OpenBB/assets/js/52fb1c53.350deb57.js

"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[57618],{3905:(t,e,n)=>{n.d(e,{Zo:()=>d,kt:()=>s});var a=n(67294);function r(t,e,n){return e in t?Object.defineProperty(t,e,{value:n,enumerable:!0,configurable:!0,writable:!0}):t[e]=n,t}function l(t,e){var n=Object.keys(t);if(Object.getOwnPropertySymbols){var a=Object.getOwnPropertySymbols(t);e&&(a=a.filter((function(e){return Object.getOwnPropertyDescriptor(t,e).enumerable}))),n.push.apply(n,a)}return n}function i(t){for(var e=1;e<arguments.length;e++){var n=null!=arguments[e]?arguments[e]:{};e%2?l(Object(n),!0).forEach((function(e){r(t,e,n[e])})):Object.getOwnPropertyDescriptors?Object.defineProperties(t,Object.getOwnPropertyDescriptors(n)):l(Object(n)).forEach((function(e){Object.defineProperty(t,e,Object.getOwnPropertyDescriptor(n,e))}))}return t}function o(t,e){if(null==t)return{};var n,a,r=function(t,e){if(null==t)return{};var n,a,r={},l=Object.keys(t);for(a=0;a<l.length;a++)n=l[a],e.indexOf(n)>=0||(r[n]=t[n]);return r}(t,e);if(Object.getOwnPropertySymbols){var l=Object.getOwnPropertySymbols(t);for(a=0;a<l.length;a++)n=l[a],e.indexOf(n)>=0||Object.prototype.propertyIsEnumerable.call(t,n)&&(r[n]=t[n])}return r}var p=a.createContext({}),u=function(t){var e=a.useContext(p),n=e;return t&&(n="function"==typeof t?t(e):i(i({},e),t)),n},d=function(t){var e=u(t.components);return a.createElement(p.Provider,{value:e},t.children)},m={inlineCode:"code",wrapper:function(t){var e=t.children;return a.createElement(a.Fragment,{},e)}},N=a.forwardRef((function(t,e){var n=t.components,r=t.mdxType,l=t.originalType,p=t.parentName,d=o(t,["components","mdxType","originalType","parentName"]),N=u(n),s=r,k=N["".concat(p,".").concat(s)]||N[s]||m[s]||l;return n?a.createElement(k,i(i({ref:e},d),{},{components:n})):a.createElement(k,i({ref:e},d))}));function s(t,e){var n=arguments,r=e&&e.mdxType;if("string"==typeof t||r){var l=n.length,i=new Array(l);i[0]=N;var o={};for(var p in e)hasOwnProperty.call(e,p)&&(o[p]=e[p]);o.originalType=t,o.mdxType="string"==typeof t?t:r,i[1]=o;for(var u=2;u<l;u++)i[u]=n[u];return a.createElement.apply(null,i)}return a.createElement.apply(null,n)}N.displayName="MDXCreateElement"},33500:(t,e,n)=>{n.r(e),n.d(e,{assets:()=>p,contentTitle:()=>i,default:()=>m,frontMatter:()=>l,metadata:()=>o,toc:()=>u});var a=n(87462),r=(n(67294),n(3905));const l={title:"tft",description:"OpenBB Terminal Function"},i="tft",o={unversionedId:"reference/forecast/tft",id:"reference/forecast/tft",title:"tft",description:"OpenBB Terminal Function",source:"@site/content/terminal/reference/forecast/tft.md",sourceDirName:"reference/forecast",slug:"/reference/forecast/tft",permalink:"/terminal/reference/forecast/tft",draft:!1,editUrl:"https://github.com/OpenBB-finance/OpenBBTerminal/edit/main/website/content/terminal/reference/forecast/tft.md",tags:[],version:"current",frontMatter:{title:"tft",description:"OpenBB Terminal Function"},sidebar:"tutorialSidebar",previous:{title:"tcn",permalink:"/terminal/reference/forecast/tcn"},next:{title:"theta",permalink:"/terminal/reference/forecast/theta"}},p={},u=[{value:"Usage",id:"usage",level:3},{value:"Parameters",id:"parameters",level:2},{value:"Examples",id:"examples",level:2}],d={toc:u};function m(t){let{components:e,...n}=t;return(0,r.kt)("wrapper",(0,a.Z)({},d,n,{components:e,mdxType:"MDXLayout"}),(0,r.kt)("h1",{id:"tft"},"tft"),(0,r.kt)("p",null,"Perform TFT forecast (Temporal Fusion Transformer): ",(0,r.kt)("a",{parentName:"p",href:"https://unit8co.github.io/darts/generated_api/darts.models.forecasting.tft_model.html"},"https://unit8co.github.io/darts/generated_api/darts.models.forecasting.tft_model.html")),(0,r.kt)("h3",{id:"usage"},"Usage"),(0,r.kt)("pre",null,(0,r.kt)("code",{parentName:"pre",className:"language-python",metastring:"wordwrap",wordwrap:!0},"tft [--lstm-layers LSTM_LAYERS] [--num-attention-heads NUM_ATTENTION_HEADS] [--full-attention] [--hidden-continuous-size HIDDEN_CONTINUOUS_SIZE] [--hidden-size HIDDEN_SIZE] [--past-covariates PAST_COVARIATES] [--all-past-covariates] [--naive] [-d {}] [-c TARGET_COLUMN] [-n N_DAYS] [-t TRAIN_SPLIT] [-i INPUT_CHUNK_LENGTH] [-o OUTPUT_CHUNK_LENGTH] [--force-reset FORCE_RESET] [--save-checkpoints SAVE_CHECKPOINTS] [--model-save-name MODEL_SAVE_NAME] [--n-epochs N_EPOCHS] [--dropout DROPOUT] [--batch-size BATCH_SIZE] [--end S_END_DATE] [--start S_START_DATE] [--residuals] [--forecast-only] [--export-pred-raw]\n")),(0,r.kt)("hr",null),(0,r.kt)("h2",{id:"parameters"},"Parameters"),(0,r.kt)("table",null,(0,r.kt)("thead",{parentName:"table"},(0,r.kt)("tr",{parentName:"thead"},(0,r.kt)("th",{parentName:"tr",align:null},"Name"),(0,r.kt)("th",{parentName:"tr",align:null},"Description"),(0,r.kt)("th",{parentName:"tr",align:null},"Default"),(0,r.kt)("th",{parentName:"tr",align:null},"Optional"),(0,r.kt)("th",{parentName:"tr",align:null},"Choices"))),(0,r.kt)("tbody",{parentName:"table"},(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"lstm_layers"),(0,r.kt)("td",{parentName:"tr",align:null},"Number of LSTM layers."),(0,r.kt)("td",{parentName:"tr",align:null},"1"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"num_attention_heads"),(0,r.kt)("td",{parentName:"tr",align:null},"Number of attention heads."),(0,r.kt)("td",{parentName:"tr",align:null},"4"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"full_attention"),(0,r.kt)("td",{parentName:"tr",align:null},"Whether to apply a multi-head attention query."),(0,r.kt)("td",{parentName:"tr",align:null},"False"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"hidden_continuous_size"),(0,r.kt)("td",{parentName:"tr",align:null},"Default hidden size for processing continuous variables."),(0,r.kt)("td",{parentName:"tr",align:null},"8"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"hidden_size"),(0,r.kt)("td",{parentName:"tr",align:null},"Size for feature maps for each hidden RNN layer (h_n)"),(0,r.kt)("td",{parentName:"tr",align:null},"16"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"past_covariates"),(0,r.kt)("td",{parentName:"tr",align:null},"Past covariates(columns/features) in same dataset. Comma separated."),(0,r.kt)("td",{parentName:"tr",align:null},"None"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"all_past_covariates"),(0,r.kt)("td",{parentName:"tr",align:null},"Adds all rows as past covariates except for date and the target column."),(0,r.kt)("td",{parentName:"tr",align:null},"False"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"naive"),(0,r.kt)("td",{parentName:"tr",align:null},"Show the naive baseline for a model."),(0,r.kt)("td",{parentName:"tr",align:null},"False"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"target_dataset"),(0,r.kt)("td",{parentName:"tr",align:null},"The name of the dataset you want to select"),(0,r.kt)("td",{parentName:"tr",align:null},"None"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"target_column"),(0,r.kt)("td",{parentName:"tr",align:null},"The name of the specific column you want to use"),(0,r.kt)("td",{parentName:"tr",align:null},"close"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"n_days"),(0,r.kt)("td",{parentName:"tr",align:null},"prediction days."),(0,r.kt)("td",{parentName:"tr",align:null},"5"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"train_split"),(0,r.kt)("td",{parentName:"tr",align:null},"Start point for rolling training and forecast window. 0.0-1.0"),(0,r.kt)("td",{parentName:"tr",align:null},"0.85"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"input_chunk_length"),(0,r.kt)("td",{parentName:"tr",align:null},"Number of past time steps for forecasting module at prediction time."),(0,r.kt)("td",{parentName:"tr",align:null},"14"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"output_chunk_length"),(0,r.kt)("td",{parentName:"tr",align:null},"The length of the forecast of the model."),(0,r.kt)("td",{parentName:"tr",align:null},"5"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"force_reset"),(0,r.kt)("td",{parentName:"tr",align:null},"If set to True, any previously-existing model with the same name will be reset (all checkpoints will be discarded)."),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"save_checkpoints"),(0,r.kt)("td",{parentName:"tr",align:null},"Whether to automatically save the untrained model and checkpoints."),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"model_save_name"),(0,r.kt)("td",{parentName:"tr",align:null},"Name of the model to save."),(0,r.kt)("td",{parentName:"tr",align:null},"tft_model"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"n_epochs"),(0,r.kt)("td",{parentName:"tr",align:null},"Number of epochs over which to train the model."),(0,r.kt)("td",{parentName:"tr",align:null},"300"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"dropout"),(0,r.kt)("td",{parentName:"tr",align:null},"Fraction of neurons affected by Dropout, from 0 to 1."),(0,r.kt)("td",{parentName:"tr",align:null},"0.1"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"batch_size"),(0,r.kt)("td",{parentName:"tr",align:null},"Number of time series (input and output) used in each training pass"),(0,r.kt)("td",{parentName:"tr",align:null},"32"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"s_end_date"),(0,r.kt)("td",{parentName:"tr",align:null},"The end date (format YYYY-MM-DD) to select for testing"),(0,r.kt)("td",{parentName:"tr",align:null},"None"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"s_start_date"),(0,r.kt)("td",{parentName:"tr",align:null},"The start date (format YYYY-MM-DD) to select for testing"),(0,r.kt)("td",{parentName:"tr",align:null},"None"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"residuals"),(0,r.kt)("td",{parentName:"tr",align:null},"Show the residuals for the model."),(0,r.kt)("td",{parentName:"tr",align:null},"False"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"forecast_only"),(0,r.kt)("td",{parentName:"tr",align:null},"Do not plot the historical data without forecasts."),(0,r.kt)("td",{parentName:"tr",align:null},"False"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")),(0,r.kt)("tr",{parentName:"tbody"},(0,r.kt)("td",{parentName:"tr",align:null},"export_pred_raw"),(0,r.kt)("td",{parentName:"tr",align:null},"Export predictions to a csv file."),(0,r.kt)("td",{parentName:"tr",align:null},"False"),(0,r.kt)("td",{parentName:"tr",align:null},"True"),(0,r.kt)("td",{parentName:"tr",align:null},"None")))),(0,r.kt)("hr",null),(0,r.kt)("h2",{id:"examples"},"Examples"),(0,r.kt)("pre",null,(0,r.kt)("code",{parentName:"pre",className:"language-python"},"2022 Jul 23, 10:36 (\ud83e\udd8b) /forecast/ $ load GME_20220719_123734.csv -a GME\n\n2022 Jul 23, 11:03 (\ud83e\udd8b) /forecast/ $ tft GME\n100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 115/115 [00:0700:00, 15.10it/s]\nTFT model obtains MAPE: 44.60%\n\n\n\n       Actual price: $ 146.64\n\u250f\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2533\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2513\n\u2503 Datetime            \u2503 Prediction \u2503\n\u2521\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2547\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2529\n\u2502 2022-07-19 00:00:00 \u2502 $ 169.69   \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 2022-07-20 00:00:00 \u2502 $ 168.53   \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 2022-07-21 00:00:00 \u2502 $ 167.33   \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 2022-07-22 00:00:00 \u2502 $ 167.23   \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 2022-07-25 00:00:00 \u2502 $ 165.82   \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n")),(0,r.kt)("p",null,(0,r.kt)("img",{parentName:"p",src:"https://user-images.githubusercontent.com/72827203/180615444-47bcdd54-0693-4415-9617-ed3a571b26c6.png",alt:"tft"})),(0,r.kt)("hr",null))}m.isMDXComponent=!0}}]);