credit.replay_buffer

credit.replay_buffer#

Classes#

`TOADataLoader`
`WeightedRMSE`	Base class for all neural network modules.
`ReplayBuffer`
`Trainer`	Helper class that provides a standard way to create an ABC using

Functions#

`cleanup`()
`cycle`(dl)
`accum_log`(log, new_logs)

Module Contents#

credit.replay_buffer.cleanup()#

credit.replay_buffer.cycle(dl)#

credit.replay_buffer.accum_log(log, new_logs)#

class credit.replay_buffer.TOADataLoader(conf)#

TOA#

times_b = None#

__call__(datetime_input)#

class credit.replay_buffer.WeightedRMSE(conf)#

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F


class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

lat_weights = None#

forward(predictions, targets)#

class credit.replay_buffer.ReplayBuffer(conf, buffer_size=32, device='cpu', dtype=np.float32, rank=0)#

buffer_size = 32#

ptr = 0#

size = 0#

dtype#

device = 'cpu'#

rank = 0#

input_shape#

forecast_hour#

index#

q_values#

rmse_scores#

dataset#

numpy_dir#

metric_fn#

add(x, lookup_key)#: Add new experience to the buffer.

sample(batch_size, epsilon=0.2)#: Sample a batch of experiences from the buffer, increment forecast_hour, and update x with new predictions.

update_q_values(indices, y_predict, y_truth)#

update(indices, new_x, new_lookup_key)#: Update existing data in the buffer.

update_with_predictions(model, sample_size, epsilon=0.2)#: Use stored predictions as inputs for future predictions.

concat_and_reshape(x1, x2)#

load_inputs(idx)#

populate()#: Populate the buffer with random data points from the dataset.

save()#: Save the forecast hours, index arrays, pointer, size, Q-values, and RMSE scores to disk.

reload()#: Reload the buffer from saved numpy files.

class credit.replay_buffer.Trainer(model: torch.nn.Module, rank: int, conf: Dict[str, Any])#

Bases: credit.trainers.base_trainer.BaseTrainer

Helper class that provides a standard way to create an ABC using inheritance.

train_one_epoch(epoch, conf, trainloader, optimizer, criterion, scaler, scheduler, metrics)#