search

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
2.31k stars 187 forks source link

feat: orjson serialization #452

Closed jmoralez closed 2 months ago

jmoralez commented 2 months ago

Uses orjson to serialize the payloads and to deserialize the responses. This is considerably faster because we don't need to convert the arrays to lists and then use json.dumps (which is slower than orjson.dumps by itself), we just provide the arrays directly to orjson. Parsing the responses is also faster.

review-notebook-app[bot] commented 2 months ago

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

github-actions[bot] commented 2 months ago
Experiment Results ## Experiment 1: air-passengers ### Description: | variable | experiment | |:--------------|:-------------| | h | 12 | | season_length | 12 | | freq | MS | | level | None | | n_windows | 1 | ### Results: | metric | timegpt-1 | timegpt-1-long-horizon | SeasonalNaive | Naive | |:-----------|------------:|-------------------------:|----------------:|-----------:| | mae | 12.6793 | 11.0623 | 47.8333 | 76 | | mape | 0.027 | 0.0232 | 0.0999 | 0.1425 | | mse | 213.936 | 199.132 | 2571.33 | 10604.2 | | total_time | 1.7847 | 1.5357 | 0.0063 | 0.0041 | ### Plot: ![](https://github.com/Nixtla/nixtla/blob/docs-figs-model-performance//action_files/models_performance/plots/plot_air-passengers_12_12_MS_None_1.png?raw=true) ## Experiment 2: air-passengers ### Description: | variable | experiment | |:--------------|:-------------| | h | 24 | | season_length | 12 | | freq | MS | | level | None | | n_windows | 1 | ### Results: | metric | timegpt-1 | timegpt-1-long-horizon | SeasonalNaive | Naive | |:-----------|------------:|-------------------------:|----------------:|-----------:| | mae | 58.1031 | 58.4587 | 71.25 | 115.25 | | mape | 0.1257 | 0.1267 | 0.1552 | 0.2358 | | mse | 4040.21 | 4110.79 | 5928.17 | 18859.2 | | total_time | 0.7624 | 0.7101 | 0.0046 | 0.004 | ### Plot: ![](https://github.com/Nixtla/nixtla/blob/docs-figs-model-performance//action_files/models_performance/plots/plot_air-passengers_24_12_MS_None_1.png?raw=true) ## Experiment 3: electricity-multiple-series ### Description: | variable | experiment | |:--------------|:-------------| | h | 24 | | season_length | 24 | | freq | H | | level | None | | n_windows | 1 | ### Results: | metric | timegpt-1 | timegpt-1-long-horizon | SeasonalNaive | Naive | |:-----------|------------:|-------------------------:|----------------:|---------------:| | mae | 178.293 | 268.121 | 269.23 | 1331.02 | | mape | 0.0234 | 0.0311 | 0.0304 | 0.1692 | | mse | 121588 | 219457 | 213677 | 4.68961e+06 | | total_time | 1.1436 | 1.1571 | 0.0053 | 0.0049 | ### Plot: ![](https://github.com/Nixtla/nixtla/blob/docs-figs-model-performance//action_files/models_performance/plots/plot_electricity-multiple-series_24_24_H_None_1.png?raw=true) ## Experiment 4: electricity-multiple-series ### Description: | variable | experiment | |:--------------|:-------------| | h | 168 | | season_length | 24 | | freq | H | | level | None | | n_windows | 1 | ### Results: | metric | timegpt-1 | timegpt-1-long-horizon | SeasonalNaive | Naive | |:-----------|------------:|-------------------------:|----------------:|---------------:| | mae | 465.532 | 346.984 | 398.956 | 1119.26 | | mape | 0.062 | 0.0437 | 0.0512 | 0.1583 | | mse | 835120 | 403787 | 656723 | 3.17316e+06 | | total_time | 0.6708 | 0.9292 | 0.0057 | 0.0051 | ### Plot: ![](https://github.com/Nixtla/nixtla/blob/docs-figs-model-performance//action_files/models_performance/plots/plot_electricity-multiple-series_168_24_H_None_1.png?raw=true) ## Experiment 5: electricity-multiple-series ### Description: | variable | experiment | |:--------------|:-------------| | h | 336 | | season_length | 24 | | freq | H | | level | None | | n_windows | 1 | ### Results: | metric | timegpt-1 | timegpt-1-long-horizon | SeasonalNaive | Naive | |:-----------|--------------:|-------------------------:|----------------:|---------------:| | mae | 558.649 | 459.769 | 602.926 | 1340.95 | | mape | 0.0697 | 0.0566 | 0.0787 | 0.17 | | mse | 1.22721e+06 | 739135 | 1.61572e+06 | 6.04619e+06 | | total_time | 0.7409 | 0.7115 | 0.0057 | 0.005 | ### Plot: ![](https://github.com/Nixtla/nixtla/blob/docs-figs-model-performance//action_files/models_performance/plots/plot_electricity-multiple-series_336_24_H_None_1.png?raw=true)