Energy Demand Forecasting with DeepVAR

!python --version

Python 3.9.16

%%capture
!pip install torch pytorch-lightning pytorch_forecasting tensorflow

!pip show pytorch_forecasting

Name: pytorch-forecasting
Version: 0.10.3
Summary: Forecasting timeseries with PyTorch - dataloaders, normalizers, metrics and models
Home-page: https://pytorch-forecasting.readthedocs.io
Author: Jan Beitner
Author-email: 
License: 
Location: /usr/local/lib/python3.9/dist-packages
Requires: matplotlib, optuna, pandas, pytorch-lightning, scikit-learn, scipy, statsmodels, torch
Required-by:

import numpy as np
import pandas as pd
import pytorch_lightning as pl
from pytorch_lightning.callbacks import EarlyStopping, LearningRateMonitor
from pytorch_lightning.loggers import TensorBoardLogger
import torch

import matplotlib.pyplot as plt

from pytorch_forecasting import Baseline, TemporalFusionTransformer, TimeSeriesDataSet,DeepAR
from pytorch_forecasting.data import GroupNormalizer
from pytorch_forecasting.metrics import SMAPE, MultivariateNormalDistributionLoss
from pytorch_forecasting.models.temporal_fusion_transformer.tuning import optimize_hyperparameters

import tensorflow as tf 
import tensorboard as tb 
tf.io.gfile = tb.compat.tensorflow_stub.io.gfile