Files
OpenBB/website/content/terminal/reference/forecast/mstl.md
DidierRLopes 4ad995fdd0 Docs/terminalpro and improvement (#5622)
* add first iteration of content for Terminal Pro

* Update index.md

* Update dashboards.md

* Update folders.md

* Update grouping.md

* Update report.md

* Update templates.md

* Update quick-start.md

* Update index.md

* Update index.md

* Update home.md

* Update news.md

* Update index.md

* Update index.md

* Update index.md

* Update data-provider.md

* Update chat-with-widget.md

* Update data-manipulation.md

* Update forecasting.md

* fix: images self closing tags

* fix: only pro visitors can see pro

* inter font

* improve SEO content and restructuring

* add new package for toggle on tutorials

* move folder around

* improve main page of each prod

* small updates and improvements

* fix logo above

* small improvement in headtitle for portfolio funcs

* fix typos from OpenAI's GPT-4

* fix _category_ json

* remove generic SEO words

* add script that generates SEO for documentation

* add missing file

* remove sdk warning message

* fix links for andrew

---------

Co-authored-by: jose-donato <zmcdonato@gmail.com>
Co-authored-by: jose-donato <43375532+jose-donato@users.noreply.github.com>
Co-authored-by: andrewkenreich <andrew.kenreich@gmail.com>
2023-10-30 21:01:29 +00:00

4.0 KiB
Vendored

title, description, keywords
title description keywords
mstl A comprehensive guide for MSTL - Multiple Seasonalities and Trend using Loess forecast analysis in Python. This page includes technical details to understand the parameters for a more accurate prediction, including details on seasonalities and trends. A practical example is provided for clarity.
MSTL forecast
Multiple Seasonalities and Trend
Predictive Modeling
Time Series Forecasting
Loess Forecast
Seasonality
Predictive Analytics Tools

import HeadTitle from '@site/src/components/General/HeadTitle.tsx';

Perform Multiple Seasonalities and Trend using Loess (MSTL) forecast: https://nixtla.github.io/statsforecast/examples/multipleseasonalities.html

Usage

mstl [--naive] [-d {}] [-c TARGET_COLUMN] [-n N_DAYS] [-s {N,A,M}] [-p SEASONAL_PERIODS] [-w START_WINDOW] [--end S_END_DATE] [--start S_START_DATE] [--residuals] [--forecast-only] [--export-pred-raw]

Parameters

Name Description Default Optional Choices
naive Show the naive baseline for a model. False True None
target_dataset The name of the dataset you want to select None True None
target_column The name of the specific column you want to use close True None
n_days prediction days. 5 True None
seasonal Seasonality: N: None, A: Additive, M: Multiplicative. A True N, A, M
seasonal_periods Seasonal periods: 4: Quarterly, 7: Daily 7 True None
start_window Start point for rolling training and forecast window. 0.0-1.0 0.85 True None
s_end_date The end date (format YYYY-MM-DD) to select for testing None True None
s_start_date The start date (format YYYY-MM-DD) to select for testing None True None
residuals Show the residuals for the model. False True None
forecast_only Do not plot the historical data without forecasts. False True None
export_pred_raw Export predictions to a csv file. False True None

Examples

2022 Nov 07, 18:16 (🦋) /forecast/ $ mstl AAPL

Cross Validation Time Series 1: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:0100:00, 103.78it/s]
Forecast: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:0000:00, 19.19it/s]
MSTL obtains MAPE: 3.37%


   Actual price: 138.38
┏━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Datetime   ┃ Prediction ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ 2022-11-07 │ 137.45     │
├────────────┼────────────┤
│ 2022-11-08 │ 142.27     │
├────────────┼────────────┤
│ 2022-11-09 │ 140.00     │
├────────────┼────────────┤
│ 2022-11-10 │ 141.32     │
├────────────┼────────────┤
│ 2022-11-11 │ 141.36     │
└────────────┴────────────┘