PyTorch2RiverRegressor¶
Compatibility layer from PyTorch to River for regression.
Parameters¶
-
net (torch.nn.modules.container.Sequential)
-
loss_fn (torch.nn.modules.loss._Loss)
-
optimizer (torch.optim.optimizer.Optimizer)
-
batch_size – defaults to
1
Examples¶
>>> from river import compat
>>> from river import datasets
>>> from river import evaluate
>>> from river import metrics
>>> from river import preprocessing
>>> import torch
>>> from torch import nn
>>> from torch import optim
>>> _ = torch.manual_seed(0)
>>> dataset = datasets.TrumpApproval()
>>> n_features = 6
>>> net = nn.Sequential(
... nn.Linear(n_features, 3),
... nn.Linear(3, 1)
... )
>>> model = (
... preprocessing.StandardScaler() |
... compat.PyTorch2RiverRegressor(
... net=net,
... loss_fn=nn.MSELoss(),
... optimizer=optim.SGD(net.parameters(), lr=1e-3),
... batch_size=2
... )
... )
>>> metric = metrics.MAE()
>>> evaluate.progressive_val_score(dataset, model, metric).get()
2.78258
Methods¶
clone
Return a fresh estimator with the same parameters.
The clone has the same parameters but has not been updated with any data. This works by looking at the parameters from the class signature. Each parameter is either - recursively cloned if it's a River classes. - deep-copied via copy.deepcopy
if not. If the calling object is stochastic (i.e. it accepts a seed parameter) and has not been seeded, then the clone will not be idempotent. Indeed, this method's purpose if simply to return a new instance with the same input parameters.
learn_one
Fits to a set of features x
and a real-valued target y
.
Parameters
- x (dict)
- y (numbers.Number)
Returns
Regressor: self
predict_one
Predicts the target value of a set of features x
.
Parameters
- x
Returns
The prediction.