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

Sort Mechanics Text Info List

Browse Source
This commit is contained in:
Inga Kirschnick
2023-06-13 17:18:00 +02:00
parent cc508cf4eb
commit 71359523ba
2 changed files with 125 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

102
app/static/js/CorpusAnalysis/CQiClient.js
View File

@@ -138,8 +138,104 @@ class CQiCorpus {
"publishing_year": 1950
},
{
"num_tokens": 800, // number of tokens in the text
"num_unique_words": 60, // number of unique words in the text
"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
@@ -158,7 +254,7 @@ class CQiCorpus {
// ...
},
"author": "Author Name 2",
"title": "Titel 2",
"title": "Titel 5",
"publishing_year": 1951
}
]