stable/freqtrade/freqai/prediction_models/PyTorchMLPRegressor.py

77 lines
2.7 KiB
Python
Raw Normal View History

2023-03-20 15:06:33 +00:00
from typing import Any, Dict
import torch
2023-03-22 15:50:00 +00:00
from freqtrade.freqai.base_models.BasePyTorchRegressor import BasePyTorchRegressor
2023-03-20 15:06:33 +00:00
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
2023-03-21 14:09:54 +00:00
from freqtrade.freqai.torch.PyTorchMLPModel import PyTorchMLPModel
from freqtrade.freqai.torch.PyTorchModelTrainer import PyTorchModelTrainer
2023-03-20 15:06:33 +00:00
2023-03-22 15:50:00 +00:00
class PyTorchMLPRegressor(BasePyTorchRegressor):
2023-03-20 15:06:33 +00:00
"""
This class implements the fit method of IFreqaiModel.
in the fit method we initialize the model and trainer objects.
the only requirement from the model is to be aligned to PyTorchRegressor
predict method that expects the model to predict tensor of type float.
the trainer defines the training loop.
parameters are passed via `model_training_parameters` under the freqai
section in the config file. e.g:
{
...
"freqai": {
...
"model_training_parameters" : {
"learning_rate": 3e-4,
"trainer_kwargs": {
"max_iters": 5000,
"batch_size": 64,
"max_n_eval_batches": null,
2023-03-20 15:06:33 +00:00
},
"model_kwargs": {
"hidden_dim": 512,
"dropout_percent": 0.2,
"n_layer": 1,
},
}
}
}
"""
2023-03-21 13:19:34 +00:00
def __init__(self, **kwargs) -> None:
2023-03-20 15:06:33 +00:00
super().__init__(**kwargs)
config = self.freqai_info.get("model_training_parameters", {})
2023-03-21 09:23:45 +00:00
self.learning_rate: float = config.get("learning_rate", 3e-4)
self.model_kwargs: Dict[str, Any] = config.get("model_kwargs", {})
self.trainer_kwargs: Dict[str, Any] = config.get("trainer_kwargs", {})
2023-03-20 15:06:33 +00:00
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary constructed by DataHandler to hold
all the training and test data/labels.
2023-03-20 15:06:33 +00:00
"""
n_features = data_dictionary["train_features"].shape[-1]
model = PyTorchMLPModel(
input_dim=n_features,
output_dim=1,
**self.model_kwargs
)
model.to(self.device)
optimizer = torch.optim.AdamW(model.parameters(), lr=self.learning_rate)
criterion = torch.nn.MSELoss()
init_model = self.get_init_model(dk.pair)
trainer = PyTorchModelTrainer(
model=model,
optimizer=optimizer,
criterion=criterion,
device=self.device,
init_model=init_model,
target_tensor_type=torch.float,
**self.trainer_kwargs,
)
2023-03-28 11:40:23 +00:00
trainer.fit(data_dictionary, self.splits)
2023-03-20 15:06:33 +00:00
return trainer