mirror of
https://github.com/marvinscham/masterthesis-playground.git
synced 2025-12-06 18:20:53 +01:00
Restructure
This commit is contained in:
BIN
data/intermediate/processed_texts.pkl
Normal file
BIN
data/intermediate/processed_texts.pkl
Normal file
Binary file not shown.
BIN
data/intermediate/processed_texts_lowprep.pkl
Normal file
BIN
data/intermediate/processed_texts_lowprep.pkl
Normal file
Binary file not shown.
9654
data/intermediate/selected_topics_documents.csv
Normal file
9654
data/intermediate/selected_topics_documents.csv
Normal file
File diff suppressed because one or more lines are too long
56449
data/original/reviews.tab
Normal file
56449
data/original/reviews.tab
Normal file
File diff suppressed because one or more lines are too long
53
data/supporting/bali_ner.json
Normal file
53
data/supporting/bali_ner.json
Normal file
@@ -0,0 +1,53 @@
|
||||
[
|
||||
"ubud",
|
||||
"kuta",
|
||||
"seminyak",
|
||||
"canggu",
|
||||
"sanur",
|
||||
"denpasar",
|
||||
"jimbaran",
|
||||
"lovina",
|
||||
"amed",
|
||||
"sidemen",
|
||||
"uluwatu",
|
||||
"nusa",
|
||||
"legian",
|
||||
"tabanan",
|
||||
"bedugul",
|
||||
"pemuteran",
|
||||
"tanah",
|
||||
"besakih",
|
||||
"goa",
|
||||
"tirta",
|
||||
"tegallalang",
|
||||
"lempuyang",
|
||||
"agung",
|
||||
"batur",
|
||||
"bratan",
|
||||
"sekumpul",
|
||||
"munduk",
|
||||
"batubulan",
|
||||
"celuk",
|
||||
"tegenungan",
|
||||
"gitgit",
|
||||
"singaraja",
|
||||
"padang",
|
||||
"kerobokan",
|
||||
"penida",
|
||||
"lembongan",
|
||||
"ceningan",
|
||||
"garuda",
|
||||
"ulun",
|
||||
"bajra",
|
||||
"kintamani",
|
||||
"taman",
|
||||
"saraswati",
|
||||
"pandawa",
|
||||
"melasti",
|
||||
"dreamland",
|
||||
"balangan",
|
||||
"bingin",
|
||||
"suluban",
|
||||
"menjangan",
|
||||
"jatiluwih"
|
||||
]
|
||||
53
data/supporting/named_entities.json
Normal file
53
data/supporting/named_entities.json
Normal file
@@ -0,0 +1,53 @@
|
||||
[
|
||||
"ubud",
|
||||
"kuta",
|
||||
"seminyak",
|
||||
"canggu",
|
||||
"sanur",
|
||||
"denpasar",
|
||||
"jimbaran",
|
||||
"lovina",
|
||||
"amed",
|
||||
"sidemen",
|
||||
"uluwatu",
|
||||
"nusa",
|
||||
"legian",
|
||||
"tabanan",
|
||||
"bedugul",
|
||||
"pemuteran",
|
||||
"tanah",
|
||||
"besakih",
|
||||
"goa",
|
||||
"tirta",
|
||||
"tegallalang",
|
||||
"lempuyang",
|
||||
"agung",
|
||||
"batur",
|
||||
"bratan",
|
||||
"sekumpul",
|
||||
"munduk",
|
||||
"batubulan",
|
||||
"celuk",
|
||||
"tegenungan",
|
||||
"gitgit",
|
||||
"singaraja",
|
||||
"padang",
|
||||
"kerobokan",
|
||||
"penida",
|
||||
"lembongan",
|
||||
"ceningan",
|
||||
"garuda",
|
||||
"ulun",
|
||||
"bajra",
|
||||
"kintamani",
|
||||
"taman",
|
||||
"saraswati",
|
||||
"pandawa",
|
||||
"melasti",
|
||||
"dreamland",
|
||||
"balangan",
|
||||
"bingin",
|
||||
"suluban",
|
||||
"menjangan",
|
||||
"jatiluwih"
|
||||
]
|
||||
1
data/supporting/stopwords-en.json
Normal file
1
data/supporting/stopwords-en.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user