Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/AminHP/gym-anytrading

The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
https://github.com/AminHP/gym-anytrading

dqn forex gym-environments openai-gym q-learning reinforcement-learning stocks trading trading-algorithms trading-environments

Last synced: 3 months ago
JSON representation

The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)

Host: GitHub
URL: https://github.com/AminHP/gym-anytrading
Owner: AminHP
License: mit
Created: 2019-09-16T17:28:27.000Z (about 5 years ago)
Default Branch: master
Last Pushed: 2024-03-14T04:33:05.000Z (8 months ago)
Last Synced: 2024-06-23T04:43:02.588Z (5 months ago)
Topics: dqn, forex, gym-environments, openai-gym, q-learning, reinforcement-learning, stocks, trading, trading-algorithms, trading-environments
Language: Python
Homepage:
Size: 3.64 MB
Stars: 2,067
Watchers: 83
Forks: 451
Open Issues: 6
Metadata Files:
- Readme: README.ipynb
- License: LICENSE

Awesome Lists containing this project

Awesome_AI4Finance - gym-anytrading

README

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# gym-anytrading\n",
"\n",
"`AnyTrading` is a collection of [OpenAI Gym](https://github.com/openai/gym) environments for reinforcement learning-based trading algorithms.\n",
"\n",
"Trading algorithms are mostly implemented in two markets: [FOREX](https://en.wikipedia.org/wiki/Foreign_exchange_market) and [Stock](https://en.wikipedia.org/wiki/Stock). AnyTrading aims to provide some Gym environments to improve and facilitate the procedure of developing and testing RL-based algorithms in this area. This purpose is obtained by implementing three Gym environments: **TradingEnv**, **ForexEnv**, and **StocksEnv**.\n",
"\n",
"TradingEnv is an abstract environment which is defined to support all kinds of trading environments. ForexEnv and StocksEnv are simply two environments that inherit and extend TradingEnv. In the future sections, more explanations will be given about them but before that, some environment properties should be discussed.\n",
"\n",
"**Note:** For experts, it is recommended to check out the [gym-mtsim](https://github.com/AminHP/gym-mtsim) project.\n",
"\n",
"## Installation\n",
"\n",
"### Via PIP\n",
"```bash\n",
"pip install gym-anytrading\n",
"```\n",
"\n",
"### From Repository\n",
"```bash\n",
"git clone https://github.com/AminHP/gym-anytrading\n",
"cd gym-anytrading\n",
"pip install -e .\n",
"\n",
"## or\n",
"\n",
"pip install --upgrade --no-deps --force-reinstall https://github.com/AminHP/gym-anytrading/archive/master.zip\n",
"```\n",
"\n",
"## Environment Properties\n",
"First of all, **you can't simply expect an RL agent to do everything for you and just sit back on your chair in such complex trading markets!**\n",
"Things need to be simplified as much as possible in order to let the agent learn in a faster and more efficient way. In all trading algorithms, the first thing that should be done is to define **actions** and **positions**. In the two following subsections, I will explain these actions and positions and how to simplify them.\n",
"\n",
"### Trading Actions\n",
"If you search on the Internet for trading algorithms, you will find them using numerous actions such as **Buy**, **Sell**, **Hold**, **Enter**, **Exit**, etc.\n",
"Referring to the first statement of this section, a typical RL agent can only solve a part of the main problem in this area. If you work in trading markets you will learn that deciding whether to hold, enter, or exit a pair (in FOREX) or stock (in Stocks) is a statistical decision depending on many parameters such as your budget, pairs or stocks you trade, your money distribution policy in multiple markets, etc. It's a massive burden for an RL agent to consider all these parameters and may take years to develop such an agent! In this case, you certainly will not use this environment but you will extend your own.\n",
"\n",
"So after months of work, I finally found out that these actions just make things complicated with no real positive impact. In fact, they just increase the learning time and an action like **Hold** will be barely used by a well-trained agent because it doesn't want to miss a single penny. Therefore there is no need to have such numerous actions and only `Sell=0` and `Buy=1` actions are adequate to train an agent just as well.\n",
"\n",
"### Trading Positions\n",
"If you're not familiar with trading positions, refer [here](https://en.wikipedia.org/wiki/Position_\\(finance\\)). It's a very important concept and you should learn it as soon as possible.\n",
"\n",
"In a simple vision: **Long** position wants to buy shares when prices are low and profit by sticking with them while their value is going up, and **Short** position wants to sell shares with high value and use this value to buy shares at a lower value, keeping the difference as profit.\n",
"\n",
"Again, in some trading algorithms, you may find numerous positions such as **Short**, **Long**, **Flat**, etc. As discussed earlier, I use only `Short=0` and `Long=1` positions.\n",
"\n",
"## Trading Environments\n",
"As I noticed earlier, now it's time to introduce the three environments. Before creating this project, I spent so much time to search for a simple and flexible Gym environment for any trading market but didn't find one. They were almost a bunch of complex codes with many unclear parameters that you couldn't simply look at them and comprehend what's going on. So I concluded to implement this project with a great focus on simplicity, flexibility, and comprehensiveness.\n",
"\n",
"In the three following subsections, I will introduce our trading environments and in the next section, some IPython examples will be mentioned and briefly explained.\n",
"\n",
"### TradingEnv\n",
"TradingEnv is an abstract class which inherits `gym.Env`. This class aims to provide a general-purpose environment for all kinds of trading markets. Here I explain its public properties and methods. But feel free to take a look at the complete [source code](https://github.com/AminHP/gym-anytrading/blob/master/gym_anytrading/envs/trading_env.py).\n",
"\n",
"* Properties:\n",
"> `df`: An abbreviation for **DataFrame**. It's a **pandas'** DataFrame which contains your dataset and is passed in the class' constructor.\n",
">\n",
"> `prices`: Real prices over time. Used to calculate profit and render the environment.\n",
">\n",
"> `signal_features`: Extracted features over time. Used to create *Gym observations*.\n",
">\n",
"> `window_size`: Number of ticks (current and previous ticks) returned as a *Gym observation*. It is passed in the class' constructor.\n",
">\n",
"> `action_space`: The *Gym action_space* property. Containing discrete values of **0=Sell** and **1=Buy**.\n",
">\n",
"> `observation_space`: The *Gym observation_space* property. Each observation is a window on `signal_features` from index **current_tick - window_size + 1** to **current_tick**. So `_start_tick` of the environment would be equal to `window_size`. In addition, initial value for `_last_trade_tick` is **window_size - 1** .\n",
">\n",
"> `shape`: Shape of a single observation.\n",
">\n",
"> `history`: Stores the information of all steps.\n",
"\n",
"* Methods:\n",
"> `seed`: Typical *Gym seed* method.\n",
">\n",
"> `reset`: Typical *Gym reset* method.\n",
">\n",
"> `step`: Typical *Gym step* method.\n",
">\n",
"> `render`: Typical *Gym render* method. Renders the information of the environment's current tick.\n",
">\n",
"> `render_all`: Renders the whole environment.\n",
">\n",
"> `close`: Typical *Gym close* method.\n",
"\n",
"* Abstract Methods:\n",
"> `_process_data`: It is called in the constructor and returns `prices` and `signal_features` as a tuple. In different trading markets, different features need to be obtained. So this method enables our TradingEnv to be a general-purpose environment and specific features can be returned for specific environments such as *FOREX*, *Stocks*, etc.\n",
">\n",
"> `_calculate_reward`: The reward function for the RL agent.\n",
">\n",
"> `_update_profit`: Calculates and updates total profit which the RL agent has achieved so far. Profit indicates the amount of units of currency you have achieved by starting with *1.0* unit (Profit = FinalMoney / StartingMoney).\n",
">\n",
"> `max_possible_profit`: The maximum possible profit that an RL agent can obtain regardless of trade fees.\n",
"\n",
"### ForexEnv\n",
"This is a concrete class which inherits TradingEnv and implements its abstract methods. Also, it has some specific properties for the *FOREX* market. For more information refer to the [source code](https://github.com/AminHP/gym-anytrading/blob/master/gym_anytrading/envs/forex_env.py).\n",
"\n",
"* Properties:\n",
"> `frame_bound`: A tuple which specifies the start and end of `df`. It is passed in the class' constructor.\n",
">\n",
"> `unit_side`: Specifies the side you start your trading. Containing string values of **left** (default value) and **right**. As you know, there are two sides in a currency pair in *FOREX*. For example in the *EUR/USD* pair, when you choose the `left` side, your currency unit is *EUR* and you start your trading with 1 EUR. It is passed in the class' constructor.\n",
">\n",
"> `trade_fee`: A default constant fee which is subtracted from the real prices on every trade.\n",
"\n",
"\n",
"### StocksEnv\n",
"Same as ForexEnv but for the *Stock* market. For more information refer to the [source code](https://github.com/AminHP/gym-anytrading/blob/master/gym_anytrading/envs/stocks_env.py).\n",
"\n",
"* Properties:\n",
"> `frame_bound`: A tuple which specifies the start and end of `df`. It is passed in the class' constructor.\n",
">\n",
"> `trade_fee_bid_percent`: A default constant fee percentage for bids. For example with trade_fee_bid_percent=0.01, you will lose 1% of your money every time you sell your shares.\n",
">\n",
"> `trade_fee_ask_percent`: A default constant fee percentage for asks. For example with trade_fee_ask_percent=0.005, you will lose 0.5% of your money every time you buy some shares.\n",
"\n",
"Besides, you can create your own customized environment by extending TradingEnv or even ForexEnv or StocksEnv with your desired policies for calculating reward, profit, fee, etc.\n",
"\n",
"## Examples\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an environment"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import gymnasium as gym\n",
"import gym_anytrading\n",
"\n",
"env = gym.make('forex-v0')\n",
"# env = gym.make('stocks-v0')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- This will create the default environment. You can change any parameters such as dataset, frame_bound, etc."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an environment with custom parameters\n",
"I put two default datasets for [*FOREX*](https://github.com/AminHP/gym-anytrading/blob/master/gym_anytrading/datasets/data/FOREX_EURUSD_1H_ASK.csv) and [*Stocks*](https://github.com/AminHP/gym-anytrading/blob/master/gym_anytrading/datasets/data/STOCKS_GOOGL.csv) but you can use your own."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from gym_anytrading.datasets import FOREX_EURUSD_1H_ASK, STOCKS_GOOGL\n",
"\n",
"custom_env = gym.make(\n",
" 'forex-v0',\n",
" df=FOREX_EURUSD_1H_ASK,\n",
" window_size=10,\n",
" frame_bound=(10, 300),\n",
" unit_side='right'\n",
")\n",
"\n",
"# custom_env = gym.make(\n",
"# 'stocks-v0',\n",
"# df=STOCKS_GOOGL,\n",
"# window_size=10,\n",
"# frame_bound=(10, 300)\n",
"# )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- It is to be noted that the first element of `frame_bound` should be greater than or equal to `window_size`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Print some information"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"env information:\n",
"> shape: (24, 2)\n",
"> df.shape: (6225, 5)\n",
"> prices.shape: (6225,)\n",
"> signal_features.shape: (6225, 2)\n",
"> max_possible_profit: 4.054407219413578\n",
"\n",
"custom_env information:\n",
"> shape: (10, 2)\n",
"> df.shape: (6225, 5)\n",
"> prices.shape: (300,)\n",
"> signal_features.shape: (300, 2)\n",
"> max_possible_profit: 1.1228998536878634\n"
]
}
],
"source": [
"print(\"env information:\")\n",
"print(\"> shape:\", env.unwrapped.shape)\n",
"print(\"> df.shape:\", env.unwrapped.df.shape)\n",
"print(\"> prices.shape:\", env.unwrapped.prices.shape)\n",
"print(\"> signal_features.shape:\", env.unwrapped.signal_features.shape)\n",
"print(\"> max_possible_profit:\", env.unwrapped.max_possible_profit())\n",
"\n",
"print()\n",
"print(\"custom_env information:\")\n",
"print(\"> shape:\", custom_env.unwrapped.shape)\n",
"print(\"> df.shape:\", custom_env.unwrapped.df.shape)\n",
"print(\"> prices.shape:\", custom_env.unwrapped.prices.shape)\n",
"print(\"> signal_features.shape:\", custom_env.unwrapped.signal_features.shape)\n",
"print(\"> max_possible_profit:\", custom_env.unwrapped.max_possible_profit())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- Here `max_possible_profit` signifies that if the market didn't have trade fees, you could have earned **4.054414887146572** (or **1.1229001800089833**) units of currency by starting with **1.0**. In other words, your money is almost *quadrupled*."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Plot the environment"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"env.reset()\n",
"env.render()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- **Short** and **Long** positions are shown in `red` and `green` colors.\n",
"- As you see, the starting *position* of the environment is always **Short**."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### A complete example"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"info: {'total_reward': 27.89616584777832, 'total_profit': 0.989812615901, 'position': }\n"
]
},
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import gymnasium as gym\n",
"import gym_anytrading\n",
"from gym_anytrading.envs import TradingEnv, ForexEnv, StocksEnv, Actions, Positions \n",
"from gym_anytrading.datasets import FOREX_EURUSD_1H_ASK, STOCKS_GOOGL\n",
"\n",
"\n",
"env = gym.make('forex-v0', frame_bound=(50, 100), window_size=10)\n",
"# env = gym.make('stocks-v0', frame_bound=(50, 100), window_size=10)\n",
"\n",
"observation = env.reset(seed=2023)\n",
"while True:\n",
" action = env.action_space.sample()\n",
" observation, reward, terminated, truncated, info = env.step(action)\n",
" done = terminated or truncated\n",
"\n",
" # env.render()\n",
" if done:\n",
" print(\"info:\", info)\n",
" break\n",
"\n",
"plt.cla()\n",
"env.unwrapped.render_all()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- You can use `render_all` method to avoid rendering on each step and prevent time-wasting.\n",
"- As you see, the first **10** points (`window_size`=10) on the plot don't have a *position*. Because they aren't involved in calculating reward, profit, etc. They just display the first observations. So the environment's `_start_tick` and initial `_last_trade_tick` are **10** and **9**."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### More examples\n",
"\n",
"[Here](https://github.com/AminHP/gym-anytrading/blob/master/examples) are some examples that mix `gym-anytrading` with some well-known libraries, such as `Stable-Baselines3` and `QuantStats`, and show how to utilize our trading environments in other RL or trading libraries."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Extend and manipulate TradingEnv\n",
"\n",
"In case you want to process data and extract features outside the environment, it can be simply done by two methods:\n",
"\n",
"**Method 1 (Recommended):**"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"def my_process_data(env):\n",
" start = env.frame_bound[0] - env.window_size\n",
" end = env.frame_bound[1]\n",
" prices = env.df.loc[:, 'Low'].to_numpy()[start:end]\n",
" signal_features = env.df.loc[:, ['Close', 'Open', 'High', 'Low']].to_numpy()[start:end]\n",
" return prices, signal_features\n",
"\n",
"\n",
"class MyForexEnv(ForexEnv):\n",
" _process_data = my_process_data\n",
"\n",
"\n",
"env = MyForexEnv(df=FOREX_EURUSD_1H_ASK, window_size=12, frame_bound=(12, len(FOREX_EURUSD_1H_ASK)))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Method 2:**"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"def my_process_data(df, window_size, frame_bound):\n",
" start = frame_bound[0] - window_size\n",
" end = frame_bound[1]\n",
" prices = df.loc[:, 'Low'].to_numpy()[start:end]\n",
" signal_features = df.loc[:, ['Close', 'Open', 'High', 'Low']].to_numpy()[start:end]\n",
" return prices, signal_features\n",
"\n",
"\n",
"class MyStocksEnv(StocksEnv):\n",
" \n",
" def __init__(self, prices, signal_features, **kwargs):\n",
" self._prices = prices\n",
" self._signal_features = signal_features\n",
" super().__init__(**kwargs)\n",
"\n",
" def _process_data(self):\n",
" return self._prices, self._signal_features\n",
"\n",
" \n",
"prices, signal_features = my_process_data(df=STOCKS_GOOGL, window_size=30, frame_bound=(30, len(STOCKS_GOOGL)))\n",
"env = MyStocksEnv(prices, signal_features, df=STOCKS_GOOGL, window_size=30, frame_bound=(30, len(STOCKS_GOOGL)))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Related Projects\n",
"\n",
"* A more complicated version of `anytrading` with five actions, three positions, and a better reward function is developed in the [DI-engine](https://github.com/opendilab/DI-engine/tree/main/dizoo/gym_anytrading) project. It is a mid-level tool (somewhere between `anytrading` and `mtsim`), appropriate for semi-experts. More information and documentation can be found [here](https://github.com/opendilab/DI-engine/tree/main/dizoo/gym_anytrading/envs)."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.6"
}
},
"nbformat": 4,
"nbformat_minor": 4
}