to_dataloader ( train = True, batch_size = batch_size, num_workers = 0 ) val_dataloader = validation. from_dataset ( training, data, predict = True, stop_randomization = True ) # create dataloaders for model batch_size = 128 # set this between 32 to 128 train_dataloader = training.
UNINSTALL FORECAST BAR SERIES
map (, # group of categorical variables can be treated as one variable time_varying_known_reals =, time_varying_unknown_categoricals =, time_varying_unknown_reals =, target_normalizer = GroupNormalizer ( groups =, transformation = "softplus" ), # use softplus and normalize by group add_relative_time_idx = True, add_target_scales = True, add_encoder_length = True, ) # create validation set (predict=True) which means to predict the last max_prediction_length points in time # for each series validation = TimeSeriesDataSet. transform ( "mean" ) # we want to encode special days as one variable and thus need to first reverse one-hot encoding special_days = data = data. astype ( "category" ) # categories have be strings data = np. min () # add additional features data = data. Further, it is beneficial to add date features, which in this case means extracting the month from the date record.įrom pytorch_ import get_stallion_data data = get_stallion_data () # add time index data = data. Most importantly, we need to add a time index that is incremented by one for each time step. The dataset is already in the correct format but misses some important features. In addition to historic sales we have information about the sales price, the location of the agency, special days such as holidays, and volume sold in the entire industry. There are about 21 000 monthly historic sales records. Our task is to make a six-month forecast of the sold volume by stock keeping units (SKU), that is products, sold by an agency, that is a store. For this tutorial, we will use the Stallion dataset from Kaggle describing sales of various beverages. Fortunately, most datasets are already in this format. Import copy from pathlib import Path import warnings 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 from pytorch_forecasting import Baseline, TemporalFusionTransformer, TimeSeriesDataSet from pytorch_forecasting.data import GroupNormalizer from pytorch_trics import SMAPE, PoissonLoss, QuantileLoss from pytorch_fusion_transformer.tuning import optimize_hyperparameters Load data #įirst, we need to transform our time series into a pandas dataframe where each row can be identified with a time step and a time series.
0 kommentar(er)
