sporada/nopaque
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git synced 2025-08-02 16:55:18 +00:00
Code Issues Projects Releases Wiki Activity

Visualization Testing Corpus Analysis

Browse Source
This commit is contained in:
Inga Kirschnick
2023-06-13 15:41:34 +02:00
parent b7ca2a2cf6
commit cc508cf4eb
6 changed files with 260 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
app/static/js/CorpusAnalysis/CQiClient.js
View File

@@ -100,7 +100,69 @@ class CQiCorpus {
getCorpusData() {
return new Promise((resolve, reject) => {
const dummyData = {};
const dummyData = {
"num_tokens": 2000, // number of tokens in the corpus
"num_unique_words": 500, // number of unique words in the corpus
"num_unique_lemmas": 200, // number of unique lemmas in the corpus
"num_sentences": 90, // number of sentences in the corpus
"average_sentence_length": 11, // average number of tokens per sentence in the corpus
"num_ent_types": 30, // number of entities in the corpus
"num_unique_ent_types":10,
"ent_type_freqs": {
"str": 10, // number of ent_types with ent_type "str"
// ...
},
"texts": [
{
"num_tokens": 11, // number of tokens in the text
"num_unique_words": 12, // number of unique words in the text
"word_freqs": { // frequency of unique words in the text (sorted by frequency)
"str": "int", // number of tokens with word "str"
// ...
},
"num_unique_lemmas": 15, // number of unique lemmas in the text
"lemma_freqs": { // frequency of unique lemmas in the text (sorted by frequency)
"str": "int", // number of tokens with lemma "str"
// ...
},
"num_sentences": 4, // number of sentences in the text
"average_sentence_length": 3, // average number of tokens per sentence in the text
"num_ent_types": 12, // number of ent_types in the text
"num_unique_ent_types": 28, // number of unique ent_types in the text
"num_entities_by_id": {
"1": "int", // number of entities with id 1
// ...
},
"author": "Author Name",
"title": "Titel",
"publishing_year": 1950
},
{
"num_tokens": 800, // number of tokens in the text
"num_unique_words": 60, // number of unique words in the text
"word_freqs": { // frequency of unique words in the text (sorted by frequency)
"testwort": 50, // number of tokens with word "str"
"testwort2": 1
},
"num_unique_lemmas": 15, // number of unique lemmas in the text
"lemma_freqs": { // frequency of unique lemmas in the text (sorted by frequency)
"testlemma": 11, // number of tokens with lemma "str"
"testlemma2": 1
},
"num_sentences": 90, // number of sentences in the text
"average_sentence_length": 7, // average number of tokens per sentence in the text
"num_ent_types": 19,
"num_unique_ent_types": 5, // number of unique ent_types in the text
"num_entities_by_id": {
"1": "int", // number of entities with id 1
// ...
},
"author": "Author Name 2",
"title": "Titel 2",
"publishing_year": 1951
}
]
};
resolve(dummyData);
/*

46
app/static/js/CorpusAnalysis/CorpusAnalysisApp.js
View File

@@ -25,7 +25,6 @@ class CorpusAnalysisApp {
init() {
this.disableActionElements();
this.elements.m.initModal.open();
// Init data
this.data.cQiClient = new CQiClient(this.settings.corpusId);
this.data.cQiClient.connect()
@@ -35,7 +34,13 @@ class CorpusAnalysisApp {
.then(
cQiCorpus => {
this.data.corpus = {o: cQiCorpus};
// TODO: Don't do this here
this.data.corpus.o.getCorpusData()
.then(corpusData => {
this.renderGeneralCorpusInfo(corpusData);
this.renderTextInfoList(corpusData);
this.renderTextProportionsGraphic(corpusData);
});
// TODO: Don't do this hgere
cQiCorpus.updateDb();
this.enableActionElements();
for (let extension of Object.values(this.extensions)) {extension.init();}
@@ -52,6 +57,7 @@ class CorpusAnalysisApp {
}
}
);
// Add event listeners
for (let extensionSelectorElement of this.elements.overview.querySelectorAll('.extension-selector')) {
@@ -95,4 +101,40 @@ class CorpusAnalysisApp {
}
}
}
renderGeneralCorpusInfo(corpusData) {
let corpusGeneralInfoListElement = document.querySelector('.corpus-general-info-list');
corpusGeneralInfoListElement.querySelector('.corpus-num-tokens').innerHTML = `<b>Number of tokens:</b> ${this.data.corpus.o.size}`;
corpusGeneralInfoListElement.querySelector('.corpus-text-count').innerHTML = `<b>Corpus text count:</b> ${corpusData.texts.length}`;
corpusGeneralInfoListElement.querySelector('.corpus-num-unique-words').innerHTML = `<b>Corpus unique word count:</b> ${corpusData.num_unique_words}`;
corpusGeneralInfoListElement.querySelector('.corpus-num-unique-lemmas').innerHTML = `<b>Corpus unique lemma count:</b> ${corpusData.num_unique_lemmas}`;
// corpusGeneralInfoListElement.querySelector('.corpus-most-frequent-words').innerHTML = `<b>Corpus most frequent words:</b> ${corpusData.most_frequent_words.join(', ');
corpusGeneralInfoListElement.querySelector('.corpus-num-sentences').innerHTML = `<b>Corpus sentence count:</b> ${corpusData.num_sentences}`;
corpusGeneralInfoListElement.querySelector('.corpus-average-sentence-length').innerHTML = `<b>Corpus average sentence length:</b> ${corpusData.average_sentence_length}`;
corpusGeneralInfoListElement.querySelector('.corpus-num-ent-types').innerHTML = `<b>Corpus entity count:</b> ${corpusData.num_ent_types}`;
corpusGeneralInfoListElement.querySelector('.corpus-num-unique-ent-types').innerHTML = `<b>Corpus unique entity count:</b> ${corpusData.num_unique_ent_types}`;
}
renderTextInfoList(corpusData) {
let corpusTextInfoListElement = document.querySelector('.corpus-text-info-list');
let corpusTextInfoList = new CorpusTextInfoList(corpusTextInfoListElement);
corpusTextInfoList.add(corpusData.texts);
}
renderTextProportionsGraphic(corpusData) {
let textProportionsGraphicElement = document.querySelector('#text-proportions-graphic');
let graphData = [
{
values: corpusData.texts.map(text => text.num_tokens),
labels: corpusData.texts.map(text => `${text.title} (${text.publishing_year})`),
type: 'pie'
}
];
let graphLayout = {
height: 400,
width: 500
};
Plotly.newPlot(textProportionsGraphicElement, graphData, graphLayout);
}
}