Skip to main content

ETNA is the first python open source framework of T-Bank AI Center. It is designed to make working with time series simple, productive, and fun.

Project description

Logo

Predict your time series the easiest way

PyPI Version Python versions Downloads

Coverage Test passing Docs publish License

Telegram Contributors Stars

Homepage | Documentation | Tutorials | Contribution Guide | Release Notes

ETNA is an easy-to-use time series forecasting framework. It includes built in toolkits for time series preprocessing, feature generation, a variety of predictive models with unified interface - from classic machine learning to SOTA neural networks, models combination methods and smart backtesting. ETNA is designed to make working with time series simple, productive, and fun.

ETNA is the first python open source framework of T-Bank.ru Artificial Intelligence Center. The library started as an internal product in our company - we use it in over 10+ projects now, so we often release updates. Contributions are welcome - check our Contribution Guide.

Quickstart

Let's load and prepare the data.

import pandas as pd
from etna.datasets import TSDataset

# Read the data
df = pd.read_csv("examples/data/example_dataset.csv")

# Create a TSDataset
ts = TSDataset(df, freq="D")

# Choose a horizon
HORIZON = 14

# Make train/test split
train_ts, test_ts = ts.train_test_split(test_size=HORIZON)

Define transformations and model:

from etna.models import CatBoostMultiSegmentModel
from etna.transforms import DateFlagsTransform
from etna.transforms import DensityOutliersTransform
from etna.transforms import FourierTransform
from etna.transforms import LagTransform
from etna.transforms import LinearTrendTransform
from etna.transforms import MeanTransform
from etna.transforms import SegmentEncoderTransform
from etna.transforms import TimeSeriesImputerTransform
from etna.transforms import TrendTransform

# Prepare transforms
transforms = [
    DensityOutliersTransform(in_column="target", distance_coef=3.0),
    TimeSeriesImputerTransform(in_column="target", strategy="forward_fill"),
    LinearTrendTransform(in_column="target"),
    TrendTransform(in_column="target", out_column="trend"),
    LagTransform(in_column="target", lags=list(range(HORIZON, 122)), out_column="target_lag"),
    DateFlagsTransform(week_number_in_month=True, out_column="date_flag"),
    FourierTransform(period=360.25, order=6, out_column="fourier"),
    SegmentEncoderTransform(),
    MeanTransform(in_column=f"target_lag_{HORIZON}", window=12, seasonality=7),
    MeanTransform(in_column=f"target_lag_{HORIZON}", window=7),
]

# Prepare model
model = CatBoostMultiSegmentModel()

Fit Pipeline and make a prediction:

from etna.pipeline import Pipeline

# Create and fit the pipeline
pipeline = Pipeline(model=model, transforms=transforms, horizon=HORIZON)
pipeline.fit(train_ts)

# Make a forecast
forecast_ts = pipeline.forecast()

Let's plot the results:

from etna.analysis import plot_forecast

plot_forecast(forecast_ts=forecast_ts, test_ts=test_ts, train_ts=train_ts, n_train_samples=50)

Print the metric value across the segments:

from etna.metrics import SMAPE

metric = SMAPE()
metric_value = metric(y_true=test_ts, y_pred=forecast_ts)
metric_value
{'segment_a': 4.799114474387907, 'segment_b': 3.271014290441896, 'segment_c': 6.758606238307858, 'segment_d': 4.512871862697337}

Notebook with this example is available here.

Installation

ETNA is available on PyPI, so you can use pip to install it.

Install default version:

pip install --upgrade pip
pip install etna

The default version doesn't contain all the dependencies, because some of them are needed only for specific models, e.g. Prophet, PyTorch. Available user extensions are the following:

  • prophet: adds prophet model`,
  • torch: adds models based on neural nets,
  • wandb: adds wandb logger,
  • auto: adds AutoML functionality,
  • statsforecast: adds models from statsforecast
  • classiciation: adds time series classification functionality.

Install extension:

pip install etna[extension-name]

Install all the extensions:

pip install etna[all]

There are also developer extensions. All the extensions are listed in pyproject.toml.

Without the appropriate extension you will get an ImportError trying to import the model that needs it. For example, etna.models.ProphetModel needs prophet extension and can't be used without it.

Configuration

ETNA supports configuration files. It means that library will check that all the specified packages are installed prior to script start and NOT during runtime.

To set up a configuration for your project you should create a .etna file at the project's root. To see the available options look at Settings. There is an example of configuration file.

Tutorials

We have also prepared a set of tutorials for an easy introduction:

Notebook Interactive launch
Get started Binder
Backtest Binder
EDA Binder
Regressors and exogenous data Binder
Deep learning models Binder
Ensembles Binder
Outliers Binder
AutoML Binder
Clustering Binder
Feature selection Binder
Forecasting strategies Binder
Mechanics of forecasting Binder
Embedding models Binder
Custom model and transform Binder
Inference: using saved pipeline on a new data Binder
Hierarchical time series Binder
Forecast interpretation Binder
Classification Binder
Prediction intervals Binder
Working with misaligned data Binder

Documentation

ETNA documentation is available here.

Community

Questions and feedback are welcome! Our channels for communication:

  • Discussions
    • Suggestions with ideas and drawbacks
    • Q&A, e.g. usage questions
    • General discussions
  • Issue tracker
    • Bug reports
    • Tasks
  • Telegram chat
    • Useful for any other form of communication

Resources

Acknowledgments

ETNA.Team

Current team members: Dmitriy Bunin, Aleksandr Chikov, Vladislav Denisov, Martin Gabdushev, Artem Makhin, Ivan Mitskovets, Albina Munirova, Ivan Nedosekov, Rodion Petrov Maxim Zherelo Yakov Malyshev Egor Baturin Mikhail Bolev,

Former team members: Andrey Alekseev, Nikita Barinov, Julia Shenshina, Sergey Kolesnikov, Yuriy Tarasyuk, Konstantin Vedernikov, Nikolai Romantsov, Sergei Zhuravlev, Alexandr Kuznetsov, Grigory Zlotin, Dmitriy Sablin, Artem Levashov, Aleksey Podkidyshev

ETNA.Contributors

GooseIt, mvakhmenin, looopka, aleksander43smith, smetam, Wapwolf, ArtemLiA, Carlosbogo, GoshaLetov, LeorFinkelberg, Pacman1984,

License

Feel free to use our library in your commercial and private applications.

ETNA is covered by Apache 2.0. Read more about this license here

Please note that etna[prophet] is covered by GPL 2.0 due to pystan package.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

etna-2.9.0.tar.gz (335.7 kB view hashes)

Uploaded Source

Built Distribution

etna-2.9.0-py3-none-any.whl (477.9 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page