Created
December 16, 2016 16:15
-
-
Save awhstin/9fc77ad98528527bb9743e71dcbf1f94 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(rvest) | |
library(tidytext) | |
library(dplyr) | |
library(stringr) | |
library(tidyr) | |
library(ggplot2) | |
library(viridis) | |
library(ggthemes) | |
library(syuzhet) | |
#get our data | |
url<-read_html('http://www.historyplace.com/speeches/previous.htm') | |
urls <- url %>% | |
html_nodes("a")%>% | |
html_attr('href') | |
name <- url %>% | |
html_nodes("font a")%>% | |
html_text()%>% | |
str_replace_all( "[\n]" , "") | |
rurls<-head(urls,40)%>%unlist() | |
rname<-head(name,40) | |
data<-data.frame(urls=rurls,name=rname,stringsAsFactors = F) | |
data$link<-paste0('http://www.historyplace.com/speeches/',data$urls) | |
#get the speeches | |
speeches<-NULL | |
for(i in 1:nrow(data)){ | |
speech <- data$link[i] %>% | |
read_html() %>% | |
html_nodes("p")%>% | |
html_text() | |
speechwords<-unlist(strsplit(speech," ")) | |
line_number<-1:length(speechwords) | |
size<-length(speechwords) | |
name<-data$name[i] | |
indiv.speeches <-data.frame(word=speechwords,line_number,name,size,stringsAsFactors = FALSE) | |
speeches<-rbind(speeches,indiv.speeches) | |
} | |
#big speeches | |
big.speeches<-filter(speeches,size>2000) | |
#tidy | |
tidy.speeches<-big.speeches %>% unnest_tokens(word,word) | |
data("stop_words") | |
tidy.speeches <- tidy.speeches %>% anti_join(stop_words) | |
tidy.speeches %>% count(word, sort = TRUE) | |
tidy.speeches$name<- gsub("\\s+"," ",tidy.speeches$name) | |
#sentiment | |
bing <- sentiments %>% | |
filter(lexicon == "bing") %>% | |
select(-score) | |
#join and sentiment | |
speech.sentiment <- tidy.speeches %>% | |
inner_join(bing) %>% | |
count(name, index = line_number %/% 80, sentiment) %>% | |
spread(sentiment, n, fill = 0) %>% | |
mutate(sentiment = positive - negative) | |
#plot etc | |
ggplot(speech.sentiment, aes(index, sentiment, color = name)) + | |
geom_line(stat = "identity", show.legend = FALSE) + | |
facet_wrap(~name, ncol = 2, scales = "free_x") + | |
theme_minimal(base_size = 13) + | |
labs(title = "Sentiment in Famous Speeches", y = "Sentiment") + | |
scale_color_viridis(end = 0.75, discrete=TRUE, direction = -1,option = 'C') + | |
scale_x_discrete(expand=c(0.02,0)) + | |
theme(strip.text=element_text(hjust=0)) + | |
theme(strip.text = element_text(face = "italic")) + | |
theme(axis.title.x=element_blank()) + | |
theme(axis.ticks.x=element_blank()) + | |
theme(axis.text.x=element_blank()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment