jerry/OpenBB
1
0
Fork 0
mirror of https://github.com/OpenBB-finance/OpenBB.git synced 2026-11-01 23:12:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update prediction readme

Browse Source
This commit is contained in:
DidierRLopes
2021-03-22 02:22:43 +00:00
committed by GitHub
parent 9df24e2cfc
commit 79c49f0b1d
1 changed files with 11 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
gamestonk_terminal/prediction_techniques/README.md
View File

@@ -24,6 +24,7 @@ This menu aims to predict the share price of a pre-loaded stock, and the usage o
- MultiLayer Perceptron
* [rnn](#rnn)
- Recurrent Neural Network
- Contains a [looping example](#looping)
* [lstm](#lstm)
- Long-Short Term Memory
- Contains a [backtesting example](#backtesting)
@@ -168,6 +169,7 @@ MulitLayer Perceptron:
* --xla_gpu: if present, will enable XLA for GPU (overrides environment variables during run).
* --force_allow_gpu_growth: if true, will force TensorFlow to allow GPU memory usage to grow as needed. Otherwise will allocate 100% of available GPU memory when CUDA is set up. Default true.
* --batch_size: batch size for model training, should not be used unless advanced user. Default None.
* --loops: number of loops to iterate and train models. Default 1.
Due to the complexity of defining a model through command line, one can define it in: [config_neural_network_models.txt](/config_neural_network_models.py)
```
@@ -204,6 +206,7 @@ Recurrent Neural Network:
* --xla_gpu: if present, will enable XLA for GPU (overrides environment variables during run).
* --force_allow_gpu_growth: if true, will force TensorFlow to allow GPU memory usage to grow as needed. Otherwise will allocate 100% of available GPU memory when CUDA is set up. Default true.
* --batch_size: batch size for model training, should not be used unless advanced user. Default None.
* --loops: number of loops to iterate and train models. Default 1.
Due to the complexity of defining a model through command line, one can define it in: [config_neural_network_models.txt](/config_neural_network_models.py)
```
@@ -222,6 +225,13 @@ Recurrent_Neural_Network \
![rnn](https://user-images.githubusercontent.com/25267873/108604940-d0d12700-73a8-11eb-837e-a5aa128942d9.png)
### Looping Example <a name="looping"></a>
![loops](https://user-images.githubusercontent.com/25267873/111932423-479b3600-8ab5-11eb-9d0b-7210d5f02e83.png)
<img width="1006" alt="Captura de ecrã 2021-03-22, às 02 14 38" src="https://user-images.githubusercontent.com/25267873/111932420-436f1880-8ab5-11eb-831c-ebb88f1c5473.png">
## lstm <a name="lstm"></a>
```
usage: lstm [-d N_DAYS] [-i N_INPUTS] [-j N_JUMPS] [-e N_EPOCHS] [-p {normalization,standardization,none}]
@@ -240,6 +250,7 @@ Long-Short Term Memory:
* --xla_gpu: if present, will enable XLA for GPU (overrides environment variables during run).
* --force_allow_gpu_growth: if true, will force TensorFlow to allow GPU memory usage to grow as needed. Otherwise will allocate 100% of available GPU memory when CUDA is set up. Default true.
* --batch_size: batch size for model training, should not be used unless advanced user. Default None.
* --loops: number of loops to iterate and train models. Default 1.
Due to the complexity of defining a model through command line, one can define it in: [config_neural_network_models.py](/config_neural_network_models.py)
```