There are some trade- and candle-related fields that are always available to output on the indicator-list so have updated the docs to include the most commonly used ones.
- moved doc from utils.md to lookahead-analysis.md and modified it (unfinished)
- added a check to automatically edit the config['backtest_cache'] to be 'none'
- adjusted test_lookahead_helper_export_to_csv to catch the new catching of errors
- adjusted test_lookahead_helper_text_table_lookahead_analysis_instances to catch the new catching of errors
- changed lookahead_analysis.start result-reporting to show that not enough trades were caught including x of y
moved doc from utils.md to lookahead-analysis.md and modified it (unfinished)
added a check to automatically edit the config['backtest_cache'] to be 'none'
Looking at has_bias should be enough to statisfy the test.
The tests could be extended with thecking the buy/sell signals and the dataframe itself -
but this should be sufficient for now.
There was a seeding error in SB3 after the gymnasium update, the stable baselines team has patched and fixed the issue, but the reset function has to be aligned.
switched from args to config (args still work)
renamed exportfilename to lookahead_analysis_exportfilename so if users decide to put something into it then it won't compete with other configurations
- optimized pairs for entry_varholder and exit_varholder to only check a single pair instead of all pairs.
- bias-check of freqai strategies now possible
- added condition to not crash when compared_df is empty (meaning no differences have been found)
open ended timeranges now work
if a file fails then it will not report as non-bias, but report in the table as error and the csv file will not have it listed.
removed args_common_optimize for strategy-updater
backtest_lookahead_bias_checker:
added args and cli-options for minimum and target trade amounts
fixed code according to best-practice coding requests of matthias (CamelCase etc)
While the actual problem is caused by a ccxt change, the change itself makes sense.
once ccxt starts returning the correct status (open) for create-orders, we can remove the fix.
closes#8079
before calling `git`. otherwise it would display git commit id from the
directory where you are calling `freqtrade` from instead of freqtrade's
current commit id
Changed logic to contain much less if conditions
currently still missing:
Webhook terminology, Telegram notification settings, Strategy/Config settings
Changed logic to contain much less if conditions
currently still missing:
Webhook terminology, Telegram notification settings, Strategy/Config settings
StrategyResolver.search_all_objects(enum_failed) set to False since we got no use in True
shortened update_code call
added modified_code8 test which currently still fails. (and thereby is commented out)
@@ -39,6 +40,7 @@ Please read the [exchange specific notes](docs/exchanges.md) to learn about even
- [X] [Binance](https://www.binance.com/)
- [X] [Gate.io](https://www.gate.io/ref/6266643)
- [X] [OKX](https://okx.com/)
- [X] [Bybit](https://bybit.com/)
Please make sure to read the [exchange specific notes](docs/exchanges.md), as well as the [trading with leverage](docs/leverage.md) documentation before diving in.
@@ -163,6 +165,10 @@ first. If it hasn't been reported, please
ensure you follow the template guide so that the team can assist you as
quickly as possible.
For every [issue](https://github.com/freqtrade/freqtrade/issues/new/choose) created, kindly follow up and mark satisfaction or reminder to close issue when equilibrium ground is reached.
@@ -75,7 +75,7 @@ This function needs to return a floating point number (`float`). Smaller numbers
## Overriding pre-defined spaces
To override a pre-defined space (`roi_space`, `generate_roi_table`, `stoploss_space`, `trailing_space`), define a nested class called Hyperopt and define the required spaces as follows:
To override a pre-defined space (`roi_space`, `generate_roi_table`, `stoploss_space`, `trailing_space`, `max_open_trades_space`), define a nested class called Hyperopt and define the required spaces as follows:
```python
from freqtrade.optimize.space import Categorical, Dimension, Integer, SKDecimal
@@ -123,6 +123,12 @@ class MyAwesomeStrategy(IStrategy):
@@ -130,7 +136,7 @@ class MyAwesomeStrategy(IStrategy):
### Dynamic parameters
Parameters can also be defined dynamically, but must be available to the instance once the * [`bot_start()` callback](strategy-callbacks.md#bot-start) has been called.
Parameters can also be defined dynamically, but must be available to the instance once the [`bot_start()` callback](strategy-callbacks.md#bot-start) has been called.
This needs the `systemd` python package installed as the dependency, which is not available on Windows. Hence, the whole journald logging functionality is not available for a bot running on Windows.
This needs the `cysystemd` python package installed as dependency (`pip install cysystemd`), which is not available on Windows. Hence, the whole journald logging functionality is not available for a bot running on Windows.
To send Freqtrade log messages to `journald` system service use the `--logfile` command line option with the value in the following format:
@@ -300,7 +301,11 @@ A backtesting result will look like that:
| Absolute profit | 0.00762792 BTC |
| Total profit % | 76.2% |
| CAGR % | 460.87% |
| Sortino | 1.88 |
| Sharpe | 2.97 |
| Calmar | 6.29 |
| Profit factor | 1.11 |
| Expectancy (Ratio) | -0.15 (-0.05) |
| Avg. stake amount | 0.001 BTC |
| Total trade volume | 0.429 BTC |
| | |
@@ -319,6 +324,7 @@ A backtesting result will look like that:
| Days win/draw/lose | 12 / 82 / 25 |
| Avg. Duration Winners | 4:23:00 |
| Avg. Duration Loser | 6:55:00 |
| Max Consecutive Wins / Loss | 3 / 4 |
| Rejected Entry signals | 3089 |
| Entry/Exit Timeouts | 0 / 0 |
| Canceled Trade Entries | 34 |
@@ -400,7 +406,11 @@ It contains some useful key metrics about performance of your strategy on backte
| Absolute profit | 0.00762792 BTC |
| Total profit % | 76.2% |
| CAGR % | 460.87% |
| Sortino | 1.88 |
| Sharpe | 2.97 |
| Calmar | 6.29 |
| Profit factor | 1.11 |
| Expectancy (Ratio) | -0.15 (-0.05) |
| Avg. stake amount | 0.001 BTC |
| Total trade volume | 0.429 BTC |
| | |
@@ -419,6 +429,7 @@ It contains some useful key metrics about performance of your strategy on backte
| Days win/draw/lose | 12 / 82 / 25 |
| Avg. Duration Winners | 4:23:00 |
| Avg. Duration Loser | 6:55:00 |
| Max Consecutive Wins / Loss | 3 / 4 |
| Rejected Entry signals | 3089 |
| Entry/Exit Timeouts | 0 / 0 |
| Canceled Trade Entries | 34 |
@@ -447,6 +458,9 @@ It contains some useful key metrics about performance of your strategy on backte
-`Absolute profit`: Profit made in stake currency.
-`Total profit %`: Total profit. Aligned to the `TOTAL` row's `Tot Profit %` from the first table. Calculated as `(End capital − Starting capital) / Starting capital`.
-`CAGR %`: Compound annual growth rate.
-`Sortino`: Annualized Sortino ratio.
-`Sharpe`: Annualized Sharpe ratio.
-`Calmar`: Annualized Calmar ratio.
-`Profit factor`: profit / loss.
-`Avg. stake amount`: Average stake amount, either `stake_amount` or the average when using dynamic stake amount.
-`Total trade volume`: Volume generated on the exchange to reach the above profit.
@@ -455,6 +469,7 @@ It contains some useful key metrics about performance of your strategy on backte
-`Best day` / `Worst day`: Best and worst day based on daily profit.
-`Days win/draw/lose`: Winning / Losing days (draws are usually days without closed trade).
-`Avg. Duration Winners` / `Avg. Duration Loser`: Average durations for winning and losing trades.
-`Max Consecutive Wins / Loss`: Maximum consecutive wins/losses in a row.
-`Rejected Entry signals`: Trade entry signals that could not be acted upon due to `max_open_trades` being reached.
-`Entry/Exit Timeouts`: Entry/exit orders which did not fill (only applicable if custom pricing is used).
-`Canceled Trade Entries`: Number of trades that have been canceled by user request via `adjust_entry_price`.
@@ -522,6 +537,7 @@ Since backtesting lacks some detailed information about what happens within a ca
- ROI
- exits are compared to high - but the ROI value is used (e.g. ROI = 2%, high=5% - so the exit will be at 2%)
- exits are never "below the candle", so a ROI of 2% may result in a exit at 2.4% if low was at 2.4% profit
- ROI entries which came into effect on the triggering candle (e.g. `120: 0.02` for 1h candles, from `60: 0.05`) will use the candle's open as exit rate
- Force-exits caused by `<N>=-1` ROI entries use low as exit value, unless N falls on the candle open (e.g. `120: -1` for 1h candles)
- Stoploss exits happen exactly at stoploss price, even if low was lower, but the loss will be `2 * fees` higher than the stoploss price
- Stoploss is evaluated before ROI within one candle. So you can often see more trades with the `stoploss` exit reason comparing to the results obtained with the same strategy in the Dry Run/Live Trade modes
@@ -12,6 +12,9 @@ This page provides you some basic concepts on how Freqtrade works and operates.
* **Indicators**: Technical indicators (SMA, EMA, RSI, ...).
* **Limit order**: Limit orders which execute at the defined limit price or better.
* **Market order**: Guaranteed to fill, may move price depending on the order size.
* **Current Profit**: Currently pending (unrealized) profit for this trade. This is mainly used throughout the bot and UI.
* **Realized Profit**: Already realized profit. Only relevant in combination with [partial exits](strategy-callbacks.md#adjust-trade-position) - which also explains the calculation logic for this.
* **Total Profit**: Combined realized and unrealized profit. The relative number (%) is calculated against the total investment in this trade.
## Fee handling
@@ -57,10 +60,10 @@ This loop will be repeated again and again until the bot is stopped.
* Load historic data for configured pairlist.
* Calls `bot_start()` once.
* Calls `bot_loop_start()` once.
* Calculate indicators (calls `populate_indicators()` once per pair).
* Calculate entry / exit signals (calls `populate_entry_trend()` and `populate_exit_trend()` once per pair).
* Loops per candle simulating entry and exit points.
* Calls `bot_loop_start()` strategy callback.
* Check for Order timeouts, either via the `unfilledtimeout` configuration, or via `check_entry_timeout()` / `check_exit_timeout()` strategy callbacks.
* Calls `adjust_entry_price()` strategy callback for open entry orders.
* Check for trade entry signals (`enter_long` / `enter_short` columns).
@@ -75,3 +78,7 @@ This loop will be repeated again and again until the bot is stopped.
!!! Note
Both Backtesting and Hyperopt include exchange default Fees in the calculation. Custom fees can be passed to backtesting / hyperopt by specifying the `--fee` argument.
!!! Warning "Callback call frequency"
Backtesting will call each callback at max. once per candle (`--timeframe-detail` modifies this behavior to once per detailed candle).
Most callbacks will be called once per iteration in live (usually every ~5s) - which can cause backtesting mismatches.
@@ -11,7 +11,7 @@ Per default, the bot loads the configuration from the `config.json` file, locate
You can specify a different configuration file used by the bot with the `-c/--config` command-line option.
If you used the [Quick start](installation.md/#quick-start) method for installing
If you used the [Quick start](docker_quickstart.md#docker-quick-start) method for installing
the bot, the installation script should have already created the default configuration file (`config.json`) for you.
If the default configuration file is not created we recommend to use `freqtrade new-config --config config.json` to generate a basic configuration file.
@@ -134,11 +134,11 @@ Mandatory parameters are marked as **Required**, which means that they are requi
| Parameter | Description |
|------------|-------------|
| `max_open_trades` | **Required.** Number of open trades your bot is allowed to have. Only one open trade per pair is possible, so the length of your pairlist is another limitation that can apply. If -1 then it is ignored (i.e. potentially unlimited open trades, limited by the pairlist). [More information below](#configuring-amount-per-trade).<br> **Datatype:** Positive integer or -1.
| `max_open_trades` | **Required.** Number of open trades your bot is allowed to have. Only one open trade per pair is possible, so the length of your pairlist is another limitation that can apply. If -1 then it is ignored (i.e. potentially unlimited open trades, limited by the pairlist). [More information below](#configuring-amount-per-trade). [Strategy Override](#parameters-in-the-strategy).<br> **Datatype:** Positive integer or -1.
| `stake_currency` | **Required.** Crypto-currency used for trading. <br> **Datatype:** String
| `stake_amount` | **Required.** Amount of crypto-currency your bot will use for each trade. Set it to `"unlimited"` to allow the bot to use all available balance. [More information below](#configuring-amount-per-trade). <br> **Datatype:** Positive float or `"unlimited"`.
| `tradable_balance_ratio` | Ratio of the total account balance the bot is allowed to trade. [More information below](#configuring-amount-per-trade). <br>*Defaults to `0.99` 99%).*<br> **Datatype:** Positive float between `0.1` and `1.0`.
| `available_capital` | Available starting capital for the bot. Useful when running multiple bots on the same exchange account.[More information below](#configuring-amount-per-trade). <br> **Datatype:** Positive float.
| `available_capital` | Available starting capital for the bot. Useful when running multiple bots on the same exchange account.[More information below](#configuring-amount-per-trade). <br> **Datatype:** Positive float.
| `amend_last_stake_amount` | Use reduced last stake amount if necessary. [More information below](#configuring-amount-per-trade). <br>*Defaults to `false`.* <br> **Datatype:** Boolean
| `last_stake_amount_min_ratio` | Defines minimum stake amount that has to be left and executed. Applies only to the last stake amount when it's amended to a reduced value (i.e. if `amend_last_stake_amount` is set to `true`). [More information below](#configuring-amount-per-trade). <br>*Defaults to `0.5`.* <br> **Datatype:** Float (as ratio)
| `amount_reserve_percent` | Reserve some amount in min pair stake amount. The bot will reserve `amount_reserve_percent` + stoploss value when calculating min pair stake amount in order to avoid possible trade refusals. <br>*Defaults to `0.05` (5%).* <br> **Datatype:** Positive Float as ratio.
@@ -155,25 +155,25 @@ Mandatory parameters are marked as **Required**, which means that they are requi
| `trailing_stop_positive_offset` | Offset on when to apply `trailing_stop_positive`. Percentage value which should be positive. More details in the [stoploss documentation](stoploss.md#trailing-stop-loss-only-once-the-trade-has-reached-a-certain-offset). [Strategy Override](#parameters-in-the-strategy). <br>*Defaults to `0.0` (no offset).* <br> **Datatype:** Float
| `trailing_only_offset_is_reached` | Only apply trailing stoploss when the offset is reached. [stoploss documentation](stoploss.md). [Strategy Override](#parameters-in-the-strategy). <br>*Defaults to `false`.* <br> **Datatype:** Boolean
| `fee` | Fee used during backtesting / dry-runs. Should normally not be configured, which has freqtrade fall back to the exchange default fee. Set as ratio (e.g. 0.001 = 0.1%). Fee is applied twice for each trade, once when buying, once when selling. <br> **Datatype:** Float (as ratio)
| `futures_funding_rate` | User-specified funding rate to be used when historical funding rates are not available from the exchange. This does not overwrite real historical rates. It is recommended that this be set to 0 unless you are testing a specific coin and you understand how the funding rate will affect freqtrade's profit calculations. [More information here](leverage.md#unavailable-funding-rates) <br>*Defaults to None.*<br> **Datatype:** Float
| `futures_funding_rate` | User-specified funding rate to be used when historical funding rates are not available from the exchange. This does not overwrite real historical rates. It is recommended that this be set to 0 unless you are testing a specific coin and you understand how the funding rate will affect freqtrade's profit calculations. [More information here](leverage.md#unavailable-funding-rates) <br>*Defaults to `None`.*<br> **Datatype:** Float
| `trading_mode` | Specifies if you want to trade regularly, trade with leverage, or trade contracts whose prices are derived from matching cryptocurrency prices. [leverage documentation](leverage.md). <br>*Defaults to `"spot"`.* <br> **Datatype:** String
| `margin_mode` | When trading with leverage, this determines if the collateral owned by the trader will be shared or isolated to each trading pair [leverage documentation](leverage.md). <br> **Datatype:** String
| `liquidation_buffer` | A ratio specifying how large of a safety net to place between the liquidation price and the stoploss to prevent a position from reaching the liquidation price [leverage documentation](leverage.md). <br>*Defaults to `0.05`.* <br> **Datatype:** Float
| | **Unfilled timeout**
| `unfilledtimeout.entry` | **Required.** How long (in minutes or seconds) the bot will wait for an unfilled entry order to complete, after which the order will be cancelled and repeated at current (new) price, as long as there is a signal. [Strategy Override](#parameters-in-the-strategy).<br> **Datatype:** Integer
| `unfilledtimeout.exit` | **Required.** How long (in minutes or seconds) the bot will wait for an unfilled exit order to complete, after which the order will be cancelled and repeated at current (new) price, as long as there is a signal. [Strategy Override](#parameters-in-the-strategy).<br> **Datatype:** Integer
| `unfilledtimeout.unit` | Unit to use in unfilledtimeout setting. Note: If you set unfilledtimeout.unit to "seconds", "internals.process_throttle_secs" must be inferior or equal to timeout [Strategy Override](#parameters-in-the-strategy). <br> *Defaults to `minutes`.* <br> **Datatype:** String
| `unfilledtimeout.unit` | Unit to use in unfilledtimeout setting. Note: If you set unfilledtimeout.unit to "seconds", "internals.process_throttle_secs" must be inferior or equal to timeout [Strategy Override](#parameters-in-the-strategy). <br> *Defaults to `"minutes"`.* <br> **Datatype:** String
| `unfilledtimeout.exit_timeout_count` | How many times can exit orders time out. Once this number of timeouts is reached, an emergency exit is triggered. 0 to disable and allow unlimited order cancels. [Strategy Override](#parameters-in-the-strategy).<br>*Defaults to `0`.* <br> **Datatype:** Integer
| | **Pricing**
| `entry_pricing.price_side` | Select the side of the spread the bot should look at to get the entry rate. [More information below](#buy-price-side).<br> *Defaults to `same`.* <br> **Datatype:** String (either `ask`, `bid`, `same` or `other`).
| `entry_pricing.price_side` | Select the side of the spread the bot should look at to get the entry rate. [More information below](#entry-price).<br> *Defaults to `"same"`.* <br> **Datatype:** String (either `ask`, `bid`, `same` or `other`).
| `entry_pricing.price_last_balance` | **Required.** Interpolate the bidding price. More information [below](#entry-price-without-orderbook-enabled).
| `entry_pricing.use_order_book` | Enable entering using the rates in [Order Book Entry](#entry-price-with-orderbook-enabled). <br> *Defaults to `True`.*<br> **Datatype:** Boolean
| `entry_pricing.use_order_book` | Enable entering using the rates in [Order Book Entry](#entry-price-with-orderbook-enabled). <br> *Defaults to `true`.*<br> **Datatype:** Boolean
| `entry_pricing.order_book_top` | Bot will use the top N rate in Order Book "price_side" to enter a trade. I.e. a value of 2 will allow the bot to pick the 2nd entry in [Order Book Entry](#entry-price-with-orderbook-enabled). <br>*Defaults to `1`.* <br> **Datatype:** Positive Integer
| `entry_pricing. check_depth_of_market.enabled` | Do not enter if the difference of buy orders and sell orders is met in Order Book. [Check market depth](#check-depth-of-market). <br>*Defaults to `false`.* <br> **Datatype:** Boolean
| `entry_pricing. check_depth_of_market.bids_to_ask_delta` | The difference ratio of buy orders and sell orders found in Order Book. A value below 1 means sell order size is greater, while value greater than 1 means buy order size is higher. [Check market depth](#check-depth-of-market) <br> *Defaults to `0`.* <br> **Datatype:** Float (as ratio)
| `exit_pricing.price_side` | Select the side of the spread the bot should look at to get the exit rate. [More information below](#exit-price-side).<br> *Defaults to `same`.* <br> **Datatype:** String (either `ask`, `bid`, `same` or `other`).
| `exit_pricing.price_side` | Select the side of the spread the bot should look at to get the exit rate. [More information below](#exit-price-side).<br> *Defaults to `"same"`.* <br> **Datatype:** String (either `ask`, `bid`, `same` or `other`).
| `exit_pricing.price_last_balance` | Interpolate the exiting price. More information [below](#exit-price-without-orderbook-enabled).
| `exit_pricing.use_order_book` | Enable exiting of open trades using [Order Book Exit](#exit-price-with-orderbook-enabled). <br> *Defaults to `True`.*<br> **Datatype:** Boolean
| `exit_pricing.use_order_book` | Enable exiting of open trades using [Order Book Exit](#exit-price-with-orderbook-enabled). <br> *Defaults to `true`.*<br> **Datatype:** Boolean
| `exit_pricing.order_book_top` | Bot will use the top N rate in Order Book "price_side" to exit. I.e. a value of 2 will allow the bot to pick the 2nd ask rate in [Order Book Exit](#exit-price-with-orderbook-enabled)<br>*Defaults to `1`.* <br> **Datatype:** Positive Integer
| `custom_price_max_distance_ratio` | Configure maximum distance ratio between current and custom entry or exit price. <br>*Defaults to `0.02` 2%).*<br> **Datatype:** Positive float
| | **TODO**
@@ -199,10 +199,10 @@ Mandatory parameters are marked as **Required**, which means that they are requi
| `exchange.ccxt_sync_config` | Additional CCXT parameters passed to the regular (sync) ccxt instance. Parameters may differ from exchange to exchange and are documented in the [ccxt documentation](https://ccxt.readthedocs.io/en/latest/manual.html#instantiation) <br> **Datatype:** Dict
| `exchange.ccxt_async_config` | Additional CCXT parameters passed to the async ccxt instance. Parameters may differ from exchange to exchange and are documented in the [ccxt documentation](https://ccxt.readthedocs.io/en/latest/manual.html#instantiation) <br> **Datatype:** Dict
| `exchange.markets_refresh_interval` | The interval in minutes in which markets are reloaded. <br>*Defaults to `60` minutes.* <br> **Datatype:** Positive Integer
| `exchange.skip_pair_validation` | Skip pairlist validation on startup.<br>*Defaults to `false`<br> **Datatype:** Boolean
| `exchange.skip_open_order_update` | Skips open order updates on startup should the exchange cause problems. Only relevant in live conditions.<br>*Defaults to `false`<br> **Datatype:** Boolean
| `exchange.skip_pair_validation` | Skip pairlist validation on startup.<br>*Defaults to `false`*<br> **Datatype:** Boolean
| `exchange.skip_open_order_update` | Skips open order updates on startup should the exchange cause problems. Only relevant in live conditions.<br>*Defaults to `false`*<br> **Datatype:** Boolean
| `exchange.unknown_fee_rate` | Fallback value to use when calculating trading fees. This can be useful for exchanges which have fees in non-tradable currencies. The value provided here will be multiplied with the "fee cost".<br>*Defaults to `None`<br> **Datatype:** float
| `exchange.log_responses` | Log relevant exchange responses. For debug mode only - use with care.<br>*Defaults to `false`<br> **Datatype:** Boolean
| `exchange.log_responses` | Log relevant exchange responses. For debug mode only - use with care.<br>*Defaults to `false`*<br> **Datatype:** Boolean
| `experimental.block_bad_exchanges` | Block exchanges known to not work with freqtrade. Leave on default unless you want to test if that exchange works now. <br>*Defaults to `true`.* <br> **Datatype:** Boolean
| | **Plugins**
| `edge.*` | Please refer to [edge configuration document](edge.md) for detailed explanation of all possible configuration options.
@@ -213,7 +213,7 @@ Mandatory parameters are marked as **Required**, which means that they are requi
| `telegram.token` | Your Telegram bot token. Only required if `telegram.enabled` is `true`. <br>**Keep it in secret, do not disclose publicly.** <br> **Datatype:** String
| `telegram.chat_id` | Your personal Telegram account id. Only required if `telegram.enabled` is `true`. <br>**Keep it in secret, do not disclose publicly.** <br> **Datatype:** String
| `telegram.balance_dust_level` | Dust-level (in stake currency) - currencies with a balance below this will not be shown by `/balance`. <br> **Datatype:** float
| `telegram.reload` | Allow "reload" buttons on telegram messages. <br>*Defaults to `True`.<br> **Datatype:** boolean
| `telegram.reload` | Allow "reload" buttons on telegram messages. <br>*Defaults to `true`.<br> **Datatype:** boolean
| `telegram.notification_settings.*` | Detailed notification settings. Refer to the [telegram documentation](telegram-usage.md) for details.<br> **Datatype:** dictionary
| `telegram.allow_custom_messages` | Enable the sending of Telegram messages from strategies via the dataprovider.send_msg() function. <br> **Datatype:** Boolean
| | **Webhook**
@@ -263,6 +263,7 @@ Values set in the configuration file always overwrite values set in the strategy
* `minimal_roi`
* `timeframe`
* `stoploss`
* `max_open_trades`
* `trailing_stop`
* `trailing_stop_positive`
* `trailing_stop_positive_offset`
@@ -665,7 +666,7 @@ You should also make sure to read the [Exchanges](exchanges.md) section of the d
### Using proxy with Freqtrade
To use a proxy with freqtrade, export your proxy settings using the variables `"HTTP_PROXY"` and `"HTTPS_PROXY"` set to the appropriate values.
This will have the proxy settings applied to everything (telegram, coingecko, ...) except exchange requests.
This will have the proxy settings applied to everything (telegram, coingecko, ...) **except** for exchange requests.
``` bash
export HTTP_PROXY="http://addr:port"
@@ -681,15 +682,14 @@ To use a proxy for exchange connections - you will have to define the proxies as
{
"exchange": {
"ccxt_config": {
"aiohttp_proxy": "http://addr:port",
"proxies": {
"http": "http://addr:port",
"https": "http://addr:port"
},
"httpsProxy": "http://addr:port",
}
}
}
```
For more information on available proxy types, please consult the [ccxt proxy documentation](https://docs.ccxt.com/#/README?id=proxy).
## Next step
Now you have configured your config.json, the next step is to [start your bot](bot-usage.md).
@@ -6,7 +6,7 @@ To download data (candles / OHLCV) needed for backtesting and hyperoptimization
If no additional parameter is specified, freqtrade will download data for `"1m"` and `"5m"` timeframes for the last 30 days.
Exchange and pairs will come from `config.json` (if specified using `-c/--config`).
Otherwise`--exchange` becomes mandatory.
Without provided configuration,`--exchange` becomes mandatory.
You can use a relative timerange (`--days 20`) or an absolute starting point (`--timerange 20200101-`). For incremental downloads, the relative approach should be used.
@@ -83,40 +83,47 @@ Common arguments:
```
!!! Tip "Downloading all data for one quote currency"
Often, you'll want to download data for all pairs of a specific quote-currency. In such cases, you can use the following shorthand:
`freqtrade download-data --exchange binance --pairs .*/USDT <...>`. The provided "pairs" string will be expanded to contain all active pairs on the exchange.
To also download data for inactive (delisted) pairs, add `--include-inactive-pairs` to the command.
!!! Note "Startup period"
`download-data` is a strategy-independent command. The idea is to download a big chunk of data once, and then iteratively increase the amount of data stored.
For that reason, `download-data` does not care about the "startup-period" defined in a strategy. It's up to the user to download additional days if the backtest should start at a specific point in time (while respecting startup period).
### Pairs file
### Start download
In alternative to the whitelist from `config.json`, a `pairs.json` file can be used.
If you are using Binance for example:
- create a directory `user_data/data/binance` and copy or create the `pairs.json` file in that directory.
- update the `pairs.json` file to contain the currency pairs you are interested in.
A very simple command (assuming an available `config.json` file) can look as follows.
```bash
mkdir -p user_data/data/binance
touch user_data/data/binance/pairs.json
freqtrade download-data --exchange binance
```
The format of the `pairs.json` file is a simple json list.
Mixing different stake-currencies is allowed for this file, since it's only used for downloading.
This will download historical candle (OHLCV) data for all the currency pairs defined in the configuration.
!!! Tip "Downloading all data for one quote currency"
Often, you'll want to download data for all pairs of a specific quote-currency. In such cases, you can use the following shorthand:
`freqtrade download-data --exchange binance --pairs .*/USDT <...>`. The provided "pairs" string will be expanded to contain all active pairs on the exchange.
To also downloaddata for inactive (delisted) pairs, add `--include-inactive-pairs` to the command.
or as regex (in this case, to download all active USDT pairs)
* To use a different directory than the exchange specific default, use `--datadir user_data/data/some_directory`.
* To change the exchange used to download the historical data from, please use a different configuration file (you'll probably need to adjust rate limits etc.)
* To use `pairs.json` from some other directory, use `--pairs-file some_other_dir/pairs.json`.
* To download historical candle (OHLCV) data for only 10 days, use `--days 10` (defaults to 30 days).
* To download historical candle (OHLCV) data from a fixed starting point, use `--timerange 20200101-` - which will download all data from January 1st, 2020.
* Use `--timeframes` to specify what timeframe download the historical candle (OHLCV) data for. Default is `--timeframes 1m 5m` which will download 1-minute and 5-minute data.
* To use exchange, timeframe and list of pairs as defined in your configuration file, use the `-c/--config` option. With this, the script uses the whitelist defined in the config as the list of currency pairs to download data for and does not require the pairs.json file. You can combine `-c/--config` with most other options.
??? Note "Permission denied errors"
If your configuration directory `user_data` was made by docker, you may get the following error:
@@ -131,39 +138,7 @@ Mixing different stake-currencies is allowed for this file, since it's only used
sudo chown -R $UID:$GID user_data
```
### Start download
Then run:
```bash
freqtrade download-data --exchange binance
```
This will download historical candle (OHLCV) data for all the currency pairs you defined in `pairs.json`.
- To use a different directory than the exchange specific default, use `--datadir user_data/data/some_directory`.
- To change the exchange used to download the historical data from, please use a different configuration file (you'll probably need to adjust rate limits etc.)
- To use `pairs.json` from some other directory, use `--pairs-file some_other_dir/pairs.json`.
- To download historical candle (OHLCV) data for only 10 days, use `--days 10` (defaults to 30 days).
- To download historical candle (OHLCV) data from a fixed starting point, use `--timerange 20200101-` - which will download all data from January 1st, 2020.
- Use `--timeframes` to specify what timeframe download the historical candle (OHLCV) data for. Default is `--timeframes 1m 5m` which will download 1-minute and 5-minute data.
- To use exchange, timeframe and list of pairs as defined in your configuration file, use the `-c/--config` option. With this, the script uses the whitelist defined in the config as the list of currency pairs to download data for and does not require the pairs.json file. You can combine `-c/--config` with most other options.
#### Download additional data before the current timerange
### Download additional data before the current timerange
Assuming you downloaded all data from 2022 (`--timerange 20220101-`) - but you'd now like to also backtest with earlier data.
You can do so by using the `--prepend` flag, combined with `--timerange` - specifying an end-date.
@@ -238,7 +213,36 @@ Size has been taken from the BTC/USDT 1m spot combination for the timerange spec
To have a best performance/size mix, we recommend the use of either feather or parquet.
#### Sub-command convert data
### Pairs file
In alternative to the whitelist from `config.json`, a `pairs.json` file can be used.
If you are using Binance for example:
* create a directory `user_data/data/binance` and copy or create the `pairs.json` file in that directory.
* update the `pairs.json` file to contain the currency pairs you are interested in.
```bash
mkdir -p user_data/data/binance
touch user_data/data/binance/pairs.json
```
The format of the `pairs.json` file is a simple json list.
Mixing different stake-currencies is allowed for this file, since it's only used for downloading.
``` json
[
"ETH/BTC",
"ETH/USDT",
"BTC/USDT",
"XRP/ETH"
]
```
!!! Note
The `pairs.json` file is only used when no configuration is loaded (implicitly by naming, or via `--config` flag).
You can force the usage of this file via `--pairs-file pairs.json` - however we recommend to use the pairlist from within the configuration, either via `exchange.pair_whitelist` or `pairs` setting in the configuration.
The following command will convert all candle (OHLCV) data available in `~/.freqtrade/data/binance` from json to jsongz, saving diskspace in the process.
It'll also remove original json data files (`--erase` parameter).
@@ -299,7 +303,7 @@ It'll also remove original json data files (`--erase` parameter).
version 2023.3 saw the removal of `populate_any_indicators` in favor of split methods for feature engineering and targets. Please read the [migration document](strategy_migration.md#freqai-strategy) for full details.
@@ -24,7 +24,7 @@ This will spin up a local server (usually on port 8000) so you can see if everyt
To configure a development environment, you can either use the provided [DevContainer](#devcontainer-setup), or use the `setup.sh` script and answer "y" when asked "Do you want to install dependencies for dev [y/N]? ".
Alternatively (e.g. if your system is not supported by the setup.sh script), follow the manual installation process and run `pip3 install -e .[all]`.
This will install all required tools for development, including `pytest`, `flake8`, `mypy`, and `coveralls`.
This will install all required tools for development, including `pytest`, `ruff`, `mypy`, and `coveralls`.
Then install the git hook scripts by running `pre-commit install`, so your changes will be verified locally before committing.
This avoids a lot of waiting for CI already, as some basic formatting checks are done locally on your machine.
@@ -327,18 +327,18 @@ To check how the new exchange behaves, you can use the following snippet:
``` python
import ccxt
from datetime import datetime
from datetime import datetime, timezone
from freqtrade.data.converter import ohlcv_to_dataframe
ct = ccxt.binance()
ct = ccxt.binance() # Use the exchange you're testing
timeframe = "1d"
pair = "XLM/BTC" # Make sure to use a pair that exists on that exchange!
pair = "BTC/USDT" # Make sure to use a pair that exists on that exchange!
They can however also be configured via configuration file. Since json doesn't support multi-line strings, you'll have to replace all newlines with `\n` to have a valid json file.
Binance has specific (unfortunately complex) [Futures Trading Quantitative Rules](https://www.binance.com/en/support/faq/4f462ebe6ff445d4a170be7d9e897272) which need to be followed, and which prohibit a too low stake-amount (among others) for too many orders.
@@ -224,8 +243,8 @@ OKX requires a passphrase for each api key, you will therefore need to add this
OKX only provides 100 candles per api call. Therefore, the strategy will only have a pretty low amount of data available in backtesting mode.
!!! Warning "Futures"
OKX Futures has the concept of "position mode" - which can be Net or long/short (hedge mode).
Freqtrade supports both modes (we recommend to use net mode) - but changing the mode mid-trading is not supported and will lead to exceptions and failures to place trades.
OKX Futures has the concept of "position mode" - which can be "Buy/Sell" or long/short (hedge mode).
Freqtrade supports both modes (we recommend to use Buy/Sell mode) - but changing the mode mid-trading is not supported and will lead to exceptions and failures to place trades.
OKX also only provides MARK candles for the past ~3 months. Backtesting futures prior to that date will therefore lead to slight deviations, as funding-fees cannot be calculated correctly without this data.
## Gate.io
@@ -236,6 +255,25 @@ OKX requires a passphrase for each api key, you will therefore need to add this
Gate.io allows the use of `POINT` to pay for fees. As this is not a tradable currency (no regular market available), automatic fee calculations will fail (and default to a fee of 0).
The configuration parameter `exchange.unknown_fee_rate` can be used to specify the exchange rate between Point and the stake currency. Obviously, changing the stake-currency will also require changes to this value.
## Bybit
Futures trading on bybit is currently supported for USDT markets, and will use isolated futures mode.
Users with unified accounts (there's no way back) can create a Sub-account which will start as "non-unified", and can therefore use isolated futures.
On startup, freqtrade will set the position mode to "One-way Mode" for the whole (sub)account. This avoids making this call over and over again (slowing down bot operations), but means that changes to this setting may result in exceptions and errors
As bybit doesn't provide funding rate history, the dry-run calculation is used for live trades as well.
API Keys for live futures trading (Subaccount on non-unified) must have the following permissions:
* Read-write
* Contract - Orders
* Contract - Positions
We do strongly recommend to limit all API keys to the IP you're going to use it from.
!!! Tip "Stoploss on Exchange"
Bybit (futures only) supports `stoploss_on_exchange` and uses `stop-loss-limit` orders. It provides great advantages, so we recommend to benefit from it by enabling stoploss on exchange.
On futures, Bybit supports both `stop-limit` as well as `stop-market` orders. You can use either `"limit"` or `"market"` in the `order_types.stoploss` configuration setting to decide which type to use.
## All exchanges
Should you experience constant errors with Nonce (like `InvalidNonce`), it is best to regenerate the API keys. Resetting Nonce is difficult and it's usually easier to regenerate the API keys.
Freqtrade supports spot trading, as well as (isolated) futures trading for some selected exchanges. Please refer to the [documentation start page](index.md#supported-futures-exchanges-experimental) for an uptodate list of supported exchanges.
### Can my bot open short positions?
@@ -142,6 +142,13 @@ To fix this, redefine order types in the strategy to use "limit" instead of "mar
The same fix should be applied in the configuration file, if order types are defined in your custom config rather than in the strategy.
### I'm trying to start the bot live, but get an API permission error
Errors like `Invalid API-key, IP, or permissions for action` mean exactly what they actually say.
Your API key is either invalid (copy/paste error? check for leading/trailing spaces in the config), expired, or the IP you're running the bot from is not enabled in the Exchange's API console.
Usually, the permission "Spot Trading" (or the equivalent in the exchange you use) will be necessary.
Futures will usually have to be enabled specifically.
### How do I search the bot logs for something?
By default, the bot writes its log into stderr stream. This is implemented this way so that you can easily separate the bot's diagnostics messages from Backtesting, Edge and Hyperopt results, output from other various Freqtrade utility sub-commands, as well as from the output of your custom `print()`'s you may have inserted into your strategy. So if you need to search the log messages with the grep utility, you need to redirect stderr to stdout and disregard stdout.
@@ -248,8 +255,26 @@ The Edge module is mostly a result of brainstorming of [@mishaker](https://githu
You can find further info on expectancy, win rate, risk management and position size in the following sources:
Nobody affiliated with the freqtrade project will ask you about your exchange keys or anything else exposing your funds to exploitation.
Should you be asked to expose your exchange keys or send funds to some random wallet, then please don't follow these instructions.
Failing to follow these guidelines will not be responsibility of freqtrade.
## "Freqtrade token"
Freqtrade does not have a Crypto token offering.
Token offerings you find on the internet referring Freqtrade, FreqAI or freqUI must be considered to be a scam, trying to exploit freqtrade's popularity for their own, nefarious gains.
Notice how the `populate_any_indicators()` is where [features](freqai-feature-engineering.md#feature-engineering) and labels/targets are added. A full example strategy is available in `templates/FreqaiExampleStrategy.py`.
Notice also the location of the labels under `if set_generalized_indicators:` at the bottom of the example. This is where single features and labels/targets should be added to the feature set to avoid duplication of them from various configuration parameters that multiply the feature set, such as `include_timeframes`.
Notice how the `feature_engineering_*()` is where [features](freqai-feature-engineering.md#feature-engineering) are added. Meanwhile `set_freqai_targets()` adds the labels/targets. A full example strategy is available in `templates/FreqaiExampleStrategy.py`.
!!! Note
The `self.freqai.start()` function cannot be called outside the `populate_indicators()`.
!!! Note
Features **must** be defined in `populate_any_indicators()`. Defining FreqAI features in `populate_indicators()`
will cause the algorithm to fail in live/dry mode. In order to add generalized features that are not associated with a specific pair or timeframe, the following structure inside `populate_any_indicators()` should be used
(as exemplified in `freqtrade/templates/FreqaiExampleStrategy.py`):
Please see the example script located in `freqtrade/templates/FreqaiExampleStrategy.py` for a full example of `populate_any_indicators()`.
Features **must** be defined in `feature_engineering_*()`. Defining FreqAI features in `populate_indicators()`
will cause the algorithm to fail in live/dry mode. In order to add generalized features that are not associated with a specific pair or timeframe, you should use `feature_engineering_standard()`
(as exemplified in `freqtrade/templates/FreqaiExampleStrategy.py`).
## Important dataframe key patterns
@@ -160,18 +158,18 @@ Below are the values you can expect to include/use inside a typical strategy dat
| DataFrame Key | Description |
|------------|-------------|
| `df['&*']` | Any dataframe column prepended with `&` in `populate_any_indicators()` is treated as a training target (label) inside FreqAI (typically following the naming convention `&-s*`). For example, to predict the close price 40 candles into the future, you would set `df['&-s_close'] = df['close'].shift(-self.freqai_info["feature_parameters"]["label_period_candles"])` with `"label_period_candles": 40` in the config. FreqAI makes the predictions and gives them back under the same key (`df['&-s_close']`) to be used in `populate_entry/exit_trend()`. <br> **Datatype:** Depends on the output of the model.
| `df['&*']` | Any dataframe column prepended with `&` in `set_freqai_targets()` is treated as a training target (label) inside FreqAI (typically following the naming convention `&-s*`). For example, to predict the close price 40 candles into the future, you would set `df['&-s_close'] = df['close'].shift(-self.freqai_info["feature_parameters"]["label_period_candles"])` with `"label_period_candles": 40` in the config. FreqAI makes the predictions and gives them back under the same key (`df['&-s_close']`) to be used in `populate_entry/exit_trend()`. <br> **Datatype:** Depends on the output of the model.
| `df['&*_std/mean']` | Standard deviation and mean values of the defined labels during training (or live tracking with `fit_live_predictions_candles`). Commonly used to understand the rarity of a prediction (use the z-score as shown in `templates/FreqaiExampleStrategy.py` and explained [here](#creating-a-dynamic-target-threshold) to evaluate how often a particular prediction was observed during training or historically with `fit_live_predictions_candles`). <br>**Datatype:** Float.
| `df['do_predict']` | Indication of an outlier data point. The return value is integer between -2 and 2, which lets you know if the prediction is trustworthy or not. `do_predict==1` means that the prediction is trustworthy. If the Dissimilarity Index (DI, see details [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di)) of the input data point is above the threshold defined in the config, FreqAI will subtract 1 from `do_predict`, resulting in `do_predict==0`. If `use_SVM_to_remove_outliers()` is active, the Support Vector Machine (SVM, see details [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm)) may also detect outliers in training and prediction data. In this case, the SVM will also subtract 1 from `do_predict`. If the input data point was considered an outlier by the SVM but not by the DI, or vice versa, the result will be `do_predict==0`. If both the DI and the SVM considers the input data point to be an outlier, the result will be `do_predict==-1`. As with the SVM, if `use_DBSCAN_to_remove_outliers` is active, DBSCAN (see details [here](freqai-feature-engineering.md#identifying-outliers-with-dbscan)) may also detect outliers and subtract 1 from `do_predict`. Hence, if both the SVM and DBSCAN are active and identify a datapoint that was above the DI threshold as an outlier, the result will be `do_predict==-2`. A particular case is when `do_predict == 2`, which means that the model has expired due to exceeding `expired_hours`. <br> **Datatype:** Integer between -2 and 2.
| `df['do_predict']` | Indication of an outlier data point. The return value is integer between -2 and 2, which lets you know if the prediction is trustworthy or not. `do_predict==1` means that the prediction is trustworthy. If the Dissimilarity Index (DI, see details [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di)) of the input data point is above the threshold defined in the config, FreqAI will subtract 1 from `do_predict`, resulting in `do_predict==0`. If `use_SVM_to_remove_outliers` is active, the Support Vector Machine (SVM, see details [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm)) may also detect outliers in training and prediction data. In this case, the SVM will also subtract 1 from `do_predict`. If the input data point was considered an outlier by the SVM but not by the DI, or vice versa, the result will be `do_predict==0`. If both the DI and the SVM considers the input data point to be an outlier, the result will be `do_predict==-1`. As with the SVM, if `use_DBSCAN_to_remove_outliers` is active, DBSCAN (see details [here](freqai-feature-engineering.md#identifying-outliers-with-dbscan)) may also detect outliers and subtract 1 from `do_predict`. Hence, if both the SVM and DBSCAN are active and identify a datapoint that was above the DI threshold as an outlier, the result will be `do_predict==-2`. A particular case is when `do_predict == 2`, which means that the model has expired due to exceeding `expired_hours`. <br> **Datatype:** Integer between -2 and 2.
| `df['DI_values']` | Dissimilarity Index (DI) values are proxies for the level of confidence FreqAI has in the prediction. A lower DI means the prediction is close to the training data, i.e., higher prediction confidence. See details about the DI [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di). <br>**Datatype:** Float.
| `df['%*']` | Any dataframe column prepended with `%` in `populate_any_indicators()` is treated as a training feature. For example, you can include the RSI in the training feature set (similar to in `templates/FreqaiExampleStrategy.py`) by setting `df['%-rsi']`. See more details on how this is done [here](freqai-feature-engineering.md). <br> **Note:** Since the number of features prepended with `%` can multiply very quickly (10s of thousands of features are easily engineered using the multiplictative functionality of, e.g., `include_shifted_candles` and `include_timeframes` as described in the [parameter table](freqai-parameter-table.md)), these features are removed from the dataframe that is returned from FreqAI to the strategy. To keep a particular type of feature for plotting purposes, you would prepend it with `%%`. <br> **Datatype:** Depends on the output of the model.
| `df['%*']` | Any dataframe column prepended with `%` in `feature_engineering_*()` is treated as a training feature. For example, you can include the RSI in the training feature set (similar to in `templates/FreqaiExampleStrategy.py`) by setting `df['%-rsi']`. See more details on how this is done [here](freqai-feature-engineering.md). <br> **Note:** Since the number of features prepended with `%` can multiply very quickly (10s of thousands of features are easily engineered using the multiplictative functionality of, e.g., `include_shifted_candles` and `include_timeframes` as described in the [parameter table](freqai-parameter-table.md)), these features are removed from the dataframe that is returned from FreqAI to the strategy. To keep a particular type of feature for plotting purposes, you would prepend it with `%%`. <br> **Datatype:** Depends on the output of the model.
## Setting the `startup_candle_count`
The `startup_candle_count` in the FreqAI strategy needs to be set up in the same way as in the standard Freqtrade strategy (see details [here](strategy-customization.md#strategy-startup-period)). This value is used by Freqtrade to ensure that a sufficient amount of data is provided when calling the `dataprovider`, to avoid any NaNs at the beginning of the first training. You can easily set this value by identifying the longest period (in candle units) which is passed to the indicator creation functions (e.g., Ta-Lib functions). In the presented example, `startup_candle_count` is 20 since this is the maximum value in `indicators_periods_candles`.
The `startup_candle_count` in the FreqAI strategy needs to be set up in the same way as in the standard Freqtrade strategy (see details [here](strategy-customization.md#strategy-startup-period)). This value is used by Freqtrade to ensure that a sufficient amount of data is provided when calling the `dataprovider`, to avoid any NaNs at the beginning of the first training. You can easily set this value by identifying the longest period (in candle units) which is passed to the indicator creation functions (e.g., TA-Lib functions). In the presented example, `startup_candle_count` is 20 since this is the maximum value in `indicators_periods_candles`.
!!! Note
There are instances where the Ta-Lib functions actually require more data than just the passed `period` or else the feature dataset gets populated with NaNs. Anecdotally, multiplying the `startup_candle_count` by 2 always leads to a fully NaN free training dataset. Hence, it is typically safest to multiply the expected `startup_candle_count` by 2. Look out for this log message to confirm that the data is clean:
There are instances where the TA-Lib functions actually require more data than just the passed `period` or else the feature dataset gets populated with NaNs. Anecdotally, multiplying the `startup_candle_count` by 2 always leads to a fully NaN free training dataset. Hence, it is typically safest to multiply the expected `startup_candle_count` by 2. Look out for this log message to confirm that the data is clean:
```
2022-08-31 15:14:04 - freqtrade.freqai.data_kitchen - INFO - dropped 0 training points due to NaNs in populated dataset 4319.
@@ -208,7 +206,7 @@ All of the aforementioned model libraries implement gradient boosted decision tr
There are also numerous online articles describing and comparing the algorithms. Some relatively light-weight examples would be [CatBoost vs. LightGBM vs. XGBoost — Which is the best algorithm?](https://towardsdatascience.com/catboost-vs-lightgbm-vs-xgboost-c80f40662924#:~:text=In%20CatBoost%2C%20symmetric%20trees%2C%20or,the%20same%20depth%20can%20differ.) and [XGBoost, LightGBM or CatBoost — which boosting algorithm should I use?](https://medium.com/riskified-technology/xgboost-lightgbm-or-catboost-which-boosting-algorithm-should-i-use-e7fda7bb36bc). Keep in mind that the performance of each model is highly dependent on the application and so any reported metrics might not be true for your particular use of the model.
There are also numerous online articles describing and comparing the algorithms. Some relatively lightweight examples would be [CatBoost vs. LightGBM vs. XGBoost — Which is the best algorithm?](https://towardsdatascience.com/catboost-vs-lightgbm-vs-xgboost-c80f40662924#:~:text=In%20CatBoost%2C%20symmetric%20trees%2C%20or,the%20same%20depth%20can%20differ.) and [XGBoost, LightGBM or CatBoost — which boosting algorithm should I use?](https://medium.com/riskified-technology/xgboost-lightgbm-or-catboost-which-boosting-algorithm-should-i-use-e7fda7bb36bc). Keep in mind that the performance of each model is highly dependent on the application and so any reported metrics might not be true for your particular use of the model.
Apart from the models already available in FreqAI, it is also possible to customize and create your own prediction models using the `IFreqaiModel` class. You are encouraged to inherit `fit()`, `train()`, and `predict()` to customize various aspects of the training procedures. You can place custom FreqAI models in `user_data/freqaimodels` - and freqtrade will pick them up from there based on the provided `--freqaimodel` name - which has to correspond to the class name of your custom model.
Make sure to use unique names to avoid overriding built-in models.
@@ -239,3 +237,181 @@ If you want to predict multiple targets you must specify all labels in the same
The PyTorch module requires large packages such as `torch`, which should be explicitly requested during `./setup.sh -i` by answering "y" to the question "Do you also want dependencies for freqai-rl or PyTorch (~700mb additional space required) [y/N]?".
Users who prefer docker should ensure they use the docker image appended with `_freqaitorch`.
We do provide an explicit docker-compose file for this in `docker/docker-compose-freqai.yml` - which can be used via `docker compose -f docker/docker-compose-freqai.yml run ...` - or can be copied to replace the original docker file.
This docker-compose file also contains a (disabled) section to enable GPU resources within docker containers. This obviously assumes the system has GPU resources available.
### Structure
#### Model
You can construct your own Neural Network architecture in PyTorch by simply defining your `nn.Module` class inside your custom [`IFreqaiModel` file](#using-different-prediction-models) and then using that class in your `def train()` function. Here is an example of logistic regression model implementation using PyTorch (should be used with nn.BCELoss criterion) for classification tasks.
The `PyTorchModelTrainer` performs the idiomatic PyTorch train loop:
Define our model, loss function, and optimizer, and then move them to the appropriate device (GPU or CPU). Inside the loop, we iterate through the batches in the dataloader, move the data to the device, compute the prediction and loss, backpropagate, and update the model parameters using the optimizer.
In addition, the trainer is responsible for the following:
- saving and loading the model
- converting the data from `pandas.DataFrame` to `torch.Tensor`.
#### Integration with Freqai module
Like all freqai models, PyTorch models inherit `IFreqaiModel`. `IFreqaiModel` declares three abstract methods: `train`, `fit`, and `predict`. we implement these methods in three levels of hierarchy.
From top to bottom:
1. `BasePyTorchModel` - Implements the `train` method. all `BasePyTorch*` inherit it. responsible for general data preparation (e.g., data normalization) and calling the `fit` method. Sets `device` attribute used by children classes. Sets `model_type` attribute used by the parent class.
2. `BasePyTorch*` - Implements the `predict` method. Here, the `*` represents a group of algorithms, such as classifiers or regressors. responsible for data preprocessing, predicting, and postprocessing if needed.
3. `PyTorch*Classifier` / `PyTorch*Regressor` - implements the `fit` method. responsible for the main train flaw, where we initialize the trainer and model objects.
#### Full example
Building a PyTorch regressor using MLP (multilayer perceptron) model, MSELoss criterion, and AdamW optimizer.
Here we create a `PyTorchMLPRegressor` class that implements the `fit` method. The `fit` method specifies the training building blocks: model, optimizer, criterion, and trainer. We inherit both `BasePyTorchRegressor` and `BasePyTorchModel`, where the former implements the `predict` method that is suitable for our regression task, and the latter implements the train method.
??? Note "Setting Class Names for Classifiers"
When using classifiers, the user must declare the class names (or targets) by overriding the `IFreqaiModel.class_names` attribute. This is achieved by setting `self.freqai.class_names` in the FreqAI strategy inside the `set_freqai_targets` method.
For example, if you are using a binary classifier to predict price movements as up or down, you can set the class names as follows:
To see a full example, you can refer to the [classifier test strategy class](https://github.com/freqtrade/freqtrade/blob/develop/tests/strategy/strats/freqai_test_classifier.py).
#### Improving performance with `torch.compile()`
Torch provides a `torch.compile()` method that can be used to improve performance for specific GPU hardware. More details can be found [here](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html). In brief, you simply wrap your `model` in `torch.compile()`:
```python
model = PyTorchMLPModel(
input_dim=n_features,
output_dim=1,
**self.model_kwargs
)
model.to(self.device)
model = torch.compile(model)
```
Then proceed to use the model as normal. Keep in mind that doing this will remove eager execution, which means errors and tracebacks will not be informative.
Low level feature engineering is performed in the user strategy within a function called `populate_any_indicators()`. That function sets the `base features` such as, `RSI`, `MFI`, `EMA`, `SMA`, time of day, volume, etc. The `base features` can be custom indicators or they can be imported from any technical-analysis library that you can find. One important syntax rule is that all `base features` string names are prepended with `%-{pair}`, while labels/targets are prepended with `&`.
Low level feature engineering is performed in the user strategy within a set of functions called `feature_engineering_*`. These function set the `base features` such as, `RSI`, `MFI`, `EMA`, `SMA`, time of day, volume, etc. The `base features` can be custom indicators or they can be imported from any technical-analysis library that you can find. FreqAI is equipped with a set of functions to simplify rapid large-scale feature engineering:
!!! Note
Adding the full pair string, e.g. XYZ/USD, in the feature name enables improved performance for dataframe caching on the backend. If you decide *not* to add the full pair string in the feature string, FreqAI will operate in a reduced performance mode.
| Function | Description |
|---------------|-------------|
| `feature_engineering_expand_all()` | This optional function will automatically expand the defined features on the config defined `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`.
| `feature_engineering_expand_basic()` | This optional function will automatically expand the defined features on the config defined `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`. Note: this function does *not* expand across `include_periods_candles`.
| `feature_engineering_standard()` | This optional function will be called once with the dataframe of the base timeframe. This is the final function to be called, which means that the dataframe entering this function will contain all the features and columns from the base asset created by the other `feature_engineering_expand` functions. This function is a good place to do custom exotic feature extractions (e.g. tsfresh). This function is also a good place for any feature that should not be auto-expanded upon (e.g., day of the week).
| `set_freqai_targets()` | Required function to set the targets for the model. All targets must be prepended with `&` to be recognized by the FreqAI internals.
Meanwhile, high level feature engineering is handled within `"feature_parameters":{}` in the FreqAI config. Within this file, it is possible to decide large scale feature expansions on top of the `base_features` such as "including correlated pairs" or "including informative timeframes" or even "including recent candles."
It is advisable to start from the template `populate_any_indicators()` in the source provided example strategy (found in `templates/FreqaiExampleStrategy.py`) to ensure that the feature definitions are following the correct conventions. Here is an example of how to set the indicators and labels in the strategy:
It is advisable to start from the template `feature_engineering_*` functions in the source provided example strategy (found in `templates/FreqaiExampleStrategy.py`) to ensure that the feature definitions are following the correct conventions. Here is an example of how to set the indicators and labels in the strategy:
In the presented example, the user does not wish to pass the `bb_lowerband` as a feature to the model,
@@ -118,14 +172,29 @@ After having defined the `base features`, the next step is to expand upon them u
}
```
The `include_timeframes` in the config above are the timeframes (`tf`) of each call to `populate_any_indicators()` in the strategy. In the presented case, the user is asking for the `5m`, `15m`, and `4h` timeframes of the `rsi`, `mfi`, `roc`, and `bb_width` to be included in the feature set.
The `include_timeframes` in the config above are the timeframes (`tf`) of each call to `feature_engineering_expand_*()` in the strategy. In the presented case, the user is asking for the `5m`, `15m`, and `4h` timeframes of the `rsi`, `mfi`, `roc`, and `bb_width` to be included in the feature set.
You can ask for each of the defined features to be included also for informative pairs using the `include_corr_pairlist`. This means that the feature set will include all the features from `populate_any_indicators` on all the `include_timeframes` for each of the correlated pairs defined in the config (`ETH/USD`, `LINK/USD`, and `BNB/USD` in the presented example).
You can ask for each of the defined features to be included also for informative pairs using the `include_corr_pairlist`. This means that the feature set will include all the features from `feature_engineering_expand_*()` on all the `include_timeframes` for each of the correlated pairs defined in the config (`ETH/USD`, `LINK/USD`, and `BNB/USD` in the presented example).
`include_shifted_candles` indicates the number of previous candles to include in the feature set. For example, `include_shifted_candles: 2` tells FreqAI to include the past 2 candles for each of the features in the feature set.
In total, the number of features the user of the presented example strat has created is: length of `include_timeframes`* no. features in `populate_any_indicators()` * length of `include_corr_pairlist` * no. `include_shifted_candles` * length of `indicator_periods_candles`
In total, the number of features the user of the presented example strat has created is: length of `include_timeframes`* no. features in `feature_engineering_expand_*()` * length of `include_corr_pairlist` * no. `include_shifted_candles` * length of `indicator_periods_candles`
$= 3 * 3 * 3 * 2 * 2 = 108$.
!!! note "Learn more about creative feature engineering"
Check out our [medium article](https://emergentmethods.medium.com/freqai-from-price-to-prediction-6fadac18b665) geared toward helping users learn how to creatively engineer features.
### Gain finer control over `feature_engineering_*` functions with `metadata`
All `feature_engineering_*` and `set_freqai_targets()` functions are passed a `metadata` dictionary which contains information about the `pair`, `tf` (timeframe), and `period` that FreqAI is automating for feature building. As such, a user can use `metadata` inside `feature_engineering_*` functions as criteria for blocking/reserving features for certain timeframes, periods, pairs etc.
This will block `ta.ROC()` from being added to any timeframes other than `"1h"`.
### Returning additional info from training
@@ -143,41 +212,7 @@ Another example, where the user wants to use live metrics from the trade databas
You need to set the standard dictionary in the config so that FreqAI can return proper dataframe shapes. These values will likely be overridden by the prediction model, but in the case where the model has yet to set them, or needs a default initial value, the pre-set values are what will be returned.
## Feature normalization
FreqAI is strict when it comes to data normalization. The train features, $X^{train}$, are always normalized to [-1, 1] using a shifted min-max normalization:
All other data (test data and unseen prediction data in dry/live/backtest) is always automatically normalized to the training feature space according to industry standards. FreqAI stores all the metadata required to ensure that test and prediction features will be properly normalized and that predictions are properly denormalized. For this reason, it is not recommended to eschew industry standards and modify FreqAI internals - however - advanced users can do so by inheriting `train()` in their custom `IFreqaiModel` and using their own normalization functions.
## Data dimensionality reduction with Principal Component Analysis
You can reduce the dimensionality of your features by activating the `principal_component_analysis` in the config:
```json
"freqai":{
"feature_parameters":{
"principal_component_analysis":true
}
}
```
This will perform PCA on the features and reduce their dimensionality so that the explained variance of the data set is >= 0.999. Reducing data dimensionality makes training the model faster and hence allows for more up-to-date models.
## Inlier metric
The `inlier_metric` is a metric aimed at quantifying how similar a the features of a data point are to the most recent historic data points.
You define the lookback window by setting `inlier_metric_window` and FreqAI computes the distance between the present time point and each of the previous `inlier_metric_window` lookback points. A Weibull function is fit to each of the lookback distributions and its cumulative distribution function (CDF) is used to produce a quantile for each lookback point. The `inlier_metric` is then computed for each time point as the average of the corresponding lookback quantiles. The figure below explains the concept for an `inlier_metric_window` of 5.
FreqAI adds the `inlier_metric` to the training features and hence gives the model access to a novel type of temporal information.
This function does **not** remove outliers from the data set.
## Weighting features for temporal importance
### Weighting features for temporal importance
FreqAI allows you to set a `weight_factor` to weight recent data more strongly than past data via an exponential function:
@@ -187,13 +222,103 @@ where $W_i$ is the weight of data point $i$ in a total set of $n$ data points. B
## Building the data pipeline
By default, FreqAI builds a dynamic pipeline based on user congfiguration settings. The default settings are robust and designed to work with a variety of methods. These two steps are a `MinMaxScaler(-1,1)` and a `VarianceThreshold` which removes any column that has 0 variance. Users can activate other steps with more configuration parameters. For example if users add `use_SVM_to_remove_outliers: true` to the `freqai` config, then FreqAI will automatically add the [`SVMOutlierExtractor`](#identifying-outliers-using-a-support-vector-machine-svm) to the pipeline. Likewise, users can add `principal_component_analysis: true` to the `freqai` config to activate PCA. The [DissimilarityIndex](#identifying-outliers-with-the-dissimilarity-index-di) is activated with `DI_threshold: 1`. Finally, noise can also be added to the data with `noise_standard_deviation: 0.1`. Finally, users can add [DBSCAN](#identifying-outliers-with-dbscan) outlier removal with `use_DBSCAN_to_remove_outliers: true`.
!!! note "More information available"
Please review the [parameter table](freqai-parameter-table.md) for more information on these parameters.
### Customizing the pipeline
Users are encouraged to customize the data pipeline to their needs by building their own data pipeline. This can be done by simply setting `dk.feature_pipeline` to their desired `Pipeline` object inside their `IFreqaiModel` `train()` function, or if they prefer not to touch the `train()` function, they can override `define_data_pipeline`/`define_label_pipeline` functions in their `IFreqaiModel`:
!!! note "More information available"
FreqAI uses the the [`DataSieve`](https://github.com/emergentmethods/datasieve) pipeline, which follows the SKlearn pipeline API, but adds, among other features, coherence between the X, y, and sample_weight vector point removals, feature removal, feature name following.
```python
from datasieve.transforms import SKLearnWrapper, DissimilarityIndex
from datasieve.pipeline import Pipeline
from sklearn.preprocessing import QuantileTransformer, StandardScaler
from freqai.base_models import BaseRegressionModel
User defines their custom label pipeline here (if they wish)
"""
label_pipeline = Pipeline([
('qt', SKLearnWrapper(StandardScaler())),
])
return label_pipeline
```
Here, you are defining the exact pipeline that will be used for your feature set during training and prediction. You can use *most* SKLearn transformation steps by wrapping them in the `SKLearnWrapper` class as shown above. In addition, you can use any of the transformations available in the [`DataSieve` library](https://github.com/emergentmethods/datasieve).
You can easily add your own transformation by creating a class that inherits from the datasieve `BaseTransform` and implementing your `fit()`, `transform()` and `inverse_transform()` methods:
```python
from datasieve.transforms.base_transform import BaseTransform
# do/dont do something with X, y, sample_weight, or/and feature_list
return X, y, sample_weight, feature_list
```
!!! note "Hint"
You can define this custom class in the same file as your `IFreqaiModel`.
### Migrating a custom `IFreqaiModel` to the new Pipeline
If you have created your own custom `IFreqaiModel` with a custom `train()`/`predict()` function, *and* you still rely on `data_cleaning_train/predict()`, then you will need to migrate to the new pipeline. If your model does *not* rely on `data_cleaning_train/predict()`, then you do not need to worry about this migration.
More details about the migration can be found [here](strategy_migration.md#freqai---new-data-pipeline).
## Outlier detection
Equity and crypto markets suffer from a high level of non-patterned noise in the form of outlier data points. FreqAI implements a variety of methods to identify such outliers and hence mitigate risk.
### Identifying outliers with the Dissimilarity Index (DI)
The Dissimilarity Index (DI) aims to quantify the uncertainty associated with each prediction made by the model.
The Dissimilarity Index (DI) aims to quantify the uncertainty associated with each prediction made by the model.
You can tell FreqAI to remove outlier data points from the training/test data sets using the DI by including the following statement in the config:
@@ -205,7 +330,7 @@ You can tell FreqAI to remove outlier data points from the training/test data se
}
```
The DI allows predictions which are outliers (not existent in the model feature space) to be thrown out due to low levels of certainty. To do so, FreqAI measures the distance between each training data point (feature vector), $X_{a}$, and all other training data points:
Which will add `DissimilarityIndex` step to your `feature_pipeline` and set the threshold to 1. The DI allows predictions which are outliers (not existent in the model feature space) to be thrown out due to low levels of certainty. To do so, FreqAI measures the distance between each training data point (feature vector), $X_{a}$, and all other training data points:
@@ -239,9 +364,9 @@ You can tell FreqAI to remove outlier data points from the training/test data se
}
```
The SVM will be trained on the training data and any data point that the SVM deems to be beyond the feature space will be removed.
Which will add `SVMOutlierExtractor` step to your `feature_pipeline`. The SVM will be trained on the training data and any data point that the SVM deems to be beyond the feature space will be removed.
FreqAI uses `sklearn.linear_model.SGDOneClassSVM` (details are available on scikit-learn's webpage [here](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.SGDOneClassSVM.html) (external website)) and you can elect to provide additional parameters for the SVM, such as `shuffle`, and `nu`.
You can elect to provide additional parameters for the SVM, such as `shuffle`, and `nu` via the `feature_parameters.svm_params` dictionary in the config.
The parameter `shuffle` is by default set to `False` to ensure consistent results. If it is set to `True`, running the SVM multiple times on the same data set might result in different outcomes due to `max_iter` being to low for the algorithm to reach the demanded `tol`. Increasing `max_iter` solves this issue but causes the procedure to take longer time.
@@ -259,7 +384,7 @@ You can configure FreqAI to use DBSCAN to cluster and remove outliers from the t
}
```
DBSCAN is an unsupervised machine learning algorithm that clusters data without needing to know how many clusters there should be.
Which will add the `DataSieveDBSCAN` step to your `feature_pipeline`. This is an unsupervised machine learning algorithm that clusters data without needing to know how many clusters there should be.
Given a number of data points $N$, and a distance $\varepsilon$, DBSCAN clusters the data set by setting all data points that have $N-1$ other data points within a distance of $\varepsilon$ as *core points*. A data point that is within a distance of $\varepsilon$ from a *core point* but that does not have $N-1$ other data points within a distance of $\varepsilon$ from itself is considered an *edge point*. A cluster is then the collection of *core points* and *edge points*. Data points that have no other data points at a distance $<\varepsilon$ are considered outliers. The figure below shows a cluster with $N = 3$.
@@ -15,13 +15,13 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
| `identifier` | **Required.**<br> A unique ID for the current model. If models are saved to disk, the `identifier` allows for reloading specific pre-trained models/data. <br>**Datatype:** String.
| `live_retrain_hours` | Frequency of retraining during dry/live runs. <br>**Datatype:** Float > 0. <br> Default: `0` (models retrain as often as possible).
| `expiration_hours` | Avoid making predictions if a model is more than `expiration_hours` old. <br>**Datatype:** Positive integer. <br> Default: `0` (models never expire).
| `purge_old_models` | Number of models to keep on disk (not relevant to backtesting). Default is 2, which means that dry/live runs will keep the latest 2 models on disk. Setting to 0 keeps all models. This parameter also accepts a boolean to maintain backwards compatibility. <br>**Datatype:**Integer. <br> Default: `2`.
| `save_backtest_models` | Save models to disk when running backtesting. Backtesting operates most efficiently by saving the prediction data and reusing them directly for subsequent runs (when you wish to tune entry/exit parameters). Saving backtesting models to disk also allows to use the same model files for starting a dry/live instance with the same model `identifier`. <br>**Datatype:** Boolean. <br> Default: `False` (no models are saved).
| `fit_live_predictions_candles` | Number of historical candles to use for computing target (label) statistics from prediction data, instead of from the training dataset (more information can be found [here](freqai-configuration.md#creating-a-dynamic-target-threshold)). <br>**Datatype:** Positive integer.
| `follow_mode` | Use a `follower` that will look for models associated with a specific `identifier` and load those for inferencing. A `follower` will **not** train new models. <br>**Datatype:** Boolean. <br> Default: `False`.
| `continual_learning` | Use the final state of the most recently trained model as starting point for the new model, allowing for incremental learning (more information can be found [here](freqai-running.md#continual-learning)). <br>**Datatype:** Boolean. <br> Default: `False`.
| `continual_learning` | Use the final state of the most recently trained model as starting point for the new model, allowing for incremental learning (more information can be found [here](freqai-running.md#continual-learning)). Beware that this is currently a naive approach to incremental learning, and it has a high probability of overfitting/getting stuck in local minima while the market moves away from your model. We have the connections here primarily for experimental purposes and so that it is ready for more mature approaches to continual learning in chaotic systems like the crypto market. <br>**Datatype:** Boolean. <br> Default: `False`.
| `write_metrics_to_disk` | Collect train timings, inference timings and cpu usage in json file. <br>**Datatype:** Boolean. <br> Default: `False`
| `data_kitchen_thread_count` | <br> Designate the number of threads you want to use for data processing (outlier methods, normalization, etc.). This has no impact on the number of threads used for training. If user does not set it (default), FreqAI will use max number of threads - 2 (leaving 1 physical core available for Freqtrade bot and FreqUI) <br>**Datatype:** Positive integer.
| `activate_tensorboard` | <br> Indicate whether or not to activate tensorboard for the tensorboard enabled modules (currently Reinforcment Learning, XGBoost, Catboost, and PyTorch). Tensorboard needs Torch installed, which means you will need the torch/RL docker image or you need to answer "yes" to the install question about whether or not you wish to install Torch. <br>**Datatype:** Boolean. <br> Default: `True`.
### Feature parameters
@@ -29,12 +29,12 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
|------------|-------------|
| | **Feature parameters within the `freqai.feature_parameters` sub dictionary**
| `feature_parameters` | A dictionary containing the parameters used to engineer the feature set. Details and examples are shown [here](freqai-feature-engineering.md). <br>**Datatype:** Dictionary.
| `include_timeframes` | A list of timeframes that all indicators in `populate_any_indicators` will be created for. The list is added as features to the base indicators dataset. <br>**Datatype:** List of timeframes (strings).
| `include_corr_pairlist` | A list of correlated coins that FreqAI will add as additional features to all `pair_whitelist` coins. All indicators set in `populate_any_indicators` during feature engineering (see details [here](freqai-feature-engineering.md)) will be created for each correlated coin. The correlated coins features are added to the base indicators dataset. <br>**Datatype:** List of assets (strings).
| `label_period_candles` | Number of candles into the future that the labels are created for. This is used in `populate_any_indicators` (see `templates/FreqaiExampleStrategy.py` for detailed usage). You can create custom labels and choose whether to make use of this parameter or not. <br>**Datatype:** Positive integer.
| `include_timeframes` | A list of timeframes that all indicators in `feature_engineering_expand_*()` will be created for. The list is added as features to the base indicators dataset. <br>**Datatype:** List of timeframes (strings).
| `include_corr_pairlist` | A list of correlated coins that FreqAI will add as additional features to all `pair_whitelist` coins. All indicators set in `feature_engineering_expand_*()` during feature engineering (see details [here](freqai-feature-engineering.md)) will be created for each correlated coin. The correlated coins features are added to the base indicators dataset. <br>**Datatype:** List of assets (strings).
| `label_period_candles` | Number of candles into the future that the labels are created for. This is used in `feature_engineering_expand_all()` (see `templates/FreqaiExampleStrategy.py` for detailed usage). You can create custom labels and choose whether to make use of this parameter or not. <br>**Datatype:** Positive integer.
| `include_shifted_candles` | Add features from previous candles to subsequent candles with the intent of adding historical information. If used, FreqAI will duplicate and shift all features from the `include_shifted_candles` previous candles so that the information is available for the subsequent candle. <br>**Datatype:** Positive integer.
| `weight_factor` | Weight training data points according to their recency (see details [here](freqai-feature-engineering.md#weighting-features-for-temporal-importance)). <br>**Datatype:** Positive float (typically <1).
|`indicator_max_period_candles`|**No longer used (#7325)**.Replacedby`startup_candle_count`whichissetinthe [strategy](freqai-configuration.md#building-a-freqai-strategy).`startup_candle_count`istimeframeindependentanddefinesthemaximum*period*usedin`populate_any_indicators()`forindicatorcreation.FreqAIusesthisparametertogetherwiththemaximumtimeframein`include_time_frames`tocalculatehowmanydatapointstodownloadsuchthatthefirstdatapointdoesnotincludeaNaN.<br>**Datatype:** Positive integer.
|`indicator_max_period_candles`|**No longer used (#7325)**.Replacedby`startup_candle_count`whichissetinthe [strategy](freqai-configuration.md#building-a-freqai-strategy).`startup_candle_count`istimeframeindependentanddefinesthemaximum*period*usedin`feature_engineering_*()`forindicatorcreation.FreqAIusesthisparametertogetherwiththemaximumtimeframein`include_time_frames`tocalculatehowmanydatapointstodownloadsuchthatthefirstdatapointdoesnotincludeaNaN.<br>**Datatype:** Positive integer.
| `indicator_periods_candles` | Time periods to calculate indicators for. The indicators are added to the base indicator dataset. <br>**Datatype:** List of positive integers.
| `principal_component_analysis` | Automatically reduce the dimensionality of the data set using Principal Component Analysis. See details about how it works [here](#reducing-data-dimensionality-with-principal-component-analysis) <br>**Datatype:** Boolean. <br> Default: `False`.
| `plot_feature_importances` | Create a feature importance plot for each model for the top/bottom `plot_feature_importances` number of features. Plot is stored in `user_data/models/<identifier>/sub-train-<COIN>_<timestamp>.html`. <br>**Datatype:** Integer. <br> Default: `0`.
@@ -42,17 +42,18 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
| `svm_params` | All parameters available in Sklearn's `SGDOneClassSVM()`. See details about some select parameters [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm). <br>**Datatype:** Dictionary.
| `use_DBSCAN_to_remove_outliers` | Cluster data using the DBSCAN algorithm to identify and remove outliers from training and prediction data. See details about how it works [here](freqai-feature-engineering.md#identifying-outliers-with-dbscan). <br>**Datatype:** Boolean.
| `inlier_metric_window` | If set, FreqAI adds an `inlier_metric` to the training feature set and set the lookback to be the `inlier_metric_window`, i.e., the number of previous time points to compare the current candle to. Details of how the `inlier_metric` is computed can be found [here](freqai-feature-engineering.md#inlier-metric). <br>**Datatype:** Integer. <br> Default: `0`.
| `noise_standard_deviation` | If set, FreqAI adds noise to the training features with the aim of preventing overfitting. FreqAI generates random deviates from a gaussian distribution with a standard deviation of `noise_standard_deviation` and adds them to all data points. `noise_standard_deviation` should be kept relative to the normalized space, i.e., between -1 and 1. In other words, since data in FreqAI is always normalized to be between -1 and 1, `noise_standard_deviation: 0.05` would result in 32% of the data being randomly increased/decreased by more than 2.5% (i.e., the percent of data falling within the first standard deviation). <br>**Datatype:** Integer. <br> Default: `0`.
| `outlier_protection_percentage` | Enable to prevent outlier detection methods from discarding too much data. If more than `outlier_protection_percentage` % of points are detected as outliers by the SVM or DBSCAN, FreqAI will log a warning message and ignore outlier detection, i.e., the original dataset will be kept intact. If the outlier protection is triggered, no predictions will be made based on the training dataset. <br>**Datatype:** Float. <br> Default: `30`.
| `reverse_train_test_order` | Split the feature dataset (see below) and use the latest data split for training and test on historical split of the data. This allows the model to be trained up to the most recent data point, while avoiding overfitting. However, you should be careful to understand the unorthodox nature of this parameter before employing it. <br>**Datatype:** Boolean. <br> Default: `False` (no reversal).
| `shuffle_after_split` | Split the data into train and test sets, and then shuffle both sets individually. <br>**Datatype:** Boolean. <br> Default: `False`.
| `buffer_train_data_candles` | Cut `buffer_train_data_candles` off the beginning and end of the training data *after* the indicators were populated. The main example use is when predicting maxima and minima, the argrelextrema function cannot know the maxima/minima at the edges of the timerange. To improve model accuracy, it is best to compute argrelextrema on the full timerange and then use this function to cut off the edges (buffer) by the kernel. In another case, if the targets are set to a shifted price movement, this buffer is unnecessary because the shifted candles at the end of the timerange will be NaN and FreqAI will automatically cut those off of the training dataset.<br>**Datatype:** Integer. <br> Default: `0`.
### Data split parameters
| Parameter | Description |
|------------|-------------|
| | **Data split parameters within the `freqai.data_split_parameters` sub dictionary**
| `data_split_parameters` | Include any additional parameters available from Scikit-learn `test_train_split()`, which are shown [here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website). <br>**Datatype:** Dictionary.
| `data_split_parameters` | Include any additional parameters available from scikit-learn `test_train_split()`, which are shown [here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website). <br>**Datatype:** Dictionary.
| `test_size` | The fraction of data that should be used for testing instead of training. <br>**Datatype:** Positive float <1.
@@ -83,12 +84,35 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
| `add_state_info` | Tell FreqAI to include state information in the feature set for training and inferencing. The current state variables include trade duration, current profit, trade position. This is only available in dry/live runs, and is automatically switched to false for backtesting. <br> **Datatype:** bool. <br> Default: `False`.
| `net_arch` | Network architecture which is well described in [`stable_baselines3` doc](https://stable-baselines3.readthedocs.io/en/master/guide/custom_policy.html#examples). In summary: `[<sharedlayers>, dict(vf=[<non-sharedvaluenetworklayers>], pi=[<non-sharedpolicynetworklayers>])]`. By default this is set to `[128, 128]`, which defines 2 shared hidden layers with 128 units each.
| `randomize_starting_position` | Randomize the starting point of each episode to avoid overfitting. <br> **Datatype:** bool. <br> Default: `False`.
| `drop_ohlc_from_features` | Do not include the normalized ohlc data in the feature set passed to the agent during training (ohlc will still be used for driving the environment in all cases) <br> **Datatype:** Boolean. <br> **Default:** `False`
| `progress_bar` | Display a progress bar with the current progress, elapsed time and estimated remaining time. <br> **Datatype:** Boolean. <br> Default: `False`.
### PyTorch parameters
#### general
| Parameter | Description |
|------------|-------------|
| | **Model training parameters within the `freqai.model_training_parameters` sub dictionary**
| `learning_rate` | Learning rate to be passed to the optimizer. <br> **Datatype:** float. <br> Default: `3e-4`.
| `model_kwargs` | Parameters to be passed to the model class. <br> **Datatype:** dict. <br> Default: `{}`.
| `trainer_kwargs` | Parameters to be passed to the trainer class. <br> **Datatype:** dict. <br> Default: `{}`.
#### trainer_kwargs
| Parameter | Description |
|------------|-------------|
| | **Model training parameters within the `freqai.model_training_parameters.model_kwargs` sub dictionary**
| `max_iters` | The number of training iterations to run. iteration here refers to the number of times we call self.optimizer.step(). used to calculate n_epochs. <br> **Datatype:** int. <br> Default: `100`.
| `batch_size` | The size of the batches to use during training.. <br> **Datatype:** int. <br> Default: `64`.
| `max_n_eval_batches` | The maximum number batches to use for evaluation.. <br> **Datatype:** int, optional. <br> Default: `None`.
### Additional parameters
| Parameter | Description |
|------------|-------------|
| | **Extraneous parameters**
| `freqai.keras` | If the selected model makes use of Keras (typical for Tensorflow-based prediction models), this flag needs to be activated so that the model save/loading follows Keras standards. <br> **Datatype:** Boolean. <br> Default: `False`.
| `freqai.conv_width` | The width of a convolutional neural network input tensor. This replaces the need for shifting candles (`include_shifted_candles`) by feeding in historical data points as the second dimension of the tensor. Technically, this parameter can also be used for regressors, but it only adds computational overhead and does not change the model training/prediction. <br> **Datatype:** Integer. <br> Default: `2`.
| `freqai.keras` | If the selected model makes use of Keras (typical for TensorFlow-based prediction models), this flag needs to be activated so that the model save/loading follows Keras standards. <br> **Datatype:** Boolean. <br> Default: `False`.
| `freqai.conv_width` | The width of a neural network input tensor. This replaces the need for shifting candles (`include_shifted_candles`) by feeding in historical data points as the second dimension of the tensor. Technically, this parameter can also be used for regressors, but it only adds computational overhead and does not change the model training/prediction. <br> **Datatype:** Integer. <br> Default: `2`.
| `freqai.reduce_df_footprint` | Recast all numeric columns to float32/int32, with the objective of reducing ram/disk usage and decreasing train/inference timing. This parameter is set in the main level of the Freqtrade configuration file (not inside FreqAI). <br> **Datatype:** Boolean. <br> Default: `False`.
@@ -24,7 +24,7 @@ The framework is built on stable_baselines3 (torch) and OpenAI gym for the base
### Important considerations
As explained above, the agent is "trained" in an artificial trading "environment". In our case, that environment may seem quite similar to a real Freqtrade backtesting environment, but it is *NOT*. In fact, the RL training environment is much more simplified. It does not incorporate any of the complicated strategy logic, such as callbacks like `custom_exit`, `custom_stoploss`, leverage controls, etc. The RL environment is instead a very "raw" representation of the true market, where the agent has free-will to learn the policy (read: stoploss, take profit, etc.) which is enforced by the `calculate_reward()`. Thus, it is important to consider that the agent training environment is not identical to the real world.
As explained above, the agent is "trained" in an artificial trading "environment". In our case, that environment may seem quite similar to a real Freqtrade backtesting environment, but it is *NOT*. In fact, the RL training environment is much more simplified. It does not incorporate any of the complicated strategy logic, such as callbacks like `custom_exit`, `custom_stoploss`, leverage controls, etc. The RL environment is instead a very "raw" representation of the true market, where the agent has freewill to learn the policy (read: stoploss, take profit, etc.) which is enforced by the `calculate_reward()`. Thus, it is important to consider that the agent training environment is not identical to the real world.
## Running Reinforcement Learning
@@ -34,65 +34,38 @@ Setting up and running a Reinforcement Learning model is the same as running a R
where `ReinforcementLearner` will use the templated `ReinforcementLearner` from `freqai/prediction_models/ReinforcementLearner` (or a custom user defined one located in `user_data/freqaimodels`). The strategy, on the other hand, follows the same base [feature engineering](freqai-feature-engineering.md) with `populate_any_indicators` as a typical Regressor:
where `ReinforcementLearner` will use the templated `ReinforcementLearner` from `freqai/prediction_models/ReinforcementLearner` (or a custom user defined one located in `user_data/freqaimodels`). The strategy, on the other hand, follows the same base [feature engineering](freqai-feature-engineering.md) with `feature_engineering_*` as a typical Regressor. The difference lies in the creation of the targets, Reinforcement Learning doesn't require them. However, FreqAI requires a default (neutral) value to be set in the action column:
# For RL, there are no direct targets to set. This is filler (neutral)
# until the agent sends an action.
dataframe["&-action"]=0
returndataframe
```
Most of the function remains the same as for typical Regressors, however, the function above shows how the strategy must pass the raw price data to the agent so that it has access to raw OHLCV in the training environment:
Most of the function remains the same as for typical Regressors, however, the function below shows how the strategy must pass the raw price data to the agent so that it has access to raw OHLCV in the training environment:
Finally, there is no explicit "label" to make - instead it is necessary to assign the `&-action` column which will contain the agent's actions when accessed in `populate_entry/exit_trends()`. In the present example, the neutral action to 0. This value should align with the environment used. FreqAI provides two environments, both use 0 as the neutral action.
@@ -162,79 +135,104 @@ Parameter details can be found [here](freqai-parameter-table.md), but in general
## Creating a custom reward function
As you begin to modify the strategy and the prediction model, you will quickly realize some important differences between the Reinforcement Learner and the Regressors/Classifiers. Firstly, the strategy does not set a target value (no labels!). Instead, you set the `calculate_reward()` function inside the `MyRLEnv` class (see below). A default `calculate_reward()` is provided inside `prediction_models/ReinforcementLearner.py` to demonstrate the necessary building blocks for creating rewards, but users are encouraged to create their own custom reinforcement learning model class (see below) and save it to `user_data/freqaimodels`. It is inside the `calculate_reward()` where creative theories about the market can be expressed. For example, you can reward your agent when it makes a winning trade, and penalize the agent when it makes a losing trade. Or perhaps, you wish to reward the agent for entering trades, and penalize the agent for sitting in trades too long. Below we show examples of how these rewards are all calculated:
!!! danger "Not for production"
Warning!
The reward function provided with the Freqtrade source code is a showcase of functionality designed to show/test as many possible environment control features as possible. It is also designed to run quickly on small computers. This is a benchmark, it is *not* for live production. Please beware that you will need to create your own custom_reward() function or use a template built by other users outside of the Freqtrade source code.
As you begin to modify the strategy and the prediction model, you will quickly realize some important differences between the Reinforcement Learner and the Regressors/Classifiers. Firstly, the strategy does not set a target value (no labels!). Instead, you set the `calculate_reward()` function inside the `MyRLEnv` class (see below). A default `calculate_reward()` is provided inside `prediction_models/ReinforcementLearner.py` to demonstrate the necessary building blocks for creating rewards, but this is *not* designed for production. Users *must* create their own custom reinforcement learning model class or use a pre-built one from outside the Freqtrade source code and save it to `user_data/freqaimodels`. It is inside the `calculate_reward()` where creative theories about the market can be expressed. For example, you can reward your agent when it makes a winning trade, and penalize the agent when it makes a losing trade. Or perhaps, you wish to reward the agent for entering trades, and penalize the agent for sitting in trades too long. Below we show examples of how these rewards are all calculated:
!!! note "Hint"
The best reward functions are ones that are continuously differentiable, and well scaled. In other words, adding a single large negative penalty to a rare event is not a good idea, and the neural net will not be able to learn that function. Instead, it is better to add a small negative penalty to a common event. This will help the agent learn faster. Not only this, but you can help improve the continuity of your rewards/penalties by having them scale with severity according to some linear/exponential functions. In other words, you'd slowly scale the penalty as the duration of the trade increases. This is better than a single large penalty occuring at a single point in time.
Reinforcement Learning models benefit from tracking training metrics. FreqAI has integrated Tensorboard to allow users to track training and evaluation performance across all coins and across all retrainings. Tensorboard is activated via the following command:
@@ -247,40 +245,37 @@ where `unique-id` is the `identifier` set in the `freqai` configuration file. Th
### Custom logging
## Custom logging
FreqAI also provides a built in episodic summary logger called `self.tensorboard_log` for adding custom information to the Tensorboard log. By default, this function is already called once per step inside the environment to record the agent actions. All values accumulated for all steps in a single episode are reported at the conclusion of each episode, followed by a full reset of all metrics to 0 in preparation for the subsequent episode.
`self.tensorboard_log` can also be used anywhere inside the environment, for example, it can be added to the `calculate_reward` function to collect more detailed information about how often various parts of the reward were called:
```py
classMyRLEnv(Base5ActionRLEnv):
"""
User made custom environment. This class inherits from BaseEnvironment and gym.env.
Users can override any functions from those parent classes. Here is an example
of a user customized `calculate_reward()` function.
"""
defcalculate_reward(self,action:int)->float:
ifnotself._is_valid(action):
self.tensorboard_log("is_valid")
return-2
```python
classMyRLEnv(Base5ActionRLEnv):
"""
User made custom environment. This class inherits from BaseEnvironment and gym.env.
Users can override any functions from those parent classes. Here is an example
of a user customized `calculate_reward()` function.
"""
defcalculate_reward(self,action:int)->float:
ifnotself._is_valid(action):
self.tensorboard_log("invalid")
return-2
```
!!! Note
The `self.tensorboard_log()` function is designed for tracking incremented objects only i.e. events, actions inside the training environment. If the event of interest is a float, the float can be passed as the second argument e.g. `self.tensorboard_log("float_metric1", 0.23)` would add 0.23 to `float_metric`. In this case you can also disable incrementing using `inc=False` parameter.
The `self.tensorboard_log()` function is designed for tracking incremented objects only i.e. events, actions inside the training environment. If the event of interest is a float, the float can be passed as the second argument e.g. `self.tensorboard_log("float_metric1", 0.23)`. In this case the metric values are not incremented.
## Choosing a base environment
### Choosing a base environment
FreqAI provides two base environments, `Base4ActionEnvironment` and `Base5ActionEnvironment`. As the names imply, the environments are customized for agents that can select from 4 or 5 actions. In the `Base4ActionEnvironment`, the agent can enter long, enter short, hold neutral, or exit position. Meanwhile, in the `Base5ActionEnvironment`, the agent has the same actions as Base4, but instead of a single exit action, it separates exit long and exit short. The main changes stemming from the environment selection include:
FreqAI provides three base environments, `Base3ActionRLEnvironment`, `Base4ActionEnvironment` and `Base5ActionEnvironment`. As the names imply, the environments are customized for agents that can select from 3, 4 or 5 actions. The `Base3ActionEnvironment` is the simplest, the agent can select from hold, long, or short. This environment can also be used for long-only bots (it automatically follows the `can_short` flag from the strategy), where long is the enter condition and short is the exit condition. Meanwhile, in the `Base4ActionEnvironment`, the agent can enter long, enter short, hold neutral, or exit position. Finally, in the `Base5ActionEnvironment`, the agent has the same actions as Base4, but instead of a single exit action, it separates exit long and exit short. The main changes stemming from the environment selection include:
* the actions available in the `calculate_reward`
* the actions consumed by the user strategy
Both of the FreqAI provided environments inherit from an action/position agnostic environment object called the `BaseEnvironment`, which contains all shared logic. The architecture is designed to be easily customized. The simplest customization is the `calculate_reward()` (see details [here](#creating-a-custom-reward-function)). However, the customizations can be further extended into any of the functions inside the environment. You can do this by simply overriding those functions inside your `MyRLEnv` in the prediction model file. Or for more advanced customizations, it is encouraged to create an entirely new environment inherited from `BaseEnvironment`.
All of the FreqAI provided environments inherit from an action/position agnostic environment object called the `BaseEnvironment`, which contains all shared logic. The architecture is designed to be easily customized. The simplest customization is the `calculate_reward()` (see details [here](#creating-a-custom-reward-function)). However, the customizations can be further extended into any of the functions inside the environment. You can do this by simply overriding those functions inside your `MyRLEnv` in the prediction model file. Or for more advanced customizations, it is encouraged to create an entirely new environment inherited from `BaseEnvironment`.
!!! Note
FreqAI does not provide by default, a long-only training environment. However, creating one should be as simple as copy-pasting one of the built in environments and removing the `short` actions (and all associated references to those).
Only the `Base3ActionRLEnv` can do long-only training/trading (set the user strategy attribute `can_short = False`).
*want* to retrain a new model with the same config file, you should simply change the `identifier`.
This way, you can return to using any model you wish by simply specifying the `identifier`.
!!! Note
Backtesting calls `set_freqai_targets()` one time for each backtest window (where the number of windows is the full backtest timerange divided by the `backtest_period_days` parameter). Doing this means that the targets simulate dry/live behavior without look ahead bias. However, the definition of the features in `feature_engineering_*()` is performed once on the entire backtest timerange. This means that you should be sure that features do look-ahead into the future.
More details about look-ahead bias can be found in [Common Mistakes](strategy-customization.md#common-mistakes-when-developing-strategies).
---
### Saving prediction data
@@ -116,7 +120,7 @@ In the presented example config, the user will only allow predictions on models
Model training parameters are unique to the selected machine learning library. FreqAI allows you to set any parameter for any library using the `model_training_parameters` dictionary in the config. The example config (found in `config_examples/config_freqai.example.json`) shows some of the example parameters associated with `Catboost` and `LightGBM`, but you can add any parameters available in those libraries or any other machine learning library you choose to implement.
Data split parameters are defined in `data_split_parameters` which can be any parameters associated with Scikit-learn's `train_test_split()` function. `train_test_split()` has a parameters called `shuffle` which allows to shuffle the data or keep it unshuffled. This is particularly useful to avoid biasing training with temporally auto-correlated data. More details about these parameters can be found the [Scikit-learn website](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website).
Data split parameters are defined in `data_split_parameters` which can be any parameters associated with scikit-learn's `train_test_split()` function. `train_test_split()` has a parameters called `shuffle` which allows to shuffle the data or keep it unshuffled. This is particularly useful to avoid biasing training with temporally auto-correlated data. More details about these parameters can be found the [scikit-learn website](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website).
The FreqAI specific parameter `label_period_candles` defines the offset (number of candles into the future) used for the `labels`. In the presented [example config](freqai-configuration.md#setting-up-the-configuration-file), the user is asking for `labels` that are 24 candles in the future.
@@ -124,6 +128,12 @@ The FreqAI specific parameter `label_period_candles` defines the offset (number
You can choose to adopt a continual learning scheme by setting `"continual_learning": true` in the config. By enabling `continual_learning`, after training an initial model from scratch, subsequent trainings will start from the final model state of the preceding training. This gives the new model a "memory" of the previous state. By default, this is set to `False` which means that all new models are trained from scratch, without input from previous models.
???+ danger "Continual learning enforces a constant parameter space"
Since `continual_learning` means that the model parameter space *cannot* change between trainings, `principal_component_analysis` is automatically disabled when `continual_learning` is enabled. Hint: PCA changes the parameter space and the number of features, learn more about PCA [here](freqai-feature-engineering.md#data-dimensionality-reduction-with-principal-component-analysis).
???+ danger "Experimental functionality"
Beware that this is currently a naive approach to incremental learning, and it has a high probability of overfitting/getting stuck in local minima while the market moves away from your model. We have the mechanics available in FreqAI primarily for experimental purposes and so that it is ready for more mature approaches to continual learning in chaotic systems like the crypto market.
## Hyperopt
You can hyperopt using the same command as for [typical Freqtrade hyperopt](hyperopt.md):
`hyperopt` requires you to have the data pre-downloaded in the same fashion as if you were doing [backtesting](#backtesting). In addition, you must consider some restrictions when trying to hyperopt FreqAI strategies:
- The `--analyze-per-epoch` hyperopt parameter is not compatible with FreqAI.
- It's not possible to hyperopt indicators in the `populate_any_indicators()` function. This means that you cannot optimize model parameters using hyperopt. Apart from this exception, it is possible to optimize all other [spaces](hyperopt.md#running-hyperopt-with-smaller-search-space).
- It's not possible to hyperopt indicators in the `feature_engineering_*()` and `set_freqai_targets()` functions. This means that you cannot optimize model parameters using hyperopt. Apart from this exception, it is possible to optimize all other [spaces](hyperopt.md#running-hyperopt-with-smaller-search-space).
- The backtesting instructions also apply to hyperopt.
The best method for combining hyperopt and FreqAI is to focus on hyperopting entry/exit thresholds/criteria. You need to focus on hyperopting parameters that are not used in your features. For example, you should not try to hyperopt rolling window lengths in the feature creation, or any part of the FreqAI config which changes predictions. In order to efficiently hyperopt the FreqAI strategy, FreqAI stores predictions as dataframes and reuses them. Hence the requirement to hyperopt entry/exit thresholds/criteria only.
@@ -151,7 +161,14 @@ This specific hyperopt would help you understand the appropriate `DI_values` for
## Using Tensorboard
CatBoost models benefit from tracking training metrics via Tensorboard. You can take advantage of the FreqAI integration to track training and evaluation performance across all coins and across all retrainings. Tensorboard is activated via the following command:
!!! note "Availability"
FreqAI includes tensorboard for a variety of models, including XGBoost, all PyTorch models, Reinforcement Learning, and Catboost. If you would like to see Tensorboard integrated into another model type, please open an issue on the [Freqtrade GitHub](https://github.com/freqtrade/freqtrade/issues)
!!! danger "Requirements"
Tensorboard logging requires the FreqAI torch installation/docker image.
The easiest way to use tensorboard is to ensure `freqai.activate_tensorboard` is set to `True` (default setting) in your configuration file, run FreqAI, then open a separate shell and run:
```bash
cd freqtrade
@@ -162,19 +179,6 @@ where `unique-id` is the `identifier` set in the `freqai` configuration file. Th
## Setting up a follower
You can indicate to the bot that it should not train models, but instead should look for models trained by a leader with a specific `identifier` by defining:
```json
"freqai":{
"enabled":true,
"follow_mode":true,
"identifier":"example",
"feature_parameters":{
// leader bots feature_parameters inserted here
},
}
```
In this example, the user has a leader bot with the `"identifier": "example"`. The leader bot is already running or is launched simultaneously with the follower. The follower will load models created by the leader and inference them to obtain predictions instead of training its own models. The user will also need to duplicate the `feature_parameters` parameters from from the leaders freqai configuration file into the freqai section of the followers config.
!!! note "Deactivate for improved performance"
Tensorboard logging can slow down training and should be deactivated for production use.
FreqAI is a software designed to automate a variety of tasks associated with training a predictive machine learning model to generate market forecasts given a set of input signals. In general, the FreqAI aims to be a sand-box for easily deploying robust machine-learning libraries on real-time data ([details])(#freqai-position-in-open-source-machine-learning-landscape).
FreqAI is a software designed to automate a variety of tasks associated with training a predictive machine learning model to generate market forecasts given a set of input signals. In general, FreqAI aims to be a sandbox for easily deploying robust machinelearning libraries on real-time data ([details](#freqai-position-in-open-source-machine-learning-landscape)).
!!! Note
FreqAI is, and always will be, a not-for-profit, open-source project. FreqAI does *not* have a crypto token, FreqAI does *not* sell signals, and FreqAI does not have a domain besides the present [freqtrade documentation](https://www.freqtrade.io/en/latest/freqai/).
Features include:
@@ -19,7 +22,7 @@ Features include:
* **Automatic data download** - Compute timeranges for data downloads and update historic data (in live deployments)
* **Cleaning of incoming data** - Handle NaNs safely before training and model inferencing
* **Dimensionality reduction** - Reduce the size of the training data via [Principal Component Analysis](freqai-feature-engineering.md#data-dimensionality-reduction-with-principal-component-analysis)
* **Deploying bot fleets** - Set one bot to train models while a fleet of [follower bots](freqai-running.md#setting-up-a-follower) inference the models and handle trades
* **Deploying bot fleets** - Set one bot to train models while a fleet of [consumers](producer-consumer.md) use signals.
## Quick start
@@ -29,7 +32,10 @@ The easiest way to quickly test FreqAI is to run it in dry mode with the followi
You will see the boot-up process of automatic data downloading, followed by simultaneous training and trading.
You will see the boot-up process of automatic data downloading, followed by simultaneous training and trading.
!!! danger "Not for production"
The example strategy provided with the Freqtrade source code is designed for showcasing/testing a wide variety of FreqAI features. It is also designed to run on small computers so that it can be used as a benchmark between developers and users. It is *not* designed to be run in production.
An example strategy, prediction model, and config to use as a starting points can be found in
`freqtrade/templates/FreqaiExampleStrategy.py`, `freqtrade/freqai/prediction_models/LightGBMRegressor.py`, and
Catboost will not be installed on arm devices (raspberry, Mac M1, ARM based VPS, ...), since it does not provide wheels for this platform.
Catboost will not be installed on low-powered arm devices (raspberry), since it does not provide wheels for this platform.
### Usage with docker
If you are using docker, a dedicated tag with FreqAI dependencies is available as `:freqai`. As such - you can replace the image line in your docker-compose file with `image: freqtradeorg/freqtrade:develop_freqai`. This image contains the regular FreqAI dependencies. Similar to native installs, Catboost will not be available on ARM based devices.
If you are using docker, a dedicated tag with FreqAI dependencies is available as `:freqai`. As such - you can replace the image line in your dockercompose file with `image: freqtradeorg/freqtrade:develop_freqai`. This image contains the regular FreqAI dependencies. Similar to native installs, Catboost will not be available on ARM based devices. If you would like to use PyTorch or Reinforcement learning, you should use the torch or RL tags, `image: freqtradeorg/freqtrade:develop_freqaitorch`, `image: freqtradeorg/freqtrade:develop_freqairl`.
!!! note "docker-compose-freqai.yml"
We do provide an explicit docker-compose file for this in `docker/docker-compose-freqai.yml` - which can be used via `docker compose -f docker/docker-compose-freqai.yml run ...` - or can be copied to replace the original docker file. This docker-compose file also contains a (disabled) section to enable GPU resources within docker containers. This obviously assumes the system has GPU resources available.
### FreqAI position in open-source machine learning landscape
Forecasting chaotic time-series based systems, such as equity/cryptocurrency markets, requires a broad set of tools geared toward testing a wide range of hypotheses. Fortunately, a recent maturation of robust machine learning libraries (e.g. `scikit-learn`) has opened up a wide range of research possibilities. Scientists from a diverse range of fields can now easily prototype their studies on an abundance of established machine learning algorithms. Similarly, these user-friendly libraries enable "citzen scientists" to use their basic Python skills for data-exploration. However, leveraging these machine learning libraries on historical and live chaotic data sources can be logistically difficult and expensive. Additionally, robust data-collection, storage, and handling presents a disparate challenge. [`FreqAI`](#freqai) aims to provide a generalized and extensible open-sourced framework geared toward live deployments of adaptive modeling for market forecasting. The `FreqAI` framework is effectively a sandbox for the rich world of open-source machine learning libraries. Inside the `FreqAI` sandbox, users find they can combine a wide variety of third-party libraries to test creative hypotheses on a free live 24/7 chaotic data source - cryptocurrency exchange data.
Forecasting chaotic time-series based systems, such as equity/cryptocurrency markets, requires a broad set of tools geared toward testing a wide range of hypotheses. Fortunately, a recent maturation of robust machine learning libraries (e.g. `scikit-learn`) has opened up a wide range of research possibilities. Scientists from a diverse range of fields can now easily prototype their studies on an abundance of established machine learning algorithms. Similarly, these user-friendly libraries enable "citzen scientists" to use their basic Python skills for dataexploration. However, leveraging these machine learning libraries on historical and live chaotic data sources can be logistically difficult and expensive. Additionally, robust datacollection, storage, and handling presents a disparate challenge. [`FreqAI`](#freqai) aims to provide a generalized and extensible open-sourced framework geared toward live deployments of adaptive modeling for market forecasting. The `FreqAI` framework is effectively a sandbox for the rich world of open-source machine learning libraries. Inside the `FreqAI` sandbox, users find they can combine a wide variety of third-party libraries to test creative hypotheses on a free live 24/7 chaotic data source - cryptocurrency exchange data.
### Citing FreqAI
FreqAI is [published in the Journal of Open Source Software](https://joss.theoj.org/papers/10.21105/joss.04864). If you find FreqAI useful in your research, please use the following citation:
```bibtex
@article{Caulk2022,
doi = {10.21105/joss.04864},
url = {https://doi.org/10.21105/joss.04864},
year = {2022}, publisher = {The Open Journal},
volume = {7}, number = {80}, pages = {4864},
author = {Robert A. Caulk and Elin Törnquist and Matthias Voppichler and Andrew R. Lawless and Ryan McMullan and Wagner Costa Santos and Timothy C. Pogue and Johan van der Vlugt and Stefan P. Gehring and Pascal Schmidt},
title = {FreqAI: generalizing adaptive modeling for chaotic time-series market forecasts},
journal = {Journal of Open Source Software} }
```
## Common pitfalls
@@ -84,6 +107,13 @@ This is for performance reasons - FreqAI relies on making quick predictions/retr
it needs to download all the training data at the beginning of a dry/live instance. FreqAI stores and appends
new candles automatically for future retrains. This means that if new pairs arrive later in the dry run due to a volume pairlist, it will not have the data ready. However, FreqAI does work with the `ShufflePairlist` or a `VolumePairlist` which keeps the total pairlist constant (but reorders the pairs according to volume).
## Additional learning materials
Here we compile some external materials that provide deeper looks into various components of FreqAI:
- [Real-time head-to-head: Adaptive modeling of financial market data using XGBoost and CatBoost](https://emergentmethods.medium.com/real-time-head-to-head-adaptive-modeling-of-financial-market-data-using-xgboost-and-catboost-995a115a7495)
- [FreqAI - from price to prediction](https://emergentmethods.medium.com/freqai-from-price-to-prediction-6fadac18b665)
## Credits
FreqAI is developed by a group of individuals who all contribute specific skillsets to the project.
@@ -99,6 +129,8 @@ Code review and software architecture brainstorming:
Software development:
Wagner Costa @wagnercosta
Emre Suzen @aemr3
Timothy Pogue @wizrds
Beta testing and bug reporting:
Stefan Gehring @bloodhunter4rc, @longyu, Andrew Lawless @paranoidandy, Pascal Schmidt @smidelis, Ryan McMullan @smarmau, Juha Nykänen @suikula, Johan van der Vlugt @jooopiert, Richárd Józsa @richardjosza, Timothy Pogue @wizrds
Stefan Gehring @bloodhunter4rc, @longyu, Andrew Lawless @paranoidandy, Pascal Schmidt @smidelis, Ryan McMullan @smarmau, Juha Nykänen @suikula, Johan van der Vlugt @jooopiert, Richárd Józsa @richardjosza
Specify which parameters to hyperopt. Space-separated
list.
--print-all Print all results, not only the best ones.
@@ -180,6 +180,7 @@ Rarely you may also need to create a [nested class](advanced-hyperopt.md#overrid
*`generate_roi_table` - for custom ROI optimization (if you need the ranges for the values in the ROI table that differ from default or the number of entries (steps) in the ROI table which differs from the default 4 steps)
*`stoploss_space` - for custom stoploss optimization (if you need the range for the stoploss parameter in the optimization hyperspace that differs from default)
*`trailing_space` - for custom trailing stop optimization (if you need the ranges for the trailing stop parameters in the optimization hyperspace that differ from default)
*`max_open_trades_space` - for custom max_open_trades optimization (if you need the ranges for the max_open_trades parameter in the optimization hyperspace that differ from default)
!!! Tip "Quickly optimize ROI, stoploss and trailing stoploss"
You can quickly optimize the spaces `roi`, `stoploss` and `trailing` without changing anything in your strategy.
@@ -365,7 +366,7 @@ class MyAwesomeStrategy(IStrategy):
timeframe = '15m'
minimal_roi = {
"0": 0.10
},
}
# Define the parameter spaces
buy_ema_short = IntParameter(3, 50, default=5)
buy_ema_long = IntParameter(15, 200, default=50)
@@ -400,7 +401,7 @@ class MyAwesomeStrategy(IStrategy):
* `roi`: just optimize the minimal profit table for your strategy
* `stoploss`: search for the best stoploss value
* `trailing`: search for the best trailing stop values
* `trades`: search for the best max open trades values
* `protection`: search for the best protection parameters (read the [protections section](#optimizing-protections) on how to properly define these)
* `default`: `all` except `trailing` and `protection`
* space-separated list of any of the above values for example `--spaces roi stoploss`
@@ -916,5 +918,5 @@ Once the optimized strategy has been implemented into your strategy, you should
To achieve same the results (number of trades, their durations, profit, etc.) as during Hyperopt, please use the same configuration and parameters (timerange, timeframe, ...) used for hyperopt `--dmmp`/`--disable-max-market-positions` and `--eps`/`--enable-position-stacking` for Backtesting.
Should results not match, please double-check to make sure you transferred all conditions correctly.
Pay special care to the stoploss (and trailing stoploss) parameters, as these are often set in configuration files, which override changes to the strategy.
You should also carefully review the log of your backtest to ensure that there were no parameters inadvertently set by the configuration (like `stoploss` or `trailing_stop`).
Pay special care to the stoploss, max_open_trades and trailing stoploss parameters, as these are often set in configuration files, which override changes to the strategy.
You should also carefully review the log of your backtest to ensure that there were no parameters inadvertently set by the configuration (like `stoploss`, `max_open_trades` or `trailing_stop`).
@@ -23,6 +23,7 @@ You may also use something like `.*DOWN/BTC` or `.*UP/BTC` to exclude leveraged
* [`StaticPairList`](#static-pair-list) (default, if not configured differently)
* [`VolumePairList`](#volume-pair-list)
* [`ProducerPairList`](#producerpairlist)
* [`RemotePairList`](#remotepairlist)
* [`AgeFilter`](#agefilter)
* [`OffsetFilter`](#offsetfilter)
* [`PerformanceFilter`](#performancefilter)
@@ -173,6 +174,58 @@ You can limit the length of the pairlist with the optional parameter `number_ass
`ProducerPairList` can also be used multiple times in sequence, combining the pairs from multiple producers.
Obviously in complex such configurations, the Producer may not provide data for all pairs, so the strategy must be fit for this.
#### RemotePairList
It allows the user to fetch a pairlist from a remote server or a locally stored json file within the freqtrade directory, enabling dynamic updates and customization of the trading pairlist.
The RemotePairList is defined in the pairlists section of the configuration settings. It uses the following configuration options:
```json
"pairlists": [
{
"method": "RemotePairList",
"mode": "whitelist",
"processing_mode": "filter",
"pairlist_url": "https://example.com/pairlist",
"number_assets": 10,
"refresh_period": 1800,
"keep_pairlist_on_failure": true,
"read_timeout": 60,
"bearer_token": "my-bearer-token"
}
]
```
The optional `mode` option specifies if the pairlist should be used as a `blacklist` or as a `whitelist`. The default value is "whitelist".
The optional `processing_mode` option in the RemotePairList configuration determines how the retrieved pairlist is processed. It can have two values: "filter" or "append".
In "filter" mode, the retrieved pairlist is used as a filter. Only the pairs present in both the original pairlist and the retrieved pairlist are included in the final pairlist. Other pairs are filtered out.
In "append" mode, the retrieved pairlist is added to the original pairlist. All pairs from both lists are included in the final pairlist without any filtering.
The `pairlist_url` option specifies the URL of the remote server where the pairlist is located, or the path to a local file (if file:/// is prepended). This allows the user to use either a remote server or a local file as the source for the pairlist.
The user is responsible for providing a server or local file that returns a JSON object with the following structure:
```json
{
"pairs": ["XRP/USDT", "ETH/USDT", "LTC/USDT"],
"refresh_period": 1800
}
```
The `pairs` property should contain a list of strings with the trading pairs to be used by the bot. The `refresh_period` property is optional and specifies the number of seconds that the pairlist should be cached before being refreshed.
The optional `keep_pairlist_on_failure` specifies whether the previous received pairlist should be used if the remote server is not reachable or returns an error. The default value is true.
The optional `read_timeout` specifies the maximum amount of time (in seconds) to wait for a response from the remote source, The default value is 60.
The optional `bearer_token` will be included in the requests Authorization Header.
!!! Note
In case of a server error the last received pairlist will be kept if `keep_pairlist_on_failure` is set to true, when set to false a empty pairlist is returned.
#### AgeFilter
Removes pairs that have been listed on the exchange for less than `min_days_listed` days (defaults to `10`) or more than `max_days_listed` days (defaults `None` mean infinity).
@@ -149,7 +149,7 @@ The below example assumes a timeframe of 1 hour:
* Locks each pair after selling for an additional 5 candles (`CooldownPeriod`), giving other pairs a chance to get filled.
* Stops trading for 4 hours (`4 * 1h candles`) if the last 2 days (`48 * 1h candles`) had 20 trades, which caused a max-drawdown of more than 20%. (`MaxDrawdown`).
* Stops trading if more than 4 stoploss occur for all pairs within a 1 day (`24 * 1h candles`) limit (`StoplossGuard`).
* Locks all pairs that had 4 Trades within the last 6 hours (`6 * 1h candles`) with a combined profit ratio of below 0.02 (<2%) (`LowProfitPairs`).
* Locks all pairs that had 2 Trades within the last 6 hours (`6 * 1h candles`) with a combined profit ratio of below 0.02 (<2%) (`LowProfitPairs`).
* Locks all pairs for 2 candles that had a profit of below 0.01 (<1%) within the last 24h (`24 * 1h candles`), a minimum of 4 trades.
@@ -51,6 +52,7 @@ Please read the [exchange specific notes](exchanges.md) to learn about eventual,
- [X] [Binance](https://www.binance.com/)
- [X] [Gate.io](https://www.gate.io/ref/6266643)
- [X] [OKX](https://okx.com/)
- [X] [Bybit](https://bybit.com/)
Please make sure to read the [exchange specific notes](exchanges.md), as well as the [trading with leverage](leverage.md) documentation before diving in.
@@ -61,6 +63,10 @@ Exchanges confirmed working by the community:
@@ -67,8 +67,6 @@ You will also have to pick a "margin mode" (explanation below) - with freqtrade
Freqtrade follows the [ccxt naming conventions for futures](https://docs.ccxt.com/en/latest/manual.html?#perpetual-swap-perpetual-future).
A futures pair will therefore have the naming of `base/quote:settle` (e.g. `ETH/USDT:USDT`).
Binance is currently still an exception to this naming scheme, where pairs are named `ETH/USDT` also for futures markets, but will be aligned as soon as CCXT is ready.
### Margin mode
On top of `trading_mode` - you will also have to configure your `margin_mode`.
@@ -92,6 +90,8 @@ One account is used to share collateral between markets (trading pairs). Margin
"margin_mode": "cross"
```
Please read the [exchange specific notes](exchanges.md) for exchanges that support this mode and how they differ.
## Set leverage to use
Different strategies and risk profiles will require different levels of leverage.
Use this csv-filename to store lookahead-analysis-
results
```
!!! Note ""
The above Output was reduced to options `lookahead-analysis` adds on top of regular backtesting commands.
### Summary
Checks a given strategy for look ahead bias via lookahead-analysis
Look ahead bias means that the backtest uses data from future candles thereby not making it viable beyond backtesting
and producing false hopes for the one backtesting.
### Introduction
Many strategies - without the programmer knowing - have fallen prey to look ahead bias.
Any backtest will populate the full dataframe including all time stamps at the beginning.
If the programmer is not careful or oblivious how things work internally
(which sometimes can be really hard to find out) then it will just look into the future making the strategy amazing
but not realistic.
This command is made to try to verify the validity in the form of the aforementioned look ahead bias.
### How does the command work?
It will start with a backtest of all pairs to generate a baseline for indicators and entries/exits.
After the backtest ran, it will look if the `minimum-trade-amount` is met
and if not cancel the lookahead-analysis for this strategy.
After setting the baseline it will then do additional runs for every entry and exit separately.
When a verification-backtest is done, it will compare the indicators as the signal (either entry or exit) and report the bias.
After all signals have been verified or falsified a result-table will be generated for the user to see.
### Caveats
-`lookahead-analysis` can only verify / falsify the trades it calculated and verified.
If the strategy has many different signals / signal types, it's up to you to select appropriate parameters to ensure that all signals have triggered at least once. Not triggered signals will not have been verified.
This could lead to a false-negative (the strategy will then be reported as non-biased).
-`lookahead-analysis` has access to everything that backtesting has too.
Please don't provoke any configs like enabling position stacking.
If you decide to do so, then make doubly sure that you won't ever run out of `max_open_trades` amount and neither leftover money in your wallet.
@@ -42,14 +42,14 @@ Enable subscribing to an instance by adding the `external_message_consumer` sect
| `producers` | **Required.** List of producers <br>**Datatype:** Array.
| `producers.name` | **Required.** Name of this producer. This name must be used in calls to `get_producer_pairs()` and `get_producer_df()` if more than one producer is used.<br>**Datatype:** string
| `producers.host` | **Required.** The hostname or IP address from your producer.<br>**Datatype:** string
| `producers.port` | **Required.** The port matching the above host.<br>**Datatype:**string
| `producers.port` | **Required.** The port matching the above host.<br>*Defaults to `8080`.*<br>**Datatype:**Integer
| `producers.secure` | **Optional.** Use ssl in websockets connection. Default False.<br>**Datatype:** string
| `producers.ws_token` | **Required.**`ws_token` as configured on the producer.<br>**Datatype:** string
| | **Optional settings**
| `wait_timeout` | Timeout until we ping again if no message is received. <br>*Defaults to `300`.*<br>**Datatype:** Integer - in seconds.
| `wait_timeout` | Ping timeout <br>*Defaults to `10`.*<br>**Datatype:** Integer - in seconds.
| `ping_timeout` | Ping timeout <br>*Defaults to `10`.*<br>**Datatype:** Integer - in seconds.
| `sleep_time` | Sleep time before retrying to connect.<br>*Defaults to `10`.*<br>**Datatype:** Integer - in seconds.
| `remove_entry_exit_signals` | Remove signal columns from the dataframe (set them to 0) on dataframe receipt.<br>*Defaults to `10`.*<br>**Datatype:**Integer - in seconds.
| `remove_entry_exit_signals` | Remove signal columns from the dataframe (set them to 0) on dataframe receipt.<br>*Defaults to `false`.*<br>**Datatype:**Boolean.
| `message_size_limit` | Size limit per message<br>*Defaults to `8`.*<br>**Datatype:** Integer - Megabytes.
Instead of (or as well as) calculating indicators in `populate_indicators()` the follower instance listens on the connection to a producer instance's messages (or multiple producer instances in advanced configurations) and requests the producer's most recently analyzed dataframes for each pair in the active whitelist.
@@ -9,9 +9,6 @@ This same command can also be used to update freqUI, should there be a new relea
Once the bot is started in trade / dry-run mode (with `freqtrade trade`) - the UI will be available under the configured port below (usually `http://127.0.0.1:8080`).
!!! info "Alpha release"
FreqUI is still considered an alpha release - if you encounter bugs or inconsistencies please open a [FreqUI issue](https://github.com/freqtrade/frequi/issues/new/choose).
!!! Note "developers"
Developers should not use this method, but instead use the method described in the [freqUI repository](https://github.com/freqtrade/frequi) to get the source-code of freqUI.
| `reload_config` | Reloads the configuration file.
| `trades` | List last trades. Limited to 500 trades per call.
| `trade/<tradeid>` | Get specific trade.
| `delete_trade<trade_id>` | Remove trade from the database. Tries to close open orders. Requires manual handling of this trade on the exchange.
| `trade/<tradeid>` | DELETE - Remove trade from the database. Tries to close open orders. Requires manual handling of this trade on the exchange.
| `trade/<tradeid>/open-order` | DELETE - Cancel open order for this trade.
| `trade/<tradeid>/reload` | GET - Reload a trade from the Exchange. Only works in live, and can potentially help recover a trade that was manually sold on the exchange.
| `show_config` | Shows part of the current configuration with relevant settings to operation.
@@ -23,10 +23,22 @@ These modes can be configured with these values:
'stoploss_on_exchange_limit_ratio': 0.99
```
!!! Note
Stoploss on exchange is only supported for Binance (stop-loss-limit), Huobi (stop-limit), Kraken (stop-loss-market, stop-loss-limit), Gateio (stop-limit), and Kucoin (stop-limit and stop-market) as of now.
<ins>Do not set too low/tight stoploss value if using stop loss on exchange!</ins>
If set to low/tight then you have greater risk of missing fill on the order and stoploss will not work.
Stoploss on exchange is only supported for the following exchanges, and not all exchanges support both stop-limit and stop-market.
The Order-type will be ignored if only one mode is available.
| Exchange | stop-loss type |
|----------|-------------|
| Binance | limit |
| Binance Futures | market, limit |
| Huobi | limit |
| kraken | market, limit |
| Gate | limit |
| Okx | limit |
| Kucoin | stop-limit, stop-market|
!!! Note "Tight stoploss"
<ins>Do not set too low/tight stoploss value when using stop loss on exchange!</ins>
If set to low/tight you will have greater risk of missing fill on the order and stoploss will not work.
### stoploss_on_exchange and stoploss_on_exchange_limit_ratio
@@ -52,6 +64,18 @@ The bot cannot do these every 5 seconds (at each iteration), otherwise it would
So this parameter will tell the bot how often it should update the stoploss order. The default value is 60 (1 minute).
This same logic will reapply a stoploss order on the exchange should you cancel it accidentally.
### stoploss_price_type
!!! Warning "Only applies to futures"
`stoploss_price_type` only applies to futures markets (on exchanges where it's available).
Freqtrade will perform a validation of this setting on startup, failing to start if an invalid setting for your exchange has been selected.
Supported price types are gonna differs between each exchanges. Please check with your exchange on which price types it supports.
Stoploss on exchange on futures markets can trigger on different price types.
The naming for these prices in exchange terminology often varies, but is usually something around "last" (or "contract price" ), "mark" and "index".
Acceptable values for this setting are `"last"`, `"mark"` and `"index"` - which freqtrade will transfer automatically to the corresponding API type, and place the [stoploss on exchange](#stoploss_on_exchange-and-stoploss_on_exchange_limit_ratio) order correspondingly.
### force_exit
`force_exit` is an optional value, which defaults to the same value as `exit` and is used when sending a `/forceexit` command from Telegram or from the Rest API.
@@ -185,11 +209,6 @@ You can also keep a static stoploss until the offset is reached, and then trail
If `trailing_only_offset_is_reached = True` then the trailing stoploss is only activated once the offset is reached. Until then, the stoploss remains at the configured `stoploss`.
This option can be used with or without `trailing_stop_positive`, but uses `trailing_stop_positive_offset` as offset.
This page explains some advanced concepts available for strategies.
If you're just getting started, please be familiar with the methods described in the [Strategy Customization](strategy-customization.md) documentation and with the [Freqtrade basics](bot-basics.md) first.
If you're just getting started, please familiarize yourself with the [Freqtrade basics](bot-basics.md) and methods described in [Strategy Customization](strategy-customization.md) first.
[Freqtrade basics](bot-basics.md) describes in which sequence each method described below is called, which can be helpful to understand which method to use for your custom needs.
The call sequence of the methods described here is covered under [bot execution logic](bot-basics.md#bot-execution-logic). Those docs are also helpful in deciding which method is most suitable for your customisation needs.
!!! Note
All callback methods described below should only be implemented in a strategy if they are actually used.
Callback methods should *only* be implemented if a strategy uses them.
!!! Tip
You can get a strategy template containing all below methods by running `freqtrade new-strategy --strategy MyAwesomeStrategy --template advanced`
Start off with a strategy template containing all available callback methods by running `freqtrade new-strategy --strategy MyAwesomeStrategy --template advanced`
## Storing information
Storing information can be accomplished by creating a new dictionary within the strategy class.
The name of the variable can be chosen at will, but should be prefixed with `cust_` to avoid naming collisions with predefined strategy variables.
The name of the variable can be chosen at will, but should be prefixed with `custom_` to avoid naming collisions with predefined strategy variables.
```python
classAwesomeStrategy(IStrategy):
@@ -80,7 +80,7 @@ class AwesomeStrategy(IStrategy):
## Enter Tag
When your strategy has multiple buy signals, you can name the signal that triggered.
Then you can access you buy signal on `custom_exit`
Then you can access your buy signal on `custom_exit`
# Combine all dataframes, and reassign the original dataframe column
dataframe = pd.concat(frames, axis=1)
```
Freqtrade does however also counter this by running `dataframe.copy()` on the dataframe right after the `populate_indicators()` method - so performance implications of this should be low to non-existant.
# return maximum stoploss value, keeping current stoploss price unchanged
return 1
@@ -659,6 +661,7 @@ Position adjustments will always be applied in the direction of the trade, so a
!!! Warning "Backtesting"
During backtesting this callback is called for each candle in `timeframe` or `timeframe_detail`, so run-time performance will be affected.
This can also cause deviating results between live and backtesting, since backtesting can adjust the trade only once per candle, whereas live could adjust the trade multiple times per candle.
``` python
from freqtrade.persistence import Trade
@@ -747,7 +750,7 @@ class DigDeeperStrategy(IStrategy):
@@ -342,16 +342,12 @@ The above configuration would therefore mean:
The calculation does include fees.
To disable ROI completely, set it to an insanely high number:
To disable ROI completely, set it to an empty dictionary:
```python
minimal_roi = {
"0": 100
}
minimal_roi = {}
```
While technically not completely disabled, this would exit once the trade reaches 10000% Profit.
To use times based on candle duration (timeframe), the following snippet can be handy.
This will allow you to change the timeframe for the strategy, and ROI times will still be set as candles (e.g. after 3 candles ...)
@@ -881,7 +877,7 @@ All columns of the informative dataframe will be available on the returning data
### *stoploss_from_open()*
Stoploss values returned from `custom_stoploss` must specify a percentage relative to `current_rate`, but sometimes you may want to specify a stoploss relative to the open price instead. `stoploss_from_open()` is a helper function to calculate a stoploss value that can be returned from `custom_stoploss` which will be equivalent to the desired percentage above the open price.
Stoploss values returned from `custom_stoploss` must specify a percentage relative to `current_rate`, but sometimes you may want to specify a stoploss relative to the entry point instead. `stoploss_from_open()` is a helper function to calculate a stoploss value that can be returned from `custom_stoploss` which will be equivalent to the desired trade profit above the entry point.
??? Example "Returning a stoploss relative to the open price from the custom stoploss function"
@@ -889,6 +885,8 @@ Stoploss values returned from `custom_stoploss` must specify a percentage relati
If we want a stop price at 7% above the open price we can call `stoploss_from_open(0.07, current_profit, False)` which will return `0.1157024793`. 11.57% below $121 is $107, which is the same as 7% above $100.
This function will consider leverage - so at 10x leverage, the actual stoploss would be 0.7% above $100 (0.7% * 10x = 7%).
``` python
@@ -907,7 +905,7 @@ Stoploss values returned from `custom_stoploss` must specify a percentage relati
# once the profit has risen above 10%, keep the stoploss at 7% above the open price
@@ -954,12 +952,14 @@ In some situations it may be confusing to deal with stops relative to current ra
## Additional data (Wallets)
The strategy provides access to the `Wallets` object. This contains the current balances on the exchange.
The strategy provides access to the `wallets` object. This contains the current balances on the exchange.
!!! Note
Wallets is not available during backtesting / hyperopt.
!!! Note "Backtesting / Hyperopt"
Wallets behaves differently depending on the function it's called.
Within `populate_*()` methods, it'll return the full wallet as configured.
Within [callbacks](strategy-callbacks.md), you'll get the wallet state corresponding to the actual simulated wallet at that point in the simulation process.
Please always check if `Wallets` is available to avoid failures during backtesting.
Please always check if `wallets` is available to avoid failures during backtesting.
``` python
if self.wallets:
@@ -989,38 +989,18 @@ from freqtrade.persistence import Trade
The following example queries for the current pair and trades from today, however other filters can easily be added.
``` python
if self.config['runmode'].value in ('live', 'dry_run'):
The `populate_any_indicators()` method has been split into `feature_engineering_expand_all()`, `feature_engineering_expand_basic()`, `feature_engineering_standard()` and`set_freqai_targets()`.
For each new function, the pair (and timeframe where necessary) will be automatically added to the column.
As such, the definition of features becomes much simpler with the new logic.
For a full explanation of each method, please go to the corresponding [freqAI documentation page](freqai-feature-engineering.md#defining-the-features)
If you have created your own custom `IFreqaiModel` with a custom `train()`/`predict()` function, *and* you still rely on `data_cleaning_train/predict()`, then you will need to migrate to the new pipeline. If your model does *not* rely on `data_cleaning_train/predict()`, then you do not need to worry about this migration. That means that this migration guide is relevant for a very small percentage of power-users. If you stumbled upon this guide by mistake, feel free to inquire in depth about your problem in the Freqtrade discord server.
The conversion involves first removing `data_cleaning_train/predict()` and replacing them with a `define_data_pipeline()` and `define_label_pipeline()` function to your `IFreqaiModel` class:
1. Data normalization and cleaning is now homogenized with the new pipeline definition. This is created in the new `define_data_pipeline()` and `define_label_pipeline()` functions. The `data_cleaning_train()` and `data_cleaning_predict()` functions are no longer used. You can override `define_data_pipeline()` to create your own custom pipeline if you wish.
2. Data normalization and cleaning is now homogenized with the new pipeline definition. This is created in the new `define_data_pipeline()` and `define_label_pipeline()` functions. The `data_cleaning_train()` and `data_cleaning_predict()` functions are no longer used. You can override `define_data_pipeline()` to create your own custom pipeline if you wish.
3. Data denormalization is done with the new pipeline. Replace this with the lines below.
@@ -162,28 +162,38 @@ official commands. You can ask at any moment for help with `/help`.
| Command | Description |
|----------|-------------|
| **System commands**
| `/start` | Starts the trader
| `/stop` | Stops the trader
| `/stopbuy | /stopentry` | Stops the trader from opening new trades. Gracefully closes open trades according to their rules.
| `/reload_config` | Reloads the configuration file
| `/show_config` | Shows part of the current configuration with relevant settings to operation
| `/logs [limit]` | Show last log messages.
| `/help` | Show help message
| `/version` | Show version
| **Status** |
| `/status` | Lists all open trades
| `/status <trade_id>` | Lists one or more specific trade. Separate multiple <trade_id> with a blank space.
| `/status table` | List all open trades in a table format. Pending buy orders are marked with an asterisk (*) Pending sell orders are marked with a double asterisk (**)
| `/trades [limit]` | List all recently closed trades in a table format.
| `/delete <trade_id>` | Delete a specific trade from the Database. Tries to close open orders. Requires manual handling of this trade on the exchange.
| `/count` | Displays number of trades used and available
| `/locks` | Show currently locked pairs.
| `/unlock <pairorlock_id>` | Remove the lock for this pair (or for this lock id).
| `/profit [<n>]` | Display a summary of your profit/loss from close trades and some stats about your performance, over the last n days (all trades by default)
| `/marketdir [long | short | even | none]` | Updates the user managed variable that represents the current market direction. If no direction is provided, the currently set direction will be displayed.
| **Modify Trade states** |
| `/forceexit <trade_id> | /fx <tradeid>` | Instantly exits the given trade (Ignoring `minimum_roi`).
| `/forceexit all | /fx all` | Instantly exits all open trades (Ignoring `minimum_roi`).
| `/fx` | alias for `/forceexit`
| `/forcelong <pair> [rate]` | Instantly buys the given pair. Rate is optional and only applies to limit orders. (`force_entry_enable` must be set to True)
| `/forceshort <pair> [rate]` | Instantly shorts the given pair. Rate is optional and only applies to limit orders. This will only work on non-spot markets. (`force_entry_enable` must be set to True)
| `/delete <trade_id>` | Delete a specific trade from the Database. Tries to close open orders. Requires manual handling of this trade on the exchange.
| `/reload_trade <trade_id>` | Reload a trade from the Exchange. Only works in live, and can potentially help recover a trade that was manually sold on the exchange.
| `/cancel_open_order <trade_id> | /coo <trade_id>` | Cancel an open order for a trade.
| **Metrics** |
| `/profit [<n>]` | Display a summary of your profit/loss from close trades and some stats about your performance, over the last n days (all trades by default)
| `/performance` | Show performance of each finished trade grouped by pair
| `/balance` | Show account balance per currency
| `/balance` | Show bot managed balance per currency
| `/balance full` | Show account balance per currency
| `/daily <n>` | Shows profit or loss per day, over the last n days (n defaults to 7)
| `/weekly <n>` | Shows profit or loss per week, over the last n weeks (n defaults to 8)
| `/monthly <n>` | Shows profit or loss per month, over the last n months (n defaults to 6)
@@ -193,8 +203,6 @@ official commands. You can ask at any moment for help with `/help`.
| `/whitelist [sorted] [baseonly]` | Show the current whitelist. Optionally display in alphabetical order and/or with just the base currency of each pairing.
| `/blacklist [pair]` | Show the current blacklist, or adds a pair to the blacklist.
| `/edge` | Show validated pairs by Edge if it is enabled.
| `/help` | Show help message
| `/version` | Show version
## Telegram commands in action
@@ -236,7 +244,7 @@ Enter Tag is configurable via Strategy.
> **Enter Tag:** Awesome Long Signal
> **Open Rate:** `0.00007489`
> **Current Rate:** `0.00007489`
> **Current Profit:** `12.95%`
> **Unrealized Profit:** `12.95%`
> **Stoploss:** `0.00007389 (-0.02%)`
### /status table
@@ -272,19 +280,26 @@ Return a summary of your profit/loss and performance.
> ∙ `33.095 EUR`
>
> **Total Trade Count:** `138`
> **Bot started:** `2022-07-11 18:40:44`
> **First Trade opened:** `3 days ago`
> **Latest Trade opened:** `2 minutes ago`
> **Avg. Duration:** `2:33:45`
> **Best Performing:** `PAY/BTC: 50.23%`
> **Trading volume:** `0.5 BTC`
> **Profit factor:** `1.04`
> **Win / Loss:** `102 / 36`
> **Winrate:** `73.91%`
> **Expectancy (Ratio):** `4.87 (1.66)`
> **Max Drawdown:** `9.23% (0.01255 BTC)`
The relative profit of `1.2%` is the average profit per trade.
The relative profit of `15.2 Σ%` is be based on the starting capital - so in this case, the starting capital was `0.00485701 * 1.152 = 0.00738 BTC`.
Starting capital is either taken from the `available_capital` setting, or calculated by using current wallet size - profits.
Profit Factor is calculated as gross profits / gross losses - and should serve as an overall metric for the strategy.
Expectancy corresponds to the average return per currency unit at risk, i.e. the winrate and the risk-reward ratio (the average gain of winning trades compared to the average loss of losing trades).
Expectancy Ratio is expected profit or loss of a subsequent trade based on the performance of all past trades.
Max drawdown corresponds to the backtesting metric `Absolute Drawdown (Account)` - calculated as `(Absolute Drawdown) / (DrawdownHigh + startingBalance)`.
Bot started date will refer to the date the bot was first started. For older bots, this will default to the first trade's open date.
If a market direction is provided the command updates the user managed variable that represents the current market direction.
This variable is not set to any valid market direction on bot startup and must be set by the user. The example below is for `/marketdir long`:
```
Successfully updated marketdirection from none to long.
```
If no market direction is provided the command outputs the currently set market directions. The example below is for `/marketdir`:
```
Currently set marketdirection: even
```
You can use the market direction in your strategy via `self.market_direction`.
!!! Warning "Bot restarts"
Please note that the market direction is not persisted, and will be reset after a bot restart/reload.
!!! Danger "Backtesting"
As this value/variable is intended to be changed manually in dry/live trading.
Strategies using `market_direction` will probably not produce reliable, reproducible results (changes to this variable will not be reflected for backtesting). Use at your own risk.
A position freqtrade enters is stored in a `Trade` object - which is persisted to the database.
It's a core concept of freqtrade - and something you'll come across in many sections of the documentation, which will most likely point you to this location.
It will be passed to the strategy in many [strategy callbacks](strategy-callbacks.md). The object passed to the strategy cannot be modified directly. Indirect modifications may occur based on callback results.
## Trade - Available attributes
The following attributes / properties are available for each individual trade - and can be used with `trade.<property>` (e.g. `trade.pair`).
| Attribute | DataType | Description |
|------------|-------------|-------------|
`pair`| string | Pair of this trade
`is_open`| boolean | Is the trade currently open, or has it been concluded
`open_rate`| float | Rate this trade was entered at (Avg. entry rate in case of trade-adjustments)
`close_rate`| float | Close rate - only set when is_open = False
`stake_amount`| float | Amount in Stake (or Quote) currency.
`amount`| float | Amount in Asset / Base currency that is currently owned.
`open_date`| datetime | Timestamp when trade was opened **use `open_date_utc` instead**
`open_date_utc`| datetime | Timestamp when trade was opened - in UTC
`close_date`| datetime | Timestamp when trade was closed **use `close_date_utc` instead**
`close_date_utc`| datetime | Timestamp when trade was closed - in UTC
`close_profit`| float | Relative profit at the time of trade closure. `0.01` == 1%
`close_profit_abs`| float | Absolute profit (in stake currency) at the time of trade closure.
`leverage` | float | Leverage used for this trade - defaults to 1.0 in spot markets.
`enter_tag`| string | Tag provided on entry via the `enter_tag` column in the dataframe
`is_short` | boolean | True for short trades, False otherwise
`orders` | Order[] | List of order objects attached to this trade (includes both filled and cancelled orders)
`date_last_filled_utc` | datetime | Time of the last filled order
`entry_side` | "buy" / "sell" | Order Side the trade was entered
`exit_side` | "buy" / "sell" | Order Side that will result in a trade exit / position reduction.
`trade_direction` | "long" / "short" | Trade direction in text - long or short.
`nr_of_successful_entries` | int | Number of successful (filled) entry orders
`nr_of_successful_exits` | int | Number of successful (filled) exit orders
## Class methods
The following are class methods - which return generic information, and usually result in an explicit query against the database.
They can be used as `Trade.<method>` - e.g. `open_trades = Trade.get_open_trade_count()`
!!! Warning "Backtesting/hyperopt"
Most methods will work in both backtesting / hyperopt and live/dry modes.
During backtesting, it's limited to usage in [strategy callbacks](strategy-callbacks.md). Usage in `populate_*()` methods is not supported and will result in wrong results.
### get_trades_proxy
When your strategy needs some information on existing (open or close) trades - it's best to use `Trade.get_trades_proxy()`.
`get_trades_proxy()` supports the following keyword arguments. All arguments are optional - calling `get_trades_proxy()` without arguments will return a list of all trades in the database.
* `pair` e.g. `pair='ETH/USDT'`
* `is_open` e.g. `is_open=False`
* `open_date` e.g. `open_date=current_date - timedelta(days=2)`
* `close_date` e.g. `close_date=current_date - timedelta(days=5)`
### get_open_trade_count
Get the number of currently open trades
``` python
from freqtrade.persistence import Trade
# ...
open_trades = Trade.get_open_trade_count()
```
### get_total_closed_profit
Retrieve the total profit the bot has generated so far.
Aggregates `close_profit_abs` for all closed trades.
``` python
from freqtrade.persistence import Trade
# ...
profit = Trade.get_total_closed_profit()
```
### total_open_trades_stakes
Retrieve the total stake_amount that's currently in trades.
``` python
from freqtrade.persistence import Trade
# ...
profit = Trade.total_open_trades_stakes()
```
### get_overall_performance
Retrieve the overall performance - similar to the `/performance` telegram command.
``` python
from freqtrade.persistence import Trade
# ...
if self.config['runmode'].value in ('live', 'dry_run'):
performance = Trade.get_overall_performance()
```
Sample return value: ETH/BTC had 5 trades, with a total profit of 1.5% (ratio of 0.015).
``` json
{"pair": "ETH/BTC", "profit": 0.015, "count": 5}
```
## Order Object
An `Order` object represents an order on the exchange (or a simulated order in dry-run mode).
An `Order` object will always be tied to it's corresponding [`Trade`](#trade-object), and only really makes sense in the context of a trade.
### Order - Available attributes
an Order object is typically attached to a trade.
Most properties here can be None as they are dependant on the exchange response.
| Attribute | DataType | Description |
|------------|-------------|-------------|
`trade` | Trade | Trade object this order is attached to
`ft_pair` | string | Pair this order is for
`ft_is_open` | boolean | is the order filled?
`order_type` | string | Order type as defined on the exchange - usually market, limit or stoploss
`status` | string | Status as defined by ccxt. Usually open, closed, expired or canceled
`side` | string | Buy or Sell
`price` | float | Price the order was placed at
`average` | float | Average price the order filled at
`amount` | float | Amount in base currency
`filled` | float | Filled amount (in base currency)
`remaining` | float | Remaining amount
`cost` | float | Cost of the order - usually average * filled (*Exchange dependant on futures, may contain the cost with or without leverage and may be in contracts.*)
`stake_amount` | float | Stake amount used for this order. *Added in 2023.7.*
`order_date` | datetime | Order creation date **use `order_date_utc` instead**
`order_date_utc` | datetime | Order creation date (in UTC)
`order_fill_date` | datetime | Order fill date **use `order_fill_utc` instead**
`order_fill_date_utc` | datetime | Order fill date
@@ -80,12 +80,18 @@ When using the Form-Encoded or JSON-Encoded configuration you can configure any
The result would be a POST request with e.g. `Status: running` body and `Content-Type: text/plain` header.
Optional parameters are available to enable automatic retries for webhook messages. The `webhook.retries` parameter can be set for the maximum number of retries the webhook request should attempt if it is unsuccessful (i.e. HTTP response status is not 200). By default this is set to `0` which is disabled. An additional `webhook.retry_delay` parameter can be set to specify the time in seconds between retry attempts. By default this is set to `0.1` (i.e. 100ms). Note that increasing the number of retries or retry delay may slow down the trader if there are connectivity issues with the webhook. Example configuration for retries:
## Additional configurations
The `webhook.retries` parameter can be set for the maximum number of retries the webhook request should attempt if it is unsuccessful (i.e. HTTP response status is not 200). By default this is set to `0` which is disabled. An additional `webhook.retry_delay` parameter can be set to specify the time in seconds between retry attempts. By default this is set to `0.1` (i.e. 100ms). Note that increasing the number of retries or retry delay may slow down the trader if there are connectivity issues with the webhook.
You can also specify `webhook.timeout` - which defines how long the bot will wait until it assumes the other host as unresponsive (defaults to 10s).
Example configuration for retries:
```json
"webhook":{
"enabled":true,
"url":"https://<YOURHOOKURL>",
"timeout":10,
"retries":3,
"retry_delay":0.2,
"status":{
@@ -109,6 +115,8 @@ Custom messages can be sent to Webhook endpoints via the `self.dp.send_msg()` fu
Different payloads can be configured for different events. Not all fields are necessary, but you should configure at least one of the dicts, otherwise the webhook will never be called.
## Webhook Message types
### Entry
The fields in `webhook.entry` are filled when the bot executes a long/short. Parameters are filled using string.format.
Install ta-lib according to the [ta-lib documentation](https://github.com/mrjbq7/ta-lib#windows).
As compiling from source on windows has heavy dependencies (requires a partial visual studio installation), there is also a repository of unofficial pre-compiled windows Wheels [here](https://www.lfd.uci.edu/~gohlke/pythonlibs/#ta-lib), which need to be downloaded and installed using `pip install TA_Lib-0.4.25-cp38-cp38-win_amd64.whl` (make sure to use the version matching your python version).
As compiling from source on windows has heavy dependencies (requires a partial visual studio installation), Freqtrade provides these dependencies (in the binary wheel format) for the latest 3 Python versions (3.8, 3.9, 3.10 and 3.11) and for 64bit Windows.
These Wheels are also used by CI running on windows, and are therefore tested together with freqtrade.
Freqtrade provides these dependencies for the latest 3 Python versions (3.8, 3.9 and 3.10) and for 64bit Windows.
Other versions must be downloaded from the above link.
``` powershell
@@ -45,8 +45,6 @@ freqtrade
The above installation script assumes you're using powershell on a 64bit windows.
Commands for the legacy CMD windows console may differ.
> Thanks [Owdr](https://github.com/Owdr) for the commands. Source: [Issue #222](https://github.com/freqtrade/freqtrade/issues/222)
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
