In general, the search for best parameters starts with a few random combinations (see [below](#reproducible-results) for more details) and then uses Bayesian search with a ML regressor algorithm (currently ExtraTreesRegressor) to quickly find a combination of parameters in the search hyperspace that minimizes the value of the [loss function](#loss-functions).
To learn how to get data for the pairs and exchange you're interested in, head over to the [Data Downloading](data-download.md) section of the documentation.
Since Hyperopt dependencies are not needed to run the bot itself, are heavy, can not be easily built on some platforms (like Raspberry PI), they are not installed by default. Before you run Hyperopt, you need to install the corresponding dependencies, as described in this section below.
*`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)
Hyperopt will first load your data into memory and will then run `populate_indicators()` once per Pair to generate all indicators.
Hyperopt will then spawn into different processes (number of processors, or `-j <n>`), and run backtesting over and over again, changing the parameters that are part of the `--spaces` defined.
For every new set of parameters, freqtrade will run first `populate_entry_trend()` followed by `populate_sell_trend()`, and then run the regular backtesting process to simulate trades.
After backtesting, the results are passed into the [loss function](#loss-functions), which will evaluate if this result was better or worse than previous results.
Based on the loss function result, hyperopt will determine the next set of parameters to try in the next round of backtesting.
2. Triggers are ones that actually trigger buy in specific moment, like "buy when EMA5 crosses over EMA10" or "buy when close price touches lower Bollinger band".
Technically, there is no difference between Guards and Triggers.
However, this guide will make this distinction to make it clear that signals should not be "sticking".
Sticking signals are signals that are active for multiple candles. This can lead into buying a signal late (right before the signal disappears - which means that the chance of success is a lot lower than right at the beginning).
The above definition says: I have five parameters I want to randomly combine to find the best combination.
`buy_rsi` is an integer parameter, which will be tested between 20 and 40. This space has a size of 20.
`buy_adx` is a decimal parameter, which will be evaluated between 20 and 40 with 1 decimal place (so values are 20.1, 20.2, ...). This space has a size of 200.
Parameters must either be assigned to a variable named `buy_*` or `sell_*` - or contain `space='buy'` | `space='sell'` to be assigned to a space correctly.
If no parameter is available for a space, you'll receive the error that no space was found when running hyperopt.
Based on the results, hyperopt will tell you which parameter combination produced the best results (based on the configured [loss function](#loss-functions)).
*`IntParameter` - defines an integral parameter with upper and lower boundaries of search space.
*`DecimalParameter` - defines a floating point parameter with a limited number of decimals (default 3). Should be preferred instead of `RealParameter` in most cases.
*`RealParameter` - defines a floating point parameter with upper and lower boundaries and no precision limit. Rarely used as it creates a space with a near infinite number of possibilities.
Hyperoptable parameters cannot be used in `populate_indicators` - as hyperopt does not recalculate indicators for each epoch, so the starting value would be used in this case.
Assuming you have a simple strategy in mind - a EMA cross strategy (2 Moving averages crossing) - and you'd like to find the ideal parameters for this strategy.
Using `self.buy_ema_short.range` will return a range object containing all entries between the Parameters low and high value.
In this case (`IntParameter(3, 50, default=5)`), the loop would run for all numbers between 3 and 50 (`[3, 4, 5, ... 49, 50]`).
By using this in a loop, hyperopt will generate 48 new columns (`['buy_ema_3', 'buy_ema_4', ... , 'buy_ema_50']`).
Hyperopt itself will then use the selected value to create the buy and sell signals
While this strategy is most likely too simple to provide consistent profit, it should serve as an example how optimize indicator parameters.
!!! Note
`self.buy_ema_short.range` will act differently between hyperopt and other modes. For hyperopt, the above example may generate 48 new columns, however for all other modes (backtesting, dry/live), it will only generate the column for the selected value. You should therefore avoid using the resulting column with explicit values (values other than `self.buy_ema_short.value`).
`range` property may also be used with `DecimalParameter` and `CategoricalParameter`. `RealParameter` does not provide this property due to infinite search space.
By doing the calculation of all possible indicators in `populate_indicators()`, the calculation of the indicator happens only once for every parameter.
While this may slow down the hyperopt startup speed, the overall performance will increase as the Hyperopt execution itself may pick the same value for multiple epochs (changing other values).
You should however try to use space ranges as small as possible. Every new column will require more memory, and every possibility hyperopt can try will increase the search space.
The protection space is not part of the default space, and is only available with the Parameters Hyperopt interface, not with the legacy hyperopt interface (which required separate hyperopt files).
Freqtrade will also automatically change the "--enable-protections" flag if the protection space is selected.
Each hyperparameter tuning requires a target. This is usually defined as a loss function (sometimes also called objective function), which should decrease for more desirable results, and increase for bad results.
A loss function must be specified via the `--hyperopt-loss <Class-name>` argument (or optionally via the configuration under the `"hyperopt_loss"` key).
*`ProfitDrawDownHyperOptLoss` - Optimizes by max Profit & min Drawdown objective. `DRAWDOWN_MULT` variable within the hyperoptloss file can be adjusted to be stricter or more flexible on drawdown purposes.
The `-e` option will set how many evaluations hyperopt will do. Since hyperopt uses Bayesian search, running too many epochs at once may not produce greater results. Experience has shown that best results are usually not improving much after 500-1000 epochs.
Doing multiple runs (executions) with a few 1000 epochs and different random state will most likely produce different results.
The default Hyperopt Search Space, used when no `--space` command line option is specified, does not include the `trailing` hyperspace. We recommend you to run optimization for the `trailing` hyperspace separately, when the best parameters for other hyperspaces were found, validated and pasted into your custom strategy.
### Automatic parameter application to the strategy
When using Hyperoptable parameters, the result of your hyperopt-run will be written to a json file next to your strategy (so for `MyAwesomeStrategy.py`, the file would be `MyAwesomeStrategy.json`).
This file is also updated when using the `hyperopt-show` sub-command, unless `--disable-param-export` is provided to either of the 2 commands.
Your strategy class can also contain these results explicitly. Simply copy hyperopt results block and paste them at class level, replacing old parameters (if any). New parameters will automatically be loaded next time strategy is executed.
If you are optimizing ROI (i.e. if optimization search-space contains 'all', 'default' or 'roi'), your result will look as follows and include a ROI table:
In order to use this best ROI table found by Hyperopt in backtesting and for live trades/dry-run, copy-paste it as the value of the `minimal_roi` attribute of your custom strategy:
```
# Minimal ROI designed for the strategy.
# This attribute will be overridden if the config file contains "minimal_roi"
If you are optimizing ROI, Freqtrade creates the 'roi' optimization hyperspace for you -- it's the hyperspace of components for the ROI tables. By default, each ROI table generated by the Freqtrade consists of 4 rows (steps). Hyperopt implements adaptive ranges for ROI tables with ranges for values in the ROI steps that depend on the timeframe used. By default the values vary in the following ranges (for some of the most used timeframes, values are rounded to 3 digits after the decimal point):
These ranges should be sufficient in most cases. The minutes in the steps (ROI dict keys) are scaled linearly depending on the timeframe used. The ROI values in the steps (ROI dict values) are scaled logarithmically depending on the timeframe used.
If you have the `generate_roi_table()` and `roi_space()` methods in your custom hyperopt, remove them in order to utilize these adaptive ROI tables and the ROI hyperoptimization space generated by Freqtrade by default.
Override the `roi_space()` method if you need components of the ROI tables to vary in other ranges. Override the `generate_roi_table()` and `roi_space()` methods and implement your own custom approach for generation of the ROI tables during hyperoptimization if you need a different structure of the ROI tables or other amount of rows (steps).
To limit the search space further, Decimals are limited to 3 decimal places (a precision of 0.001). This is usually sufficient, every value more precise than this will usually result in overfitted results. You can however [overriding pre-defined spaces](advanced-hyperopt.md#pverriding-pre-defined-spaces) to change this to your needs.
If you are optimizing stoploss values (i.e. if optimization search-space contains 'all', 'default' or 'stoploss'), your result will look as follows and include stoploss:
In order to use this best stoploss value found by Hyperopt in backtesting and for live trades/dry-run, copy-paste it as the value of the `stoploss` attribute of your custom strategy:
If you are optimizing stoploss values, Freqtrade creates the 'stoploss' optimization hyperspace for you. By default, the stoploss values in that hyperspace vary in the range -0.35...-0.02, which is sufficient in most cases.
If you have the `stoploss_space()` method in your custom hyperopt file, remove it in order to utilize Stoploss hyperoptimization space generated by Freqtrade by default.
Override the `stoploss_space()` method and define the desired range in it if you need stoploss values to vary in other range during hyperoptimization. A sample for this method can be found in the [overriding pre-defined spaces section](advanced-hyperopt.md#overriding-pre-defined-spaces).
To limit the search space further, Decimals are limited to 3 decimal places (a precision of 0.001). This is usually sufficient, every value more precise than this will usually result in overfitted results. You can however [overriding pre-defined spaces](advanced-hyperopt.md#pverriding-pre-defined-spaces) to change this to your needs.
If you are optimizing trailing stop values (i.e. if optimization search-space contains 'all' or 'trailing'), your result will look as follows and include trailing stop parameters:
In order to use these best trailing stop parameters found by Hyperopt in backtesting and for live trades/dry-run, copy-paste them as the values of the corresponding attributes of your custom strategy:
If you are optimizing trailing stop values, Freqtrade creates the 'trailing' optimization hyperspace for you. By default, the `trailing_stop` parameter is always set to True in that hyperspace, the value of the `trailing_only_offset_is_reached` vary between True and False, the values of the `trailing_stop_positive` and `trailing_stop_positive_offset` parameters vary in the ranges 0.02...0.35 and 0.01...0.1 correspondingly, which is sufficient in most cases.
Override the `trailing_space()` method and define the desired range in it if you need values of the trailing stop parameters to vary in other ranges during hyperoptimization. A sample for this method can be found in the [overriding pre-defined spaces section](advanced-hyperopt.md#overriding-pre-defined-spaces).
To limit the search space further, Decimals are limited to 3 decimal places (a precision of 0.001). This is usually sufficient, every value more precise than this will usually result in overfitted results. You can however [overriding pre-defined spaces](advanced-hyperopt.md#overriding-pre-defined-spaces) to change this to your needs.
The search for optimal parameters starts with a few (currently 30) random combinations in the hyperspace of parameters, random Hyperopt epochs. These random epochs are marked with an asterisk character (`*`) in the first column in the Hyperopt output.
The initial state for generation of these random values (random state) is controlled by the value of the `--random-state` command line option. You can set it to some arbitrary value of your choice to obtain reproducible results.
If you have not set this value explicitly in the command line options, Hyperopt seeds the random state with some random value for you. The random state value for each Hyperopt run is shown in the log, so you can copy and paste it into the `--random-state` command line option to repeat the set of the initial random epochs used.
If you have not changed anything in the command line options, configuration, timerange, Strategy and Hyperopt classes, historical data and the Loss Function -- you should obtain same hyper-optimization results with same random state value used.
By default, hyperopt prints colorized results -- epochs with positive profit are printed in the green color. This highlighting helps you find epochs that can be interesting for later analysis. Epochs with zero total profit or with negative profits (losses) are printed in the normal color. If you do not need colorization of results (for instance, when you are redirecting hyperopt output to a file) you can switch colorization off by specifying the `--no-color` option in the command line.
You can use the `--print-all` command line option if you would like to see all results in the hyperopt output, not only the best ones. When `--print-all` is used, current best results are also colorized by default -- they are printed in bold (bright) style. This can also be switched off with the `--no-color` command line option.
!!! Note "Windows and color output"
Windows does not support color-output natively, therefore it is automatically disabled. To have color-output for hyperopt running under windows, please consider using WSL.
As hyperopt consumes a lot of memory (the complete data needs to be in memory once per parallel backtesting process), it's likely that you run into "out of memory" errors.
To combat these, you have multiple options:
* reduce the amount of pairs
* reduce the timerange used (`--timerange <timerange>`)
* reduce the number of parallel processes (`-j <n>`)
After you run Hyperopt for the desired amount of epochs, you can later list all results for analysis, select only best or profitable once, and show the details for any of the epochs previously evaluated. This can be done with the `hyperopt-list` and `hyperopt-show` sub-commands. The usage of these sub-commands is described in the [Utils](utils.md#list-hyperopt-results) chapter.
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.
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`).
