ETNA Time Series Library

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 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.


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

pip install --upgrade pip
pip install etna-ts

Get started

Here's some example code for a quick start.

import pandas as pd
from etna.datasets.tsdataset import TSDataset
from etna.models import ProphetModel

# Read the data
df = pd.read_csv("example_dataset.csv")
df["timestamp"] = pd.to_datetime(df["timestamp"])

# Create a TSDataset
df = TSDataset.to_dataset(df)
ts = TSDataset(df,freq='1d')

# Choose a horizon

# Fit the model
model = ProphetModel()

# Make the forecast
future_ts = ts.make_future(HORIZON)
forecast_ts = model.forecast(future_ts)


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

01. Get started

  • Creating TSDataset and time series plotting
  • Forecast single time series - Simple forecast, Prophet, Catboost
  • Forecast multiple time series

02. Backtest

  • What is backtest and how it works
  • How to run a validation
  • Validation visualisation

03. EDA

  • Visualization
  • Plot
  • Partial autocorrelation
  • Cross-correlation
  • Distribution
  • Outliers
  • Median method
  • Density method


ETNA documentation is available here.


GitHub - tinkoff-ai/etna-ts
Contribute to tinkoff-ai/etna-ts development by creating an account on GitHub.