Added more hyperopt documentation

This commit is contained in:
Stephen Dade 2018-03-31 16:49:06 +11:00 committed by Matthias
parent 5816d1c1bd
commit 40368bd1b2
2 changed files with 20 additions and 9 deletions

View File

@ -204,6 +204,8 @@ optional arguments:
number)
--timerange TIMERANGE
specify what timerange of data to use.
--hyperopt PATH specify hyperopt file (default:
freqtrade/optimize/default_hyperopt.py)
-e INT, --epochs INT specify number of epochs (default: 100)
-s {all,buy,roi,stoploss} [{all,buy,roi,stoploss} ...], --spaces {all,buy,roi,stoploss} [{all,buy,roi,stoploss} ...]
Specify which parameters to hyperopt. Space separate

View File

@ -19,15 +19,23 @@ and still take a long time.
## Prepare Hyperopting
We recommend you start by taking a look at `hyperopt.py` file located in [freqtrade/optimize](https://github.com/freqtrade/freqtrade/blob/develop/freqtrade/optimize/hyperopt.py)
## Prepare Hyperopt
Before we start digging in Hyperopt, we recommend you to take a look at
an example hyperopt file located into [user_data/strategies/](https://github.com/gcarq/freqtrade/blob/develop/user_data/hyperopts/test_hyperopt.py)
### 1. Install a Custom Hyperopt File
This is very simple. Put your hyperopt file into the folder
`user_data/hyperopts`.
Let assume you want a hyperopt file `awesome_hyperopt.py`:
1. Copy the file `user_data/hyperopts/test_hyperopt.py` into `user_data/hyperopts/awesome_hyperopt.py`
### 1. Configure your Guards and Triggers
There are two places you need to change in your strategy file to add a
new buy strategy for testing:
- Inside [populate_buy_trend()](https://github.com/freqtrade/freqtrade/blob/develop/user_data/hyperopts/test_hyperopt.py#L230-L251).
- Inside [indicator_space()](https://github.com/freqtrade/freqtrade/blob/develop/user_data/hyperopts/test_hyperopt.py#L207-L223).
### 2. Configure your Guards and Triggers
There are two places you need to change in your hyperopt file to add a
new buy hyperopt for testing:
- Inside [populate_buy_trend()](https://github.com/gcarq/freqtrade/blob/develop/user_data/hyperopts/test_hyperopt.py#L230-L251).
- Inside [indicator_space()](https://github.com/gcarq/freqtrade/blob/develop/user_data/hyperopts/test_hyperopt.py#L207-L223).
There you have two different type of indicators: 1. `guards` and 2.
`triggers`.
@ -130,7 +138,8 @@ We strongly recommend to use `screen` or `tmux` to prevent any connection loss.
python3 ./freqtrade/main.py -s <strategyname> --hyperopt <hyperoptname> -c config.json hyperopt -e 5000
```
Use `<strategyname>` and `<hyperoptname>` as the names of the custom strategy and custom hyperopt used.
Use `<strategyname>` and `<hyperoptname>` as the names of the custom strategy
(only required for generating sells) and the custom hyperopt used.
The `-e` flag will set how many evaluations hyperopt will do. We recommend
running at least several thousand evaluations.