Getting started¶

In [1]:

#!pip install deepts_forecasting

#!pip install deepts_forecasting

Import libraries¶

In [2]:

import numpy as np
import pandas as pd
import torch
from deepts_forecasting.utils.data import TimeSeriesDataSet
from torch.utils.data import DataLoader
from deepts_forecasting.models.seq2seq import Seq2SeqNetwork
import pytorch_lightning as pl
from pytorch_lightning.callbacks import EarlyStopping, LearningRateMonitor
from pytorch_lightning.loggers import TensorBoardLogger
from deepts_forecasting.utils.data.encoders import TorchNormalizer
from deepts_forecasting.datasets import AirPassengersDataset

import numpy as np import pandas as pd import torch from deepts_forecasting.utils.data import TimeSeriesDataSet from torch.utils.data import DataLoader from deepts_forecasting.models.seq2seq import Seq2SeqNetwork import pytorch_lightning as pl from pytorch_lightning.callbacks import EarlyStopping, LearningRateMonitor from pytorch_lightning.loggers import TensorBoardLogger from deepts_forecasting.utils.data.encoders import TorchNormalizer from deepts_forecasting.datasets import AirPassengersDataset

Dataset¶

In [3]:

data = AirPassengersDataset().load()
data['year'] = data['Month'].dt.year
data['month'] = data['Month'].dt.month
data['group'] = '0'
data['time_idx'] = np.arange(len(data))
data['Passengers'] = data['Passengers'].astype(float)
data['month'] = data['month'].astype('str')
data.head()

data = AirPassengersDataset().load() data['year'] = data['Month'].dt.year data['month'] = data['Month'].dt.month data['group'] = '0' data['time_idx'] = np.arange(len(data)) data['Passengers'] = data['Passengers'].astype(float) data['month'] = data['month'].astype('str') data.head()

Out[3]:

	Month	Passengers	year	month	group	time_idx
0	1949-01-01	112.0	1949	1	0	0
1	1949-02-01	118.0	1949	2	0	1
2	1949-03-01	132.0	1949	3	0	2
3	1949-04-01	129.0	1949	4	0	3
4	1949-05-01	121.0	1949	5	0	4

Split train/test sets¶

In [ ]:

max_encoder_length = 14
max_prediction_length = 12

training_cutoff = data["time_idx"].max() - max_encoder_length - max_prediction_length

training = TimeSeriesDataSet(
    data[lambda x: x.time_idx <= training_cutoff],
    max_encoder_length= max_encoder_length,
    min_encoder_length=max_encoder_length,
    max_prediction_length=max_prediction_length,
    min_prediction_length=max_prediction_length,
    time_idx="time_idx",
    target="Passengers",
    group_ids=["group"],
    static_categoricals=[],
    static_reals=[],
    time_varying_known_categoricals=['month'],
    time_varying_known_reals=[],
    time_varying_unknown_reals=["Passengers"],
    time_varying_unknown_categoricals=[],
    target_normalizer=TorchNormalizer(method="standard",
                                      transformation=None),
    )

training.get_parameters()
validation = TimeSeriesDataSet.from_dataset(training,
                                            data[lambda x: x.time_idx > training_cutoff])

batch_size = 16
train_dataloader = DataLoader(training, batch_size=batch_size, shuffle=False, drop_last=False)
val_dataloader = DataLoader(validation, batch_size=batch_size, shuffle=False, drop_last=False)

max_encoder_length = 14 max_prediction_length = 12 training_cutoff = data["time_idx"].max() - max_encoder_length - max_prediction_length training = TimeSeriesDataSet( data[lambda x: x.time_idx <= training_cutoff], max_encoder_length= max_encoder_length, min_encoder_length=max_encoder_length, max_prediction_length=max_prediction_length, min_prediction_length=max_prediction_length, time_idx="time_idx", target="Passengers", group_ids=["group"], static_categoricals=[], static_reals=[], time_varying_known_categoricals=['month'], time_varying_known_reals=[], time_varying_unknown_reals=["Passengers"], time_varying_unknown_categoricals=[], target_normalizer=TorchNormalizer(method="standard", transformation=None), ) training.get_parameters() validation = TimeSeriesDataSet.from_dataset(training, data[lambda x: x.time_idx > training_cutoff]) batch_size = 16 train_dataloader = DataLoader(training, batch_size=batch_size, shuffle=False, drop_last=False) val_dataloader = DataLoader(validation, batch_size=batch_size, shuffle=False, drop_last=False)

Define model¶

In [ ]:

pl.seed_everything(1234)
# create PyTorch Lighning Trainer with early stopping
early_stop_callback = EarlyStopping(monitor="val_loss", min_delta=1e-4,
                                    patience=60, verbose=False, mode="min")
lr_logger = LearningRateMonitor()

trainer = pl.Trainer(
    max_epochs=300,
    gpus=0,  # run on CPU, if on multiple GPUs, use accelerator="ddp"
    gradient_clip_val=0.1,
    limit_train_batches=30,  # 30 batches per epoch
    callbacks=[lr_logger, early_stop_callback],
    logger=TensorBoardLogger("lightning_logs")
)

model = Seq2SeqNetwork.from_dataset(training,
                                    hidden_size=50,
                                    rnn_layers=3)
model.summarize

pl.seed_everything(1234) # create PyTorch Lighning Trainer with early stopping early_stop_callback = EarlyStopping(monitor="val_loss", min_delta=1e-4, patience=60, verbose=False, mode="min") lr_logger = LearningRateMonitor() trainer = pl.Trainer( max_epochs=300, gpus=0, # run on CPU, if on multiple GPUs, use accelerator="ddp" gradient_clip_val=0.1, limit_train_batches=30, # 30 batches per epoch callbacks=[lr_logger, early_stop_callback], logger=TensorBoardLogger("lightning_logs") ) model = Seq2SeqNetwork.from_dataset(training, hidden_size=50, rnn_layers=3) model.summarize

In [ ]:

model.hparams

model.hparams

Train model with early stopping¶

In [ ]:

trainer.fit(
    model, train_dataloader=train_dataloader, val_dataloaders=val_dataloader,
)

trainer.fit( model, train_dataloader=train_dataloader, val_dataloaders=val_dataloader, )

In [ ]:

# (given that we use early stopping, this is not necessarily the last epoch)
best_model_path = trainer.checkpoint_callback.best_model_path
best_model = Seq2SeqNetwork.load_from_checkpoint(best_model_path)

# calcualte mean absolute error on validation set
actuals = torch.cat([model.transform_output(prediction=y, target_scale=x['target_scale'])
                     for x, y in iter(val_dataloader)])
predictions, raw_y = best_model.predict(val_dataloader, return_target=True)
mae = (actuals - predictions).abs().mean()
# print('predictions shape is:', predictions.shape)
# print('actuals shape is:', actuals.shape)
print(torch.cat([actuals, predictions]))
print('MAE is:', mae)

# (given that we use early stopping, this is not necessarily the last epoch) best_model_path = trainer.checkpoint_callback.best_model_path best_model = Seq2SeqNetwork.load_from_checkpoint(best_model_path) # calcualte mean absolute error on validation set actuals = torch.cat([model.transform_output(prediction=y, target_scale=x['target_scale']) for x, y in iter(val_dataloader)]) predictions, raw_y = best_model.predict(val_dataloader, return_target=True) mae = (actuals - predictions).abs().mean() # print('predictions shape is:', predictions.shape) # print('actuals shape is:', actuals.shape) print(torch.cat([actuals, predictions])) print('MAE is:', mae)

In [ ]:

# (given that we use early stopping, this is not necessarily the last epoch)
best_model_path = trainer.checkpoint_callback.best_model_path
best_model = Seq2SeqNetwork.load_from_checkpoint(best_model_path)

# calcualte mean absolute error on validation set
actuals = torch.cat([model.transform_output(prediction=y, target_scale=x['target_scale'])
                     for x, y in iter(val_dataloader)])
predictions, raw_y = best_model.predict(val_dataloader, return_target=True)
mae = (actuals - predictions).abs().mean()
# print('predictions shape is:', predictions.shape)
# print('actuals shape is:', actuals.shape)
print(torch.cat([actuals, predictions]))
print('MAE is:', mae)

# (given that we use early stopping, this is not necessarily the last epoch) best_model_path = trainer.checkpoint_callback.best_model_path best_model = Seq2SeqNetwork.load_from_checkpoint(best_model_path) # calcualte mean absolute error on validation set actuals = torch.cat([model.transform_output(prediction=y, target_scale=x['target_scale']) for x, y in iter(val_dataloader)]) predictions, raw_y = best_model.predict(val_dataloader, return_target=True) mae = (actuals - predictions).abs().mean() # print('predictions shape is:', predictions.shape) # print('actuals shape is:', actuals.shape) print(torch.cat([actuals, predictions])) print('MAE is:', mae)

In [ ]:

# (given that we use early stopping, this is not necessarily the last epoch)
best_model_path = trainer.checkpoint_callback.best_model_path
best_model = Seq2SeqNetwork.load_from_checkpoint(best_model_path)

# calcualte mean absolute error on validation set
actuals = torch.cat([model.transform_output(prediction=y, target_scale=x['target_scale'])
                     for x, y in iter(val_dataloader)])
predictions, raw_y = best_model.predict(val_dataloader, return_target=True)
mae = (actuals - predictions).abs().mean()
# print('predictions shape is:', predictions.shape)
# print('actuals shape is:', actuals.shape)
print(torch.cat([actuals, predictions]))
print('MAE is:', mae)

# (given that we use early stopping, this is not necessarily the last epoch) best_model_path = trainer.checkpoint_callback.best_model_path best_model = Seq2SeqNetwork.load_from_checkpoint(best_model_path) # calcualte mean absolute error on validation set actuals = torch.cat([model.transform_output(prediction=y, target_scale=x['target_scale']) for x, y in iter(val_dataloader)]) predictions, raw_y = best_model.predict(val_dataloader, return_target=True) mae = (actuals - predictions).abs().mean() # print('predictions shape is:', predictions.shape) # print('actuals shape is:', actuals.shape) print(torch.cat([actuals, predictions])) print('MAE is:', mae)

In [ ]:

# (given that we use early stopping, this is not necessarily the last epoch)
best_model_path = trainer.checkpoint_callback.best_model_path
best_model = Seq2SeqNetwork.load_from_checkpoint(best_model_path)

# calcualte mean absolute error on validation set
actuals = torch.cat([model.transform_output(prediction=y, target_scale=x['target_scale'])
                     for x, y in iter(val_dataloader)])
predictions, raw_y = best_model.predict(val_dataloader, return_target=True)
mae = (actuals - predictions).abs().mean()
# print('predictions shape is:', predictions.shape)
# print('actuals shape is:', actuals.shape)
print(torch.cat([actuals, predictions]))
print('MAE is:', mae)

# (given that we use early stopping, this is not necessarily the last epoch) best_model_path = trainer.checkpoint_callback.best_model_path best_model = Seq2SeqNetwork.load_from_checkpoint(best_model_path) # calcualte mean absolute error on validation set actuals = torch.cat([model.transform_output(prediction=y, target_scale=x['target_scale']) for x, y in iter(val_dataloader)]) predictions, raw_y = best_model.predict(val_dataloader, return_target=True) mae = (actuals - predictions).abs().mean() # print('predictions shape is:', predictions.shape) # print('actuals shape is:', actuals.shape) print(torch.cat([actuals, predictions])) print('MAE is:', mae)