目录
头文件
1、继承gluon.HybridBlock类,自定义深度神经网络(隐藏层为【40, 40】的MLP)
2、继承MyTrainNetwork,构建预测类
3、继承GluonEstimator类,实现自定义的训练器
4、预测、评估、可视化
import mxnet as mx
from mxnet import gluon
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import json
from gluonts.dataset.common import ListDataset
class MyTrainNetwork(gluon.HybridBlock):
def __init__(self, prediction_length, **kwargs):
super().__init__(**kwargs)
self.prediction_length = prediction_length
with self.name_scope():
# Set up a 3 layer neural network that directly predicts the target values
self.nn = mx.gluon.nn.HybridSequential()
self.nn.add(mx.gluon.nn.Dense(units=40, activation='relu'))
self.nn.add(mx.gluon.nn.Dense(units=40, activation='relu'))
self.nn.add(mx.gluon.nn.Dense(units=self.prediction_length, activation='softrelu'))
def hybrid_forward(self, F, past_target, future_target):
prediction = self.nn(past_target)
# calculate L1 loss with the future_target to learn the median
return (prediction - future_target).abs().mean(axis=-1)
注释:这里的hybrid_forward和tf2.0的call类似,但是call只需要给出网路出口即可,但是这个需要给出损失
class MyPredNetwork(MyTrainNetwork):
# The prediction network only receives past_target and returns predictions
def hybrid_forward(self, F, past_target):
prediction = self.nn(past_target)
return prediction.expand_dims(axis=1)
from gluonts.model.estimator import GluonEstimator
from gluonts.model.predictor import Predictor, RepresentableBlockPredictor
from gluonts.core.component import validated
from gluonts.support.util import copy_parameters
from gluonts.transform import ExpectedNumInstanceSampler, Transformation, InstanceSplitter
from gluonts.dataset.field_names import FieldName
from mxnet.gluon import HybridBlock
from gluonts.trainer import Trainer
class MyEstimator(GluonEstimator):
@validated()
def __init__(
self,
freq: str,
context_length: int,
prediction_length: int,
trainer: Trainer = Trainer()
) -> None:
super().__init__(trainer=trainer)
self.context_length = context_length
self.prediction_length = prediction_length
self.freq = freq
def create_transformation(self):
# Feature transformation that the model uses for input.
# Here we use a transformation that randomly select training samples from all time series.
return InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
train_sampler=ExpectedNumInstanceSampler(num_instances=1),
past_length=self.context_length,
future_length=self.prediction_length,
)
def create_training_network(self) -> MyTrainNetwork:
return MyTrainNetwork(
prediction_length=self.prediction_length
)
def create_predictor(
self, transformation: Transformation, trained_network: HybridBlock
) -> Predictor:
prediction_network = MyPredNetwork(
prediction_length=self.prediction_length
)
copy_parameters(trained_network, prediction_network)
return RepresentableBlockPredictor(
input_transform=transformation,
prediction_net=prediction_network,
batch_size=self.trainer.batch_size,
freq=self.freq,
prediction_length=self.prediction_length,
ctx=self.trainer.ctx,
)
estimator = MyEstimator(
prediction_length=prediction_length,
context_length=100,
freq=freq,
trainer=Trainer(ctx="cpu",
epochs=20,
learning_rate=1e-3,
num_batches_per_epoch=1
)
)
predictor = estimator.train(train_ds)
from gluonts.evaluation.backtest import make_evaluation_predictions
forecast_it, ts_it = make_evaluation_predictions(
dataset=test_ds,
predictor=predictor,
num_samples=10
)
forcasts = list(forecast_it)
tss = list(ts_it)
plot_prob_forecasts(forcasts[0], tss[0])
实验结果(这里由于没有定义预测置信区间,故而没显示)