#
# hands on - first attempt
#

one <- 1

one + one

two <- one + one

two

#
# data classes - properties of elements
#

as.numeric(10.49)

as.integer(10.49)

as.character(-1)

as.numeric("anythingwithinquotes")

5 > 10

as.character(5 > 10)

#
# R objects - vector
#


c(2,3,5)

c("aa", "bb", "cc", "dd", "ee")

c(TRUE, FALSE, TRUE, FALSE, FALSE)


#
# R objects - matrix
#

m <- matrix(data = c(1,2,3,4,5,6,7,8,9,10,11,12), 
            nrow = 3, 
            ncol = 4)

m

#
# R objects - list
#

n <- c(2, 3, 5)
s <- c("aa", "bb", "cc", "dd", "ee")
x <- list(n, s, b, 3) # x contains copy of n, s

x

#
# R objects - data frame
#

teams <- c("PHI","NYM","FLA","ATL","WSN")
wins <- c(92,89,94,72,59)
losses <- c(70,73,77,90,102)

data <- data.frame(teams,wins,losses)

data

#
# R functions
#


sqrt(9)

sample(x = 0:100, size = 10, rep = FALSE)

sample()

#
# libraries
#

install.packages("network")

library("network")

library(network)

require("network") 

detach("package:network", unload = TRUE) 

#
# libraries we might use
#

install.packages("tm")

install.packages("wordcloud")

install.packages("quanteda")

#
# basic functions
# 

c() # combine two or more elements into an object

class() # explore elements’ data class
length() # explore number of first dim. of object
dim() # explore dimensions of two-dimensional obj.
nrow() # number of rows
ncol() # number of columns

head() # first few rows of data 
tail() # last few rows of data 
str() # explore structure of object

names() # names in the named vector - one dimension 
rownames() # names of rows - two dimensions 
colnames() # names of columns - two dimensions

#
# working directory
#

setwd("C:\\Users\\Lukas\\Desktop\\data")

setwd("C:/Users/Lukas/Desktop/data")

#
# exporting object - tabular
#

frequencies <- c(92,89,94,72,59) 

write.table(frequencies, 
            "frequencies.csv", 
            sep = ",", 
            row.names = FALSE, 
            col.names = TRUE, 
            fileEncoding = "UTF-8") 

#
# explorting object - unstructured
#

frequencies <- c(92,89,94,72,59) 

writeLines(frequencies, 
           "frequencies.txt") 

#
# loading tm package
#

library(tm)

#
# corpus
#

getSources()

?Corpus()

?inspect()

my.texts <-  "C:\\Users\\Lukas\\Desktop\\data\\"

directory.source <- DirSource(directory = my.texts)

text.corpus <- Corpus(directory.source) 

text.corpus

#
# corpus operations
#

?removePunctuation()

?removeWords()

?stripWhitespace()

?removeNumbers()

?stemDocument()

?PlainTextDocument()

#
# corpus operations
#

edited.corpus <- text.corpus

edited.corpus <- tm_map(edited.corpus, removeNumbers)

edited.corpus <- tm_map(edited.corpus, removePunctuation)

edited.corpus <- tm_map(edited.corpus, stripWhitespace)

edited.corpus <- tm_map(edited.corpus, 
                        removeWords, 
                        stopwords("english"))

#
# term-document matrix
#

?TermDocumentMatrix()

?DocumentTermMatrix()

?as.matrix()

#
# term-document matrix
#

tdm <- TermDocumentMatrix(edited.corpus) 

dtm <- DocumentTermMatrix(edited.corpus) 

tdm.matrixed <- as.matrix(tdm) 

#
# useful functions
#

?removeSparseTerms()

?findFreqTerms()

?findAssocs()

#
# frequencies
#

tdm.matrixed <- as.matrix(tdm) 

frequencies <- rowSums(tdm.matrixed)

frequencies <- sort(frequencies, decreasing = T)

head(frequencies)

#
# wordcloud
#

tdm.matrixed <- as.matrix(tdm)

frequencies <- rowSums(tdm.matrixed)

frequencies <- sort(frequencies,decreasing = T)

frequencies <- frequencies[1:40]

terms <- names(frequencies) 

library(wordcloud)

wordcloud(words = terms, 
          freq = frequencies,
          scale = c(5,0.5),
          max.words = 150,
          random.order = F,
          rot.per = 0,
          colors = "royalblue")

#
# well done!
#