automl/Auto-PyTorch

pip install autoPyTorch

pip install autoPyTorch[forecasting]

# Following commands assume the user is in a cloned directory of Auto-Pytorch

# We also need to initialize the automl_common repository as follows
# You can find more information about this here:
# https://github.com/automl/automl_common/
git submodule update --init --recursive

# Create the environment
conda create -n auto-pytorch python=3.8
conda activate auto-pytorch
conda install swig
python setup.py install

git submodule update --init --recursive

conda create -n auto-pytorch python=3.8
conda activate auto-pytorch
conda install swig
pip install -e[forecasting]

from autoPyTorch.api.tabular_classification import TabularClassificationTask

# data and metric imports
import sklearn.model_selection
import sklearn.datasets
import sklearn.metrics
X, y = sklearn.datasets.load_digits(return_X_y=True)
X_train, X_test, y_train, y_test = \
        sklearn.model_selection.train_test_split(X, y, random_state=1)

# initialise Auto-PyTorch api
api = TabularClassificationTask()

# Search for an ensemble of machine learning algorithms
api.search(
    X_train=X_train,
    y_train=y_train,
    X_test=X_test,
    y_test=y_test,
    optimize_metric='accuracy',
    total_walltime_limit=300,
    func_eval_time_limit_secs=50
)

# Calculate test accuracy
y_pred = api.predict(X_test)
score = api.score(y_pred, y_test)
print("Accuracy score", score)

from autoPyTorch.api.time_series_forecasting import TimeSeriesForecastingTask

# data and metric imports
from sktime.datasets import load_longley
targets, features = load_longley()

# define the forecasting horizon
forecasting_horizon = 3

# Dataset optimized by APT-TS can be a list of np.ndarray/ pd.DataFrame where each series represents an element in the 
# list, or a single pd.DataFrame that records the series
# index information: to which series the timestep belongs? This id can be stored as the DataFrame's index or a separate
# column
# Within each series, we take the last forecasting_horizon as test targets. The items before that as training targets
# Normally the value to be forecasted should follow the training sets
y_train = [targets[: -forecasting_horizon]]
y_test = [targets[-forecasting_horizon:]]

# same for features. For uni-variant models, X_train, X_test can be omitted and set as None
X_train = [features[: -forecasting_horizon]]
# Here x_test indicates the 'known future features': they are the features known previously, features that are unknown
# could be replaced with NAN or zeros (which will not be used by our networks). If no feature is known beforehand,
# we could also omit X_test
known_future_features = list(features.columns)
X_test = [features[-forecasting_horizon:]]

start_times = [targets.index.to_timestamp()[0]]
freq = '1Y'

# initialise Auto-PyTorch api
api = TimeSeriesForecastingTask()

# Search for an ensemble of machine learning algorithms
api.search(
    X_train=X_train,
    y_train=y_train,
    X_test=X_test, 
    optimize_metric='mean_MAPE_forecasting',
    n_prediction_steps=forecasting_horizon,
    memory_limit=16 * 1024,  # Currently, forecasting models use much more memories
    freq=freq,
    start_times=start_times,
    func_eval_time_limit_secs=50,
    total_walltime_limit=60,
    min_num_test_instances=1000,  # proxy validation sets. This only works for the tasks with more than 1000 series
    known_future_features=known_future_features,
)

# our dataset could directly generate sequences for new datasets
test_sets = api.dataset.generate_test_seqs()

# Calculate test accuracy
y_pred = api.predict(test_sets)
score = api.score(y_pred, y_test)
print("Forecasting score", score)

$ cd examples/

$ git checkout development

  @article{zimmer-tpami21a,
  author = {Lucas Zimmer and Marius Lindauer and Frank Hutter},
  title = {Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2021},
  note = {also available under https://arxiv.org/abs/2006.13799},
  pages = {3079 - 3090}
}

@incollection{mendoza-automlbook18a,
  author    = {Hector Mendoza and Aaron Klein and Matthias Feurer and Jost Tobias Springenberg and Matthias Urban and Michael Burkart and Max Dippel and Marius Lindauer and Frank Hutter},
  title     = {Towards Automatically-Tuned Deep Neural Networks},
  year      = {2018},
  month     = dec,
  editor    = {Hutter, Frank and Kotthoff, Lars and Vanschoren, Joaquin},
  booktitle = {AutoML: Methods, Sytems, Challenges},
  publisher = {Springer},
  chapter   = {7},
  pages     = {141--156}
}

@article{deng-ecml22,
  author    = {Difan Deng and Florian Karl and Frank Hutter and Bernd Bischl and Marius Lindauer},
  title     = {Efficient Automated Deep Learning for Time Series Forecasting},
  year      = {2022},
  booktitle = {Machine Learning and Knowledge Discovery in Databases. Research Track
               - European Conference, {ECML} {PKDD} 2022},
  url       = {https://doi.org/10.48550/arXiv.2205.05511},
}