def from_synthetic_ar_data(
seasonality: float = 10.0,
timesteps: int = 400,
n_series: int = 100,
max_encoder_length: int = 60,
max_prediction_length: int = 20,
batch_size: int = 4,
num_workers: int = 0,
**time_series_dataset_kwargs,
) -> TabularForecastingData:
"""Creates and loads a synthetic Auto-Regressive (AR) data set."""
data = generate_ar_data(seasonality=seasonality,
timesteps=timesteps,
n_series=n_series,
seed=42)
data["date"] = pd.Timestamp("2020-01-01") + pd.to_timedelta(
data.time_idx, "D")
training_cutoff = data["time_idx"].max() - max_prediction_length
return TabularForecastingData.from_data_frame(
time_idx="time_idx",
target="value",
categorical_encoders={"series": NaNLabelEncoder().fit(data.series)},
group_ids=["series"],
# only unknown variable is "value" - and N-Beats can also not take any additional variables
time_varying_unknown_reals=["value"],
max_encoder_length=max_encoder_length,
max_prediction_length=max_prediction_length,
train_data_frame=data[lambda x: x.time_idx <= training_cutoff],
val_data_frame=data,
batch_size=batch_size,
num_workers=num_workers,
**time_series_dataset_kwargs,
)
def dataloaders_fixed_window_without_covariates():
data = generate_ar_data(seasonality=10.0, timesteps=400, n_series=10)
validation = data.series.iloc[:2]
max_encoder_length = 60
max_prediction_length = 20
training = TimeSeriesDataSet(
data[lambda x: ~x.series.isin(validation)],
time_idx="time_idx",
target="value",
categorical_encoders={"series": NaNLabelEncoder().fit(data.series)},
group_ids=["series"],
static_categoricals=[],
max_encoder_length=max_encoder_length,
max_prediction_length=max_prediction_length,
time_varying_unknown_reals=["value"],
target_normalizer=EncoderNormalizer(),
)
validation = TimeSeriesDataSet.from_dataset(
training,
data[lambda x: x.series.isin(validation)],
stop_randomization=True,
)
batch_size = 4
train_dataloader = training.to_dataloader(train=True,
batch_size=batch_size,
num_workers=0)
val_dataloader = validation.to_dataloader(train=False,
batch_size=batch_size,
num_workers=0)
return dict(train=train_dataloader, val=val_dataloader)
def sample_data():
data = generate_ar_data(seasonality=10.0,
timesteps=100,
n_series=2,
seed=42)
data["date"] = pd.Timestamp("2020-01-01") + pd.to_timedelta(
data.time_idx, "D")
max_prediction_length = 20
training_cutoff = data["time_idx"].max() - max_prediction_length
return data, training_cutoff, max_prediction_length
import flash
from flash.core.integrations.pytorch_forecasting import convert_predictions
from flash.core.utilities.imports import example_requires
from flash.tabular.forecasting import TabularForecaster, TabularForecastingData
example_requires(["tabular", "matplotlib"])
import matplotlib.pyplot as plt # noqa: E402
import pandas as pd # noqa: E402
from pytorch_forecasting.data import NaNLabelEncoder # noqa: E402
from pytorch_forecasting.data.examples import generate_ar_data # noqa: E402
# Example based on this tutorial: https://pytorch-forecasting.readthedocs.io/en/latest/tutorials/ar.html
# 1. Create the DataModule
data = generate_ar_data(seasonality=10.0, timesteps=400, n_series=100, seed=42)
data["date"] = pd.Timestamp("2020-01-01") + pd.to_timedelta(data.time_idx, "D")
max_prediction_length = 20
training_cutoff = data["time_idx"].max() - max_prediction_length
datamodule = TabularForecastingData.from_data_frame(
time_idx="time_idx",
target="value",
categorical_encoders={"series": NaNLabelEncoder().fit(data.series)},
group_ids=["series"],
# only unknown variable is "value" - and N-Beats can also not take any additional variables
time_varying_unknown_reals=["value"],
max_encoder_length=60,
max_prediction_length=max_prediction_length,
