The capstone project aims to develop a predictive text model employing a huge text corpus of documents as training data. Natural language processing techniques will be employed to do the analysis.
library(stringi)
library(tm)
## Loading required package: NLP
library(NLP)
library(RWeka)
library(ggplot2)
##
## Attaching package: 'ggplot2'
## The following object is masked from 'package:NLP':
##
## annotate
setwd("E:/Coursera/Coursera-SwiftKey/final/en_US")
blogs <- readLines("en_US.blogs.txt", warn = FALSE, encoding = "UTF-8")
news <- readLines("en_US.news.txt", warn = FALSE, encoding = "UTF-8")
twitter <- readLines("en_US.twitter.txt", warn = FALSE, encoding = "UTF-8")
# Get file statistics
size_blogs <- file.info("en_US.blogs.txt")$size / 1024^2 # Megabytes
size_news <- file.info("en_US.news.txt")$size / 1024^2 # Megabytes
size_twitter <- file.info("en_US.twitter.txt")$size / 1024^2 # Megabytes
# Get number of lines
len_blogs <- length(blogs) # 899,288 lines
len_news <- length(news) # 1,010,242 lines
len_twitter <- length(twitter) # 2,360,148
# Get number of characters
nchar_blogs <- sum(nchar(blogs))
nchar_news <- sum(nchar(news))
nchar_twitter <- sum(nchar(twitter))
# Get number of words
nword_blogs <- sum(stri_count_words(blogs)) # words at blogs = 37,546,246
nword_news <- sum(stri_count_words(news)) # words at news = 34,762,395
nword_twitter <-sum(stri_count_words(twitter)) # words at twitter = 30,093,410
# Create table
data.frame(file.name = c("Blogs", "News", "Twitter"),
files.size.MB = c(size_blogs, size_news, size_twitter),
num.lines = c(len_blogs, len_news, len_twitter),
num.character = c(nchar_blogs, nchar_news, nchar_twitter),
num.words = c(nword_blogs, nword_news, nword_twitter))
## file.name files.size.MB num.lines num.character num.words
## 1 Blogs NA 899288 206824505 37546806
## 2 News NA 77259 15639408 2674561
## 3 Twitter NA 2360148 162096031 30096649
Remove all non-English characters, then create a sample dataset that includes 1% of each of the three original datasets.
set.seed(12345)
blogs1 <- iconv(blogs, "latin1", "ASCII", sub = "")
news1 <- iconv(news, "latin1", "ASCII", sub = "")
twitter1 <- iconv(twitter, "latin1", "ASCII", sub = "")
# Sample data set: 1% of each file
sample_data <- c(sample(blogs1, length(blogs1) * 0.01),
sample(news1, length(news1) * 0.01),
sample(twitter1, length(twitter1) * 0.01))
Since Data sets is too big for processing, so using sample() function, I sample 1% of each file.
corpus <- VCorpus(VectorSource(sample_data))
corpus1 <- tm_map(corpus, removePunctuation)
corpus2 <- tm_map(corpus1, stripWhitespace)
corpus3 <- tm_map(corpus2, tolower) # Convert to lowercase
corpus4 <- tm_map(corpus3, removeNumbers)
corpus5 <- tm_map(corpus4, PlainTextDocument)
# Remove stop words in English (e.g., "a", "as", "at", "so", etc.)
corpus6 <- tm_map(corpus5, removeWords, stopwords("english"))
In Natural Language Processing (NLP), n-gram is a contiguous sequence of n items from a given sequence of text or speech. Unigrams are single words. Bigrams are two words combinations. Trigrams are three-word combinations.
The following function is used to extract 1-grams, 2-grams, 3-grams from the text Corpus using RWeka.
# Functions to tokenize the sample and construct matrices of unigrams, bigrams, and trigrams.
one <- function(x) NGramTokenizer(x, Weka_control(min = 1, max = 1))
two <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2))
thr <- function(x) NGramTokenizer(x, Weka_control(min = 3, max = 3))
one_table <- TermDocumentMatrix(corpus6, control = list(tokenize = one))
two_table <- TermDocumentMatrix(corpus6, control = list(tokenize = two))
thr_table <- TermDocumentMatrix(corpus6, control = list(tokenize = thr))
# Find the frequency of terms in each of these 3 matrices and construct dataframes of these frequencies.
one_corpus <- findFreqTerms(one_table, lowfreq = 1000)
two_corpus <- findFreqTerms(two_table, lowfreq = 80)
thr_corpus <- findFreqTerms(thr_table, lowfreq = 10)
one_corpus_num <- rowSums(as.matrix(one_table[one_corpus,]))
one_corpus_table <- data.frame(Word = names(one_corpus_num), frequency = one_corpus_num)
one_corpus_sort <- one_corpus_table[order(-one_corpus_table$frequency),]
head(one_corpus_sort)
## Word frequency
## just just 2576
## like like 2218
## will will 2211
## one one 2049
## get get 1869
## can can 1866
two_corpus_num <- rowSums(as.matrix(two_table[two_corpus,]))
two_corpus_table <- data.frame(Word = names(two_corpus_num), frequency = two_corpus_num)
two_corpus_sort <- two_corpus_table[order(-two_corpus_table$frequency),]
head(two_corpus_sort)
## Word frequency
## cant wait cant wait 208
## right now right now 206
## dont know dont know 164
## last night last night 148
## im going im going 130
## feel like feel like 125
thr_corpus_num <- rowSums(as.matrix(thr_table[thr_corpus,]))
thr_corpus_table <- data.frame(Word = names(thr_corpus_num), frequency = thr_corpus_num)
thr_corpus_sort <- thr_corpus_table[order(-thr_corpus_table$frequency),]
head(thr_corpus_sort)
## Word frequency
## cant wait see cant wait see 45
## happy mothers day happy mothers day 36
## happy new year happy new year 24
## im pretty sure im pretty sure 18
## italy lakes holidays italy lakes holidays 18
## little italy boston little italy boston 17
The frequency distribution of each n-grams category were visualized into 3 different bar plots.
# Bar plots for unigrams, bigrams, and trigrams
one_g <- ggplot(one_corpus_sort[1:10, ], aes(x = reorder(Word, -frequency), y = frequency, fill = frequency)) +
geom_bar(stat = "identity") +
labs(title = "Unigrams", x = "Words", y = "Frequency") +
theme(axis.text.x = element_text(angle = 90),
plot.title = element_text(color = "blue", size = 14, face = "bold"))
two_g <- ggplot(two_corpus_sort[1:10, ], aes(x = reorder(Word, -frequency), y = frequency, fill = frequency)) +
geom_bar(stat = "identity") +
labs(title = "Bigrams", x = "Words", y = "Frequency") +
theme(axis.text.x = element_text(angle = 90),
plot.title = element_text(color = "green", size = 14, face = "bold"))
thr_g <- ggplot(thr_corpus_sort[1:10, ], aes(x = reorder(Word, -frequency), y = frequency, fill = frequency)) +
geom_bar(stat = "identity") +
labs(title = "Trigrams", x = "Words", y = "Frequency") +
theme(axis.text.x = element_text(angle = 90),
plot.title = element_text(color = "red", size = 14, face = "bold"))
one_g
two_g
thr_g
Ideas: Use a text input box as the user interface of the Shiny app.
Next Steps: 1.Build a predictive algorithm 2.Build a a Shiny app, that suggest the most likely next word after a phrase is typed 3.Prepare a pitch about the app and publish it at “shinyapps.io” server.