit from all finished trades, over the last n days.
  • /profit_long [<n>]: Lists cumulative profit from all finished long trades, over the last n days.
  • /profit_short [<n>]: Lists cumulative profit from all finished short trades, over the last n days.
  • /forceexit <trade_id>|all: Instantly exits the given trade (Ignoring minimum_roi).
  • /fx <trade_id>|all: Alias to /forceexit
  • /performance: Show performance of each finished trade grouped by pair
  • /balance: Show account balance per currency.
  • /daily <n>: Shows profit or loss per day, over the last n days.
  • /help: Show help message.
  • /version: Show version.

Development branches

The project is currently setup in two main branches:

  • develop - This branch has often new features, but might also contain breaking changes. We try hard to keep this branch as stable as possible.
  • stable - This branch contains the latest stable release. This branch is generally well tested.
  • feat/* - These are feature branches, which are being worked on heavily. Please don't use these unless you want to test a specific feature.

Support

Help / Discord

For any questions not covered by the documentation or for further information about the bot, or to simply engage with like-minded individuals, we encourage you to join the Freqtrade discord server.

Bugs / Issues

If you discover a bug in the bot, please search the issue tracker first. If it hasn't been reported, please create a new issue and ensure you follow the template guide so that the team can assist you as quickly as possible.

For every issue created, kindly follow up and mark satisfaction or reminder to close issue when equilibrium ground is reached.

--Maintain github's community policy--

Feature Requests

Have you a great idea to improve the bot you want to share? Please, first search if this feature was not already discussed. If it hasn't been requested, please create a new request and ensure you follow the template guide so that it does not get lost in the bug reports.

Pull Requests

Feel like the bot is missing a feature? We welcome your pull requests!

Please read the Contributing document to understand the requirements before sending your pull-requests.

Coding is not a necessity to contribute - maybe start with improving the documentation? Issues labeled good first issue can be good first contributions, and will help get you familiar with the codebase.

Note before starting any major new feature work, please open an issue describing what you are planning to do or talk to us on discord (please use the #dev channel for this). This will ensure that interested parties can give valuable feedback on the feature, and let others know that you are working on it.

Important: Always create your PR against the develop branch, not stable.

Requirements

Up-to-date clock

The clock must be accurate, synchronized to a NTP server very frequently to avoid problems with communication to the exchanges.

Minimum hardware required

To run this bot we recommend you a cloud instance with a minimum of:

  • Minimal (advised) system requirements: 2GB RAM, 1GB disk space, 2vCPU

Software requirements

Owner

  • Name: freqtrade
  • Login: freqtrade
  • Kind: organization
  • Email: freqtrade@protonmail.com

JOSS Publication

FreqAI: generalizing adaptive modeling for chaotic time-series market forecasts
Published
December 15, 2022
Volume 7, Issue 80, Page 4864
Authors
Robert A. Caulk ORCID
Emergent Methods LLC, Arvada Colorado, 80005, USA, Freqtrade open source project
Elin Törnquist ORCID
Emergent Methods LLC, Arvada Colorado, 80005, USA, Freqtrade open source project
Matthias Voppichler
Freqtrade open source project
Andrew R. Lawless
Freqtrade open source project
Ryan McMullan
Freqtrade open source project
Wagner Costa Santos
Emergent Methods LLC, Arvada Colorado, 80005, USA, Freqtrade open source project
Timothy C. Pogue
Emergent Methods LLC, Arvada Colorado, 80005, USA, Freqtrade open source project
Johan van der Vlugt
Freqtrade open source project
Stefan P. Gehring
Freqtrade open source project
Pascal Schmidt ORCID
Freqtrade open source project
Editor
Fei Tao ORCID
Tags
Machine Learning adaptive modeling chaotic systems time-series forecasting

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 21,620
  • Total Committers: 354
  • Avg Commits per committer: 61.073
  • Development Distribution Score (DDS): 0.473
Past Year
  • Commits: 2,830
  • Committers: 37
  • Avg Commits per committer: 76.486
  • Development Distribution Score (DDS): 0.322
Top Committers
Name Email Commits
Matthias x****s@o****m 11,389
dependabot[bot] 4****] 2,098
hroff-1902 h****f@m****u 752
Sam Germain s****n@u****a 729
robcaulk r****k@g****m 671
pyup-bot g****t@p****o 590
misagh m****i@g****m 485
gcarq m****r@t****t 387
Janne Sinivirta j****a@g****m 386
Axel-CH a****n@g****m 244
dependabot-preview[bot] 2****] 241
Stefano Ariestasia s****a@g****m 208
Timothy Pogue me@p****v 193
Joe Schr 8****r 186
Gerald Lonlas g****s@g****m 156
Yinon Polak i****1@g****m 126
froggleston r****y@e****k 118
Reigo Reinmets r****o@r****e 94
Samuel Husso s****o@i****i 90
Rokas Kupstys r****s@z****m 87
Jean-Baptiste LE STANG j****g@g****m 82
Yazeed Al Oyoun y****n@g****m 81
iuvbio l****n@g****m 78
Fredrik81 d****1@g****m 71
creslinux c****n@g****m 68
Wagner Costa Santos w****r@w****r 66
eSeR1805 c****v@g****m 62
Meng Xiangzhuo a****o@f****m 55
kevinjulian s****u@g****m 45
Italo 4****o 44
and 324 more...

Issues and Pull Requests

Last synced: 4 months ago

All Time
  • Total issues: 1,429
  • Total pull requests: 2,866
  • Average time to close issues: 15 days
  • Average time to close pull requests: 5 days
  • Total issue authors: 791
  • Total pull request authors: 189
  • Average comments per issue: 3.58
  • Average comments per pull request: 1.44
  • Merged pull requests: 2,251
  • Bot issues: 10
  • Bot pull requests: 1,602
Past Year
  • Issues: 690
  • Pull requests: 1,460
  • Average time to close issues: 2 days
  • Average time to close pull requests: 1 day
  • Issue authors: 404
  • Pull request authors: 96
  • Average comments per issue: 2.79
  • Average comments per pull request: 1.27
  • Merged pull requests: 1,111
  • Bot issues: 4
  • Bot pull requests: 871
Top Authors
Issue Authors
  • myNextCoder (43)
  • winposs (20)
  • WinPoss (16)
  • dobremha (15)
  • moinonin (13)
  • thkwon9474 (13)
  • Axel-CH (13)
  • VerDoe (12)
  • dependabot[bot] (10)
  • Johan1974 (10)
  • NeoWang9999 (9)
  • uplight-dev (9)
  • kivinblue1 (9)
  • viotemp1 (9)
  • 731315163 (8)
Pull Request Authors
  • dependabot[bot] (1,601)
  • xmatthias (308)
  • freqtrade-bot (262)
  • pyup-bot (96)
  • robcaulk (47)
  • froggleston (36)
  • stash86 (35)
  • mrpabloyeah (32)
  • xzmeng (25)
  • Axel-CH (20)
  • hippocritical (15)
  • arenstar (13)
  • creslinux (13)
  • TheJoeSchr (12)
  • gcarq (10)
Top Labels
Issue Labels
Question (1,034) Strategy assistance (178) Triage Needed (160) freqAI (101) Hyperopt (49) Bug (48) Docker (42) Backtest (42) Question - Outdated Version (36) RPC (31) Install (31) Enhancement (30) CCXT (26) unsupported exchange (26) Non-spot (23) Duplicate (23) freqUI (20) Wont fix / Not a bug (20) Data download (13) Dependencies (12) Pairlist (12) Stoploss (11) Python (8) Discussion (7) Good first issue (5) Plotting (4) Documentation (3) Tech maintenance (2) Edge (2) github_actions (2)
Pull Request Labels
Dependencies (1,882) Python (1,519) Tech maintenance (331) Enhancement (142) freqAI (82) github_actions (57) Docker (46) Bug (26) RPC (25) Backtest (22) Documentation (21) WIP (21) Pairlist (14) Hyperopt (14) Question (10) Non-spot (7) Install (4) Data download (3) Wont fix / Not a bug (2) freqUI (2) Triage Needed (2) Strategy assistance (2) Discussion (1) Stoploss (1) CCXT (1) Edge (1) Question - Outdated Version (1) Plotting (1)

Packages

  • Total packages: 2
  • Total downloads:
    • pypi 75,723 last-month
  • Total docker downloads: 51
  • Total dependent packages: 2
    (may contain duplicates)
  • Total dependent repositories: 16
    (may contain duplicates)
  • Total versions: 106
  • Total maintainers: 2
pypi.org: freqtrade

Freqtrade - Crypto Trading Bot

  • Versions: 82
  • Dependent Packages: 1
  • Dependent Repositories: 16
  • Downloads: 28,922 Last month
  • Docker Downloads: 51
Rankings
Forks count: 0.1%
Stargazers count: 0.1%
Docker downloads count: 3.4%
Dependent repos count: 3.6%
Average: 3.8%
Downloads: 5.6%
Dependent packages count: 10.1%
Maintainers (2)
Last synced: 4 months ago
pypi.org: freqtrade-client

Freqtrade - Client scripts

  • Versions: 24
  • Dependent Packages: 1
  • Dependent Repositories: 0
  • Downloads: 46,801 Last month
Rankings
Dependent packages count: 9.6%
Average: 36.6%
Dependent repos count: 63.5%
Maintainers (1)
Last synced: 4 months ago

Dependencies

.github/workflows/pre-commit-update.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • peter-evans/create-pull-request v5 composite
.github/workflows/ci.yml actions
  • actions/cache v3 composite
  • actions/checkout v4 composite
  • actions/download-artifact v4 composite
  • actions/setup-python v5 composite
  • actions/upload-artifact v4 composite
  • crazy-max/ghaction-docker-buildx v3.3.1 composite
  • pre-commit/action v3.0.0 composite
  • pypa/gh-action-pypi-publish v1.8.11 composite
  • rjstone/discord-webhook-notify v1 composite
  • scherermichael-oss/action-has-permission 1.0.6 composite
.github/workflows/docker_update_readme.yml actions
  • actions/checkout v4 composite
  • peter-evans/dockerhub-description v3 composite
.devcontainer/Dockerfile docker
  • freqtradeorg/freqtrade develop_freqairl build
Dockerfile docker
  • base latest build
  • python 3.11.6-slim-bookworm build
docker/docker-compose-freqai.yml docker
  • freqtradeorg/freqtrade stable_freqaitorch
docker/docker-compose-jupyter.yml docker
docker-compose.yml docker
  • freqtradeorg/freqtrade stable
docs/requirements-docs.txt pypi
  • jinja2 ==3.1.2
  • markdown ==3.5.1
  • mdx_truly_sane_lists ==1.3
  • mkdocs ==1.5.3
  • mkdocs-material ==9.5.2
  • pymdown-extensions ==10.5
pyproject.toml pypi
requirements-dev.txt pypi
  • coveralls ==3.3.1 development
  • isort ==5.13.2 development
  • mypy ==1.7.1 development
  • nbconvert ==7.12.0 development
  • pre-commit ==3.6.0 development
  • pytest ==7.4.3 development
  • pytest-asyncio ==0.21.1 development
  • pytest-cov ==4.1.0 development
  • pytest-mock ==3.12.0 development
  • pytest-random-order ==1.1.0 development
  • ruff ==0.1.8 development
  • time-machine ==2.13.0 development
  • types-cachetools ==5.3.0.7 development
  • types-filelock ==3.2.7 development
  • types-python-dateutil ==2.8.19.14 development
  • types-requests ==2.31.0.10 development
  • types-tabulate ==0.9.0.3 development
requirements-freqai-rl.txt pypi
  • gymnasium ==0.29.1
  • sb3_contrib >=2.0.0a9
  • stable_baselines3 ==2.2.1
  • torch ==2.1.2
  • tqdm ==4.66.1
requirements-freqai.txt pypi
  • catboost ==1.2.2
  • datasieve ==0.1.7
  • joblib ==1.3.2
  • lightgbm ==4.1.0
  • scikit-learn ==1.3.2
  • tensorboard ==2.15.1
  • xgboost ==2.0.2
requirements-hyperopt.txt pypi
  • filelock ==3.13.1
  • ft-scikit-optimize ==0.9.2
  • scikit-learn ==1.3.2
  • scipy ==1.11.4
requirements-plot.txt pypi
  • plotly ==5.18.0
requirements.txt pypi
  • SQLAlchemy ==2.0.23
  • TA-Lib ==0.4.28
  • aiofiles ==23.2.1
  • aiohttp ==3.9.1
  • arrow ==1.3.0
  • ast-comments ==1.2.0
  • cachetools ==5.3.2
  • ccxt ==4.1.91
  • colorama ==0.4.6
  • cryptography ==41.0.7
  • fastapi ==0.105.0
  • httpx >=0.24.1
  • janus ==1.0.0
  • jinja2 ==3.1.2
  • joblib ==1.3.2
  • jsonschema ==4.20.0
  • numpy ==1.26.2
  • orjson ==3.9.10
  • packaging ==23.2
  • pandas ==2.1.4
  • pandas-ta ==0.3.14b
  • prompt-toolkit ==3.0.36
  • psutil ==5.9.7
  • py_find_1st ==1.1.6
  • pyarrow ==14.0.1
  • pycoingecko ==3.1.0
  • pydantic ==2.5.2
  • pyjwt ==2.8.0
  • python-dateutil ==2.8.2
  • python-rapidjson ==1.14
  • python-telegram-bot ==20.7
  • questionary ==2.0.1
  • requests ==2.31.0
  • rich ==13.7.0
  • schedule ==1.2.1
  • sdnotify ==0.3.2
  • tables ==3.9.1
  • tabulate ==0.9.0
  • technical ==1.4.2
  • urllib3 ==2.1.0
  • uvicorn ==0.24.0.post1
  • websockets ==12.0
setup.py pypi
  • SQLAlchemy >=2.0.6
  • TA-Lib *
  • aiofiles *
  • aiohttp *
  • arrow >=1.0.0
  • ast-comments *
  • cachetools *
  • ccxt >=4.0.0
  • colorama *
  • cryptography *
  • fastapi *
  • from *
  • httpx >=0.24.1
  • janus *
  • jinja2 *
  • joblib >=1.2.0
  • jsonschema *
  • numpy *
  • orjson *
  • packaging *
  • pandas *
  • pandas-ta *
  • prompt-toolkit *
  • psutil *
  • py_find_1st *
  • pyarrow *
  • pycoingecko *
  • pydantic >=2.2.0
  • pyjwt *
  • python-dateutil *
  • python-rapidjson *
  • python-telegram-bot >=20.1
  • questionary *
  • requests *
  • rich *
  • schedule *
  • sdnotify *
  • tabulate *
  • technical *
  • urllib3 *
  • uvicorn *
  • websockets *