Last active
November 20, 2020 18:37
-
-
Save bradlindblad/313fbee70dd3dbae07a7c9879428d818 to your computer and use it in GitHub Desktop.
R NLP
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(dplyr) | |
library(ggplot2) | |
library(tidytext) | |
library(tm) | |
library(wordcloud) | |
# input: a dataframe called raw, in this case the text col is biggest_concern, and X is the ID col | |
mydata <- dplyr::select(raw, biggest_concern, X) | |
# Split cells of sentences to each word = record | |
mydata <- dplyr::select(mydata, biggest_concern, X) | |
# # Split cells of sentences to each word = record | |
mydata <-stack(tapply(mydata$biggest_concern, mydata$X, function(x) scan(text=x, what=''))) %>% | |
dplyr::select(ID = ind, word = values) | |
mydata <- mydata %>% | |
anti_join(stop_words) %>% | |
dplyr::mutate(word = str_replace_all(word, "[[:punct:]]", " ")) %>% | |
dplyr::mutate(word = tolower(word)) | |
emotions <- mydata %>% | |
unnest_tokens(word, word) %>% | |
anti_join(stop_words, by = "word") %>% | |
filter(!grepl('[0-9]', word)) %>% | |
left_join(get_sentiments("nrc"), by = "word") %>% | |
filter(!(sentiment == "negative" | sentiment == "positive")) %>% | |
group_by(sentiment) %>% | |
summarize( freq = n()) %>% | |
mutate(percent=round(freq/sum(freq)*100)) %>% | |
select(-freq) %>% | |
ungroup() | |
overall_mean_sd <- emotions %>% | |
group_by(sentiment) %>% | |
summarize(overall_mean=mean(percent), sd=sd(percent)) | |
### draw a bar graph with error bars | |
ggplot(overall_mean_sd, aes(x = reorder(sentiment, -overall_mean), y=overall_mean)) + | |
geom_bar(stat="identity", fill="darkgreen", alpha=0.7) + | |
geom_errorbar(aes(ymin=overall_mean-sd, ymax=overall_mean+sd), width=0.2,position=position_dodge(.9)) + | |
xlab("Emotion") + | |
ylab("Emotion expressed in % of responses") + | |
# ggtitle("Emotion words expressed in Mr. Buffett's \n annual shareholder letters (1977 – 2016)") + | |
theme(axis.text.x=element_text(angle=45, hjust=1)) + | |
coord_flip( ) + | |
theme_minimal() |
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(dplyr) | |
library(tidytext) | |
library(tm) | |
library(wordcloud) | |
# input: a dataframe called raw, in this case the text col is biggest_concern, and X is the ID col | |
mydata <- dplyr::select(raw, biggest_concern, X) | |
# Split cells of sentences to each word = record | |
mydata <- dplyr::select(mydata, biggest_concern, X) | |
# # Split cells of sentences to each word = record | |
mydata <-stack(tapply(mydata$biggest_concern, mydata$X, function(x) scan(text=x, what=''))) %>% | |
dplyr::select(ID = ind, word = values) | |
mydata <- mydata %>% | |
anti_join(stop_words) %>% | |
dplyr::mutate(word = str_replace_all(word, "[[:punct:]]", " ")) %>% | |
dplyr::mutate(word = tolower(word)) | |
mydata %>% | |
inner_join(get_sentiments("bing")) %>% | |
dplyr::count(word, sentiment, sort=TRUE) %>% | |
reshape2::acast(word ~ sentiment, value.var = "n", fill = 0) %>% | |
comparison.cloud(colors = c("red", "darkgreen"), | |
max.words=40) | |
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(dplyr) | |
library(tidytext) | |
library(tm) | |
library(wordcloud) | |
# input: a dataframe called raw, in this case the text col is biggest_concern, and X is the ID col | |
mydata <- dplyr::select(raw, biggest_concern, X) | |
# Split cells of sentences to each word = record | |
mydata <- dplyr::select(mydata, biggest_concern, X) | |
# # Split cells of sentences to each word = record | |
mydata <-stack(tapply(mydata$biggest_concern, mydata$X, function(x) scan(text=x, what=''))) %>% | |
dplyr::select(ID = ind, word = values) | |
mydata <- mydata %>% | |
anti_join(stop_words) %>% | |
dplyr::mutate(word = str_replace_all(word, "[[:punct:]]", " ")) %>% | |
dplyr::mutate(word = tolower(word)) | |
text <- mydata$word | |
docs <- Corpus(VectorSource(text)) | |
docs <- docs %>% | |
tm_map(removeNumbers) %>% | |
tm_map(removePunctuation) %>% | |
tm_map(stripWhitespace) | |
docs <- tm_map(docs, content_transformer(tolower)) | |
docs <- tm_map(docs, removeWords, stopwords("english")) | |
dtm <- TermDocumentMatrix(docs) | |
matrix <- as.matrix(dtm) | |
words <- sort(rowSums(matrix),decreasing=TRUE) | |
df <- data.frame(word = names(words),freq=words) | |
set.seed(1234) # for reproducibility | |
wordcloud(words = df$word, freq = df$freq, min.freq = 1, max.words=100, random.order=FALSE, rot.per=0.35, colors=brewer.pal(8, "Dark2")) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment