Created
April 17, 2024 01:51
-
-
Save caitlinhudon/f8b1d0533279d0791788da3cd121c078 to your computer and use it in GitHub Desktop.
text_analysis.R
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(tidytext) | |
library(dplyr) | |
library(tokenizers) | |
library(ggplot2) | |
library(wordcloud) | |
# Function to stem generic text input, generate n-grams, and plot results | |
generate_ngrams_and_plots <- function(text_input) { | |
# Convert text input to a tibble | |
text_input_df <- tibble(text = text_input) | |
# Tokenize and stem the text | |
tokens <- text_input_df %>% | |
unnest_tokens(word, text) %>% | |
mutate(word = SnowballC::wordStem(word)) | |
# Generate n-grams for n=1,2,3,4 and combine into a single data frame | |
ngrams_df <- bind_rows(lapply(1:4, function(n) { | |
tokens %>% | |
unnest_tokens(input = word, output = paste("ngram", n, sep="_"), token = "ngrams", n = n) %>% | |
mutate(n = n) | |
})) | |
# Count the frequency of each n-gram | |
ngrams_freq <- ngrams_df %>% | |
count(n, value = paste("ngram", n, sep="_"), name = "ngram", sort = TRUE) | |
# Plot the most frequent n-grams for each n | |
ngrams_freq %>% | |
group_by(n) %>% | |
top_n(10, n) %>% | |
ungroup() %>% | |
ggplot(aes(x = reorder(ngram, n), y = n)) + | |
geom_bar(stat = "identity") + | |
facet_wrap(~n, scales = "free") + | |
xlab("N-gram") + | |
ylab("Frequency") + | |
theme_minimal() + | |
theme(axis.text.x = element_text(angle = 45, hjust = 1)) | |
# Generate word clouds for the most frequent terms for each n | |
lapply(unique(ngrams_freq$n), function(n) { | |
subset_ngrams <- subset(ngrams_freq, n == n) | |
wordcloud(words = subset_ngrams$ngram, freq = subset_ngrams$n, min.freq = 1, | |
max.words = 100, random.order = FALSE, rot.per = 0.35, | |
colors = brewer.pal(8, "Dark2")) | |
}) | |
} | |
# Example usage | |
text_input <- c("example_document.txt", "sample_file.pdf", "test_script.py") | |
generate_ngrams_and_plots(text_input) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment