177 |
178 |
181 | Back to top
182 |
183 |
197 |
198 |
199 |
207 |
208 |
209 |
210 |
211 |
212 |
234 |
176 |
235 |
240 | \n", 47 | "Our toolbox supports these types of analyses in the modules [Prediction](https://glhmm.readthedocs.io/en/latest/prediction.html) and [Statistics](https://glhmm.readthedocs.io/en/latest/statistics.html)\n", 48 | "\n", 49 | "### Prediction\n", 50 | "This module enables the utilization of individual brain activity patterns for various applications, including predictions (such as cognitive abilities) and classifications (of subjects or clinical groups, for example). For a tutorial, see [Prediction tutorial](./Prediction_tutorial.ipynb).\n", 51 | "\n", 52 | "### Statistics\n", 53 | "This module provides powerful permutation testing analysis, which allows for statistical significance assessment without data distribution assumptions. It supports various test types, such as between- and within-session/subject tests. Users can choose between permutation testing with regression or correlation for a wide range of research questions. For a tutorial demonstrating the application of testing look at the following examples: \n", 54 | "- [Testing across subjects](./Testing_across_subjects.ipynb)\n", 55 | "- [Testing across sessions](./Testing_across_sessions_within_subject.ipynb)\n", 56 | "- [Testing across trials](./Testing_across_trials_within_session.ipynb)\n", 57 | "- [Testing across visits](./Testing_across_visits.ipynb)\n" 58 | ] 59 | } 60 | ], 61 | "metadata": { 62 | "kernelspec": { 63 | "display_name": "Python 3 (ipykernel)", 64 | "language": "python", 65 | "name": "python3" 66 | }, 67 | "language_info": { 68 | "codemirror_mode": { 69 | "name": "ipython", 70 | "version": 3 71 | }, 72 | "file_extension": ".py", 73 | "mimetype": "text/x-python", 74 | "name": "python", 75 | "nbconvert_exporter": "python", 76 | "pygments_lexer": "ipython3", 77 | "version": "3.11.4" 78 | } 79 | }, 80 | "nbformat": 4, 81 | "nbformat_minor": 2 82 | } 83 | -------------------------------------------------------------------------------- /docs/_build/html/_static/scripts/furo.js: -------------------------------------------------------------------------------- 1 | /*! For license information please see furo.js.LICENSE.txt */ 2 | (()=>{var t={212:function(t,e,n){var o,r;r=void 0!==n.g?n.g:"undefined"!=typeof window?window:this,o=function(){return function(t){"use strict";var e={navClass:"active",contentClass:"active",nested:!1,nestedClass:"active",offset:0,reflow:!1,events:!0},n=function(t,e,n){if(n.settings.events){var o=new CustomEvent(t,{bubbles:!0,cancelable:!0,detail:n});e.dispatchEvent(o)}},o=function(t){var e=0;if(t.offsetParent)for(;t;)e+=t.offsetTop,t=t.offsetParent;return e>=0?e:0},r=function(t){t&&t.sort((function(t,e){return o(t.content)
' + 106 | '' + 107 | _("Hide Search Matches") + 108 | "
" 109 | ) 110 | ); 111 | }, 112 | 113 | /** 114 | * helper function to hide the search marks again 115 | */ 116 | hideSearchWords: () => { 117 | document 118 | .querySelectorAll("#searchbox .highlight-link") 119 | .forEach((el) => el.remove()); 120 | document 121 | .querySelectorAll("span.highlighted") 122 | .forEach((el) => el.classList.remove("highlighted")); 123 | localStorage.removeItem("sphinx_highlight_terms") 124 | }, 125 | 126 | initEscapeListener: () => { 127 | // only install a listener if it is really needed 128 | if (!DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS) return; 129 | 130 | document.addEventListener("keydown", (event) => { 131 | // bail for input elements 132 | if (BLACKLISTED_KEY_CONTROL_ELEMENTS.has(document.activeElement.tagName)) return; 133 | // bail with special keys 134 | if (event.shiftKey || event.altKey || event.ctrlKey || event.metaKey) return; 135 | if (DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS && (event.key === "Escape")) { 136 | SphinxHighlight.hideSearchWords(); 137 | event.preventDefault(); 138 | } 139 | }); 140 | }, 141 | }; 142 | 143 | _ready(SphinxHighlight.highlightSearchWords); 144 | _ready(SphinxHighlight.initEscapeListener); 145 | -------------------------------------------------------------------------------- /docs/_build/html/_static/language_data.js: -------------------------------------------------------------------------------- 1 | /* 2 | * language_data.js 3 | * ~~~~~~~~~~~~~~~~ 4 | * 5 | * This script contains the language-specific data used by searchtools.js, 6 | * namely the list of stopwords, stemmer, scorer and splitter. 7 | * 8 | * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS. 9 | * :license: BSD, see LICENSE for details. 10 | * 11 | */ 12 | 13 | var stopwords = ["a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "near", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"]; 14 | 15 | 16 | /* Non-minified version is copied as a separate JS file, is available */ 17 | 18 | /** 19 | * Porter Stemmer 20 | */ 21 | var Stemmer = function() { 22 | 23 | var step2list = { 24 | ational: 'ate', 25 | tional: 'tion', 26 | enci: 'ence', 27 | anci: 'ance', 28 | izer: 'ize', 29 | bli: 'ble', 30 | alli: 'al', 31 | entli: 'ent', 32 | eli: 'e', 33 | ousli: 'ous', 34 | ization: 'ize', 35 | ation: 'ate', 36 | ator: 'ate', 37 | alism: 'al', 38 | iveness: 'ive', 39 | fulness: 'ful', 40 | ousness: 'ous', 41 | aliti: 'al', 42 | iviti: 'ive', 43 | biliti: 'ble', 44 | logi: 'log' 45 | }; 46 | 47 | var step3list = { 48 | icate: 'ic', 49 | ative: '', 50 | alize: 'al', 51 | iciti: 'ic', 52 | ical: 'ic', 53 | ful: '', 54 | ness: '' 55 | }; 56 | 57 | var c = "[^aeiou]"; // consonant 58 | var v = "[aeiouy]"; // vowel 59 | var C = c + "[^aeiouy]*"; // consonant sequence 60 | var V = v + "[aeiou]*"; // vowel sequence 61 | 62 | var mgr0 = "^(" + C + ")?" + V + C; // [C]VC... is m>0 63 | var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$"; // [C]VC[V] is m=1 64 | var mgr1 = "^(" + C + ")?" + V + C + V + C; // [C]VCVC... is m>1 65 | var s_v = "^(" + C + ")?" + v; // vowel in stem 66 | 67 | this.stemWord = function (w) { 68 | var stem; 69 | var suffix; 70 | var firstch; 71 | var origword = w; 72 | 73 | if (w.length < 3) 74 | return w; 75 | 76 | var re; 77 | var re2; 78 | var re3; 79 | var re4; 80 | 81 | firstch = w.substr(0,1); 82 | if (firstch == "y") 83 | w = firstch.toUpperCase() + w.substr(1); 84 | 85 | // Step 1a 86 | re = /^(.+?)(ss|i)es$/; 87 | re2 = /^(.+?)([^s])s$/; 88 | 89 | if (re.test(w)) 90 | w = w.replace(re,"$1$2"); 91 | else if (re2.test(w)) 92 | w = w.replace(re2,"$1$2"); 93 | 94 | // Step 1b 95 | re = /^(.+?)eed$/; 96 | re2 = /^(.+?)(ed|ing)$/; 97 | if (re.test(w)) { 98 | var fp = re.exec(w); 99 | re = new RegExp(mgr0); 100 | if (re.test(fp[1])) { 101 | re = /.$/; 102 | w = w.replace(re,""); 103 | } 104 | } 105 | else if (re2.test(w)) { 106 | var fp = re2.exec(w); 107 | stem = fp[1]; 108 | re2 = new RegExp(s_v); 109 | if (re2.test(stem)) { 110 | w = stem; 111 | re2 = /(at|bl|iz)$/; 112 | re3 = new RegExp("([^aeiouylsz])\\1$"); 113 | re4 = new RegExp("^" + C + v + "[^aeiouwxy]$"); 114 | if (re2.test(w)) 115 | w = w + "e"; 116 | else if (re3.test(w)) { 117 | re = /.$/; 118 | w = w.replace(re,""); 119 | } 120 | else if (re4.test(w)) 121 | w = w + "e"; 122 | } 123 | } 124 | 125 | // Step 1c 126 | re = /^(.+?)y$/; 127 | if (re.test(w)) { 128 | var fp = re.exec(w); 129 | stem = fp[1]; 130 | re = new RegExp(s_v); 131 | if (re.test(stem)) 132 | w = stem + "i"; 133 | } 134 | 135 | // Step 2 136 | re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/; 137 | if (re.test(w)) { 138 | var fp = re.exec(w); 139 | stem = fp[1]; 140 | suffix = fp[2]; 141 | re = new RegExp(mgr0); 142 | if (re.test(stem)) 143 | w = stem + step2list[suffix]; 144 | } 145 | 146 | // Step 3 147 | re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/; 148 | if (re.test(w)) { 149 | var fp = re.exec(w); 150 | stem = fp[1]; 151 | suffix = fp[2]; 152 | re = new RegExp(mgr0); 153 | if (re.test(stem)) 154 | w = stem + step3list[suffix]; 155 | } 156 | 157 | // Step 4 158 | re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/; 159 | re2 = /^(.+?)(s|t)(ion)$/; 160 | if (re.test(w)) { 161 | var fp = re.exec(w); 162 | stem = fp[1]; 163 | re = new RegExp(mgr1); 164 | if (re.test(stem)) 165 | w = stem; 166 | } 167 | else if (re2.test(w)) { 168 | var fp = re2.exec(w); 169 | stem = fp[1] + fp[2]; 170 | re2 = new RegExp(mgr1); 171 | if (re2.test(stem)) 172 | w = stem; 173 | } 174 | 175 | // Step 5 176 | re = /^(.+?)e$/; 177 | if (re.test(w)) { 178 | var fp = re.exec(w); 179 | stem = fp[1]; 180 | re = new RegExp(mgr1); 181 | re2 = new RegExp(meq1); 182 | re3 = new RegExp("^" + C + v + "[^aeiouwxy]$"); 183 | if (re.test(stem) || (re2.test(stem) && !(re3.test(stem)))) 184 | w = stem; 185 | } 186 | re = /ll$/; 187 | re2 = new RegExp(mgr1); 188 | if (re.test(w) && re2.test(w)) { 189 | re = /.$/; 190 | w = w.replace(re,""); 191 | } 192 | 193 | // and turn initial Y back to y 194 | if (firstch == "y") 195 | w = firstch.toLowerCase() + w.substr(1); 196 | return w; 197 | } 198 | } 199 | 200 | -------------------------------------------------------------------------------- /docs/_build/html/_static/skeleton.css: -------------------------------------------------------------------------------- 1 | /* Some sane resets. */ 2 | html { 3 | height: 100%; 4 | } 5 | 6 | body { 7 | margin: 0; 8 | min-height: 100%; 9 | } 10 | 11 | /* All the flexbox magic! */ 12 | body, 13 | .sb-announcement, 14 | .sb-content, 15 | .sb-main, 16 | .sb-container, 17 | .sb-container__inner, 18 | .sb-article-container, 19 | .sb-footer-content, 20 | .sb-header, 21 | .sb-header-secondary, 22 | .sb-footer { 23 | display: flex; 24 | } 25 | 26 | /* These order things vertically */ 27 | body, 28 | .sb-main, 29 | .sb-article-container { 30 | flex-direction: column; 31 | } 32 | 33 | /* Put elements in the center */ 34 | .sb-header, 35 | .sb-header-secondary, 36 | .sb-container, 37 | .sb-content, 38 | .sb-footer, 39 | .sb-footer-content { 40 | justify-content: center; 41 | } 42 | /* Put elements at the ends */ 43 | .sb-article-container { 44 | justify-content: space-between; 45 | } 46 | 47 | /* These elements grow. */ 48 | .sb-main, 49 | .sb-content, 50 | .sb-container, 51 | article { 52 | flex-grow: 1; 53 | } 54 | 55 | /* Because padding making this wider is not fun */ 56 | article { 57 | box-sizing: border-box; 58 | } 59 | 60 | /* The announcements element should never be wider than the page. */ 61 | .sb-announcement { 62 | max-width: 100%; 63 | } 64 | 65 | .sb-sidebar-primary, 66 | .sb-sidebar-secondary { 67 | flex-shrink: 0; 68 | width: 17rem; 69 | } 70 | 71 | .sb-announcement__inner { 72 | justify-content: center; 73 | 74 | box-sizing: border-box; 75 | height: 3rem; 76 | 77 | overflow-x: auto; 78 | white-space: nowrap; 79 | } 80 | 81 | /* Sidebars, with checkbox-based toggle */ 82 | .sb-sidebar-primary, 83 | .sb-sidebar-secondary { 84 | position: fixed; 85 | height: 100%; 86 | top: 0; 87 | } 88 | 89 | .sb-sidebar-primary { 90 | left: -17rem; 91 | transition: left 250ms ease-in-out; 92 | } 93 | .sb-sidebar-secondary { 94 | right: -17rem; 95 | transition: right 250ms ease-in-out; 96 | } 97 | 98 | .sb-sidebar-toggle { 99 | display: none; 100 | } 101 | .sb-sidebar-overlay { 102 | position: fixed; 103 | top: 0; 104 | width: 0; 105 | height: 0; 106 | 107 | transition: width 0ms ease 250ms, height 0ms ease 250ms, opacity 250ms ease; 108 | 109 | opacity: 0; 110 | background-color: rgba(0, 0, 0, 0.54); 111 | } 112 | 113 | #sb-sidebar-toggle--primary:checked 114 | ~ .sb-sidebar-overlay[for="sb-sidebar-toggle--primary"], 115 | #sb-sidebar-toggle--secondary:checked 116 | ~ .sb-sidebar-overlay[for="sb-sidebar-toggle--secondary"] { 117 | width: 100%; 118 | height: 100%; 119 | opacity: 1; 120 | transition: width 0ms ease, height 0ms ease, opacity 250ms ease; 121 | } 122 | 123 | #sb-sidebar-toggle--primary:checked ~ .sb-container .sb-sidebar-primary { 124 | left: 0; 125 | } 126 | #sb-sidebar-toggle--secondary:checked ~ .sb-container .sb-sidebar-secondary { 127 | right: 0; 128 | } 129 | 130 | /* Full-width mode */ 131 | .drop-secondary-sidebar-for-full-width-content 132 | .hide-when-secondary-sidebar-shown { 133 | display: none !important; 134 | } 135 | .drop-secondary-sidebar-for-full-width-content .sb-sidebar-secondary { 136 | display: none !important; 137 | } 138 | 139 | /* Mobile views */ 140 | .sb-page-width { 141 | width: 100%; 142 | } 143 | 144 | .sb-article-container, 145 | .sb-footer-content__inner, 146 | .drop-secondary-sidebar-for-full-width-content .sb-article, 147 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 148 | width: 100vw; 149 | } 150 | 151 | .sb-article, 152 | .match-content-width { 153 | padding: 0 1rem; 154 | box-sizing: border-box; 155 | } 156 | 157 | @media (min-width: 32rem) { 158 | .sb-article, 159 | .match-content-width { 160 | padding: 0 2rem; 161 | } 162 | } 163 | 164 | /* Tablet views */ 165 | @media (min-width: 42rem) { 166 | .sb-article-container { 167 | width: auto; 168 | } 169 | .sb-footer-content__inner, 170 | .drop-secondary-sidebar-for-full-width-content .sb-article, 171 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 172 | width: 42rem; 173 | } 174 | .sb-article, 175 | .match-content-width { 176 | width: 42rem; 177 | } 178 | } 179 | @media (min-width: 46rem) { 180 | .sb-footer-content__inner, 181 | .drop-secondary-sidebar-for-full-width-content .sb-article, 182 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 183 | width: 46rem; 184 | } 185 | .sb-article, 186 | .match-content-width { 187 | width: 46rem; 188 | } 189 | } 190 | @media (min-width: 50rem) { 191 | .sb-footer-content__inner, 192 | .drop-secondary-sidebar-for-full-width-content .sb-article, 193 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 194 | width: 50rem; 195 | } 196 | .sb-article, 197 | .match-content-width { 198 | width: 50rem; 199 | } 200 | } 201 | 202 | /* Tablet views */ 203 | @media (min-width: 59rem) { 204 | .sb-sidebar-secondary { 205 | position: static; 206 | } 207 | .hide-when-secondary-sidebar-shown { 208 | display: none !important; 209 | } 210 | .sb-footer-content__inner, 211 | .drop-secondary-sidebar-for-full-width-content .sb-article, 212 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 213 | width: 59rem; 214 | } 215 | .sb-article, 216 | .match-content-width { 217 | width: 42rem; 218 | } 219 | } 220 | @media (min-width: 63rem) { 221 | .sb-footer-content__inner, 222 | .drop-secondary-sidebar-for-full-width-content .sb-article, 223 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 224 | width: 63rem; 225 | } 226 | .sb-article, 227 | .match-content-width { 228 | width: 46rem; 229 | } 230 | } 231 | @media (min-width: 67rem) { 232 | .sb-footer-content__inner, 233 | .drop-secondary-sidebar-for-full-width-content .sb-article, 234 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 235 | width: 67rem; 236 | } 237 | .sb-article, 238 | .match-content-width { 239 | width: 50rem; 240 | } 241 | } 242 | 243 | /* Desktop views */ 244 | @media (min-width: 76rem) { 245 | .sb-sidebar-primary { 246 | position: static; 247 | } 248 | .hide-when-primary-sidebar-shown { 249 | display: none !important; 250 | } 251 | .sb-footer-content__inner, 252 | .drop-secondary-sidebar-for-full-width-content .sb-article, 253 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 254 | width: 59rem; 255 | } 256 | .sb-article, 257 | .match-content-width { 258 | width: 42rem; 259 | } 260 | } 261 | 262 | /* Full desktop views */ 263 | @media (min-width: 80rem) { 264 | .sb-article, 265 | .match-content-width { 266 | width: 46rem; 267 | } 268 | .sb-footer-content__inner, 269 | .drop-secondary-sidebar-for-full-width-content .sb-article, 270 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 271 | width: 63rem; 272 | } 273 | } 274 | 275 | @media (min-width: 84rem) { 276 | .sb-article, 277 | .match-content-width { 278 | width: 50rem; 279 | } 280 | .sb-footer-content__inner, 281 | .drop-secondary-sidebar-for-full-width-content .sb-article, 282 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 283 | width: 67rem; 284 | } 285 | } 286 | 287 | @media (min-width: 88rem) { 288 | .sb-footer-content__inner, 289 | .drop-secondary-sidebar-for-full-width-content .sb-article, 290 | .drop-secondary-sidebar-for-full-width-content .match-content-width { 291 | width: 67rem; 292 | } 293 | .sb-page-width { 294 | width: 88rem; 295 | } 296 | } 297 | -------------------------------------------------------------------------------- /docs/_build/html/_static/styles/furo-extensions.css.map: -------------------------------------------------------------------------------- 1 | {"version":3,"file":"styles/furo-extensions.css","mappings":"AAGA,2BACE,oFACA,4CAKE,6CAHA,YACA,eAEA,CACA,kDACE,yCAEF,8CACE,sCAEJ,8CACE,kDAEJ,2BAGE,uBACA,cAHA,gBACA,UAEA,CAGA,yCACE,mBAEF,gDAEE,gDADA,YACA,CACA,sDACE,gDACF,yDACE,sCAEJ,+CACE,UACA,qDACE,UAGF,mDACE,eAEJ,yEAEE,4DAEA,mHASE,mBAPA,kBAEA,YADA,oBAGA,aADA,gBAIA,CAEA,qIAEE,WADA,UACA,CAEJ,uGACE,aAEF,iUAGE,cAEF,mHACE,aC1EJ,gCACE,mCAEF,0BAKE,mBAUA,8CACA,YAFA,mCAKA,eAZA,cALA,UASA,YADA,YAYA,iCAdA,YAcA,CAEA,gCAEE,8CADA,gCACA,CAEF,gCAGE,6BADA,mCADA,YAEA,CAEF,kCAEE,cADA,oBACA,CACA,wCACE,cAEJ,8BACE,UC5CN,KAEE,6CAA8C,CAC9C,uDAAwD,CACxD,uDAAwD,CAGxD,iCAAsC,CAGtC,+CAAgD,CAChD,uDAAwD,CACxD,uDAAwD,CACxD,oDAAqD,CACrD,6DAA8D,CAC9D,6DAA8D,CAG9D,uDAAwD,CACxD,yDAA0D,CAC1D,4DAA6D,CAC7D,2DAA4D,CAC5D,8DAA+D,CAC/D,iEAAkE,CAClE,uDAAwD,CACxD,wDAAyD,CAG3D,gBACE,qFAGF,SACE,6EAEF,cACE,uFAEF,cACE,uFAEF,cACE,uFAGF,qBACE,eAEF,mBACE,WACA,eChDF,KACE,gDAAiD,CACjD,uDAAwD,CACxD,qDAAsD,CACtD,4DAA6D,CAC7D,oCAAqC,CACrC,2CAA4C,CAC5C,4CAA6C,CAC7C,mDAAoD,CACpD,wBAAyB,CACzB,oBAAqB,CACrB,6CAA8C,CAC9C,gCAAiC,CACjC,yDAA0D,CAC1D,uDAAwD,CACxD,8DAA+D,CCbjE,uBACE,eACA,eACA,gBAGF,iBACE,YACA,+EAGF,iBACE,mDACA","sources":["webpack:///./src/furo/assets/styles/extensions/_readthedocs.sass","webpack:///./src/furo/assets/styles/extensions/_copybutton.sass","webpack:///./src/furo/assets/styles/extensions/_sphinx-design.sass","webpack:///./src/furo/assets/styles/extensions/_sphinx-inline-tabs.sass","webpack:///./src/furo/assets/styles/extensions/_sphinx-panels.sass"],"sourcesContent":["// This file contains the styles used for tweaking how ReadTheDoc's embedded\n// contents would show up inside the theme.\n\n#furo-sidebar-ad-placement\n padding: var(--sidebar-item-spacing-vertical) var(--sidebar-item-spacing-horizontal)\n .ethical-sidebar\n // Remove the border and box-shadow.\n border: none\n box-shadow: none\n // Manage the background colors.\n background: var(--color-background-secondary)\n &:hover\n background: var(--color-background-hover)\n // Ensure the text is legible.\n a\n color: var(--color-foreground-primary)\n\n .ethical-callout a\n color: var(--color-foreground-secondary) !important\n\n#furo-readthedocs-versions\n position: static\n width: 100%\n background: transparent\n display: block\n\n // Make the background color fit with the theme's aesthetic.\n .rst-versions\n background: rgb(26, 28, 30)\n\n .rst-current-version\n cursor: unset\n background: var(--color-sidebar-item-background)\n &:hover\n background: var(--color-sidebar-item-background)\n .fa-book\n color: var(--color-foreground-primary)\n\n > .rst-other-versions\n padding: 0\n small\n opacity: 1\n\n .injected\n .rst-versions\n position: unset\n\n &:hover,\n &:focus-within\n box-shadow: 0 0 0 1px var(--color-sidebar-background-border)\n\n .rst-current-version\n // Undo the tweaks done in RTD's CSS\n font-size: inherit\n line-height: inherit\n height: auto\n text-align: right\n padding: 12px\n\n // Match the rest of the body\n background: #1a1c1e\n\n .fa-book\n float: left\n color: white\n\n .fa-caret-down\n display: none\n\n .rst-current-version,\n .rst-other-versions,\n .injected\n display: block\n\n > .rst-current-version\n display: none\n",".highlight\n &:hover button.copybtn\n color: var(--color-code-foreground)\n\n button.copybtn\n // Make it visible\n opacity: 1\n\n // Align things correctly\n align-items: center\n\n height: 1.25em\n width: 1.25em\n\n top: 0.625rem // $code-spacing-vertical\n right: 0.5rem\n\n // Make it look better\n color: var(--color-background-item)\n background-color: var(--color-code-background)\n border: none\n\n // Change to cursor to make it obvious that you can click on it\n cursor: pointer\n\n // Transition smoothly, for aesthetics\n transition: color 300ms, opacity 300ms\n\n &:hover\n color: var(--color-brand-content)\n background-color: var(--color-code-background)\n\n &::after\n display: none\n color: var(--color-code-foreground)\n background-color: transparent\n\n &.success\n transition: color 0ms\n color: #22863a\n &::after\n display: block\n\n svg\n padding: 0\n","body\n // Colors\n --sd-color-primary: var(--color-brand-primary)\n --sd-color-primary-highlight: var(--color-brand-content)\n --sd-color-primary-text: var(--color-background-primary)\n\n // Shadows\n --sd-color-shadow: rgba(0, 0, 0, 0.05)\n\n // Cards\n --sd-color-card-border: var(--color-card-border)\n --sd-color-card-border-hover: var(--color-brand-content)\n --sd-color-card-background: var(--color-card-background)\n --sd-color-card-text: var(--color-foreground-primary)\n --sd-color-card-header: var(--color-card-marginals-background)\n --sd-color-card-footer: var(--color-card-marginals-background)\n\n // Tabs\n --sd-color-tabs-label-active: var(--color-brand-content)\n --sd-color-tabs-label-hover: var(--color-foreground-muted)\n --sd-color-tabs-label-inactive: var(--color-foreground-muted)\n --sd-color-tabs-underline-active: var(--color-brand-content)\n --sd-color-tabs-underline-hover: var(--color-foreground-border)\n --sd-color-tabs-underline-inactive: var(--color-background-border)\n --sd-color-tabs-overline: var(--color-background-border)\n --sd-color-tabs-underline: var(--color-background-border)\n\n// Tabs\n.sd-tab-content\n box-shadow: 0 -2px var(--sd-color-tabs-overline), 0 1px var(--sd-color-tabs-underline)\n\n// Shadows\n.sd-card // Have a shadow by default\n box-shadow: 0 0.1rem 0.25rem var(--sd-color-shadow), 0 0 0.0625rem rgba(0, 0, 0, 0.1)\n\n.sd-shadow-sm\n box-shadow: 0 0.1rem 0.25rem var(--sd-color-shadow), 0 0 0.0625rem rgba(0, 0, 0, 0.1) !important\n\n.sd-shadow-md\n box-shadow: 0 0.3rem 0.75rem var(--sd-color-shadow), 0 0 0.0625rem rgba(0, 0, 0, 0.1) !important\n\n.sd-shadow-lg\n box-shadow: 0 0.6rem 1.5rem var(--sd-color-shadow), 0 0 0.0625rem rgba(0, 0, 0, 0.1) !important\n\n// Cards\n.sd-card-hover:hover // Don't change scale on hover\n transform: none\n\n.sd-cards-carousel // Have a bit of gap in the carousel by default\n gap: 0.25rem\n padding: 0.25rem\n","// This file contains styles to tweak sphinx-inline-tabs to work well with Furo.\n\nbody\n --tabs--label-text: var(--color-foreground-muted)\n --tabs--label-text--hover: var(--color-foreground-muted)\n --tabs--label-text--active: var(--color-brand-content)\n --tabs--label-text--active--hover: var(--color-brand-content)\n --tabs--label-background: transparent\n --tabs--label-background--hover: transparent\n --tabs--label-background--active: transparent\n --tabs--label-background--active--hover: transparent\n --tabs--padding-x: 0.25em\n --tabs--margin-x: 1em\n --tabs--border: var(--color-background-border)\n --tabs--label-border: transparent\n --tabs--label-border--hover: var(--color-foreground-muted)\n --tabs--label-border--active: var(--color-brand-content)\n --tabs--label-border--active--hover: var(--color-brand-content)\n","// This file contains styles to tweak sphinx-panels to work well with Furo.\n\n// sphinx-panels includes Bootstrap 4, which uses .container which can conflict\n// with docutils' `.. container::` directive.\n[role=\"main\"] .container\n max-width: initial\n padding-left: initial\n padding-right: initial\n\n// Make the panels look nicer!\n.shadow.docutils\n border: none\n box-shadow: 0 0.2rem 0.5rem rgba(0, 0, 0, 0.05), 0 0 0.0625rem rgba(0, 0, 0, 0.1) !important\n\n// Make panel colors respond to dark mode\n.sphinx-bs .card\n background-color: var(--color-background-secondary)\n color: var(--color-foreground)\n"],"names":[],"sourceRoot":""} -------------------------------------------------------------------------------- /docs/_build/html/search.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 |
115 |
116 |
140 |
174 |
242 |
243 |
244 |
245 |
246 |
247 |
248 |
249 |
250 |
--------------------------------------------------------------------------------
/docs/_build/html/_modules/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
117 |
121 |
122 |
123 |
125 | GLHMM 0.0.1 documentation
124 |
126 |
139 |
127 |
133 |
134 |
138 |
175 |
241 |
117 |
118 |
142 |
176 |
239 |
240 |
241 |
242 |
243 |
244 |
--------------------------------------------------------------------------------
/docs/_build/html/searchindex.js:
--------------------------------------------------------------------------------
1 | Search.setIndex({"docnames": ["auxiliary", "glhmm", "glossary", "io_glhmm", "modules", "preproc", "utils"], "filenames": ["auxiliary.md", "glhmm.md", "glossary.md", "io_glhmm.md", "modules.md", "preproc.md", "utils.md"], "titles": ["auxiliary module", "glhmm module", "Glossary", "io_glhmm module", "API", "preproc module", "utils module"], "terms": {"function": [0, 1, 3, 5, 6], "gaussian": [0, 1, 3, 5, 6], "linear": [0, 1, 3, 5, 6], "hidden": [0, 1, 2, 3, 5, 6], "markov": [0, 1, 2, 3, 5, 6], "model": [0, 1, 2, 3, 5, 6], "author": [0, 1, 3, 5, 6], "diego": [0, 1, 3, 5, 6], "vidaurr": [0, 1, 3, 5, 6], "2022": [0, 2, 6], "glhmm": [0, 3, 4, 5, 6], "gamma_entropi": [0, 4], "gamma": [0, 1, 6], "xi": [0, 1], "indic": [0, 1, 3, 5, 6], "sourc": [0, 1, 3, 5, 6], "comput": [0, 1, 6], "entropi": [0, 1, 6], "distribut": [0, 1], "sequenc": [0, 1, 6], "transit": [0, 1], "probabl": [0, 1, 6], "arrai": [0, 1, 5, 6], "like": [0, 1, 5, 6], "shape": [0, 1, 5, 6], "n_sampl": [0, 1, 2, 5, 6], "n_state": [0, 1, 2, 6], "The": [0, 1, 2, 5, 6], "posterior": 0, "variabl": [0, 1, 5], "n_session": [0, 1, 2, 5, 6], "joint": [0, 1], "past": [0, 1], "futur": [0, 1], "state": [0, 1, 2, 6], "condit": [0, 1, 6], "data": [0, 1, 3, 5, 6], "2": [0, 1, 5, 6], "start": [0, 1, 5, 6], "end": [0, 1, 5, 6], "each": [0, 1, 3, 5, 6], "trial": [0, 1, 5, 6], "session": [0, 1, 2, 5, 6], "input": [0, 1, 3, 5, 6], "float": [0, 1, 5, 6], "gamma_indices_to_xi_indic": [0, 4], "convert": 0, "from": [0, 1, 3], "format": [0, 5], "note": 0, "ha": [0, 1, 5], "1": [0, 1, 5, 6], "sampl": [0, 1, 4], "less": 0, "than": [0, 2, 6], "per": [0, 1, 6], "i": [0, 1, 2, 3, 5, 6], "e": [0, 1, 5, 6], "indices_xi": 0, "approximate_xi": [0, 4], "approxim": 0, "base": [0, 1], "time": [0, 1, 6], "seri": [0, 6], "compute_alpha_beta": [0, 4], "l": [0, 1], "pi": 0, "p": 0, "alpha": 0, "beta": [0, 1], "valu": [0, 1, 6], "scale": [0, 1], "factor": [0, 1], "matrix": [0, 1, 5, 6], "initi": [0, 1, 3], "across": [0, 6], "b": 0, "sc": 0, "compute_qstar": [0, 4], "most": [0, 1, 6], "qstar": 0, "dirichlet_kl": [0, 4], "alpha_q": 0, "alpha_p": 0, "kullback": 0, "leibler": 0, "diverg": [0, 1], "between": [0, 1], "two": 0, "dirichlet": [0, 1], "concentr": 0, "first": [0, 5, 6], "second": [0, 5], "gamma_kl": [0, 4], "shape_q": 0, "rate_q": 0, "shape_p": 0, "rate_p": 0, "rate": [0, 6], "measur": 0, "how": 0, "differ": [0, 1], "ar": [0, 1, 5], "thi": [0, 1, 6], "implement": 0, "follow": [0, 1, 6], "formula": 0, "present": 0, "here": 0, "http": [0, 2, 6], "statproofbook": 0, "github": 0, "io": 0, "gam": 0, "kl": [0, 1], "book": 0, "normal": [0, 6], "wishart": 0, "densiti": 0, "penni": 0, "william": 0, "d": [0, 5], "2001": 0, "numpi": [0, 1, 5], "ndarrai": [0, 5], "gauss1d_kl": [0, 4], "mu_q": 0, "sigma_q": 0, "mu_p": 0, "sigma_p": 0, "univari": 0, "n_parcel": [0, 1, 2, 5], "mean": [0, 1, 5], "varianc": [0, 5], "gauss_kl": [0, 4], "multivari": 0, "jls_extract_def": [0, 4], "make_indices_from_t": [0, 4], "t": 0, "creat": 0, "length": [0, 1, 5, 6], "contain": [0, 1, 3], "slice_matrix": [0, 4], "m": 0, "slice": 0, "row": [0, 1, 6], "along": 0, "axi": 0, "0": [0, 1, 6], "defin": [0, 1, 6], "section": 0, "process": [0, 1], "m_slice": 0, "n_total_sampl": 0, "wishart_kl": [0, 4], "c_q": 0, "c_p": 0, "2023": [1, 3, 5, 6], "class": 1, "k": [1, 6], "10": 1, "covtyp": 1, "shareddiag": 1, "model_mean": 1, "model_beta": 1, "dirichlet_diag": 1, "connect": [1, 5, 6], "none": [1, 3, 5], "pstructur": 1, "pistructur": 1, "object": 1, "decod": [1, 4], "stimulu": 1, "int": [1, 5, 6], "default": [1, 5, 6], "number": [1, 2, 5, 6], "str": 1, "diag": 1, "type": 1, "covari": 1, "choos": 1, "have": [1, 6], "one": [1, 6], "diagon": 1, "all": [1, 6], "full": [1, 5], "If": [1, 5, 6], "timeseri": [1, 5, 6], "us": [1, 3, 5, 6], "drive": 1, "regress": [1, 5], "coeffici": 1, "higher": 1, "more": [1, 2, 6], "persist": 1, "rel": 1, "prior": 1, "compet": 1, "so": 1, "veri": 1, "long": 1, "mai": 1, "littl": 1, "effect": [1, 5], "unless": 1, "set": [1, 5], "larg": 1, "array_lik": 1, "option": [1, 5, 6], "binari": [1, 5], "can": [1, 5, 6], "onli": [1, 6], "allow": 1, "ones": 1, "possibl": 1, "vector": 1, "requir": 1, "math": 1, "scipi": 1, "sy": 1, "warn": 1, "copi": 1, "x": [1, 5], "y": [1, 5], "file": [1, 3, 5], "viterbi": [1, 6], "fals": [1, 3, 5, 6], "calcul": [1, 5, 6], "cours": 1, "either": 1, "parallel": 1, "sequenti": 1, "list": [1, 5, 6], "filenam": 1, "correspond": 1, "bool": [1, 5, 6], "whether": [1, 2, 5], "algorithm": 1, "should": [1, 5], "index": 1, "true": [1, 5, 6], "vpath": [1, 6], "free": 1, "energi": 1, "dataset": 1, "automat": 1, "except": [1, 6], "been": 1, "train": [1, 4], "dual_estim": [1, 4], "dual": 1, "estim": [1, 6], "hmm": [1, 2, 3, 5], "singl": [1, 2], "segment": [1, 5], "span": 1, "entir": [1, 2], "observ": 1, "hmm_dual": 1, "A": [1, 5, 6], "updat": 1, "dynam": 1, "get_beta": [1, 4], "specifi": 1, "which": [1, 5, 6], "retriev": 1, "yet": 1, "get_covariance_matrix": [1, 4], "get_f": [1, 4], "todo": 1, "an": [1, 5], "depend": 1, "n_term": 1, "5": 1, "element": [1, 5], "see": [1, 6], "fe_term": 1, "variat": 1, "separ": 1, "term": 1, "neg": 1, "log": 1, "likelihood": 1, "3": 1, "4": 1, "specif": 1, "For": [1, 2, 6], "inform": [1, 2, 6], "smith": 1, "j": 1, "et": [1, 2, 6], "al": [1, 2, 6], "approach": 1, "bayesian": 1, "learn": 1, "switch": [1, 6], "system": 1, "journal": 1, "machin": 1, "research": 1, "vol": 1, "18": 1, "2017": 1, "get_inverse_covariance_matrix": [1, 4], "invers": 1, "get_mean": [1, 4], "compon": [1, 5], "loglikelihood": [1, 4], "point": [1, 6], "gicven": 1, "given": [1, 6], "size": 1, "gener": [1, 5], "dimension": 1, "repres": [1, 6], "sample_gamma": [1, 4], "big": 1, "cut": 1, "assum": 1, "": 1, "load": [1, 3], "ignor": 1, "dict": 1, "dictionari": 1, "control": 1, "fe": 1, "iter": 1, "brain": 2, "parcel": 2, "region": 2, "seed": 2, "total": 2, "timepoint": 2, "mix": [2, 6], "refer": 2, "capabl": 2, "captur": 2, "within": 2, "modul": [2, 4], "rather": 2, "assign": 2, "largest": 2, "part": 2, "them": 2, "visit": [2, 6], "ahrend": [2, 6], "articl": 2, "pubm": [2, 6], "ncbi": [2, 6], "nlm": [2, 6], "nih": [2, 6], "gov": [2, 6], "35217207": [2, 6], "output": 3, "load_fil": [3, 4, 5], "do_only_indic": [3, 5], "return": 3, "individu": 3, "read_flattened_hmm_mat": [3, 4], "read": 3, "matlab": 3, "paramet": 3, "those": [3, 6], "preprocess": 5, "apply_pca": [4, 5], "whiten": 5, "exact": 5, "appli": 5, "pca": 5, "transform": 5, "keep": 5, "percentag": 5, "explain": 5, "n_compon": 5, "svd": 5, "solver": 5, "x_transform": 5, "after": 5, "build_data_autoregress": [4, 5], "autoregressive_ord": 5, "center_data": 5, "build": 5, "autoregress": 5, "well": 5, "adapt": 5, "predefin": 5, "right": 5, "center": 5, "lag": 5, "includ": 5, "regressor": 5, "predict": 5, "target": 5, "indices_new": 5, "new": 5, "connectivity_new": 5, "build_data_partial_connect": [4, 5], "partial": 5, "essenti": 5, "out": 5, "thing": 5, "when": [5, 6], "get": 5, "rid": 5, "dimens": 5, "np": 5, "affect": 5, "zero": 5, "x_new": 5, "n_active_parcel": 5, "remov": 5, "unus": 5, "predictor": 5, "y_new": 5, "same": [5, 6], "structur": 5, "build_data_td": [4, 5], "standardise_pc": 5, "tempor": 5, "delai": 5, "embed": 5, "precomput": 5, "project": 5, "skip": 5, "standardis": 5, "princip": 5, "befor": 5, "rwindow": 5, "n_lag": 5, "run": 5, "preprocess_data": [4, 5], "f": 5, "filter": 5, "detrend": 5, "onpow": 5, "exact_pca": 5, "downsampl": 5, "frequenc": 5, "standard": 5, "tupl": 5, "low": 5, "pass": 5, "high": 5, "threshold": [5, 6], "power": 5, "hilbert": 5, "data_process": 5, "n_samples_process": 5, "indices_process": 5, "n_sessions_process": 5, "some": 6, "public": 6, "get_fo": [4, 6], "summat": 6, "fraction": 6, "occup": 6, "sum": 6, "otherwis": 6, "fo": 6, "get_fo_entropi": [4, 6], "we": 6, "understand": 6, "get_life_tim": [4, 6], "averag": 6, "median": 6, "maximum": 6, "life": 6, "path": 6, "exclud": 6, "durat": 6, "below": 6, "meanlf": 6, "medianlf": 6, "maxlf": 6, "contigu": 6, "activ": 6, "get_visit": [4, 6], "get_maxfo": [4, 6], "argument": 6, "also": 6, "maxfo": 6, "assess": 6, "amount": 6, "r": 6, "consider": 6, "vari": 6, "fmri": 6, "neuroimag": 6, "252": 6, "119026": 6, "get_state_evoked_respons": [4, 6], "evok": 6, "respons": 6, "ser": 6, "violat": 6, "ani": 6, "There": 6, "Not": 6, "get_state_evoked_response_entropi": [4, 6], "get_state_onset": [4, 6], "onset": 6, "get_switching_r": [4, 6], "sr": 6, "where": 6, "greater": 6, "io_glhmm": 4, "preproc": 4, "auxiliari": 4, "util": 4}, "objects": {"glhmm": [[0, 0, 0, "-", "auxiliary"], [1, 0, 0, "-", "glhmm"], [3, 0, 0, "-", "io_glhmm"], [5, 0, 0, "-", "preproc"], [6, 0, 0, "-", "utils"]], "glhmm.auxiliary": [[0, 1, 1, "", "Gamma_entropy"], [0, 1, 1, "", "Gamma_indices_to_Xi_indices"], [0, 1, 1, "", "approximate_Xi"], [0, 1, 1, "", "compute_alpha_beta"], [0, 1, 1, "", "compute_qstar"], [0, 1, 1, "", "dirichlet_kl"], [0, 1, 1, "", "gamma_kl"], [0, 1, 1, "", "gauss1d_kl"], [0, 1, 1, "", "gauss_kl"], [0, 1, 1, "", "jls_extract_def"], [0, 1, 1, "", "make_indices_from_T"], [0, 1, 1, "", "slice_matrix"], [0, 1, 1, "", "wishart_kl"]], "glhmm.glhmm": [[1, 2, 1, "", "glhmm"]], "glhmm.glhmm.glhmm": [[1, 3, 1, "", "decode"], [1, 3, 1, "", "dual_estimate"], [1, 3, 1, "", "get_beta"], [1, 3, 1, "", "get_covariance_matrix"], [1, 3, 1, "", "get_fe"], [1, 3, 1, "", "get_inverse_covariance_matrix"], [1, 3, 1, "", "get_mean"], [1, 3, 1, "", "loglikelihood"], [1, 3, 1, "", "sample"], [1, 3, 1, "", "sample_Gamma"], [1, 3, 1, "", "train"]], "glhmm.io_glhmm": [[3, 1, 1, "", "load_files"], [3, 1, 1, "", "read_flattened_hmm_mat"]], "glhmm.preproc": [[5, 1, 1, "", "apply_pca"], [5, 1, 1, "", "build_data_autoregressive"], [5, 1, 1, "", "build_data_partial_connectivity"], [5, 1, 1, "", "build_data_tde"], [5, 1, 1, "", "load_files"], [5, 1, 1, "", "preprocess_data"]], "glhmm.utils": [[6, 1, 1, "", "get_FO"], [6, 1, 1, "", "get_FO_entropy"], [6, 1, 1, "", "get_life_times"], [6, 1, 1, "", "get_maxFO"], [6, 1, 1, "", "get_state_evoked_response"], [6, 1, 1, "", "get_state_evoked_response_entropy"], [6, 1, 1, "", "get_state_onsets"], [6, 1, 1, "", "get_switching_rate"], [6, 1, 1, "", "get_visits"]]}, "objtypes": {"0": "py:module", "1": "py:function", "2": "py:class", "3": "py:method"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "function", "Python function"], "2": ["py", "class", "Python class"], "3": ["py", "method", "Python method"]}, "titleterms": {"auxiliari": 0, "modul": [0, 1, 3, 5, 6], "paramet": [0, 1, 5, 6], "return": [0, 1, 5, 6], "glhmm": 1, "attribut": 1, "note": [1, 6], "rais": [1, 6], "refer": [1, 6], "glossari": 2, "io_glhmm": 3, "preproc": 5, "util": 6, "api": 4}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "nbsphinx": 4, "sphinx.ext.viewcode": 1, "sphinx": 57}, "alltitles": {"Glossary": [[2, "glossary"]], "io_glhmm module": [[3, "module-glhmm.io_glhmm"]], "auxiliary module": [[0, "module-glhmm.auxiliary"]], "Parameters:": [[0, "parameters"], [0, "id1"], [0, "id3"], [0, "id5"], [0, "id7"], [0, "id9"], [0, "id11"], [0, "id13"], [0, "id15"], [0, "id17"], [0, "id19"], [0, "id21"], [1, "parameters"], [1, "id1"], [1, "id3"], [1, "id6"], [1, "id9"], [1, "id13"], [1, "id16"], [1, "id19"], [1, "id22"], [1, "id24"], [1, "id26"], [5, "parameters"], [5, "id1"], [5, "id3"], [5, "id5"], [5, "id7"], [6, "parameters"], [6, "id1"], [6, "id3"], [6, "id5"], [6, "id8"], [6, "id10"], [6, "id12"], [6, "id15"], [6, "id17"]], "Returns:": [[0, "returns"], [0, "id2"], [0, "id4"], [0, "id6"], [0, "id8"], [0, "id10"], [0, "id12"], [0, "id14"], [0, "id16"], [0, "id18"], [0, "id20"], [0, "id22"], [1, "returns"], [1, "id2"], [1, "id4"], [1, "id7"], [1, "id10"], [1, "id14"], [1, "id17"], [1, "id20"], [1, "id23"], [1, "id25"], [1, "id27"], [5, "returns"], [5, "id2"], [5, "id4"], [5, "id6"], [5, "id8"], [6, "returns"], [6, "id2"], [6, "id4"], [6, "id6"], [6, "id9"], [6, "id11"], [6, "id13"], [6, "id16"], [6, "id18"]], "glhmm module": [[1, "module-glhmm.glhmm"]], "Attributes:": [[1, "attributes"]], "Notes:": [[1, "notes"], [1, "id12"], [6, "notes"], [6, "id7"], [6, "id14"], [6, "id19"]], "Raises:": [[1, "raises"], [1, "id5"], [1, "id8"], [1, "id11"], [1, "id15"], [1, "id18"], [1, "id21"], [6, "raises"]], "References:": [[1, "references"], [6, "references"]], "preproc module": [[5, "module-glhmm.preproc"]], "utils module": [[6, "module-glhmm.utils"]], "API": [[4, "api"]]}, "indexentries": {}})
--------------------------------------------------------------------------------
/docs/_build/html/py-modindex.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
119 |
123 |
124 |
125 |
127 | GLHMM 0.0.1 documentation
126 |
128 |
141 |
129 |
135 |
136 |
140 |
177 |
238 |
178 |
232 |
237 |
179 |
180 |
183 | Back to top
184 |
185 |
199 |
200 |
208 |
209 |
231 | All modules for which code is available
201 |- glhmm.auxiliary 202 |
- glhmm.glhmm 203 |
- glhmm.io_glhmm 204 |
- glhmm.preproc 205 |
- glhmm.utils 206 |
116 |
117 |
141 |
175 |
282 |
283 |
284 |
285 |
286 |
287 |
--------------------------------------------------------------------------------
/glhmm/utils.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | # -*- coding: utf-8 -*-
3 | """
4 | Some public useful functions - Gaussian Linear Hidden Markov Model
5 | @author: Diego Vidaurre 2023
6 | """
7 |
8 | import numpy as np
9 | import statistics
10 | import math
11 | from scipy.optimize import linear_sum_assignment
12 |
13 | def get_FO(Gamma,indices,summation=False):
14 | """Calculates the fractional occupancy of each state.
15 |
16 | Parameters:
17 | -----------
18 | Gamma : array-like, shape (n_samples, n_states)
19 | The state probability time series.
20 | indices : array-like, shape (n_sessions, 2)
21 | The start and end indices of each trial/session in the input data.
22 | summation : bool, optional, default=False
23 | If True, the sum of each row is not normalized, otherwise it is.
24 |
25 | Returns:
26 | --------
27 | FO : array-like, shape (n_sessions, n_states)
28 | The fractional occupancy of each state per session.
29 |
30 | """
31 |
32 | N = indices.shape[0]
33 | K = Gamma.shape[1]
34 | FO = np.zeros((N,K))
35 | for j in range(N):
36 | ind = np.arange(indices[j,0],indices[j,1])
37 | FO[j,:] = np.sum(Gamma[ind,:],axis=0)
38 | if not summation:
39 | FO[j,:] /= np.sum(FO[j,:])
40 | return FO
41 |
42 |
43 | def get_maxFO(Gamma,indices):
44 | """Calculates the maximum fractional occupancy per session.
45 |
46 | The first argument can also be a viterbi path (vpath).
47 |
48 | Parameters:
49 | -----------
50 | Gamma : array-like of shape (n_samples, n_states); or a vpath, array of shape (n_samples,)
51 | The Gamma represents the state probability timeseries and the vpath represents the most likely state sequence.
52 | indices : array-like of shape (n_sessions, 2)
53 | The start and end indices of each trial/session in the input data.
54 |
55 | Returns:
56 | --------
57 | maxFO: array-like of shape (n_sessions,)
58 | The maximum fractional occupancy across states for each trial/session
59 |
60 | Notes:
61 | ------
62 | The maxFO is useful to assess the amount of `state mixing`. For more information, see [^1].
63 |
64 | References:
65 | -----------
66 | [^1]: Ahrends, R., et al. (2022). Data and model considerations for estimating time-varying functional connectivity in fMRI. NeuroImage 252, 119026.
67 | https://pubmed.ncbi.nlm.nih.gov/35217207/)
68 |
69 | """
70 | FO = get_FO(Gamma,indices)
71 | return np.max(FO,axis=1)
72 |
73 |
74 | def get_state_evoked_response(Gamma,indices):
75 | """Calculates the state evoked response
76 |
77 | The first argument can also be a viterbi path (vpath).
78 |
79 | Parameters:
80 | ---------------
81 | Gamma : array-like of shape (n_samples, n_states), or a vpath array of shape (n_samples,)
82 | The Gamma represents the state probability timeseries and the vpath represents the most likely state sequence.
83 | indices : array-like of shape (n_sessions, 2)
84 | The start and end indices of each trial/session in the input data.
85 |
86 | Returns:
87 | ------------
88 | ser : array-like of shape (n_samples, n_states)
89 | The state evoked response matrix.
90 |
91 | Raises:
92 | -------
93 | Exception
94 | If the input data violates any of the following conditions:
95 | - There is only one trial/session
96 | - Not all trials/sessions have the same length.
97 | """
98 |
99 | N = indices.shape[0]
100 | if N == 1:
101 | raise Exception("There is only one segment / trial")
102 | T = indices[:,1] - indices[:,0]
103 | if not(np.all(T[0]==T)):
104 | raise Exception("All segments / trials must have the same length")
105 | K = Gamma.shape[1]
106 | T = T[0]
107 |
108 | ser = np.mean(np.reshape(Gamma,(T,N,K),order='F'),axis=1)
109 | return ser
110 |
111 |
112 | def get_switching_rate(Gamma,indices):
113 | """Calculates the switching rate.
114 |
115 | The first argument can also be a viterbi path (vpath).
116 |
117 | Parameters:
118 | ---------------
119 | Gamma : array-like of shape (n_samples, n_states), or a vpath array of shape (n_samples,)
120 | The Gamma represents the state probability timeseries and the vpath represents the most likely state sequence.
121 | indices : array-like of shape (n_sessions, 2)
122 | The start and end indices of each trial/session in the input data.
123 |
124 | Returns:
125 | ------------
126 | SR : array-like of shape (n_sessions, n_states)
127 | The switching rate matrix.
128 |
129 | """
130 | N = indices.shape[0]
131 | K = Gamma.shape[1]
132 | SR = np.zeros((N,K))
133 | for j in range(N):
134 | ind = np.arange(indices[j,0],indices[j,1])
135 | SR[j,:] = np.mean(np.abs(Gamma[ind[1:],:]-Gamma[ind[0:-1],:]),axis=0)
136 | return SR
137 |
138 |
139 | def get_visits(vpath,k,threshold=0):
140 | """Computes a list of visits for state k, given a viterbi path (vpath).
141 |
142 | Parameters:
143 | ---------------
144 | vpath : array-like of shape (n_samples,)
145 | The viterbi path represents the most likely state sequence.
146 | k : int
147 | The state for which to compute the visits.
148 | threshold : int, optional, default=0
149 | A threshold value used to exclude visits with a duration below this value.
150 |
151 | Returns:
152 | ------------
153 | lengths : list of floats
154 | A list of visit durations for state k, where each duration is greater than the threshold.
155 | onsets : list of ints
156 | A list of onset time points for each visit.
157 |
158 | Notes:
159 | ------
160 | A visit to state k is defined as a contiguous sequence of time points in which state k is active.
161 |
162 | """
163 |
164 | lengths = []
165 | onsets = []
166 | T = vpath.shape[0]
167 | vpath_k = vpath[:,k]
168 | t = 0
169 | while t < T:
170 | t += np.where(vpath_k[t:]==1)[0]
171 | if len(t)==0:
172 | break
173 | t = t[0]
174 | onsets.append(t)
175 | tend = np.where(vpath_k[t:]==0)[0]
176 | if len(tend)==0:
177 | length_visit = len(vpath_k)-t
178 | if length_visit > threshold: lengths.append(float(length_visit))
179 | break
180 | tend = tend[0]
181 | length_visit = tend
182 | if length_visit > threshold: lengths.append(float(length_visit))
183 | t += tend
184 | return lengths,onsets
185 |
186 |
187 | def get_life_times(vpath,indices,threshold=0):
188 | """Calculates the average, median and maximum life times for each state.
189 |
190 | Parameters:
191 | -----------
192 | vpath : array-like of shape (n_samples,)
193 | The viterbi path represents the most likely state sequence.
194 | indices : array-like of shape (n_sessions, 2)
195 | The start and end indices of each trial/session in the input data.
196 | threshold : int, optional, default=0
197 | A threshold value used to exclude visits with a duration below this value.
198 |
199 | Returns:
200 | --------
201 | meanLF : array-like of shape (n_sessions, n_states)
202 | The average visit duration for each state in each trial/session.
203 | medianLF : array-like of shape (n_sessions, n_states)
204 | The median visit duration for each state in each trial/session.
205 | maxLF : array-like of shape (n_sessions, n_states)
206 | The maximum visit duration for each state in each trial/session.
207 |
208 | Notes:
209 | ------
210 | A visit to a state is defined as a contiguous sequence of time points in which the state is active.
211 | The duration of a visit is the number of time points in the sequence.
212 | This function uses the `get_visits` function to compute the visits and exclude those below the threshold.
213 |
214 | """
215 | N = indices.shape[0]
216 | K = vpath.shape[1]
217 | meanLF = np.zeros((N,K))
218 | medianLF = np.zeros((N,K))
219 | maxLF = np.zeros((N,K))
220 | for j in range(N):
221 | ind = np.arange(indices[j,0],indices[j,1]).astype(int)
222 | for k in range(K):
223 | visits,_ = get_visits(vpath[ind,:],k,threshold=threshold)
224 | if len(visits) > 0:
225 | meanLF[j,k] = statistics.mean(visits)
226 | medianLF[j,k] = statistics.median(visits)
227 | maxLF[j,k] = max(visits)
228 | return meanLF, medianLF, maxLF
229 |
230 |
231 | def get_state_onsets(vpath,indices,threshold=0):
232 | """Calculates the state onsets, i.e., the time points when each state activates.
233 |
234 | Parameters:
235 | ---------------
236 | vpath : array-like of shape (n_samples, n_states)
237 | The viterbi path represents the most likely state sequence.
238 | indices : array-like of shape (n_sessions, 2)
239 | The start and end indices of each trial/session in the input data.
240 | threshold : int, optional, default=0
241 | A threshold value used to exclude visits with a duration below this value.
242 |
243 | Returns:
244 | --------
245 | onsets : list of lists of ints
246 | A list of the time points when each state activates for each trial/session.
247 |
248 | Notes:
249 | ------
250 | A visit to a state is defined as a contiguous sequence of time points in which the state is active.
251 | This function uses the `get_visits` function to compute the visits and exclude those below the threshold.
252 |
253 | """
254 |
255 | N = indices.shape[0]
256 | K = vpath.shape[1]
257 | onsets = []
258 | for j in range(N):
259 | onsets_j = []
260 | ind = np.arange(indices[j,0],indices[j,1]).astype(int)
261 | for k in range(K):
262 | _,onsets_k = get_visits(vpath[ind,:],k,threshold=threshold)
263 | onsets_j.append(onsets_k)
264 | onsets.append(onsets_j)
265 | return onsets
266 |
267 |
268 | def get_FO_entropy(Gamma,indices):
269 | """Calculates the entropy of each session, if we understand fractional occupancies as probabilities.
270 |
271 | Parameters:
272 | --------------
273 | Gamma : array-like of shape (n_samples, n_states)
274 | The Gamma represents the state probability timeseries.
275 | indices : array-like of shape (n_sessions, 2)
276 | The start and end indices of each trial/session in the input data.
277 |
278 | Returns:
279 | --------
280 | entropy : array-like of shape (n_sessions,)
281 | The entropy of each session.
282 |
283 | """
284 | fo = get_FO(Gamma,indices)
285 | N,K = fo.shape
286 | entropy = np.zeros(N)
287 | for j in range(N):
288 | for k in range(K):
289 | if fo[j,k] == 0: continue
290 | entropy[j] -= math.log(fo[j,k]) * fo[j,k]
291 | return entropy
292 |
293 |
294 | def get_state_evoked_response_entropy(Gamma,indices):
295 | """Calculates the entropy of each time point, if we understand state evoked responses as probabilities.
296 |
297 | Parameters:
298 | ---------------
299 | Gamma: array-like of shape (n_samples, n_states)
300 | The Gamma represents the state probability timeseries.
301 | indices : array-like of shape (n_sessions, 2)
302 | The start and end indices of each trial/session in the input data.
303 |
304 | Returns:
305 | ------------
306 | entropy: array-like of shape (n_samples,)
307 | The entropy of each time point.
308 |
309 | """
310 | ser = get_state_evoked_response(Gamma,indices)
311 | T,K = ser.shape
312 | entropy = np.zeros(T)
313 | for t in range(T):
314 | for k in range(K):
315 | if ser[t,k] == 0: continue
316 | entropy[t] -= math.log(ser[t,k]) * ser[t,k]
317 | return entropy
318 |
319 |
320 | def get_gamma_similarity(gamma1, gamma2):
321 | """Computes a measure of similarity between two sets of state time courses.
322 |
323 | These can have different numbers of states, but they must have the same
324 | number of time points.
325 |
326 | Parameters:
327 | -----------
328 | gamma1 : numpy.ndarray
329 | First set of state time courses with shape (T, K).
330 | gamma2 : numpy.ndarray
331 | Second set of state time courses with shape (T, K2), where K2 may be different from K.
332 |
333 | Returns:
334 | --------
335 | S : float
336 | Similarity, measured as the sum of joint probabilities under the optimal state alignment.
337 | assig : numpy.ndarray
338 | Optimal state alignment for gamma2 (uses Munkres' algorithm).
339 | gamma2 : numpy.ndarray
340 | The second set of state time courses reordered to match gamma1.
341 | """
342 |
343 | T, K = gamma1.shape
344 | gamma1_0 = gamma1.copy()
345 | g = gamma2
346 | K2 = g.shape[1]
347 |
348 | if K < K2:
349 | gamma1 = np.hstack((gamma1_0, np.zeros((T, K2 - K))))
350 | K = K2
351 | elif K > K2:
352 | g = np.hstack((g, np.zeros((T, K - K2))))
353 |
354 | M = np.zeros((K, K)) # cost
355 |
356 | for k1 in range(K):
357 | for k2 in range(K):
358 | M[k1, k2] += (T - np.sum(np.minimum(gamma1[:, k1], g[:, k2]))) / T
359 |
360 | row_ind, col_ind = linear_sum_assignment(M)
361 | S = K - M[row_ind, col_ind].sum()
362 |
363 | gamma2 = g[:, col_ind]
364 |
365 | return S, col_ind, gamma2
366 |
367 |
368 |
--------------------------------------------------------------------------------
/docs/_build/html/glossary.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
118 |
122 |
123 |
124 |
126 | GLHMM 0.0.1 documentation
125 |
127 |
140 |
128 |
134 |
135 |
139 |
176 |
281 |
177 |
275 |
280 |
178 |
179 |
182 | Back to top
183 |
184 |
198 |
199 |
200 |
201 |
204 |
205 |
249 |
250 |
251 |
252 |
274 | Python Module Index
202 | 203 || 207 | | ||
| g | 210 | | |
| 214 | |
215 | glhmm | 216 | | 217 |
| 220 | |
221 | glhmm.auxiliary | 222 | | 223 |
| 226 | |
227 | glhmm.glhmm | 228 | | 229 |
| 232 | |
233 | glhmm.io_glhmm | 234 | | 235 |
| 238 | |
239 | glhmm.preproc | 240 | | 241 |
| 244 | |
245 | glhmm.utils | 246 | | 247 |
118 |
119 |
143 |
177 |
262 |
263 |
264 |
265 |
266 |
267 |
--------------------------------------------------------------------------------
/docs/_build/html/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
120 |
124 |
125 |
126 |
128 | GLHMM 0.0.1 documentation
127 |
129 |
142 |
130 |
136 |
137 |
141 |
178 |
261 |
179 |
255 |
260 |
180 |
181 |
184 | Back to top
185 |
186 |
201 |
202 |
203 |
219 |
220 |
221 |
222 |
254 | Glossary#
204 |-
205 |
- HMM#
Hidden Markov Model.
206 |
207 | - n_parcels#
The number of brain parcels/regions/seeds.
208 |
209 | - n_samples#
The number of total timepoints.
210 |
211 | - n_sessions#
The number of total sessions.
212 |
213 | - n_states#
The number of hidden states in the HMM.
214 |
215 | - state mixing#
Refers to whether the model is capable of capturing within-session state modulations, rather than assigning the entire sessions (or the largest part of them) to a single state. For more information visit Ahrends et al. (2022) article <https://pubmed.ncbi.nlm.nih.gov/35217207/>.
216 |
217 |
118 |
119 |
143 |
177 |
296 |
297 |
298 |
299 |
300 |
301 |
--------------------------------------------------------------------------------
/docs/_build/html/io_glhmm.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
120 |
124 |
125 |
126 |
128 | GLHMM 0.0.1 documentation
127 |
129 |
142 |
130 |
136 |
137 |
141 |
178 |
295 |
179 |
289 |
294 |
180 |
181 |
184 | Back to top
185 |
186 |
201 |
202 |
203 |
205 |
206 |
212 |
218 |
219 |
230 |
231 |
235 |
236 |
237 |
238 |
254 |
255 |
256 |
257 |
258 |
288 | #
204 |GLHMM#
207 |Gaussian Linear Hidden Markov Models:
208 |209 |211 |Warning: The documentation of this library is under heavy development
210 |
Important links#
213 |-
214 |
Official source code repo: https://github.com/vidaurre/glhmm
215 | HTML documentation (stable release): https://
216 |
Dependencies#
220 |The required dependencies to use glhmm are:
221 |-
222 |
Python >= 3.6
223 | NumPy
224 | scikit-learn
225 | scipy
226 | matplotlib
227 | numba
228 |
Installation#
232 |To install from the repo, use the following command:
233 |pip install --user git+https://github.com/vidaurre/glhmm
234 | Documentation#
239 |
240 |
253 | Contents:
241 |-
242 |
- API
-
243 |
- glhmm module 244 |
- io_glhmm module 245 |
- preproc module 246 |
- auxiliary module 247 |
- utils module 248 |
250 | - Glossary 251 |
118 |
119 |
143 |
177 |
290 |
291 |
292 |
293 |
294 |
295 |
--------------------------------------------------------------------------------
/glhmm/io.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | # -*- coding: utf-8 -*-
3 | """
4 | Input/output functions - Gaussian Linear Hidden Markov Model
5 | @author: Diego Vidaurre 2023
6 | """
7 |
8 | import numpy as np
9 | import scipy.special
10 | import scipy.io
11 | import pickle
12 | import os
13 | import warnings
14 | import h5py
15 |
16 | from glhmm import glhmm
17 | from glhmm import auxiliary
18 |
19 | def load_files(files,I=None,do_only_indices=False):
20 | """
21 | Loads data from files and returns the loaded data, indices, and individual indices for each file.
22 | """
23 |
24 | X = []
25 | Y = []
26 | indices = []
27 | indices_individual = []
28 | sum_T = 0
29 |
30 | if I is None:
31 | I = np.arange(len(files))
32 | elif type(I) is int:
33 | I = np.array([I])
34 |
35 | for ij in range(I.shape[0]):
36 |
37 | j = I[ij]
38 |
39 | # if type(files[j]) is tuple:
40 | # if len(files[j][0]) > 0: # X
41 | # if files[j][0][-4:] == '.npy':
42 | # X.append(np.load(files[j][0]))
43 | # elif files[j][0][-4:] == '.txt':
44 |
45 | if files[j][-4:] == '.mat':
46 | # depending on the matlab version used to create the data,
47 | #scipy.io or h5py will be used to load them
48 | try:
49 | dat = scipy.io.loadmat(files[j])
50 | except:
51 | dat = h5py.File(files[j],'r')
52 |
53 |
54 | elif files[j][-4:] == '.npz':
55 | dat = np.load(files[j])
56 |
57 | if not do_only_indices:
58 | if ('X' in dat) and (not 'Y' in dat):
59 | Y.append(np.array(dat["X"]))
60 | else:
61 | if 'X' in dat: X.append(np.array(dat["X"]))
62 | Y.append(np.array(dat["Y"]))
63 | if 'indices' in dat:
64 | ind = np.array(dat['indices'])
65 | elif 'T' in dat:
66 | ind = auxiliary.make_indices_from_T(np.array(dat['T']))
67 | else:
68 | ind = np.zeros((1,2)).astype(int)
69 | ind[0,0] = 0
70 | ind[0,1] = Y[-1].shape[0]
71 | if len(ind.shape) == 1: ind = np.expand_dims(ind,axis=0)
72 | indices_individual.append(ind)
73 | indices.append(ind + sum_T)
74 |
75 | sum_T += dat["Y"].shape[0]
76 |
77 | if not do_only_indices:
78 | if len(X) > 0: X = np.concatenate(X)
79 | Y = np.concatenate(Y)
80 | indices = np.concatenate(indices)
81 | if len(indices.shape) == 1: indices = np.expand_dims(indices,axis=0)
82 | if len(X) == 0: X = None
83 |
84 | return X,Y,indices,indices_individual
85 |
86 |
87 | def read_flattened_hmm_mat(file):
88 | """
89 | Reads a MATLAB file containing hidden Markov model (HMM) parameters from the HMM-MAR toolbox,
90 | and initializes a Gaussian linear hidden Markov model (GLHMM) using those parameters.
91 | """
92 | try:
93 | hmm_mat = scipy.io.loadmat(file,simplify_cells=True)
94 | except:
95 | hmm_mat = h5py.File(file,'r')
96 |
97 | try:
98 | K = int(hmm_mat["K"])
99 | except:
100 | hmm_mat = hmm_mat["hmm"]
101 | K = int(hmm_mat["K"])
102 |
103 | covtype = str(hmm_mat["train"]["covtype"])
104 | zeromean = int(hmm_mat["train"]["zeromean"])
105 | model_mean = 'state' if not zeromean else 'no'
106 |
107 |
108 | if not zeromean: model_mean = 'state'
109 | else: model_mean = 'no'
110 | if "state_0_Mu_W" in hmm_mat:
111 | if (model_mean == 'state') and (hmm_mat["state_0_Mu_W"].shape[0] == 1):
112 | model_beta = 'no'
113 | elif hmm_mat["state_0_Mu_W"].shape[0] == 0:
114 | model_beta = 'no'
115 | else:
116 | model_beta = 'state'
117 | else:
118 | model_beta = 'no'
119 | dirichlet_diag = int(hmm_mat["train"]["DirichletDiag"])
120 | Pstructure = np.array(hmm_mat["train"]["Pstructure"], dtype=bool)
121 | Pistructure = np.squeeze(np.array(hmm_mat["train"]["Pistructure"], dtype=bool))
122 | shared_covmat = (covtype == 'shareddiag') or (covtype == 'sharedfull')
123 | diagonal_covmat = (covtype == 'shareddiag') or (covtype == 'diag')
124 | # Only use S if diagonal; otherwise disable to avoid the warning.
125 | connectivity = np.array(hmm_mat["train"]["S"]) if diagonal_covmat else None
126 |
127 |
128 | # detect schema
129 | is_flat = (
130 | ("prior_Omega_Gam_rate" in hmm_mat) or
131 | ("state_0_prior_Omega_Gam_rate" in hmm_mat) or
132 | ("state_0_Mu_W" in hmm_mat)
133 | )
134 | is_nested = (("prior" in hmm_mat) or ("state" in hmm_mat))
135 |
136 |
137 | # prior over Omega
138 | if is_flat:
139 | if "prior_Omega_Gam_rate" in hmm_mat and "prior_Omega_Gam_shape" in hmm_mat:
140 | prior_Omega_Gam_rate = np.array(hmm_mat["prior_Omega_Gam_rate"])
141 | prior_Omega_Gam_shape = int(np.array(hmm_mat["prior_Omega_Gam_shape"]).squeeze())
142 | else:
143 | prior_Omega_Gam_rate = np.array(hmm_mat["state_0_prior_Omega_Gam_rate"])
144 | prior_Omega_Gam_shape = int(np.array(hmm_mat["state_0_prior_Omega_Gam_shape"]).squeeze())
145 | elif is_nested:
146 | if "prior" in hmm_mat and "Omega" in hmm_mat["prior"]:
147 | prior_Omega_Gam_rate = np.array(hmm_mat["prior"]["Omega"]["Gam_rate"])
148 | prior_Omega_Gam_shape = int(np.array(hmm_mat["prior"]["Omega"]["Gam_shape"]).squeeze())
149 | else:
150 | prior_Omega_Gam_rate = np.array(hmm_mat["state"][0]["prior"]["Omega"]["Gam_rate"])
151 | prior_Omega_Gam_shape = int(np.array(hmm_mat["state"][0]["prior"]["Omega"]["Gam_shape"]).squeeze())
152 | else:
153 | raise KeyError("Unrecognized HMM .mat schema.")
154 |
155 |
156 | if diagonal_covmat: prior_Omega_Gam_rate = np.squeeze(prior_Omega_Gam_rate)
157 | q = prior_Omega_Gam_rate.shape[0]
158 |
159 | # p
160 | if is_flat:
161 | p = hmm_mat["state_0_Mu_W"].shape[0] if "state_0_Mu_W" in hmm_mat else 0
162 | else:
163 | if "state" in hmm_mat and "W" in hmm_mat["state"][0] and "Mu_W" in hmm_mat["state"][0]["W"]:
164 | p = hmm_mat["state"][0]["W"]["Mu_W"].shape[0]
165 | else:
166 | p = 0
167 |
168 | hmm = glhmm.glhmm(
169 | K=K,
170 | covtype=covtype,
171 | model_mean=model_mean,
172 | model_beta=model_beta,
173 | dirichlet_diag=dirichlet_diag,
174 | connectivity=connectivity,
175 | Pstructure=Pstructure,
176 | Pistructure=Pistructure
177 | )
178 |
179 | # mean
180 | if model_mean == 'state':
181 | hmm.mean = []
182 | for k in range(K):
183 | hmm.mean.append({})
184 | if is_flat:
185 | Sigma_W = np.squeeze(hmm_mat[f"state_{k}_S_W"])
186 | Mu_W = np.squeeze(hmm_mat[f"state_{k}_Mu_W"])
187 | else:
188 | Sigma_W = np.squeeze(hmm_mat["state"][k]["W"]["S_W"])
189 | Mu_W = np.squeeze(hmm_mat["state"][k]["W"]["Mu_W"])
190 |
191 | if model_beta == 'state':
192 | if q==1: hmm.mean[k]["Mu"] = np.array(Mu_W[0])
193 | else: hmm.mean[k]["Mu"] = Mu_W[0,:]
194 | else:
195 | if q==1: hmm.mean[k]["Mu"] = np.array(Mu_W)
196 | else: hmm.mean[k]["Mu"] = Mu_W
197 | if diagonal_covmat:
198 | if model_beta == 'state':
199 | if q==1: hmm.mean[k]["Sigma"] = np.array([[Sigma_W[0,0]]])
200 | else: hmm.mean[k]["Sigma"] = np.diag(Sigma_W[:,0,0])
201 | else:
202 | if q==1: hmm.mean[k]["Sigma"] = np.array([[Sigma_W]])
203 | hmm.mean[k]["Sigma"] = np.diag(Sigma_W)
204 | else:
205 | if q==1: np.array([[Sigma_W[0,0]]])
206 | else: hmm.mean[k]["Sigma"] = Sigma_W[0:q,0:q]
207 |
208 | # beta
209 | if model_beta == 'state':
210 | if model_mean == 'state': j0 = 1
211 | else: j0 = 0
212 | hmm.beta = []
213 | for k in range(K):
214 | hmm.beta.append({})
215 | if is_flat:
216 | Sigma_W = np.array(hmm_mat[f"state_{k}_S_W"])
217 | Mu_W = np.array(hmm_mat[f"state_{k}_Mu_W"])
218 | else:
219 | Sigma_W = np.array(hmm_mat["state"][k]["W"]["S_W"])
220 | Mu_W = np.array(hmm_mat["state"][k]["W"]["Mu_W"])
221 | hmm.beta[k]["Mu"] = np.zeros((p,q))
222 | hmm.beta[k]["Mu"][:,:] = Mu_W[j0:,:]
223 | if diagonal_covmat:
224 | hmm.beta[k]["Sigma"] = np.zeros((p,p,q))
225 | if q==1:
226 | hmm.beta[k]["Sigma"][:,:,0] = Sigma_W[j0:,j0:]
227 | else:
228 | for j in range(q):
229 | hmm.beta[k]["Sigma"][:,:,j] = Sigma_W[j,j0:,j0:]
230 | else:
231 | hmm.beta[k]["Sigma"] = Sigma_W[(j0*q):,(j0*q):]
232 |
233 | hmm._glhmm__init_priors_sub(prior_Omega_Gam_rate,prior_Omega_Gam_shape,p,q)
234 | hmm._glhmm__update_priors()
235 |
236 | # covmatrix
237 | hmm.Sigma = []
238 | if diagonal_covmat and shared_covmat:
239 | hmm.Sigma.append({})
240 | hmm.Sigma[0]["rate"] = np.zeros(q)
241 | if is_flat:
242 | hmm.Sigma[0]["rate"][:] = np.array(hmm_mat["Omega_Gam_rate"])
243 | hmm.Sigma[0]["shape"] = int(np.array(hmm_mat["Omega_Gam_shape"]).squeeze())
244 | else:
245 | hmm.Sigma[0]["rate"][:] = np.array(hmm_mat["Omega"]["Gam_rate"])
246 | hmm.Sigma[0]["shape"] = int(np.array(hmm_mat["Omega"]["Gam_shape"]).squeeze())
247 |
248 | elif diagonal_covmat and not shared_covmat:
249 | for k in range(K):
250 | hmm.Sigma.append({})
251 | hmm.Sigma[k]["rate"] = np.zeros(q)
252 | if is_flat:
253 | hmm.Sigma[k]["rate"][:] = np.array(hmm_mat[f"state_{k}_Omega_Gam_rate"])
254 | hmm.Sigma[k]["shape"] = int(np.array(hmm_mat[f"state_{k}_Omega_Gam_shape"]).squeeze())
255 | else:
256 | hmm.Sigma[k]["rate"][:] = np.array(hmm_mat["state"][k]["Omega"]["Gam_rate"])
257 | hmm.Sigma[k]["shape"] = int(np.array(hmm_mat["state"][k]["Omega"]["Gam_shape"]).squeeze())
258 |
259 | hmm.Sigma[k]["rate"][:] = hmm_mat["state"][k]["Omega"]["Gam_rate"]
260 | hmm.Sigma[k]["shape"] = int(np.array(hmm_mat["state"][k]["Omega"]["Gam_shape"]))
261 | elif (not diagonal_covmat) and shared_covmat:
262 | hmm.Sigma.append({})
263 | if is_flat:
264 | hmm.Sigma[0]["rate"] = np.array(hmm_mat["Omega_Gam_rate"])
265 | hmm.Sigma[0]["irate"] = np.array(hmm_mat["Omega_Gam_irate"])
266 | hmm.Sigma[0]["shape"] = int(np.array(hmm_mat["Omega_Gam_shape"]).squeeze())
267 | else:
268 | hmm.Sigma[0]["rate"] = np.array(hmm_mat["Omega"]["Gam_rate"])
269 | hmm.Sigma[0]["irate"] = np.array(hmm_mat["Omega"]["Gam_irate"])
270 | hmm.Sigma[0]["shape"] = int(np.array(hmm_mat["Omega"]["Gam_shape"]).squeeze())
271 |
272 | else: # not diagonal_covmat and not shared_covmat
273 | for k in range(K):
274 | hmm.Sigma.append({})
275 | if is_flat:
276 | hmm.Sigma[k]["rate"] = np.array(hmm_mat[f"state_{k}_Omega_Gam_rate"])
277 | hmm.Sigma[k]["irate"] = np.array(hmm_mat[f"state_{k}_Omega_Gam_irate"])
278 | hmm.Sigma[k]["shape"] = int(np.array(hmm_mat[f"state_{k}_Omega_Gam_shape"]).squeeze())
279 | else:
280 | hmm.Sigma[k]["rate"] = np.array(hmm_mat["state"][k]["Omega"]["Gam_rate"])
281 | hmm.Sigma[k]["irate"] = np.array(hmm_mat["state"][k]["Omega"]["Gam_irate"])
282 | hmm.Sigma[k]["shape"] = int(np.array(hmm_mat["state"][k]["Omega"]["Gam_shape"]).squeeze())
283 |
284 | #hmm.init_dynamics()
285 | hmm.P = np.array(hmm_mat["P"])
286 | hmm.Pi = np.squeeze(hmm_mat["Pi"])
287 | hmm.Dir2d_alpha = np.array(hmm_mat["Dir2d_alpha"])
288 | hmm.Dir_alpha = np.squeeze(hmm_mat["Dir_alpha"])
289 |
290 | hmm.trained = True
291 |
292 | return hmm
293 |
294 |
295 | def save_hmm(hmm, filename, directory=None):
296 | """
297 | Save a glhmm object in the specified directory with the given filename.
298 |
299 | Parameters:
300 | -----------
301 | hmm (object)
302 | The glhmm object to be saved.
303 | filename (str)
304 | The name of the file to which the object will be saved.
305 | directory (str, optional), default=None:
306 | The directory where the file will be saved. If None, saves in the current working directory.
307 |
308 | """
309 | # Combine the directory path and filename
310 | if directory:
311 | # Ensure the directory exists, create it if not
312 | if not os.path.exists(directory):
313 | print(f"Created a folder here: {directory}")
314 | os.makedirs(directory)
315 | filepath = os.path.join(directory, filename)
316 |
317 | else:
318 | filepath = filename
319 |
320 | # Save the glhmm object to the specified file
321 | with open(filepath, 'wb') as outp: # Overwrites any existing file.
322 | pickle.dump(hmm, outp, pickle.HIGHEST_PROTOCOL)
323 |
324 | print(f"{filename} saved to: {filepath}") if directory else print(f"{filename} saved")
325 |
326 |
327 | def load_hmm(filename, directory=None):
328 | """
329 | Load a glhmm object from the specified file.
330 |
331 | Parameters:
332 | -----------
333 | filename (str):
334 | Name of the file containing the glhmm object.
335 | directory (str, optional), default=None:
336 | Directory where the file is located. If None, searches in the current working directory.
337 |
338 | Returns:
339 | --------
340 | glhmm : object
341 | Loaded glhmm object.
342 | """
343 | # Combine the directory path and filename
344 | if directory:
345 | filepath = os.path.join(directory, filename)
346 | else:
347 | filepath = filename
348 |
349 | # Check if the directory exists
350 | if directory and not os.path.exists(directory):
351 | warnings.warn(f"The specified directory '{directory}' does not exist.")
352 |
353 | # Load the glhmm object from the specified file
354 | with open(filepath, 'rb') as inp:
355 | hmm = pickle.load(inp)
356 | return hmm
357 |
358 |
359 |
360 | def save_statistics(data_dict, filename='statistics', directory=None, format='npy'):
361 | """
362 | Save statistics data to a file in the specified directory with optional format (npy or npz).
363 |
364 | Parameters
365 | ----------
366 | data_dict (dict):
367 | Dictionary containing statistics data to be saved.
368 | filename (str, optional), default='statistics':
369 | Name of the file.
370 | directory (str, optional), default=None:
371 | Directory path where the file will be saved (default is the current working directory).
372 | format (str, optional), default='npy':
373 | Serialization format ('npy' or 'npz').
374 | """
375 |
376 | # Construct the full file path
377 | if directory:
378 | # Ensure the directory exists, create it if not
379 | if not os.path.exists(directory):
380 | print(f"Created a folder here: {directory}")
381 | os.makedirs(directory)
382 | filepath = os.path.join(directory, f'{filename}.{format}')
383 | else:
384 | filepath = f'{filename}.{format}'
385 |
386 | # Save the dictionary to the file using the specified format
387 | if format == 'npy':
388 | np.save(filepath, data_dict)
389 | elif format == 'npz':
390 | np.savez(filepath, **data_dict)
391 | else:
392 | raise ValueError("Invalid format. Use 'npy' or 'npz'.")
393 | print(f"{filename}.{format} saved to: {filepath}") if directory else print(f"{filename}.{format} saved")
394 |
395 | def load_statistics(filename, directory=None):
396 | """
397 | Load statistics data from a file.
398 |
399 | Parameters
400 | ----------
401 | filename : str
402 | The name of the file containing the saved statistics data, with or without extension.
403 | load_directory (str, optional), default=None:
404 | The directory path where the file is located (default is the current working directory).
405 |
406 | Returns
407 | -------
408 | data_dict : dict
409 | The dictionary containing the loaded statistics data.
410 | """
411 | # Set default directory to current working directory if not provided
412 | directory = directory or os.getcwd()
413 |
414 | # Construct the full file path
415 | file_path = os.path.join(directory, filename)
416 |
417 | if not os.path.exists(file_path):
418 | # If the file with the given name does not exist, try adding '.npy' and '.npz' extensions
419 | file_path_npy = file_path + '.npy'
420 | file_path_npz = file_path + '.npz'
421 |
422 | if not (os.path.exists(file_path_npy) or os.path.exists(file_path_npz)):
423 | raise FileNotFoundError(f"File not found: {filename} or {filename}.npy or {filename}.npz")
424 |
425 | try:
426 | if os.path.exists(file_path):
427 | # If the file exists with the given name, use it
428 | # The .item() method extracts the single item from the loaded data.
429 | data_dict = np.load(file_path, allow_pickle=True).item()
430 | elif os.path.exists(file_path_npy):
431 | data_dict = np.load(file_path_npy, allow_pickle=True).item()
432 | elif os.path.exists(file_path_npz):
433 | loaded_data = np.load(file_path_npz, allow_pickle=True)
434 | data_dict = {key: loaded_data[key] for key in loaded_data.files}
435 | except Exception as e:
436 | raise ValueError(f"Error loading data from {filename}: {e}")
437 |
438 | return data_dict
439 |
440 |
441 |
--------------------------------------------------------------------------------
/docs/_build/html/_static/basic.css:
--------------------------------------------------------------------------------
1 | /*
2 | * basic.css
3 | * ~~~~~~~~~
4 | *
5 | * Sphinx stylesheet -- basic theme.
6 | *
7 | * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
8 | * :license: BSD, see LICENSE for details.
9 | *
10 | */
11 |
12 | /* -- main layout ----------------------------------------------------------- */
13 |
14 | div.clearer {
15 | clear: both;
16 | }
17 |
18 | div.section::after {
19 | display: block;
20 | content: '';
21 | clear: left;
22 | }
23 |
24 | /* -- relbar ---------------------------------------------------------------- */
25 |
26 | div.related {
27 | width: 100%;
28 | font-size: 90%;
29 | }
30 |
31 | div.related h3 {
32 | display: none;
33 | }
34 |
35 | div.related ul {
36 | margin: 0;
37 | padding: 0 0 0 10px;
38 | list-style: none;
39 | }
40 |
41 | div.related li {
42 | display: inline;
43 | }
44 |
45 | div.related li.right {
46 | float: right;
47 | margin-right: 5px;
48 | }
49 |
50 | /* -- sidebar --------------------------------------------------------------- */
51 |
52 | div.sphinxsidebarwrapper {
53 | padding: 10px 5px 0 10px;
54 | }
55 |
56 | div.sphinxsidebar {
57 | float: left;
58 | width: 230px;
59 | margin-left: -100%;
60 | font-size: 90%;
61 | word-wrap: break-word;
62 | overflow-wrap : break-word;
63 | }
64 |
65 | div.sphinxsidebar ul {
66 | list-style: none;
67 | }
68 |
69 | div.sphinxsidebar ul ul,
70 | div.sphinxsidebar ul.want-points {
71 | margin-left: 20px;
72 | list-style: square;
73 | }
74 |
75 | div.sphinxsidebar ul ul {
76 | margin-top: 0;
77 | margin-bottom: 0;
78 | }
79 |
80 | div.sphinxsidebar form {
81 | margin-top: 10px;
82 | }
83 |
84 | div.sphinxsidebar input {
85 | border: 1px solid #98dbcc;
86 | font-family: sans-serif;
87 | font-size: 1em;
88 | }
89 |
90 | div.sphinxsidebar #searchbox form.search {
91 | overflow: hidden;
92 | }
93 |
94 | div.sphinxsidebar #searchbox input[type="text"] {
95 | float: left;
96 | width: 80%;
97 | padding: 0.25em;
98 | box-sizing: border-box;
99 | }
100 |
101 | div.sphinxsidebar #searchbox input[type="submit"] {
102 | float: left;
103 | width: 20%;
104 | border-left: none;
105 | padding: 0.25em;
106 | box-sizing: border-box;
107 | }
108 |
109 |
110 | img {
111 | border: 0;
112 | max-width: 100%;
113 | }
114 |
115 | /* -- search page ----------------------------------------------------------- */
116 |
117 | ul.search {
118 | margin: 10px 0 0 20px;
119 | padding: 0;
120 | }
121 |
122 | ul.search li {
123 | padding: 5px 0 5px 20px;
124 | background-image: url(file.png);
125 | background-repeat: no-repeat;
126 | background-position: 0 7px;
127 | }
128 |
129 | ul.search li a {
130 | font-weight: bold;
131 | }
132 |
133 | ul.search li p.context {
134 | color: #888;
135 | margin: 2px 0 0 30px;
136 | text-align: left;
137 | }
138 |
139 | ul.keywordmatches li.goodmatch a {
140 | font-weight: bold;
141 | }
142 |
143 | /* -- index page ------------------------------------------------------------ */
144 |
145 | table.contentstable {
146 | width: 90%;
147 | margin-left: auto;
148 | margin-right: auto;
149 | }
150 |
151 | table.contentstable p.biglink {
152 | line-height: 150%;
153 | }
154 |
155 | a.biglink {
156 | font-size: 1.3em;
157 | }
158 |
159 | span.linkdescr {
160 | font-style: italic;
161 | padding-top: 5px;
162 | font-size: 90%;
163 | }
164 |
165 | /* -- general index --------------------------------------------------------- */
166 |
167 | table.indextable {
168 | width: 100%;
169 | }
170 |
171 | table.indextable td {
172 | text-align: left;
173 | vertical-align: top;
174 | }
175 |
176 | table.indextable ul {
177 | margin-top: 0;
178 | margin-bottom: 0;
179 | list-style-type: none;
180 | }
181 |
182 | table.indextable > tbody > tr > td > ul {
183 | padding-left: 0em;
184 | }
185 |
186 | table.indextable tr.pcap {
187 | height: 10px;
188 | }
189 |
190 | table.indextable tr.cap {
191 | margin-top: 10px;
192 | background-color: #f2f2f2;
193 | }
194 |
195 | img.toggler {
196 | margin-right: 3px;
197 | margin-top: 3px;
198 | cursor: pointer;
199 | }
200 |
201 | div.modindex-jumpbox {
202 | border-top: 1px solid #ddd;
203 | border-bottom: 1px solid #ddd;
204 | margin: 1em 0 1em 0;
205 | padding: 0.4em;
206 | }
207 |
208 | div.genindex-jumpbox {
209 | border-top: 1px solid #ddd;
210 | border-bottom: 1px solid #ddd;
211 | margin: 1em 0 1em 0;
212 | padding: 0.4em;
213 | }
214 |
215 | /* -- domain module index --------------------------------------------------- */
216 |
217 | table.modindextable td {
218 | padding: 2px;
219 | border-collapse: collapse;
220 | }
221 |
222 | /* -- general body styles --------------------------------------------------- */
223 |
224 | div.body {
225 | min-width: 360px;
226 | max-width: 800px;
227 | }
228 |
229 | div.body p, div.body dd, div.body li, div.body blockquote {
230 | -moz-hyphens: auto;
231 | -ms-hyphens: auto;
232 | -webkit-hyphens: auto;
233 | hyphens: auto;
234 | }
235 |
236 | a.headerlink {
237 | visibility: hidden;
238 | }
239 |
240 | h1:hover > a.headerlink,
241 | h2:hover > a.headerlink,
242 | h3:hover > a.headerlink,
243 | h4:hover > a.headerlink,
244 | h5:hover > a.headerlink,
245 | h6:hover > a.headerlink,
246 | dt:hover > a.headerlink,
247 | caption:hover > a.headerlink,
248 | p.caption:hover > a.headerlink,
249 | div.code-block-caption:hover > a.headerlink {
250 | visibility: visible;
251 | }
252 |
253 | div.body p.caption {
254 | text-align: inherit;
255 | }
256 |
257 | div.body td {
258 | text-align: left;
259 | }
260 |
261 | .first {
262 | margin-top: 0 !important;
263 | }
264 |
265 | p.rubric {
266 | margin-top: 30px;
267 | font-weight: bold;
268 | }
269 |
270 | img.align-left, figure.align-left, .figure.align-left, object.align-left {
271 | clear: left;
272 | float: left;
273 | margin-right: 1em;
274 | }
275 |
276 | img.align-right, figure.align-right, .figure.align-right, object.align-right {
277 | clear: right;
278 | float: right;
279 | margin-left: 1em;
280 | }
281 |
282 | img.align-center, figure.align-center, .figure.align-center, object.align-center {
283 | display: block;
284 | margin-left: auto;
285 | margin-right: auto;
286 | }
287 |
288 | img.align-default, figure.align-default, .figure.align-default {
289 | display: block;
290 | margin-left: auto;
291 | margin-right: auto;
292 | }
293 |
294 | .align-left {
295 | text-align: left;
296 | }
297 |
298 | .align-center {
299 | text-align: center;
300 | }
301 |
302 | .align-default {
303 | text-align: center;
304 | }
305 |
306 | .align-right {
307 | text-align: right;
308 | }
309 |
310 | /* -- sidebars -------------------------------------------------------------- */
311 |
312 | div.sidebar,
313 | aside.sidebar {
314 | margin: 0 0 0.5em 1em;
315 | border: 1px solid #ddb;
316 | padding: 7px;
317 | background-color: #ffe;
318 | width: 40%;
319 | float: right;
320 | clear: right;
321 | overflow-x: auto;
322 | }
323 |
324 | p.sidebar-title {
325 | font-weight: bold;
326 | }
327 |
328 | nav.contents,
329 | aside.topic,
330 | div.admonition, div.topic, blockquote {
331 | clear: left;
332 | }
333 |
334 | /* -- topics ---------------------------------------------------------------- */
335 |
336 | nav.contents,
337 | aside.topic,
338 | div.topic {
339 | border: 1px solid #ccc;
340 | padding: 7px;
341 | margin: 10px 0 10px 0;
342 | }
343 |
344 | p.topic-title {
345 | font-size: 1.1em;
346 | font-weight: bold;
347 | margin-top: 10px;
348 | }
349 |
350 | /* -- admonitions ----------------------------------------------------------- */
351 |
352 | div.admonition {
353 | margin-top: 10px;
354 | margin-bottom: 10px;
355 | padding: 7px;
356 | }
357 |
358 | div.admonition dt {
359 | font-weight: bold;
360 | }
361 |
362 | p.admonition-title {
363 | margin: 0px 10px 5px 0px;
364 | font-weight: bold;
365 | }
366 |
367 | div.body p.centered {
368 | text-align: center;
369 | margin-top: 25px;
370 | }
371 |
372 | /* -- content of sidebars/topics/admonitions -------------------------------- */
373 |
374 | div.sidebar > :last-child,
375 | aside.sidebar > :last-child,
376 | nav.contents > :last-child,
377 | aside.topic > :last-child,
378 | div.topic > :last-child,
379 | div.admonition > :last-child {
380 | margin-bottom: 0;
381 | }
382 |
383 | div.sidebar::after,
384 | aside.sidebar::after,
385 | nav.contents::after,
386 | aside.topic::after,
387 | div.topic::after,
388 | div.admonition::after,
389 | blockquote::after {
390 | display: block;
391 | content: '';
392 | clear: both;
393 | }
394 |
395 | /* -- tables ---------------------------------------------------------------- */
396 |
397 | table.docutils {
398 | margin-top: 10px;
399 | margin-bottom: 10px;
400 | border: 0;
401 | border-collapse: collapse;
402 | }
403 |
404 | table.align-center {
405 | margin-left: auto;
406 | margin-right: auto;
407 | }
408 |
409 | table.align-default {
410 | margin-left: auto;
411 | margin-right: auto;
412 | }
413 |
414 | table caption span.caption-number {
415 | font-style: italic;
416 | }
417 |
418 | table caption span.caption-text {
419 | }
420 |
421 | table.docutils td, table.docutils th {
422 | padding: 1px 8px 1px 5px;
423 | border-top: 0;
424 | border-left: 0;
425 | border-right: 0;
426 | border-bottom: 1px solid #aaa;
427 | }
428 |
429 | th {
430 | text-align: left;
431 | padding-right: 5px;
432 | }
433 |
434 | table.citation {
435 | border-left: solid 1px gray;
436 | margin-left: 1px;
437 | }
438 |
439 | table.citation td {
440 | border-bottom: none;
441 | }
442 |
443 | th > :first-child,
444 | td > :first-child {
445 | margin-top: 0px;
446 | }
447 |
448 | th > :last-child,
449 | td > :last-child {
450 | margin-bottom: 0px;
451 | }
452 |
453 | /* -- figures --------------------------------------------------------------- */
454 |
455 | div.figure, figure {
456 | margin: 0.5em;
457 | padding: 0.5em;
458 | }
459 |
460 | div.figure p.caption, figcaption {
461 | padding: 0.3em;
462 | }
463 |
464 | div.figure p.caption span.caption-number,
465 | figcaption span.caption-number {
466 | font-style: italic;
467 | }
468 |
469 | div.figure p.caption span.caption-text,
470 | figcaption span.caption-text {
471 | }
472 |
473 | /* -- field list styles ----------------------------------------------------- */
474 |
475 | table.field-list td, table.field-list th {
476 | border: 0 !important;
477 | }
478 |
479 | .field-list ul {
480 | margin: 0;
481 | padding-left: 1em;
482 | }
483 |
484 | .field-list p {
485 | margin: 0;
486 | }
487 |
488 | .field-name {
489 | -moz-hyphens: manual;
490 | -ms-hyphens: manual;
491 | -webkit-hyphens: manual;
492 | hyphens: manual;
493 | }
494 |
495 | /* -- hlist styles ---------------------------------------------------------- */
496 |
497 | table.hlist {
498 | margin: 1em 0;
499 | }
500 |
501 | table.hlist td {
502 | vertical-align: top;
503 | }
504 |
505 | /* -- object description styles --------------------------------------------- */
506 |
507 | .sig {
508 | font-family: 'Consolas', 'Menlo', 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', monospace;
509 | }
510 |
511 | .sig-name, code.descname {
512 | background-color: transparent;
513 | font-weight: bold;
514 | }
515 |
516 | .sig-name {
517 | font-size: 1.1em;
518 | }
519 |
520 | code.descname {
521 | font-size: 1.2em;
522 | }
523 |
524 | .sig-prename, code.descclassname {
525 | background-color: transparent;
526 | }
527 |
528 | .optional {
529 | font-size: 1.3em;
530 | }
531 |
532 | .sig-paren {
533 | font-size: larger;
534 | }
535 |
536 | .sig-param.n {
537 | font-style: italic;
538 | }
539 |
540 | /* C++ specific styling */
541 |
542 | .sig-inline.c-texpr,
543 | .sig-inline.cpp-texpr {
544 | font-family: unset;
545 | }
546 |
547 | .sig.c .k, .sig.c .kt,
548 | .sig.cpp .k, .sig.cpp .kt {
549 | color: #0033B3;
550 | }
551 |
552 | .sig.c .m,
553 | .sig.cpp .m {
554 | color: #1750EB;
555 | }
556 |
557 | .sig.c .s, .sig.c .sc,
558 | .sig.cpp .s, .sig.cpp .sc {
559 | color: #067D17;
560 | }
561 |
562 |
563 | /* -- other body styles ----------------------------------------------------- */
564 |
565 | ol.arabic {
566 | list-style: decimal;
567 | }
568 |
569 | ol.loweralpha {
570 | list-style: lower-alpha;
571 | }
572 |
573 | ol.upperalpha {
574 | list-style: upper-alpha;
575 | }
576 |
577 | ol.lowerroman {
578 | list-style: lower-roman;
579 | }
580 |
581 | ol.upperroman {
582 | list-style: upper-roman;
583 | }
584 |
585 | :not(li) > ol > li:first-child > :first-child,
586 | :not(li) > ul > li:first-child > :first-child {
587 | margin-top: 0px;
588 | }
589 |
590 | :not(li) > ol > li:last-child > :last-child,
591 | :not(li) > ul > li:last-child > :last-child {
592 | margin-bottom: 0px;
593 | }
594 |
595 | ol.simple ol p,
596 | ol.simple ul p,
597 | ul.simple ol p,
598 | ul.simple ul p {
599 | margin-top: 0;
600 | }
601 |
602 | ol.simple > li:not(:first-child) > p,
603 | ul.simple > li:not(:first-child) > p {
604 | margin-top: 0;
605 | }
606 |
607 | ol.simple p,
608 | ul.simple p {
609 | margin-bottom: 0;
610 | }
611 |
612 | aside.footnote > span,
613 | div.citation > span {
614 | float: left;
615 | }
616 | aside.footnote > span:last-of-type,
617 | div.citation > span:last-of-type {
618 | padding-right: 0.5em;
619 | }
620 | aside.footnote > p {
621 | margin-left: 2em;
622 | }
623 | div.citation > p {
624 | margin-left: 4em;
625 | }
626 | aside.footnote > p:last-of-type,
627 | div.citation > p:last-of-type {
628 | margin-bottom: 0em;
629 | }
630 | aside.footnote > p:last-of-type:after,
631 | div.citation > p:last-of-type:after {
632 | content: "";
633 | clear: both;
634 | }
635 |
636 | dl.field-list {
637 | display: grid;
638 | grid-template-columns: fit-content(30%) auto;
639 | }
640 |
641 | dl.field-list > dt {
642 | font-weight: bold;
643 | word-break: break-word;
644 | padding-left: 0.5em;
645 | padding-right: 5px;
646 | }
647 |
648 | dl.field-list > dd {
649 | padding-left: 0.5em;
650 | margin-top: 0em;
651 | margin-left: 0em;
652 | margin-bottom: 0em;
653 | }
654 |
655 | dl {
656 | margin-bottom: 15px;
657 | }
658 |
659 | dd > :first-child {
660 | margin-top: 0px;
661 | }
662 |
663 | dd ul, dd table {
664 | margin-bottom: 10px;
665 | }
666 |
667 | dd {
668 | margin-top: 3px;
669 | margin-bottom: 10px;
670 | margin-left: 30px;
671 | }
672 |
673 | dl > dd:last-child,
674 | dl > dd:last-child > :last-child {
675 | margin-bottom: 0;
676 | }
677 |
678 | dt:target, span.highlighted {
679 | background-color: #fbe54e;
680 | }
681 |
682 | rect.highlighted {
683 | fill: #fbe54e;
684 | }
685 |
686 | dl.glossary dt {
687 | font-weight: bold;
688 | font-size: 1.1em;
689 | }
690 |
691 | .versionmodified {
692 | font-style: italic;
693 | }
694 |
695 | .system-message {
696 | background-color: #fda;
697 | padding: 5px;
698 | border: 3px solid red;
699 | }
700 |
701 | .footnote:target {
702 | background-color: #ffa;
703 | }
704 |
705 | .line-block {
706 | display: block;
707 | margin-top: 1em;
708 | margin-bottom: 1em;
709 | }
710 |
711 | .line-block .line-block {
712 | margin-top: 0;
713 | margin-bottom: 0;
714 | margin-left: 1.5em;
715 | }
716 |
717 | .guilabel, .menuselection {
718 | font-family: sans-serif;
719 | }
720 |
721 | .accelerator {
722 | text-decoration: underline;
723 | }
724 |
725 | .classifier {
726 | font-style: oblique;
727 | }
728 |
729 | .classifier:before {
730 | font-style: normal;
731 | margin: 0 0.5em;
732 | content: ":";
733 | display: inline-block;
734 | }
735 |
736 | abbr, acronym {
737 | border-bottom: dotted 1px;
738 | cursor: help;
739 | }
740 |
741 | /* -- code displays --------------------------------------------------------- */
742 |
743 | pre {
744 | overflow: auto;
745 | overflow-y: hidden; /* fixes display issues on Chrome browsers */
746 | }
747 |
748 | pre, div[class*="highlight-"] {
749 | clear: both;
750 | }
751 |
752 | span.pre {
753 | -moz-hyphens: none;
754 | -ms-hyphens: none;
755 | -webkit-hyphens: none;
756 | hyphens: none;
757 | white-space: nowrap;
758 | }
759 |
760 | div[class*="highlight-"] {
761 | margin: 1em 0;
762 | }
763 |
764 | td.linenos pre {
765 | border: 0;
766 | background-color: transparent;
767 | color: #aaa;
768 | }
769 |
770 | table.highlighttable {
771 | display: block;
772 | }
773 |
774 | table.highlighttable tbody {
775 | display: block;
776 | }
777 |
778 | table.highlighttable tr {
779 | display: flex;
780 | }
781 |
782 | table.highlighttable td {
783 | margin: 0;
784 | padding: 0;
785 | }
786 |
787 | table.highlighttable td.linenos {
788 | padding-right: 0.5em;
789 | }
790 |
791 | table.highlighttable td.code {
792 | flex: 1;
793 | overflow: hidden;
794 | }
795 |
796 | .highlight .hll {
797 | display: block;
798 | }
799 |
800 | div.highlight pre,
801 | table.highlighttable pre {
802 | margin: 0;
803 | }
804 |
805 | div.code-block-caption + div {
806 | margin-top: 0;
807 | }
808 |
809 | div.code-block-caption {
810 | margin-top: 1em;
811 | padding: 2px 5px;
812 | font-size: small;
813 | }
814 |
815 | div.code-block-caption code {
816 | background-color: transparent;
817 | }
818 |
819 | table.highlighttable td.linenos,
820 | span.linenos,
821 | div.highlight span.gp { /* gp: Generic.Prompt */
822 | user-select: none;
823 | -webkit-user-select: text; /* Safari fallback only */
824 | -webkit-user-select: none; /* Chrome/Safari */
825 | -moz-user-select: none; /* Firefox */
826 | -ms-user-select: none; /* IE10+ */
827 | }
828 |
829 | div.code-block-caption span.caption-number {
830 | padding: 0.1em 0.3em;
831 | font-style: italic;
832 | }
833 |
834 | div.code-block-caption span.caption-text {
835 | }
836 |
837 | div.literal-block-wrapper {
838 | margin: 1em 0;
839 | }
840 |
841 | code.xref, a code {
842 | background-color: transparent;
843 | font-weight: bold;
844 | }
845 |
846 | h1 code, h2 code, h3 code, h4 code, h5 code, h6 code {
847 | background-color: transparent;
848 | }
849 |
850 | .viewcode-link {
851 | float: right;
852 | }
853 |
854 | .viewcode-back {
855 | float: right;
856 | font-family: sans-serif;
857 | }
858 |
859 | div.viewcode-block:target {
860 | margin: -1px -10px;
861 | padding: 0 10px;
862 | }
863 |
864 | /* -- math display ---------------------------------------------------------- */
865 |
866 | img.math {
867 | vertical-align: middle;
868 | }
869 |
870 | div.body div.math p {
871 | text-align: center;
872 | }
873 |
874 | span.eqno {
875 | float: right;
876 | }
877 |
878 | span.eqno a.headerlink {
879 | position: absolute;
880 | z-index: 1;
881 | }
882 |
883 | div.math:hover a.headerlink {
884 | visibility: visible;
885 | }
886 |
887 | /* -- printout stylesheet --------------------------------------------------- */
888 |
889 | @media print {
890 | div.document,
891 | div.documentwrapper,
892 | div.bodywrapper {
893 | margin: 0 !important;
894 | width: 100%;
895 | }
896 |
897 | div.sphinxsidebar,
898 | div.related,
899 | div.footer,
900 | #top-link {
901 | display: none;
902 | }
903 | }
--------------------------------------------------------------------------------
120 |
124 |
125 |
126 |
128 | GLHMM 0.0.1 documentation
127 |
129 |
142 |
130 |
136 |
137 |
141 |
178 |
289 |
179 |
263 |
288 |
180 |
181 |
184 | Back to top
185 |
186 |
201 |
202 |
203 |
219 |
220 |
221 |
222 |
262 | io_glhmm module#
204 |Input/output functions - Gaussian Linear Hidden Markov Model 205 | @author: Diego Vidaurre 2023
206 | 211 | 212 | 217 | 218 |