Refine preprocessing, add LDA

bali_ner.json

@@ -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"
+]

lda_output/topics.txt

@@ -0,0 +1,3 @@
+(0, '0.191*"temple" + 0.102*"view" + 0.079*"sunset" + 0.061*"cliff" + 0.041*"uluwatu" + 0.031*"dance" + 0.030*"kecak_dance" + 0.027*"tourist" + 0.015*"hour" + 0.013*"sun"')
+(1, '0.052*"sea" + 0.041*"ocean" + 0.038*"guide" + 0.036*"bit" + 0.033*"water" + 0.031*"location" + 0.027*"beach" + 0.025*"wave" + 0.021*"day" + 0.014*"rock"')
+(2, '0.174*"monkey" + 0.046*"time" + 0.030*"people" + 0.028*"lot" + 0.026*"visit" + 0.022*"glass" + 0.016*"sunglass" + 0.016*"photo" + 0.015*"trip" + 0.014*"day"')