In alishinski/clustRcompaR: Easy Interface for Clustering a Set of Documents and Exploring Group- Based Patterns

knitr::opts_chunk$set(echo = TRUE)

library(clustRcompaR)
library(dplyr)

# inaugural addresses
d <- inaugural_addresses
d <- mutate(d, century = ifelse(Year < 1800, "17th",
                                ifelse(Year >= 1800 & Year < 1900, "18th",
                                       ifelse(Year >= 1900 & Year < 2000, "19th", "20th"))))

three_clusters <- cluster(d, n_clusters = 3)
extract_terms(three_clusters)
three_clusters_comparison <- compare(three_clusters, "century")
compare_plot(three_clusters_comparison)
compare_test(three_clusters_comparison)

d <- readr::read_csv("../scip_data.csv")
d <- select(d, audience2, everything())
four_cluster_solution <- cluster(d, n_clusters = 4)
four_cluster_comparison <- compare(four_cluster_solution, "teacher")
compare_plot(four_cluster_comparison)
compare_test(four_cluster_comparison)

sessionInfo()
save.image("1-11-2018.Rdata")

alishinski/clustRcompaR documentation built on May 12, 2019, 9:54 a.m.