Creole Linguistics Analysis(Trial).Rmd

---
title: "Creole Linguistics Analysis"
author: "Tariq Williams" 
date: "April 2023"
output: 
  github_document: 
    toc: true
    toc_depth: 2
---

```{r setup, include = FALSE}
# This setup chunk sets global defaults and includes the tidyverse packages
# The option include = FALSE prevents warnings and messages from printing to your report.
# Change the next option to echo = FALSE to hide code chunks by default 
knitr::opts_chunk$set(echo = FALSE)
library(tidyverse)
library(tm)
library(readxl)
```

#Read in data

```{r}

Song_Scrape_Trial <- read_excel("Song Scrape Trial.xlsx")

english_words_patois_edit <- read.table("english_words_patois_edit.txt", header = FALSE, col.names = "words")

zongo <- read_excel("lyrics_3.xlsx")

lyrics_data <- read_excel("lyrics_3.xlsx")
```

#Data test 

```{r}


# download the English Words 
#download.file("https://raw.githubusercontent.com/dwyl/english-words/master/words.txt",
              # destfile = "english_words.txt", quiet = TRUE)

# read in the Patois text
text <- "Dem love chat, dem nuh run dem block Run dem block, 1st Class Outside wid half-dozen gunman ready fi do the action"

# extract all words from the text
all_words <- unlist(strsplit(text, "\\W+"))

# read in the English Words 
english_words <- readLines("english_words.txt")


# identify the English words in the Patois text
english_words_in_text <- all_words[all_words %in% english_words]

# print the identified English words
english_words_in_text



````


#Data test Trial 2 

```{r}

# read in the Patois text
text <- "Dem love chat, dem nuh run dem block Run dem block, 1st Class Outside wid half-dozen gunman ready fi do the action"

# extract all words from the text
all_words <- unlist(strsplit(text, "\\W+"))

# read in the English Words 
english_words <- readLines("english_words.txt")


# identify the English words in the Patois text
english_words_in_text <- all_words[all_words %in% english_words]

# print the identified English words
english_words_in_text


````

#Test 3 

````{r}

# read in the English words 
english_words <- readLines("english_words_patois_edit.txt")

# create an empty list to store the identified English words in each song
english_words_by_song <- list()

# loop over each row of the dataset and extract English words from the lyrics
for(i in 1:nrow(Song_Scrape_Trial)) {
  # extract the lyrics of the current song
  lyrics <- Song_Scrape_Trial$Lyrics[i]
  # extract all words from the lyrics
  all_words <- unlist(strsplit(lyrics, "\\W+"))
  # identify the English words in the lyrics
  english_words_in_song <- all_words[all_words %in% english_words]
  # add the identified English words to the list
  english_words_by_song[[i]] <- english_words_in_song
}

# print the identified English words in each song
for(i in 1:length(english_words_by_song)) {
  cat("Song", i , "English words:", english_words_by_song[[i]], "\n")}



````


#Final Test 

```{r}


# read in the English Words 
english_words <- readLines("english_words_patois_edit.txt")

# create variables to store the counts
english_word_count <- numeric(nrow(Song_Scrape_Trial))
patois_word_count <- numeric(nrow(Song_Scrape_Trial))

# loop through each row in the table
for (i in 1:nrow(Song_Scrape_Trial)) {
  # extract the lyrics from the row
  lyrics <- Song_Scrape_Trial$Lyrics[i]
  
  # split the lyrics into individual words
  words <- unlist(strsplit(lyrics, "\\W+"))
  
  # count the number of English and non-English words
  english_word_count[i] <- sum(words %in% english_words)
  patois_word_count[i] <- length(words) - english_word_count[i]
}

# create a data frame with the results
word_counts <- data.frame(Song_Scrape_Trial$Song, english_word_count, patois_word_count)
colnames(word_counts) <- c("Song", "English Words", "Patois Words")


````


#Final Test with new data frame 3 

```{r}

# create variables to store the counts
english_word_count <- numeric(nrow(Try_2))
patois_word_count <- numeric(nrow(Try_2))

# loop through each row in the table
for (i in 1:nrow(Try_2)) {
  # extract the lyrics from the row
  lyrics <- Try_2$Lyrics[i]
  
  # split the lyrics into individual words
  words <- unlist(strsplit(lyrics, "\\W+"))
  
  # count the number of English and non-English words
  english_word_count[i] <- sum(words %in% english_words)
  patois_word_count[i] <- length(words) - english_word_count[i]
}

# create a data frame with the results
word_counts <- data.frame(Try_2$Song, english_word_count, patois_word_count)
colnames(word_counts) <- c("Song", "English Words", "Patois Words")


```` 


#Final Test with new data frame 3 

```{r}

# create variables to store the counts
english_word_count <- numeric(nrow(Try_2))
patois_word_count <- numeric(nrow(Try_2))

# loop through each row in the table
for (i in 1:nrow(Try_2)) {
  # extract the lyrics from the row
  lyrics <- Try_2$Lyrics[i]
  
  # split the lyrics into individual words
  words <- unlist(strsplit(lyrics, "\\W+"))
  
  # count the number of English and non-English words
  english_word_count[i] <- sum(words %in% english_words)
  patois_word_count[i] <- length(words) - english_word_count[i]
}

# create a data frame with the results
word_counts <- data.frame(Try_2$Song, english_word_count, patois_word_count)
colnames(word_counts) <- c("Song", "English Words", "Patois Words")


```` 

#Verification 

```{r}

# read in the English Words
english_words <- readLines("english_words_patois_edit.txt")

# convert all the words in the English dictionary to lowercase
english_words <- tolower(english_words)

# initialize lists to store english and patois words
english_words_list <- list()
patois_words_list <- list()

# loop through each row in the Song_Scrape_Trial data frame
for (i in 1:nrow(lyrics_data)) {
  # extract lyrics from the current row
  lyrics <- lyrics_data[i, "Lyrics"]
  
    # convert all the words in the lyrics to lowercase
  lyrics <- tolower(lyrics)
  
  # extract all words from the lyrics
  all_words <- unlist(strsplit(as.character(lyrics), "\\W+"))
  
  # identify the English words in the lyrics
  english_words_in_lyrics <- all_words[all_words %in% english_words]
  
  # add the English words to the english_words_list
  english_words_list[[i]] <- english_words_in_lyrics
  
  # add the patois words to the patois_words_list
  patois_words_list[[i]] <- all_words[!all_words %in% english_words]
}

# flatten the english and patois word lists
english_words <- unlist(english_words_list)
patois_words <- unlist(patois_words_list)

# print all the English words found
cat("English words:\n")
print(unique(english_words))

# print all the patois words found
cat("\n Patois words:\n")
print(unique(patois_words))



`````

# Specified Verification W/ lyrics_data (25 variables)

`````{r}

# remove words ending with "embed" from the Lyrics column
lyrics_data$Lyrics <- gsub("\\b\\w+embed\\b", "", lyrics_data$Lyrics, ignore.case = TRUE)


``````

`````{r}

# read in the English Words
english_words <- readLines("english_words_patois_edit.txt")

# convert all the words in the English dictionary to lowercase
english_words <- tolower(english_words)



# initialize lists to store english and patois words
english_words_list <- list()
patois_words_list <- list()

# specify the song to analyze
song_index <- 1

# loop through each row in the Song_Scrape_Trial data frame
for (i in 1:nrow(lyrics_data)) {
  # extract lyrics from the current row
  lyrics <- lyrics_data[song_index, "Lyrics"]
  
    # convert all the words in the lyrics to lowercase
  lyrics <- tolower(lyrics)
  
  # extract all words from the lyrics
  all_words <- unlist(strsplit(as.character(lyrics), "\\W+"))
  
  # identify the English words in the lyrics
  english_words_in_lyrics <- all_words[all_words %in% english_words]
  
  # add the English words to the english_words_list
  english_words_list[[i]] <- english_words_in_lyrics
  
  # add the patois words to the patois_words_list
  patois_words_list[[i]] <- all_words[!all_words %in% english_words]
}

# flatten the english and patois word lists
english_words <- unlist(english_words_list)
patois_words <- unlist(patois_words_list)

# print all the English words found
cat("English words:\n")
print(unique(english_words))

# print all the patois words found
cat("\n Patois words:\n")
print(unique(patois_words))



`````


# Specified Verification W/ lyrics_final (100 variables)


`````{r}

# read in the English Words
english_words <- readLines("english_words_patois_edit.txt")

# convert all the words in the English dictionary to lowercase
english_words <- tolower(english_words)

# initialize lists to store english and patois words
english_words_list <- list()
patois_words_list <- list()

# specify the song to analyze
song_index <- 1

# loop through each row in the Song_Scrape_Trial data frame
for (i in 1:nrow(lyrics_final)) {
  # extract lyrics from the current row
  lyrics <- lyrics_final[song_index, "Lyrics"]
  
    # convert all the words in the lyrics to lowercase
  lyrics <- tolower(lyrics)
  
  # extract all words from the lyrics
  all_words <- unlist(strsplit(as.character(lyrics), "\\W+"))
  
  # identify the English words in the lyrics
  english_words_in_lyrics <- all_words[all_words %in% english_words]
  
  # add the English words to the english_words_list
  english_words_list[[i]] <- english_words_in_lyrics
  
  # add the patois words to the patois_words_list
  patois_words_list[[i]] <- all_words[!all_words %in% english_words]
}

# flatten the english and patois word lists
english_words <- unlist(english_words_list)
patois_words <- unlist(patois_words_list)

# print all the English words found
cat("English words:\n")
print(unique(english_words))

# print all the patois words found
cat("\n Patois words:\n")
print(unique(patois_words))

`````