mirror of
https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git
synced 2025-11-04 12:22:47 +00:00
visualization testing
This commit is contained in:
Inga Kirschnick
@@ -101,164 +101,188 @@ class CQiCorpus {
|
||||
getCorpusData() {
|
||||
return new Promise((resolve, reject) => {
|
||||
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"
|
||||
// ...
|
||||
"corpus": {
|
||||
"bounds": [1, 689],
|
||||
"counts": {
|
||||
"token": 743,
|
||||
"ent": 321,
|
||||
"s": 234
|
||||
},
|
||||
"freqs": {
|
||||
"word": {
|
||||
"1": 876,
|
||||
"2": 234,
|
||||
"3": 657
|
||||
},
|
||||
"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"
|
||||
// ...
|
||||
"lemma": {
|
||||
"1": 543,
|
||||
"2": 876,
|
||||
"3": 321
|
||||
},
|
||||
"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": 15, // number of tokens in the text
|
||||
"num_unique_words": 4, // 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": 90, // 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": 11, // number of sentences in the text
|
||||
"average_sentence_length": 3, // average number of tokens per sentence in the text
|
||||
"num_ent_types": 4, // number of ent_types in the text
|
||||
"num_unique_ent_types": 300, // 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 1",
|
||||
"publishing_year": 1962
|
||||
},
|
||||
{
|
||||
"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": 64, // 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": 52, // number of sentences in the text
|
||||
"average_sentence_length": 3, // average number of tokens per sentence in the text
|
||||
"num_ent_types": 45, // number of ent_types in the text
|
||||
"num_unique_ent_types": 68, // 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 2",
|
||||
"publishing_year": 1850
|
||||
},
|
||||
{
|
||||
"num_tokens": 56, // number of tokens in the text
|
||||
"num_unique_words": 13, // 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": 43, // 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": 45, // number of sentences in the text
|
||||
"average_sentence_length": 56, // average number of tokens per sentence in the text
|
||||
"num_ent_types": 8792, // number of ent_types in the text
|
||||
"num_unique_ent_types": 56758, // 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 3",
|
||||
"publishing_year": 1504
|
||||
},
|
||||
{
|
||||
"num_tokens": 54345, // number of tokens in the text
|
||||
"num_unique_words": 561, // 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": 546, // 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": 5427, // number of sentences in the text
|
||||
"average_sentence_length": 657, // average number of tokens per sentence in the text
|
||||
"num_ent_types": 3465, // number of ent_types in the text
|
||||
"num_unique_ent_types": 45, // 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 4",
|
||||
"publishing_year": 1712
|
||||
},
|
||||
{
|
||||
"num_tokens": 4354, // number of tokens in the text
|
||||
"num_unique_words": 45234, // 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 5",
|
||||
"publishing_year": 1951
|
||||
"pos": {
|
||||
"1": 456,
|
||||
"2": 789,
|
||||
"3": 234
|
||||
},
|
||||
"simple_pos": {
|
||||
"1": 987,
|
||||
"2": 876,
|
||||
"3": 543
|
||||
},
|
||||
"ent": {
|
||||
"1": 654,
|
||||
"2": 321,
|
||||
"3": 987
|
||||
}
|
||||
}
|
||||
]
|
||||
};
|
||||
},
|
||||
"text": {
|
||||
"1": {
|
||||
"bounds": [0, 435],
|
||||
"counts": {
|
||||
"token": 345,
|
||||
"ent_type": 123,
|
||||
"s": 89
|
||||
},
|
||||
"freqs": {
|
||||
"word": {
|
||||
"1": 25,
|
||||
"2": 90,
|
||||
"3": 200
|
||||
},
|
||||
"lemma": {
|
||||
"1": 654,
|
||||
"2": 321,
|
||||
"3": 987
|
||||
},
|
||||
"pos": {
|
||||
"1": 543,
|
||||
"2": 876,
|
||||
"3": 234
|
||||
},
|
||||
"simple_pos": {
|
||||
"1": 987,
|
||||
"2": 654,
|
||||
"3": 321
|
||||
},
|
||||
"ent_type": {
|
||||
"1": 234,
|
||||
"2": 789,
|
||||
"3": 543
|
||||
}
|
||||
},
|
||||
"values": {
|
||||
"author": 1,
|
||||
"publishing_year":1950,
|
||||
"title": 1
|
||||
}
|
||||
},
|
||||
"2": {
|
||||
"bounds": [435, 689],
|
||||
"counts": {
|
||||
"token": 389,
|
||||
"ent_type": 198,
|
||||
"s": 145
|
||||
},
|
||||
"freqs": {
|
||||
"word": {
|
||||
"1": 60,
|
||||
"2": 70,
|
||||
"3": 100
|
||||
},
|
||||
"lemma": {
|
||||
"1": 654,
|
||||
"2": 321,
|
||||
"3": 987
|
||||
},
|
||||
"pos": {
|
||||
"1": 543,
|
||||
"2": 876,
|
||||
"3": 234
|
||||
},
|
||||
"simple_pos": {
|
||||
"1": 987,
|
||||
"2": 654,
|
||||
"3": 321
|
||||
},
|
||||
"ent_type": {
|
||||
"1": 234,
|
||||
"2": 789,
|
||||
"3": 543
|
||||
}
|
||||
},
|
||||
"values": {
|
||||
"author": 2,
|
||||
"publishing_year":1951,
|
||||
"title": 2
|
||||
}
|
||||
}
|
||||
},
|
||||
"s": {
|
||||
"1": {
|
||||
"bounds": [345, 678]
|
||||
}
|
||||
},
|
||||
"ent": {
|
||||
"1": {
|
||||
"bounds": [567, 890],
|
||||
"values": {
|
||||
"type": 789
|
||||
}
|
||||
}
|
||||
},
|
||||
"token": {
|
||||
"310": {
|
||||
"values": {
|
||||
"word": 1,
|
||||
"lemma": 2,
|
||||
"pos": 1,
|
||||
"simple_pos": 1
|
||||
}
|
||||
}
|
||||
},
|
||||
"value_lookups": {
|
||||
"text": {
|
||||
"author": {
|
||||
"1": "John Doe",
|
||||
"2": "Jane Smith"
|
||||
},
|
||||
"title": {
|
||||
"1": "Test Title 1",
|
||||
"2": "Test Title 2"
|
||||
}
|
||||
},
|
||||
"ent": {
|
||||
"type": {
|
||||
"1": "Person",
|
||||
"2": "Organization"
|
||||
}
|
||||
},
|
||||
"token": {
|
||||
"word": {
|
||||
"1": "apple",
|
||||
"2": "banana",
|
||||
"3": "orange"
|
||||
},
|
||||
"lemma": {
|
||||
"1": "run",
|
||||
"2": "walk",
|
||||
"3": "jump"
|
||||
},
|
||||
"pos": {
|
||||
"1": "noun",
|
||||
"2": "verb",
|
||||
"3": "adjective"
|
||||
},
|
||||
"simple_pos": {
|
||||
"1": "subject",
|
||||
"2": "object",
|
||||
"3": "predicate"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
resolve(dummyData);
|
||||
/*
|
||||
|
||||
@@ -39,6 +39,8 @@ class CorpusAnalysisApp {
|
||||
this.renderGeneralCorpusInfo(corpusData);
|
||||
this.renderTextInfoList(corpusData);
|
||||
this.renderTextProportionsGraphic(corpusData);
|
||||
this.renderWordFrequenciesGraphic(corpusData);
|
||||
this.renderWordDistributionsGraphic(corpusData);
|
||||
});
|
||||
// TODO: Don't do this hgere
|
||||
cQiCorpus.updateDb();
|
||||
@@ -103,38 +105,85 @@ 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}`;
|
||||
document.querySelector('.corpus-num-tokens').innerHTML = corpusData.corpus.counts.token;
|
||||
document.querySelector('.corpus-num-s').innerHTML = corpusData.corpus.counts.s;
|
||||
// corpusGeneralInfoListElement.querySelector('.corpus-text-count').innerHTML = <b>Corpus text count:</b> ${Object.entries(corpusData.text).length;
|
||||
document.querySelector('.corpus-num-unique-words').innerHTML = Object.entries(corpusData.corpus.freqs.word).length;
|
||||
document.querySelector('.corpus-num-unique-lemmas').innerHTML = Object.entries(corpusData.corpus.freqs.lemma).length;
|
||||
document.querySelector('.corpus-num-unique-pos').innerHTML = Object.entries(corpusData.corpus.freqs.pos).length;
|
||||
document.querySelector('.corpus-num-unique-simple-pos').innerHTML = Object.entries(corpusData.corpus.freqs.simple_pos).length;
|
||||
}
|
||||
|
||||
renderTextInfoList(corpusData) {
|
||||
let corpusTextInfoListElement = document.querySelector('.corpus-text-info-list');
|
||||
let corpusTextInfoList = new CorpusTextInfoList(corpusTextInfoListElement);
|
||||
corpusTextInfoList.add(corpusData.texts);
|
||||
|
||||
// let corpusTextInfoListElement = document.querySelector('.corpus-text-info-list');
|
||||
// let corpusTextInfoList = new CorpusTextInfoList(corpusTextInfoListElement);
|
||||
// for (let text of Object.values(corpusData.text)) {
|
||||
// text.values.title = corpusData.value_lookups.text.title[text.values.title];
|
||||
// }
|
||||
// corpusTextInfoList.add(Object.values(corpusData.text));
|
||||
|
||||
// let textCountChipElement = document.querySelector('.text-count-chip');
|
||||
// textCountChipElement.innerHTML = `Text count: ${Object.values(corpusData.text).length}`;
|
||||
}
|
||||
|
||||
renderTextProportionsGraphic(corpusData) {
|
||||
let textProportionsGraphicElement = document.querySelector('#text-proportions-graphic');
|
||||
let graphData = [
|
||||
{
|
||||
values: corpusData.texts.map(text => text.num_tokens),
|
||||
labels: corpusData.texts.map(text => `${text.title} (${text.publishing_year})`),
|
||||
type: 'pie'
|
||||
}
|
||||
];
|
||||
let graphLayout = {
|
||||
height: 400,
|
||||
width: 500
|
||||
};
|
||||
Plotly.newPlot(textProportionsGraphicElement, graphData, graphLayout);
|
||||
// let textProportionsGraphicElement = document.querySelector('#text-proportions-graphic');
|
||||
// let texts = Object.values(corpusData.text);
|
||||
// let graphData = [
|
||||
// {
|
||||
// values: texts.map(text => text.counts.token),
|
||||
// labels: texts.map(text => `${text.values.title} (${text.values.publishing_year})`),
|
||||
// type: 'pie'
|
||||
// }
|
||||
// ];
|
||||
// let graphLayout = {
|
||||
// height: 400,
|
||||
// width: 500
|
||||
// };
|
||||
// Plotly.newPlot(textProportionsGraphicElement, graphData, graphLayout);
|
||||
}
|
||||
|
||||
renderWordFrequenciesGraphic(corpusData) {
|
||||
// let wordFrequenciesGraphicElement = document.querySelector('#word-frequencies-graphic');
|
||||
// let words = Object.entries(corpusData.value_lookups.token.word);
|
||||
// let texts = Object.values(corpusData.text);
|
||||
// let graphData = [];
|
||||
// for (let word of words) {
|
||||
// let data = {
|
||||
// x: texts.map(text => `${text.values.title} (${text.values.publishing_year})`),
|
||||
// y: texts.map(text => text.freqs.word[word[0]]),
|
||||
// name: word[1],
|
||||
// type: 'bar'
|
||||
// };
|
||||
// graphData.push(data);
|
||||
// }
|
||||
|
||||
// let graphLayout = {
|
||||
// height: 400,
|
||||
// width: 500,
|
||||
// barmode: 'stack',
|
||||
// type: 'bar'
|
||||
// };
|
||||
// Plotly.newPlot(wordFrequenciesGraphicElement, graphData, graphLayout);
|
||||
}
|
||||
|
||||
renderWordDistributionsGraphic(corpusData) {
|
||||
// let wordDistributionGraphicElement = document.querySelector('#word-distributions-graphic');
|
||||
// var trace1 = {
|
||||
// x: [1, 2, 3, 4],
|
||||
// y: [10, 11, 12, 13],
|
||||
// mode: 'markers',
|
||||
// marker: {
|
||||
// size: [40, 60, 80, 100]
|
||||
// }
|
||||
// };
|
||||
// var data = [trace1];
|
||||
// var layout = {
|
||||
// title: 'Marker Size',
|
||||
// showlegend: false,
|
||||
// height: 600,
|
||||
// width: 600
|
||||
// };
|
||||
// Plotly.newPlot(wordDistributionGraphicElement, data, layout);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -29,11 +29,11 @@ class CorpusTextInfoList extends ResourceList {
|
||||
<tr class="list-item clickable hoverable">
|
||||
<td><span class="title"></span> (<span class="publishing_year"></span>)</td>
|
||||
<td><span class="num_tokens"></span></td>
|
||||
<td><span class="num_sentences"></span></td>
|
||||
<td><span class="num_unique_words"></span></td>
|
||||
<td><span class="num_unique_lemmas"></span></td>
|
||||
<td><span class="num_sentences"></span></td>
|
||||
<td><span class="average_sentence_length"></span></td>
|
||||
<td><span class="num_unique_ent_types"></span></td>
|
||||
<td><span class="num_unique_pos"></span></td>
|
||||
<td><span class="num_unique_simple_pos"></span></td>
|
||||
</tr>
|
||||
`.trim();
|
||||
}
|
||||
@@ -44,11 +44,11 @@ class CorpusTextInfoList extends ResourceList {
|
||||
'title',
|
||||
'publishing_year',
|
||||
'num_tokens',
|
||||
'num_sentences',
|
||||
'num_unique_words',
|
||||
'num_unique_lemmas',
|
||||
'num_sentences',
|
||||
'average_sentence_length',
|
||||
'num_unique_ent_types'
|
||||
'num_unique_pos',
|
||||
'num_unique_simple_pos'
|
||||
];
|
||||
}
|
||||
|
||||
@@ -68,11 +68,11 @@ class CorpusTextInfoList extends ResourceList {
|
||||
<tr>
|
||||
<th>Text<span class="sort right material-icons" data-sort="title" style="cursor:pointer; color:#aa9cc9">arrow_drop_down</span></th>
|
||||
<th>Number of tokens<span class="sort right material-icons" data-sort="num_tokens" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
<th>Number of sentences<span class="sort right material-icons" data-sort="num_sentences" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
<th>Number of unique words<span class="sort right material-icons" data-sort="num_unique_words" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
<th>Number of unique lemmas<span class="sort right material-icons" data-sort="num_unique_lemmas" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
<th>Number of sentences<span class="sort right material-icons" data-sort="num_sentences" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
<th>Average sentence length<span class="sort right material-icons" data-sort="average_sentence_length" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
<th>Number of unique entity types<span class="sort right material-icons" data-sort="num_unique_ent_types" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
<th>Number of unique pos<span class="sort right material-icons" data-sort="num_unique_pos" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
<th>Number of unique simple pos<span class="sort right material-icons" data-sort="num_unique_simple_pos" style="cursor:pointer">arrow_drop_down</span></th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody class="list"></tbody>
|
||||
@@ -83,14 +83,14 @@ class CorpusTextInfoList extends ResourceList {
|
||||
|
||||
mapResourceToValue(corpusTextData) {
|
||||
return {
|
||||
title: corpusTextData.title,
|
||||
publishing_year: corpusTextData.publishing_year,
|
||||
num_tokens: corpusTextData.num_tokens,
|
||||
num_unique_words: corpusTextData.num_unique_words,
|
||||
num_unique_lemmas: corpusTextData.num_unique_lemmas,
|
||||
num_sentences: corpusTextData.num_sentences,
|
||||
average_sentence_length: corpusTextData.average_sentence_length,
|
||||
num_unique_ent_types: corpusTextData.num_unique_ent_types
|
||||
title: corpusTextData.values.title,
|
||||
publishing_year: corpusTextData.values.publishing_year,
|
||||
num_tokens: corpusTextData.counts.token,
|
||||
num_sentences: corpusTextData.counts.s,
|
||||
num_unique_words: Object.entries(corpusTextData.freqs.word).length,
|
||||
num_unique_lemmas: Object.entries(corpusTextData.freqs.lemma).length,
|
||||
num_unique_pos: Object.entries(corpusTextData.freqs.pos).length,
|
||||
num_unique_simple_pos: Object.entries(corpusTextData.freqs.simple_pos).length
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user