.Rhistory

Year = factor(year(pubDate), levels = 2017:2014)) %>%
filter(!is.na(duration_minutes)) %>%
ggplot(aes(x = duration_minutes, y = Year)) +
geom_density_ridges() +
theme_set(theme_jk_ridge()) +
labs(x = "방송시간 (분)", y = "연도",
title = "지적 대화를 위한 넓고 얕은 지식",
subtitle = "연도별 방송시간 분포") +
scale_x_continuous(breaks = seq(0, 150, 30), limits = c(0, 150))
rb_df <- feed_to_df("http://www.wisdomhouse.kr/sns/redbooks/redbooks.xml")
load("~/Downloads/sensesensibility.rda")
head(sensesensibility)
head(sensesensibility, 20)
271+268+256+275+288+301+296+287+282+245+292+252+246+244+270+230+241+220+221
a <- c(2.4866, 2.4988, 2.4902, 2.4802)
b <- c(2.4866, 2.4849, 2.4802, 2.4800)
ifelse(a > b, 1, 0)
options()
Sys.getenv()
remove.packages("rJava")
options("java.home")
options("java.home"="/Library/Java/JavaVirtualMachines/jdk-9.0.1.jdk/Contents/Home")
install.packages("rJava",,"http://rforge.net/",type="source")
install.packages("rJava")
library(rJava)
remove.packages("rJava")
options("java.home"="/Library/Java/JavaVirtualMachines/jdk-9.0.1.jdk/Contents/Home")
install.packages("rJava",,"http://rforge.net/",type="source")
totalPop2010 <- 3831074
Years65_2010 <- 533533
Years85_2010 <- 77872
DWDA_65_2010 <- 19
DWDA_75_2010 <- 15
DWDA_85_2010 <- 12
DWDA_ALL_2010 <- 65
(DWDA_65_2010 + DWDA_75_2010) / (Years65_2010 - Years85_2010)
DWDA_85_2010 / Years85_2010
DWDA_ALL_2010 / totalPop2010
format(DWDA_ALL_2010 / totalPop2010, scientific = FALSE)
format((DWDA_65_2010 + DWDA_75_2010) / (Years65_2010 - Years85_2010), scientific = FALSE)
(DWDA_85_2010 / Years85_2010) / (DWDA_65_2010 + DWDA_75_2010) / (Years65_2010 - Years85_2010)
(DWDA_85_2010 / Years85_2010) / ((DWDA_65_2010 + DWDA_75_2010) / (Years65_2010 - Years85_2010))
(DWDA_85_2010 / Years85_2010) / (DWDA_ALL_2010 / totalPop2010)
10/1127
HIVAIDSPop <- 2735 + 3621 + 386 + 480
10/HIVAIDSPop
(10/HIVAIDSPop) / (DWDA_ALL_2010 / totalPop2010)
HIVAIDSPop
highschoolRate <- 0.898
bachelorRate <- 0.308
highschoolPop <- highschoolRate * totalPop2010
bachelorPop <- bachelorRate * totalPop2010
lowerEduPop <- totalPop2010 - highschoolPop
(4 / lowerEduPop) / (DWDA_ALL_2010 / totalPop2010)
(13 / (highschoolPop - bachelorPop)) / (DWDA_ALL_2010 / totalPop2010)
install.packages("rtweet")
library(rtweet)
Sys.getenv("TWITTER_APP")
appname <- "junhewk_roauth"
key <- "iFP1iQ7RNukQ4iBHT6zVUCaQZ"
secret <- "kaBayK9c0chgkfUizJFlfaxS6wLMVuJpg0dEuj5WUTKMo62LLD"
twitter_token <- create_token(
app = appname,
consumer_key = key,
consumer_secret = secret
)
rtweet_folks <- search_tweets("#rstats", n = 300)
dplyr::glimpse(rtweet_folks)
team_rstats <- search_twets("#rstats", n = 500)
team_rstats <- search_tweets("#rstats", n = 500)
users_data(team_rstats) %>%
head()
kylo_is_a_mole <- get_timeline("KyloR3n", n = 2000)
head(kylo_is_a_mole)
users_data(kylo_is_a_mole)
imwithher <- stream_tweets("HillaryClinton", timeout = 120)
head(imwithher)
head(users_data(imwithher))
harder_science <- search_users("social science", n = 500)
harder_science
users <- c("KimKardashian", "justinbieber", "taylorswift13",
"espn", "JoelEmbiid", "cstonehoops", "KUHoops",
"upshotnyt", "fivethirtyeight", "hadleywickham",
"cnn", "foxnews", "msnbc", "maddow", "seanhannity",
"potus", "epa", "hillaryclinton", "realdonaldtrump",
"natesilver538", "ezraklein", "annecoulter")
famous_tweeters <- lookup_users(users)
famous_tweeters
colbert_nation <- get_followers("stephanathome", n = 18000)
colbert_nation <- get_followers("stephenathome", n = 18000)
society_korean_users <- c("wonsoonpark", "moonriver365", "hcroh",
"urimal365", "OneFuturePower", "actormoon",
"ssaribi", "kennedian3", "GH_PARK", "Park_Youngsun")
politial_tweeters <- lookup_users(society_korean_users)
dplyr::glimpse(politial_tweeters)
colbert_nation <- get_followers("stephenathome", n = 18000)
library(rvest)
library(stringr)
temp_html <- read_html(temp)
temp <- "http://www.melon.com/chart/age/index.htm?chartType=YE&chartGenre=KPOP&chartDate=1964"
temp_html <- read_html(temp)
temp_html %>% html_table("lst50")
temp_html %>% html_node("lst50") %>% html_table
temp_html %>% html_node("lst50") %>% html_table()
temp_html %>% html_table()
temp_html %>% html_node("lst50")
temp_html
temp_html %>% html_nodes(xpath="//tr[class='lst50']")
temp_html %>% html_nodes(xpath = "//tr[@class='lst50']")
temp_html %>% html_nodes(xpath = "//tr")
temp_html <- read_html(temp)
temp_html %>% html_nodes(xpath = "//tr")
temp_html %>% html_nodes(xpath = "//div[class='tb_list type02 d_song_list']")
temp_html %>% html_nodes(xpath = "/div[class='tb_list type02 d_song_list']")
?html_nodes
temp_html %>% html_nodes("table")
temp_html
temp_html %>% html_text()
library(Rselenium)
install.packages("Rselenium")
install.packages("RSelenium")
library(RSelenium)
??RSelenium
library(RSelenium)
remDr <- remoteDriver(remoteServerAddr="localhost", port=4445L, browserName="chrome")
remDr$open()
remDr$getStatus()
remDr$navigate("http://www.melon.com/chart/age/index.htm?chartType=YE&chartGenre=KPOP&chartDate=1964")
?findElement
webElem <- remDr$findElement(using="xpath", value="//form[@id='frm']/table")
webElem
webElem$getPageSource
webElem$getPageSource()
webElem <- remDr$findElement(using="css selector", value="form.id.frm")
webElem <- remDr$findElement(using="css selector", value="form#frm")
webElem$getPageSource()
html(webElem$getPageSource([[1]])
html(webElem$getPageSource()[[1]])
read_html(webElem$getPageSource()[[1]])
library(rvest)
html(webElem$getPageSource()[[1]])
read_html(webElem$getPageSource()[[1]])
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_table()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div#wrap_song_info") %>%
html_text()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div#wrap_song_info")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap_song_info") %>%
html_text()
library(stringr)
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap_song_info") %>%
html_text() %>%
str_replace_all("[\\n|\\t]*", ",")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap_song_info") %>%
html_text() %>%
str_replace_all("[\\n|\\t]+", ",")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap_song_info") %>%
html_text() %>%
str_replace_all("[\\n|\\t]+", ",") %>%
str_split(",")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap a")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap a.btn btn_icon_detail")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap a.btn")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap a.btn") %>%
html_attr("onclick")
read_html("http://www.melon.com/chart/age/index.htm?chartType=YE&chartGenre=KPOP&chartDate=1964") %>%
html_node("form#frm table") %>%
html_nodes("div.wrap_song_info") %>%
html_text() %>%
str_replace_all("[\\n|\\t]+", ",") %>%
str_split(",")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.ellipsis span strong") %>%
html_text()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.ellipsis a.fc_mgray") %>%
html_text()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.'ellipsis rank02' a.fc_mgray") %>%
html_text()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.rank02 a.fc_mgray") %>%
html_text()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes(span.checkEllipsis a.fc_mgray") %>%
html_text()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("span.checkEllipsis a.fc_mgray") %>%
html_text()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("span.checkEllipsis") %>%
html_text()
seq(1964, 2016, 1)
song <- "http://www.melon.com/song/detail.htm?songId=4083218"
remDr$navigate(song)
webElem <- remDr$findElement(using = "uss selector", value = "div.wrap_lyric")
webElem <- remDr$findElement(using = "css selector", value = "div.wrap_lyric")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
html_text()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric")
?html_attr
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
html_children()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
html_attrs()
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
gsub(pattern = "<.*?>", replacement = "|")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
gsub(pattern = "<.*?>", replacement = "|") %>%
str_trim("both")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
gsub(pattern = "<.*?>", replacement = "|") %>%
str_split("|") %>%
str_trim("both")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
gsub(pattern = "<.*?>", replacement = "|") %>%
str_split("\\|") %>%
str_trim("both")
remDr$navigate("http://www.melon.com/chart/age/index.htm?chartType=YE&chartGenre=KPOP&chartDate=1964")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("form#frm table") %>%
html_nodes("div.wrap_song_info") %>%
html_node("div.rank01") %>%
html_text()
song_none <- "http://www.melon.com/song/detail.htm?songId=3003849"
remDr$navigate(song_none)
webElem <- remDr$findElement(using = "css selector", value = "div.wrap_lyric")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric")
read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
gsub(pattern = "<.*?>", replacement = "|") %>%
str_split("\\|") %>%
str_trim("both")
lyrics <- read_html(webElem$getPageSource()[[1]]) %>%
html_node("div.lyric") %>%
gsub(pattern = "<.*?>", replacement = "|") %>%
str_split("\\|") %>%
str_trim("both")
is.na(lyrics)
a <- c("temp")
a
a <- c(a, NA)
a
install.packages("wdman")
install.packages("wdman")
devtools::install_github("johndharrison/wdman")
?UseMethod
?attrs
?attributes
library(tokenizers)
tokenize_ngrams(c("가", "나", "다"), n = 3L, n_min = 1L)
tokenize_ngrams(c("가", "나", "다"), n = 3L, n_min = 2L)
tokenize_ngrams(c("가", "나", "다"), n = 4L, n_min = 1L)
?tokenize_ngrams
song <-  paste0("How many roads must a man walk down\n",
"Before you call him a man?\n",
"How many seas must a white dove sail\n",
"Before she sleeps in the sand?\n",
"\n",
"How many times must the cannonballs fly\n",
"Before they're forever banned?\n",
"The answer, my friend, is blowin' in the wind.\n",
"The answer is blowin' in the wind.\n")
tokenize_ngrams(song, n = 4)
tokenize_ngrams("가 나 다"), n = 4L, n_min = 1L)
tokenize_ngrams("가 나 다", n = 4L, n_min = 1L)
tokenize_ngrams("가 나 다", n = 3L)
tokenize_ngrams("가 나 다", n = 2L)
library(RmecabKo)
txt <- paste("설렌다 Me Likey Me Likey Likey",
"Likey Me Likey Likey Likey",
"두근두근두근 Heart Heart",
"Me Likey Me Likey Likey Likey",
"Me Likey Likey Likey",
"두근두근두근",
"자꾸 드러내고 싶지",
"자꾸만 사소한 것 하나까지 전부다",
"작은 화면 속에 내가",
"제일 예뻐 보이고파",
"아직은 감춰 이런 내 마음 꾹꾹",
"멋 부린다는 건 정말 귀찮은 거",
"그렇다고 절대 대충할 수가 없는걸",
"매일 가슴 뛰게 해",
"이건 네가 몰라야만 돼",
"그러면서 뻔뻔하게",
"BB크림 파파파 립스틱을 맘맘마",
"카메라에 담아볼까 예쁘게",
"이거 보면 웃어줘 그리고 꼭 눌러줘",
"저 밑에 앙증맞고",
"새빨간 Heart Heart",
"근데 좋아요란 말은 뻔해",
"내 맘 표현하기엔 부족한데",
"근데 좋아요 잠도 못 자도",
"지각하게 돼도 좋은걸")
token_morph(txt)
txt <- paste("자꾸 드러내고 싶지",
"자꾸만 사소한 것 하나까지 전부다",
"작은 화면 속에 내가",
"제일 예뻐 보이고파",
"아직은 감춰 이런 내 마음 꾹꾹")
token_morph(txt)
txt <- paste("자꾸 드러내고 싶지",
"자꾸만 사소한 것 하나까지 전부다",
"작은 화면 속에 내가",
"제일 예뻐 보이고파",
"아직은 감춰 이런 내 마음 꾹꾹")
token_morph(txt)
token_words(txt)
token_nouns(txt)
knitr::opts_chunk$set(echo = TRUE)
txt <- paste("자꾸 드러내고 싶지",
"자꾸만 사소한 것 하나까지 전부다",
"작은 화면 속에 내가",
"제일 예뻐 보이고파",
"아직은 감춰 이런 내 마음 꾹꾹")
token_morph(txt)
token_words(txt)
token_nouns(txt)
token_ngrams(txt, n = 2L)
library(tidyverse)
library(tidytext)
library(RmecabKo)
library(stringr)
library(ggplot2)
setwd("/Volumes/Database/Data/R/lyrics")
songListLyrics <- read_csv("melon_ranking_lyrics_1964-2016.csv")
songListLyrics <- songListLyrics %>%
mutate(decade = floor(year / 10) * 10)
lyricsWords <- songListLyrics %>%
unnest_tokens(word, lyric, token = token_words)
lyticsWords %>%
count(word, sort = TRUE)
lyricsWords %>%
count(word, sort = TRUE)
wordsByDecade <- lyricsWords %>%
count(decade, word, sort = TRUE) %>%
ungroup()
wordsByDecade
tfIdf <- wordsByDecade %>%
bind_tf_idf(word, decade, n) %>%
arrange(desc(tf_idf))
tfIdf
tfIdf %>%
group_by(decade) %>%
top_n(12, tf_idf) %>%
ungroup() %>%
mutate(word = reorder(word, tf_idf)) %>%
ggplot(aes(word, tf_idf, fill = decade)) +
geom_col(show.legend = FALSE) +
face_wrap(~ decade, scales = "free") +
ylab("tf-idf") +
coord_flip()
tfIdf %>%
group_by(decade) %>%
top_n(12, tf_idf) %>%
ungroup() %>%
mutate(word = reorder(word, tf_idf)) %>%
ggplot(aes(word, tf_idf, fill = decade)) +
geom_col(show.legend = FALSE) +
facet_wrap(~ decade, scales = "free") +
ylab("tf-idf") +
coord_flip()
tfIdf %>%
group_by(decade) %>%
top_n(12, tf_idf) %>%
ungroup() %>%
mutate(word = reorder(word, tf_idf)) %>%
ggplot(aes(word, tf_idf, fill = decade)) +
geom_col(show.legend = FALSE) +
facet_wrap(~ decade, scales = "free") +
ylab("tf-idf") +
coord_flip() +
theme(axis.text.x = element_text(family = "Apple Gothic SD Neo"))
tfIdf %>%
group_by(decade) %>%
top_n(12, tf_idf) %>%
ungroup() %>%
mutate(word = reorder(word, tf_idf)) %>%
ggplot(aes(word, tf_idf, fill = decade)) +
geom_col(show.legend = FALSE) +
facet_wrap(~ decade, scales = "free") +
ylab("tf-idf") +
coord_flip() +
theme(axis.text.x = element_text(family = "Apple SD Gothic Neo"))
tfIdf %>%
group_by(decade) %>%
top_n(12, tf_idf) %>%
ungroup() %>%
mutate(word = reorder(word, tf_idf)) %>%
ggplot(aes(word, tf_idf, fill = decade)) +
geom_col(show.legend = FALSE) +
facet_wrap(~ decade, scales = "free") +
ylab("tf-idf") +
coord_flip() +
theme(axis.text.y = element_text(family = "Apple SD Gothic Neo"))
library(widyr)
decadeCors <- wordsByDecade %>%
pairwise_cor(decade, word, n, sort = TRUE)
decadeCors
songListLyrics <- songListLyrics %>%
na_omit() %>%
mutate(decade = floor(year / 10) * 10)
lyricsWords <- songListLyrics %>%
unnest_tokens(word, lyric, token = token_words)
lyricsWords %>%
count(word, sort = TRUE)
wordsByDecade <- lyricsWords %>%
count(decade, word, sort = TRUE) %>%
ungroup()
wordsByDecade
tfIdf <- wordsByDecade %>%
bind_tf_idf(word, decade, n) %>%
arrange(desc(tf_idf))
tfIdf
tfIdf %>%
group_by(decade) %>%
top_n(12, tf_idf) %>%
ungroup() %>%
mutate(word = reorder(word, tf_idf)) %>%
ggplot(aes(word, tf_idf, fill = decade)) +
geom_col(show.legend = FALSE) +
facet_wrap(~ decade, scales = "free") +
ylab("tf-idf") +
coord_flip() +
theme(axis.text.y = element_text(family = "Apple SD Gothic Neo"))
library(widyr)
decadeCors <- wordsByDecade %>%
pairwise_cor(decade, word, n, sort = TRUE)
decadeCors
?na.omit
songListLyrics <- songListLyrics %>%
na.omit() %>%
mutate(decade = floor(year / 10) * 10)
lyricsWords <- songListLyrics %>%
unnest_tokens(word, lyric, token = token_words)
lyricsWords %>%
count(word, sort = TRUE)
wordsByDecade <- lyricsWords %>%
count(decade, word, sort = TRUE) %>%
ungroup()
wordsByDecade
tfIdf <- wordsByDecade %>%
bind_tf_idf(word, decade, n) %>%
arrange(desc(tf_idf))
tfIdf
tfIdf %>%
group_by(decade) %>%
top_n(12, tf_idf) %>%
ungroup() %>%
mutate(word = reorder(word, tf_idf)) %>%
ggplot(aes(word, tf_idf, fill = decade)) +
geom_col(show.legend = FALSE) +
facet_wrap(~ decade, scales = "free") +
ylab("tf-idf") +
coord_flip() +
theme(axis.text.y = element_text(family = "Apple SD Gothic Neo"))
library(widyr)
decadeCors <- wordsByDecade %>%
pairwise_cor(decade, word, n, sort = TRUE)
decadeCors
install.packages(ggraph)
install.packages(c("ggraph", "igraph"))
library(ggraph)
library(igraph)
decadeCors %>%
graph_from_data_frame() %>%
ggraph(layout = "fr") +
geom_edge_link(aes(alpha = correlation, width = correlation)) +
geom_node_point(size = 6, color = "lightblue") +
geom_node_text(aes(label = name), repel = TRUE) +
theme_void()