sporada/nopaque
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git synced 2025-01-18 14:00:33 +00:00
Code Issues Projects Releases Wiki Activity

Compare commits

base: sporada:11b697145b3c7096e8e505ef93f3d94350ad503e
Branches Tags
sporada:master
sporada:development
sporada:manual
sporada:access-pipeline
sporada:prototype
sporada:1.1.0
sporada:1.0.2
sporada:1.0.1
sporada:1.0.0
..
compare: sporada:972f514e6bc88e0dd651dfb966c5ec9aacb6a62e
Branches Tags
sporada:development
sporada:master
sporada:manual
sporada:access-pipeline
sporada:prototype
sporada:1.1.0
sporada:1.0.2
sporada:1.0.1
sporada:1.0.0

No commits in common. "11b697145b3c7096e8e505ef93f3d94350ad503e" and "972f514e6bc88e0dd651dfb966c5ec9aacb6a62e" have entirely different histories.
11b697145b ... 972f514e6b

5 changed files with 265 additions and 429 deletions
Show Stats Expand all files Collapse all files

67
app/corpora/cqi_over_socketio/cqi_corpora_corpus.py
View File

@ -50,52 +50,9 @@ def cqi_corpora_corpus_update_db(cqi_client: cqi.CQiClient, corpus_name: str):
@cqi_over_socketio @cqi_over_socketio
def cqi_corpora_corpus_get_visualization_data(cqi_client: cqi.CQiClient, corpus_name: str): def cqi_corpora_corpus_get_visualization_data(cqi_client: cqi.CQiClient, corpus_name: str):
corpus = cqi_client.corpora.get(corpus_name) corpus = cqi_client.corpora.get(corpus_name)
# s_attrs = [x for x in corpus.structural_attributes.list() if not x.has_values]
# p_attrs = corpus.positional_attributes.list()
# payload = {
# 's_attrs': {},
# 'p_attrs': {},
# 'values': {
# 's_attrs': {},
# 'p_attrs': {}
# }
# }
# for s_attr in s_attrs:
# s_attr_lbound, s_attr_rbound = s_attr.cpos_by_id(text_id)
# s_attr_cpos_range = range(s_attr_lbound, s_attr_rbound + 1)
# payload['text']['lexicon'][text_id] = {
# 's_attrs': [s_attr_lbound, s_attr_rbound],
# 'counts': {
# 'token': s_attr_rbound - s_attr_lbound + 1
# },
# 'freqs': {
# p_attr.name: dict(Counter(p_attr.ids_by_cpos(list(s_attr_cpos_range))))
# for p_attr in p_attrs
# }
# }
# for p_attr in p_attrs:
# payload['p_attrs'] = dict(
# )
# payload['values']['p_attrs'] = dict(
# zip(
# range(0, p_attr.lexicon_size),
# p_attr.values_by_ids(list(range(0, p_attr.lexicon_size)))
# )
# )
text = corpus.structural_attributes.get('text') text = corpus.structural_attributes.get('text')
text_value_names = []
text_values = []
for text_sub_attr in corpus.structural_attributes.list(filters={'part_of': text}):
text_value_names.append(text_sub_attr.name[(len(text.name) + 1):])
text_values.append(text_sub_attr.values_by_ids(list(range(0, text.size))))
s = corpus.structural_attributes.get('s') s = corpus.structural_attributes.get('s')
ent = corpus.structural_attributes.get('ent') ent = corpus.structural_attributes.get('ent')
ent_value_names = []
ent_values = []
for ent_sub_attr in corpus.structural_attributes.list(filters={'part_of': ent}):
ent_value_names.append(ent_sub_attr.name[(len(ent.name) + 1):])
ent_values.append(ent_sub_attr.values_by_ids(list(range(0, ent.size))))
word = corpus.positional_attributes.get('word') word = corpus.positional_attributes.get('word')
lemma = corpus.positional_attributes.get('lemma') lemma = corpus.positional_attributes.get('lemma')
pos = corpus.positional_attributes.get('pos') pos = corpus.positional_attributes.get('pos')
@ -165,7 +122,10 @@ def cqi_corpora_corpus_get_visualization_data(cqi_client: cqi.CQiClient, corpus_
) )
} }
} }
payload['text']['values'] = text_value_names payload['text']['values'] = [
sub_attr.name[(len(text.name) + 1):]
for sub_attr in corpus.structural_attributes.list(filters={'part_of': text})
]
payload['s'] = {'lexicon': {}, 'values': None} payload['s'] = {'lexicon': {}, 'values': None}
for s_id in range(0, s.size): for s_id in range(0, s.size):
payload['s']['lexicon'][s_id] = { payload['s']['lexicon'][s_id] = {
@ -180,22 +140,15 @@ def cqi_corpora_corpus_get_visualization_data(cqi_client: cqi.CQiClient, corpus_
payload['ent']['lexicon'][ent_id] = { payload['ent']['lexicon'][ent_id] = {
# 'bounds': ent.cpos_by_id(ent_id) # 'bounds': ent.cpos_by_id(ent_id)
} }
payload['ent']['values'] = ent_value_names payload['ent']['values'] = [
sub_attr.name[(len(ent.name) + 1):]
for sub_attr in corpus.structural_attributes.list(filters={'part_of': ent})
]
payload['lookups'] = { payload['lookups'] = {
'corpus': {}, 'corpus': {},
'text': { 'text': {},
text_id: {
text_value_name: text_values[text_value_name_idx][text_id_idx]
for text_value_name_idx, text_value_name in enumerate(text_value_names)
} for text_id_idx, text_id in enumerate(range(0, text.size))
},
's': {}, 's': {},
'ent': { 'ent': {},
ent_id: {
ent_value_name: ent_values[ent_value_name_idx][ent_id_idx]
for ent_value_name_idx, ent_value_name in enumerate(ent_value_names)
} for ent_id_idx, ent_id in enumerate(range(0, ent.size))
},
'word': dict( 'word': dict(
zip( zip(
range(0, word.lexicon_size), range(0, word.lexicon_size),

330
app/static/js/CorpusAnalysis/CQiClient.js
View File

@ -115,188 +115,164 @@ class CQiCorpus {
getCorpusData() { getCorpusData() {
return new Promise((resolve, reject) => { return new Promise((resolve, reject) => {
const dummyData = { const dummyData = {
"corpus": { "num_tokens": 2000, // number of tokens in the corpus
"bounds": [1, 689], "num_unique_words": 500, // number of unique words in the corpus
"counts": { "num_unique_lemmas": 200, // number of unique lemmas in the corpus
"token": 743, "num_sentences": 90, // number of sentences in the corpus
"ent": 321, "average_sentence_length": 11, // average number of tokens per sentence in the corpus
"s": 234 "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
}, },
"freqs": { {
"word": { "num_tokens": 15, // number of tokens in the text
"1": 876, "num_unique_words": 4, // number of unique words in the text
"2": 234, "word_freqs": { // frequency of unique words in the text (sorted by frequency)
"3": 657 "str": "int", // number of tokens with word "str"
}, // ...
"lemma": { },
"1": 543, "num_unique_lemmas": 90, // number of unique lemmas in the text
"2": 876, "lemma_freqs": { // frequency of unique lemmas in the text (sorted by frequency)
"3": 321 "str": "int", // number of tokens with lemma "str"
}, // ...
"pos": { },
"1": 456, "num_sentences": 11, // number of sentences in the text
"2": 789, "average_sentence_length": 3, // average number of tokens per sentence in the text
"3": 234 "num_ent_types": 4, // number of ent_types in the text
}, "num_unique_ent_types": 300, // number of unique ent_types in the text
"simple_pos": { "num_entities_by_id": {
"1": 987, "1": "int", // number of entities with id 1
"2": 876, // ...
"3": 543 },
}, "author": "Author Name",
"ent": { "title": "Titel 1",
"1": 654, "publishing_year": 1962
"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], "num_tokens": 11, // number of tokens in the text
"counts": { "num_unique_words": 12, // number of unique words in the text
"token": 389, "word_freqs": { // frequency of unique words in the text (sorted by frequency)
"ent_type": 198, "str": "int", // number of tokens with word "str"
"s": 145 // ...
}, },
"freqs": { "num_unique_lemmas": 64, // number of unique lemmas in the text
"word": { "lemma_freqs": { // frequency of unique lemmas in the text (sorted by frequency)
"1": 60, "str": "int", // number of tokens with lemma "str"
"2": 70, // ...
"3": 100 },
}, "num_sentences": 52, // number of sentences in the text
"lemma": { "average_sentence_length": 3, // average number of tokens per sentence in the text
"1": 654, "num_ent_types": 45, // number of ent_types in the text
"2": 321, "num_unique_ent_types": 68, // number of unique ent_types in the text
"3": 987 "num_entities_by_id": {
}, "1": "int", // number of entities with id 1
"pos": { // ...
"1": 543, },
"2": 876, "author": "Author Name",
"3": 234 "title": "Titel 2",
}, "publishing_year": 1850
"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": { "num_tokens": 56, // number of tokens in the text
"1": "Person", "num_unique_words": 13, // number of unique words in the text
"2": "Organization" "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
}, },
"token": { {
"word": { "num_tokens": 54345, // number of tokens in the text
"1": "apple", "num_unique_words": 561, // number of unique words in the text
"2": "banana", "word_freqs": { // frequency of unique words in the text (sorted by frequency)
"3": "orange" "str": "int", // number of tokens with word "str"
}, // ...
"lemma": { },
"1": "run", "num_unique_lemmas": 546, // number of unique lemmas in the text
"2": "walk", "lemma_freqs": { // frequency of unique lemmas in the text (sorted by frequency)
"3": "jump" "str": "int", // number of tokens with lemma "str"
}, // ...
"pos": { },
"1": "noun", "num_sentences": 5427, // number of sentences in the text
"2": "verb", "average_sentence_length": 657, // average number of tokens per sentence in the text
"3": "adjective" "num_ent_types": 3465, // number of ent_types in the text
}, "num_unique_ent_types": 45, // number of unique ent_types in the text
"simple_pos": { "num_entities_by_id": {
"1": "subject", "1": "int", // number of entities with id 1
"2": "object", // ...
"3": "predicate" },
} "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
} }
} ]
} };
resolve(dummyData); resolve(dummyData);
/* /*

104
app/static/js/CorpusAnalysis/CorpusAnalysisApp.js
View File

@ -34,7 +34,6 @@ class CorpusAnalysisApp {
.then( .then(
cQiCorpus => { cQiCorpus => {
this.data.corpus = {o: cQiCorpus}; this.data.corpus = {o: cQiCorpus};
this.data.corpus.o.getVisualizationData().then(data => console.log(data));
// this.data.corpus.o.getVisualizationData() // this.data.corpus.o.getVisualizationData()
// .then( // .then(
// (visualizationData) => { // (visualizationData) => {
@ -49,8 +48,6 @@ class CorpusAnalysisApp {
this.renderGeneralCorpusInfo(corpusData); this.renderGeneralCorpusInfo(corpusData);
this.renderTextInfoList(corpusData); this.renderTextInfoList(corpusData);
this.renderTextProportionsGraphic(corpusData); this.renderTextProportionsGraphic(corpusData);
this.renderWordFrequenciesGraphic(corpusData);
this.renderWordDistributionsGraphic(corpusData);
}); });
// TODO: Don't do this hgere // TODO: Don't do this hgere
cQiCorpus.updateDb(); cQiCorpus.updateDb();
@ -115,85 +112,38 @@ class CorpusAnalysisApp {
} }
renderGeneralCorpusInfo(corpusData) { renderGeneralCorpusInfo(corpusData) {
document.querySelector('.corpus-num-tokens').innerHTML = corpusData.corpus.counts.token; let corpusGeneralInfoListElement = document.querySelector('.corpus-general-info-list');
document.querySelector('.corpus-num-s').innerHTML = corpusData.corpus.counts.s; 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> ${Object.entries(corpusData.text).length; corpusGeneralInfoListElement.querySelector('.corpus-text-count').innerHTML = `<b>Corpus text count:</b> ${corpusData.texts.length}`;
document.querySelector('.corpus-num-unique-words').innerHTML = Object.entries(corpusData.corpus.freqs.word).length; corpusGeneralInfoListElement.querySelector('.corpus-num-unique-words').innerHTML = `<b>Corpus unique word count:</b> ${corpusData.num_unique_words}`;
document.querySelector('.corpus-num-unique-lemmas').innerHTML = Object.entries(corpusData.corpus.freqs.lemma).length; corpusGeneralInfoListElement.querySelector('.corpus-num-unique-lemmas').innerHTML = `<b>Corpus unique lemma count:</b> ${corpusData.num_unique_lemmas}`;
document.querySelector('.corpus-num-unique-pos').innerHTML = Object.entries(corpusData.corpus.freqs.pos).length; // corpusGeneralInfoListElement.querySelector('.corpus-most-frequent-words').innerHTML = `<b>Corpus most frequent words:</b> ${corpusData.most_frequent_words.join(', ');
document.querySelector('.corpus-num-unique-simple-pos').innerHTML = Object.entries(corpusData.corpus.freqs.simple_pos).length; 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) { renderTextInfoList(corpusData) {
// let corpusTextInfoListElement = document.querySelector('.corpus-text-info-list'); let corpusTextInfoListElement = document.querySelector('.corpus-text-info-list');
// let corpusTextInfoList = new CorpusTextInfoList(corpusTextInfoListElement); let corpusTextInfoList = new CorpusTextInfoList(corpusTextInfoListElement);
// for (let text of Object.values(corpusData.text)) { corpusTextInfoList.add(corpusData.texts);
// 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: ${Object.values(corpusData.text).length}`;
} }
renderTextProportionsGraphic(corpusData) { renderTextProportionsGraphic(corpusData) {
// let textProportionsGraphicElement = document.querySelector('#text-proportions-graphic'); let textProportionsGraphicElement = document.querySelector('#text-proportions-graphic');
// let texts = Object.values(corpusData.text); let graphData = [
// let graphData = [ {
// { values: corpusData.texts.map(text => text.num_tokens),
// values: texts.map(text => text.counts.token), labels: corpusData.texts.map(text => `${text.title} (${text.publishing_year})`),
// labels: texts.map(text => `${text.values.title} (${text.values.publishing_year})`), type: 'pie'
// type: 'pie' }
// } ];
// ]; let graphLayout = {
// let graphLayout = { height: 400,
// height: 400, width: 500
// width: 500 };
// }; Plotly.newPlot(textProportionsGraphicElement, graphData, graphLayout);
// Plotly.newPlot(textProportionsGraphicElement, graphData, graphLayout);
}
renderWordFrequenciesGraphic(corpusData) {
// let wordFrequenciesGraphicElement = document.querySelector('#word-frequencies-graphic');
// let words = Object.entries(corpusData.value_lookups.token.word);
// let texts = Object.values(corpusData.text);
// let graphData = [];
// for (let word of words) {
// let data = {
// x: texts.map(text => `${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);
} }
} }

34
app/static/js/ResourceLists/CorpusTextInfoList.js
View File

@ -29,11 +29,11 @@ class CorpusTextInfoList extends ResourceList {
<tr class="list-item clickable hoverable"> <tr class="list-item clickable hoverable">
<td><span class="title"></span> (<span class="publishing_year"></span>)</td> <td><span class="title"></span> (<span class="publishing_year"></span>)</td>
<td><span class="num_tokens"></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_words"></span></td>
<td><span class="num_unique_lemmas"></span></td> <td><span class="num_unique_lemmas"></span></td>
<td><span class="num_unique_pos"></span></td> <td><span class="num_sentences"></span></td>
<td><span class="num_unique_simple_pos"></span></td> <td><span class="average_sentence_length"></span></td>
<td><span class="num_unique_ent_types"></span></td>
</tr> </tr>
`.trim(); `.trim();
} }
@ -44,11 +44,11 @@ class CorpusTextInfoList extends ResourceList {
'title', 'title',
'publishing_year', 'publishing_year',
'num_tokens', 'num_tokens',
'num_sentences',
'num_unique_words', 'num_unique_words',
'num_unique_lemmas', 'num_unique_lemmas',
'num_unique_pos', 'num_sentences',
'num_unique_simple_pos' 'average_sentence_length',
'num_unique_ent_types'
]; ];
} }
@ -68,11 +68,11 @@ class CorpusTextInfoList extends ResourceList {
<tr> <tr>
<th>Text<span class="sort right material-icons" data-sort="title" style="cursor:pointer; color:#aa9cc9">arrow_drop_down</span></th> <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 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 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 unique lemmas<span class="sort right material-icons" data-sort="num_unique_lemmas" 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 sentences<span class="sort right material-icons" data-sort="num_sentences" 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> <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>
</tr> </tr>
</thead> </thead>
<tbody class="list"></tbody> <tbody class="list"></tbody>
@ -83,14 +83,14 @@ class CorpusTextInfoList extends ResourceList {
mapResourceToValue(corpusTextData) { mapResourceToValue(corpusTextData) {
return { return {
title: corpusTextData.values.title, title: corpusTextData.title,
publishing_year: corpusTextData.values.publishing_year, publishing_year: corpusTextData.publishing_year,
num_tokens: corpusTextData.counts.token, num_tokens: corpusTextData.num_tokens,
num_sentences: corpusTextData.counts.s, num_unique_words: corpusTextData.num_unique_words,
num_unique_words: Object.entries(corpusTextData.freqs.word).length, num_unique_lemmas: corpusTextData.num_unique_lemmas,
num_unique_lemmas: Object.entries(corpusTextData.freqs.lemma).length, num_sentences: corpusTextData.num_sentences,
num_unique_pos: Object.entries(corpusTextData.freqs.pos).length, average_sentence_length: corpusTextData.average_sentence_length,
num_unique_simple_pos: Object.entries(corpusTextData.freqs.simple_pos).length num_unique_ent_types: corpusTextData.num_unique_ent_types
}; };
} }

159
app/templates/corpora/analysis.html.j2
View File

@ -19,112 +19,69 @@
<div class="row" id="corpus-analysis-app-overview"> <div class="row" id="corpus-analysis-app-overview">
<div class="col s12"> <div class="col s12">
<h1>{{ title }}</h1> <h1>{{ title }}</h1>
</div>
{% for extension in extensions %} {% for extension in extensions %}
<div class="col s3"> <div class="col s3">
<div class="card extension-selector hoverable" data-target="{{ extension.id_prefix }}-container"> <div class="card extension-selector hoverable" data-target="{{ extension.id_prefix }}-container">
<div class="card-content"> <div class="card-content">
<span class="card-title">{{ extension.name }}</span> <span class="card-title">{{ extension.name }}</span>
<p>{{ extension.description }}</p> <p>{{ extension.description }}</p>
</div>
</div>
</div>
{% endfor %}
<div class="row">
<div class="col s12">
<h4><i class="material-icons left">query_stats</i>Visualizations</h4>
</div>
</div>
<div class="row">
<div class="col s2">
<div class="card hoverable" style="border-radius: 10px !important; background-color:#6b3f89; color:white">
<div class="card-content" style="padding:10px !important; text-align:center;">
<p>Number of tokens</p>
<span class="card-title corpus-num-tokens"></span>
</div>
</div>
</div>
<div class="col s2">
<div class="card hoverable" style="border-radius: 10px !important; background-color:#6b3f89; color:white">
<div class="card-content" style="padding:10px !important; text-align:center">
<p>Number of sentences</p>
<span class="card-title corpus-num-s"></span>
</div>
</div>
</div>
<div class="col s2">
<div class="card hoverable" style="border-radius: 10px !important; background-color:#6b3f89; color:white">
<div class="card-content" style="padding:10px !important; text-align:center">
<p>Number of unique words</p>
<span class="card-title corpus-num-unique-words"></span>
</div>
</div>
</div>
<div class="col s2">
<div class="card hoverable" style="border-radius: 10px !important; background-color:#6b3f89; color:white">
<div class="card-content" style="padding:10px !important; text-align:center">
<p>Number of unique lemmas</p>
<span class="card-title corpus-num-unique-lemmas"></span>
</div>
</div>
</div>
<div class="col s2">
<div class="card hoverable" style="border-radius: 10px !important; background-color:#6b3f89; color:white">
<div class="card-content" style="padding:10px !important; text-align:center">
<p>Number of unique pos</p>
<span class="card-title corpus-num-unique-pos"></span>
</div>
</div>
</div>
<div class="col s2">
<div class="card hoverable" style="border-radius: 10px !important; background-color:#6b3f89; color:white">
<div class="card-content" style="padding:10px !important; text-align:center">
<p>Number of unique simple_pos</p>
<span class="card-title corpus-num-unique-simple-pos"></span>
</div>
</div>
</div>
</div>
<div class="row">
<div class="col s12">
<div class="card hoverable">
<div class="card-content">
<span class="card-title">Text information</span>
<div class="chip text-count-chip" style="background-color:#6b3f89; color:white""></div>
<div class="corpus-text-info-list no-autoinit"></div>
</div>
</div>
</div>
</div>
<div class="row">
<div class="col s3">
<div class="card hoverable">
<div class="card-content">
<span class="card-title">Text proportions within the corpus</span>
<div id="text-proportions-graphic"></div>
</div>
</div>
</div>
<div class="col s3">
<div class="card hoverable">
<div class="card-content">
<span class="card-title">Word frequencies</span>
<div id="word-frequencies-graphic"></div>
</div>
</div>
</div>
<div class="col s6">
<div class="card hoverable">
<div class="card-content">
<span class="card-title">Word distributions</span>
<div id="word-distributions-graphic"></div>
</div>
</div>
</div> </div>
</div> </div>
</div> </div>
{% endfor %}
</div>
<div class="row">
<div class="col s12">
<h4><i class="material-icons left">query_stats</i>Visualizations</h4>
</div>
<div class="col s4" >
<div class="card hoverable">
<div class="card-content">
<span class="card-title">General information about the Corpus</span>
<p></p>
<br>
<ul class="corpus-general-info-list">
<li class="corpus-num-tokens"></li>
<br>
<li class="corpus-text-count"></li>
<br>
<li class="corpus-num-unique-words"></li>
<br>
<li class="corpus-num-unique-lemmas"></li>
<br>
<li class="corpus-num-sentences"></li>
<br>
<li class="corpus-average-sentence-length"></li>
<br>
<li class="corpus-num-ent-types"></li>
<br>
<li class="corpus-num-unique-ent-types"></li>
<br>
</ul>
</div>
</div>
</div>
<div class="col s8">
<div class="card hoverable">
<div class="card-content">
<span class="card-title">Text information</span>
<div class="corpus-text-info-list no-autoinit"></div>
</div>
</div>
</div>
</div>
<div class="row">
<div class="col 12">
<div class="card hoverable">
<div class="card-content">
<span class="card-title">Text proportions within the corpus</span>
<div id="text-proportions-graphic"></div>
</div>
</div>
</div>
</div> </div>