#
# This is a Shiny web application. You can run the application by clicking
# the 'Run App' button above.
#
# Find out more about building applications with Shiny here:
#
# http://shiny.rstudio.com/
#
# Load Libraries
v_required_packages <- c("shiny", "shinythemes", "shinyjs",
"dplyr", "pdftools", "tm", "wordcloud",
"DT", "readr", "textclean", "SnowballC")
for (v_package in v_required_packages) {
if(v_package %in% rownames(installed.packages()) == FALSE)
{
install.packages(v_package, dependencies=TRUE)
}
}
library(shiny)
library(shinythemes)
library(shinyjs)
##
## Attaching package: 'shinyjs'
## The following object is masked from 'package:shiny':
##
## runExample
## The following objects are masked from 'package:methods':
##
## removeClass, show
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(pdftools)
library(tm)
## Loading required package: NLP
library(wordcloud)
## Loading required package: RColorBrewer
library(DT)
##
## Attaching package: 'DT'
## The following objects are masked from 'package:shiny':
##
## dataTableOutput, renderDataTable
library(readr)
library(textclean)
library(SnowballC)
C_SLIDER_DEFAULT_VALUE <- 50
C_TEXT_FILE_INDICATOR <- "TXT"
C_PDF_FILE_INDICATOR <- "PDF"
v_df <- reactive({
data.frame(ind = c("test1", "test2"), n = c(10, 20))
})
v_prev_file_type <- C_TEXT_FILE_INDICATOR
gatherFileStatistics <- function(p_input_file_name) {
v_file_name <- p_input_file_name
v_generation_date <- format(Sys.Date(), "%Y-%m-%d")
v_total_words <- nrow(v_df())
### Form the record
v_record <- tibble(
v_file_name,
v_generation_date,
v_total_words
)
return(v_record)
}
# Define UI for application
ui <- fluidPage(
shinyjs::useShinyjs(),
theme = shinytheme("united"),
tags$head(
tags$style(
HTML(".shiny-notification {
position:fixed;
top: calc(50%);
left: calc(50%);
font-family:Verdana;
fontSize:xx-large;
}
"
)
)
),
# Application title
fluidRow(
column(width = 3,
img(src="ParthaInPetra.jpg", width=200, height=112)
),
column(width = 6,
h1("ShabdhMegh", style="color:blue; text-align: center;"),
h3("Word Cloud Producer", style="color:darkred; text-align: center;")
),
column(width = 3,
h4("...", style="color:blue; text-align: right;"),
h4("Developed by: Partha Majumdar", style="color:blue; text-align: right;"),
h5("Riyadh (Saudi Arabia), 30-December-2019", style="color:black; text-align: right;")
)
),
fluidRow(
column(width = 4,
wellPanel(
radioButtons("v_file_type", h3("Select the File Type to Upload"),
c("Text File" = C_TEXT_FILE_INDICATOR,
"PDF File" = C_PDF_FILE_INDICATOR),
inline = TRUE),
fluidRow(
h3("Select a file from your Computer to get started to analyse the contents of the file.", style="color:blue; text-align: center;"),
h4("Please select a FILE, before clicking on any TAB. This is a bug in the system.", style="color:darkred; text-align: center;"),
fileInput("v_input_file_txt", h3("Choose Text File"),
multiple = FALSE, placeholder = "No file selected",
accept = c("text/csv",
"text/comma-separated-values,text/plain",
".txt")
),
fileInput("v_input_file_pdf", h3("Choose PDF File"),
multiple = FALSE, placeholder = "No file selected",
accept = c("application/PDF",
".pdf")
)
),
fluidRow(
wellPanel(
p("To learn how to use SaabdhMegh, visit the ",
a("SaabdhMegh Demonstration Video.",
href = "https://youtu.be/iAxIHqfEZsc",
target="_blank")
)
)
),
fluidRow(
downloadButton("report", "Download Report")
)
)
),
column(width = 8,
fluidRow(
div(id = "DummyDisplay",
img(src="CourseLogo.jpg", width=1200, height=900)
),
div(id = "OutputTabsPDF",
tabsetPanel(id = "mainTabsetPDF", type = "tabs",
tabPanel("DATA",
h3("Word Frequency"),
dataTableOutput("PDFcontents")
),
tabPanel("Word Cloud",
sliderInput("v_number_of_words_pdf",
h4("Set Number of Words to Display"),
min = 20, max = 500,
value = C_SLIDER_DEFAULT_VALUE,
step = 10, ticks = TRUE),
plotOutput("wordCloudPDF", width = "100%")
)
)
),
div(id = "OutputTabsTXT",
tabsetPanel(id = "mainTabsetTXT", type = "tabs",
tabPanel("DATA",
h3("Word Frequency"),
dataTableOutput("TXTcontents")
),
tabPanel("Word Cloud",
sliderInput("v_number_of_words_txt",
h4("Set Number of Words to Display"),
min = 20, max = 500,
value = C_SLIDER_DEFAULT_VALUE,
step = 10, ticks = TRUE),
plotOutput("wordCloudTXT", width = "100%")
)
)
)
)
)
)
)
# Define server logic required to draw a histogram
server <- function(input, output, session) {
observe({
if ( input$v_file_type == C_TEXT_FILE_INDICATOR ) {
shinyjs::hide("v_input_file_pdf")
shinyjs::show("v_input_file_txt")
} else {
shinyjs::show("v_input_file_pdf")
shinyjs::hide("v_input_file_txt")
}
if ( (is.null(input$v_input_file_pdf) || input$v_input_file_pdf == "") &&
(is.null(input$v_input_file_txt) || input$v_input_file_txt == "")
)
{
shinyjs::show("DummyDisplay")
shinyjs::hide("OutputTabsPDF")
shinyjs::hide("OutputTabsTXT")
shinyjs::disable("report")
} else {
if ( input$v_file_type == C_TEXT_FILE_INDICATOR ) {
if (is.null(input$v_input_file_txt) || input$v_input_file_txt == "")
{
shinyjs::hide("OutputTabsTXT")
shinyjs::show("DummyDisplay")
shinyjs::disable("report")
} else {
if (v_prev_file_type == C_PDF_FILE_INDICATOR) {
shinyjs::hide("OutputTabsTXT")
shinyjs::show("DummyDisplay")
shinyjs::disable("report")
} else {
shinyjs::show("OutputTabsTXT")
shinyjs::hide("DummyDisplay")
shinyjs::enable("report")
}
}
shinyjs::hide("OutputTabsPDF")
v_prev_file_type <<- C_TEXT_FILE_INDICATOR
} else {
if (is.null(input$v_input_file_pdf) || input$v_input_file_pdf == "")
{
shinyjs::hide("OutputTabsPDF")
shinyjs::show("DummyDisplay")
shinyjs::disable("report")
} else {
if (v_prev_file_type == C_TEXT_FILE_INDICATOR) {
shinyjs::hide("OutputTabsPDF")
shinyjs::show("DummyDisplay")
shinyjs::disable("report")
} else {
shinyjs::show("OutputTabsPDF")
shinyjs::hide("DummyDisplay")
shinyjs::enable("report")
}
}
shinyjs::hide("OutputTabsTXT")
v_prev_file_type <<- C_PDF_FILE_INDICATOR
}
}
})
observeEvent(input$v_input_file_pdf, {
# Reset Display to DATA TAB
updateTabsetPanel(session, "mainTabsetPDF",
selected = "DATA"
)
# Reset the Slider
updateSliderInput(session, 'v_number_of_words_pdf', value = C_SLIDER_DEFAULT_VALUE)
})
observeEvent(input$v_input_file_txt, {
# Reset Display to DATA TAB
updateTabsetPanel(session, "mainTabsetTXT",
selected = "DATA"
)
# Reset the Slider
updateSliderInput(session, 'v_number_of_words_txt', value = C_SLIDER_DEFAULT_VALUE)
})
output$PDFcontents <- renderDataTable({
# input$v_input_file_pdf will be NULL initially. After the user selects
# and uploads a file, data will be shown.
# cat(paste("Point 1: ***", input$v_input_file, "+++\n", sep = ''), file = stderr())
req(input$v_input_file_pdf)
v_df <<- reactive({
# Read the PDF File
v_raw_text <- pdf_text(input$v_input_file_pdf$datapath) %>%
strsplit("\n")
# Calculate Word Frequency
calculateWordFrequency(v_raw_text)
})
## Gather Statistics and Save Statistics
writeStatistics(input$v_input_file_pdf$name)
displayDataTable()
})
output$TXTcontents <- renderDataTable({
# input$v_input_file_pdf will be NULL initially. After the user selects
# and uploads a file, data will be shown.
# cat(paste("Point 1: ***", input$v_input_file, "+++\n", sep = ''), file = stderr())
req(input$v_input_file_txt)
v_df <<- reactive({
# Read the TXT File
v_text <- tibble(text = gsub("[^[:alnum:]///' ]", "",
read_lines(input$v_input_file_txt$datapath)))
# Drop the Empty Lines
v_raw_text <- drop_empty_row(v_text)
# Calculate Word Frequency
calculateWordFrequency(v_raw_text)
})
## Gather Statistics and Save Statistics
writeStatistics(input$v_input_file_txt$name)
displayDataTable()
})
writeStatistics <- function(l_file_name) {
v_record <- gatherFileStatistics(l_file_name)
if(file.exists("./ShabdhMegh_statistics.csv")) {
v_statistics1 <- read.csv("./ShabdhMegh_statistics.csv")
v_statistics1$X <- NULL
v_statistics <- rbind(v_statistics1, v_record)
} else {
v_statistics <- v_record
}
write.csv(v_statistics, file = "./ShabdhMegh_statistics.csv")
}
displayDataTable <- function() {
DT::datatable(
{ v_df() },
caption = htmltools::tags$caption(
style = 'caption-side: bottom; text-align: center;',
'Table 1: ', htmltools::em('Word Frequency.')
),
extensions = 'Buttons',
options = list(
fixedColumns = TRUE,
autoWidth = TRUE,
ordering = TRUE,
dom = 'Bftsp',
buttons = c('copy', 'csv', 'excel')
))
}
calculateWordFrequency <- function(l_text) {
v_data <- reactive({
# Create the Corpus
v_corpus <- Corpus(VectorSource(l_text))
# Create the Term Document Matrix after cleaning the Corpus
v_tdm <- TermDocumentMatrix(v_corpus,
control =
list(removePunctuation = TRUE,
stopwords = TRUE,
tolower = TRUE,
stemming = TRUE,
removeNumbers = TRUE,
bounds = list(global = c(1, Inf))
)
)
# Find the Frequent Words
v_ft <- findFreqTerms(v_tdm, lowfreq = 1, highfreq = Inf)
# Convert to a Matrix
v_matrix <- as.matrix(v_tdm[v_ft,])
# Sort the Words in DESCENDING Order and create Data Frame
stack(sort(apply(v_matrix, 1, sum), decreasing = TRUE))
})
return (v_data())
}
######## WORD CLOUD
output$wordCloudPDF <- renderPlot({
req(input$v_input_file_pdf)
generateWordCloud(input$v_number_of_words_pdf)
})
######## WORD CLOUD
output$wordCloudTXT <- renderPlot({
req(input$v_input_file_txt)
generateWordCloud(input$v_number_of_words_txt)
})
generateWordCloud <- function(l_number_of_words) {
withProgress(message = 'Generating',
detail = 'This may take a while...', value = 0, {
wordcloud(words = v_df()$ind, freq = v_df()$values, min.freq = 1,
max.words = l_number_of_words,
random.order=FALSE,
colors=brewer.pal(8, "Dark2")
)
})
}
output$report <- downloadHandler(
# For PDF output, change this to "report.pdf"
filename <- "report.pdf",
content <- function(file) {
withProgress(message = 'Generating Report. This takes a minute or two...', value = 0, {
if (input$v_file_type == C_TEXT_FILE_INDICATOR) {
l_file_name <- input$v_input_file_txt$name
l_words_to_display <- input$v_number_of_words_txt
} else {
l_file_name <- input$v_input_file_pdf$name
l_words_to_display <- input$v_number_of_words_pdf
}
# Set up parameters to pass to Rmd document
v_params <- list(
p_input_file = l_file_name,
p_number_of_words_to_display = l_words_to_display,
p_word_frequency = v_df()
)
# Knit the document, passing in the `params` list, and eval it in a
# child of the global environment (this isolates the code in the document
# from the code in this app).
rmarkdown::render("ShabdhMegh.Rmd",
output_file = file,
params = v_params,
envir = new.env(parent = globalenv())
)
})
}
)
}
# Run the application
shinyApp(ui = ui, server = server)
##
## Listening on http://127.0.0.1:4174
