Document Clustering

Sys.setenv(NOAWT=TRUE)
library(tm)

## Loading required package: NLP

library(magrittr)
library(SnowballC)
library(ggplot2)

## 
## Attaching package: 'ggplot2'
## 
## The following object is masked from 'package:NLP':
## 
##     annotate

library(ggdendro)

my.corpus <- Corpus(DirSource("~/dev/tracts-for-the-times/clean/")) %>%
  tm_map(removePunctuation) %>%
  tm_map(removeWords, stopwords("english")) %>%
  tm_map(content_transformer(tolower)) %>%
  tm_map(removeNumbers) %>%
  tm_map(stemDocument)

my.dtm <- DocumentTermMatrix(my.corpus,
                             control = list(weighting = weightTfIdf,
                                            stopwords = TRUE))

fit <- my.dtm %>%
  as.matrix() %>% 
  as.data.frame() %>%
  scale() %>%
  dist() %>%
  hclust(method = "ward.D") 

The plot:

plot(fit)
rect.hclust(fit, k=8, border="red")

In ggplot2:

ggdendrogram(fit, rotate = TRUE) +
  ggtitle("Tracts for the Times")