• Stars
    star
    2,208
  • Rank 20,899 (Top 0.5 %)
  • Language
    Jupyter Notebook
  • License
    Other
  • Created about 3 years ago
  • Updated about 2 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

Nixtla   Tweet  Slack

NixtlaTS

Forecast using TimeGPT

CI Python PyPi License docs Downloads

NixtlaTS offers a collection of classes and methods to interact with the API of TimeGPT.

Certainly, adding a bit of personality and visual appeal can make your README stand out. Here's a reworked version:


🕰️ TimeGPT: Revolutionizing Time-Series Analysis

Developed by Nixtla, TimeGPT is a cutting-edge generative pre-trained transformer model dedicated to prediction tasks. 🚀 By leveraging the most extensive dataset ever – financial, weather, energy, and sales data – TimeGPT brings unparalleled time-series analysis right to your terminal! 👩‍💻👨‍💻

In seconds, TimeGPT can discern complex patterns and predict future data points, transforming the landscape of data science and predictive analytics.

⚙️ Fine-Tuning: For Precision Prediction

In addition to its core capabilities, TimeGPT supports fine-tuning, enhancing its specialization for specific prediction tasks. 🎯 This feature is like training a machine learning model on a targeted data subset to improve its task-specific performance, making TimeGPT an even more versatile tool for your predictive needs.

🔄 NixtlaTS: Your Gateway to TimeGPT

With NixtlaTS, you can easily interact with TimeGPT through simple API calls, making the power of TimeGPT readily accessible in your projects.

💻 Installation

Get NixtlaTS up and running with a simple pip command:

pip install nixtlats>=0.1.0

🎈 Quick Start

Get started with TimeGPT now:

from nixtlats import TimeGPT
timegpt = TimeGPT(token=os.environ['TIMEGPT_TOKEN'])
fcst_df = timegpt.forecast(df, h=24, freq='H', level=[80, 90])

More Repositories

1

statsforecast

Lightning ⚡️ fast forecasting with statistical and econometric models.
Python
3,846
star
2

neuralforecast

Scalable and user friendly neural 🧠 forecasting algorithms.
Python
3,001
star
3

hierarchicalforecast

Probabilistic Hierarchical forecasting 👑 with statistical and econometric methods.
Python
568
star
4

mlforecast

Scalable machine 🤖 learning for time series forecasting.
Python
501
star
5

tsfeatures

Calculates various features from time series data. Python implementation of the R package tsfeatures.
Python
362
star
6

Nixtla

Automated time series processing and forecasting.
Python
253
star
7

transfer-learning-time-series

Transfer 🤗 Learning for Time Series Forecasting
Jupyter Notebook
123
star
8

datasetsforecast

Datasets for time series forecasting
Jupyter Notebook
38
star
9

fpp3-python

Forecasting: principles and practice in python
Jupyter Notebook
13
star
10

timegpt-forecaster-streamlit

TimeGPT forecaster example using streamlit
Python
12
star
11

vantage

Use TimeGPT to predict cloud costs and detect anomalies.
Python
11
star
12

public-slides

Nixtla Public Slides
Python
6
star
13

nixtlats

6
star
14

popol-vuh

Popol Vuh: Nixtla's operating system
Python
6
star
15

utilsforecast

Python
4
star
16

nixtlar

R SDK for TimeGPT
R
3
star
17

m4-forecasts

ZIP version of M4 forecasts uploaded to https://github.com/Mcompetitions/M4-methods/tree/master/Point%20Forecasts.
2
star
18

m5-forecasts

ZIP version of dataset and forecasts uploaded to https://drive.google.com/drive/folders/1D6EWdVSaOtrP1LEFh1REjI3vej6iUS_4.
2
star
19

nixtla-commons

Nixtla shared assets
CSS
2
star
20

blog

Jupyter Notebook
1
star
21

docs

MDX
1
star
22

how-to-contribute-nixtlaverse

Instruction to contribute to the Nixtla libraries
1
star