Nixtla / nixtla

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 🚀.
https://docs.nixtla.io
Other
1.91k stars 153 forks source link

No plot display #375

Open Matgn34 opened 1 month ago

Matgn34 commented 1 month ago

In the quickstart guide vhen I use the exemple nixtla_client.plot(df, timegpt_fcst_df, time_col='timestamp', target_col='value')

No plot is showing on my screen, is this normal ? How can I resolve this ? Thanks

elephaint commented 1 month ago

Thanks for using TimeGPT! I need a bit more details to be able to help you:

Matgn34 commented 1 month ago

Thanks for your answer. I have a an API key and it runs in a IDE. I simply test your study cases provided in installation. import pandas as pd import os from nixtla import NixtlaClient

Configurez les variables d'environnement pour le proxy

os.environ['HTTP_PROXY'] = '' os.environ['HTTPS_PROXY'] = ''

nixtla_client = NixtlaClient( api_key = '' ) nixtla_client.validate_api_key()

df = pd.read_csv('https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/air_passengers.csv') df.head() nixtla_client.plot(df, time_col='timestamp', target_col='value') timegpt_fcst_df = nixtla_client.forecast(df=df, h=12, freq='MS', time_col='timestamp', target_col='value') timegpt_fcst_df.head() nixtla_client.plot(df, timegpt_fcst_df, time_col='timestamp', target_col='value')