Readability and other minor edits

.gitignore

@@ -1,10 +1,10 @@
 .DS_Store
 .dropbox
+*.Rhistory
 code_check*
 nohup.out
-+*.pdf
+*.pdf
+*.csv
 slides/01-Slides/cache
 slides/01-Slides/data
 slides/05-Slides/cache
-
-

03-Classification/email_classify.R

@@ -59,7 +59,7 @@ ggsave(plot = ex1,
 # words as features
 get.msg <- function(path)
 {
-  con <- file(path, open = "rt", encoding = "latin1")
+  con <- file(path, open = "rb", encoding = "latin1")
   text <- readLines(con)
   # The message always begins after the first full line break
   msg <- text[seq(which(text == "")[1] + 1, length(text), 1)]

04-Ranking/priority_inbox.R

@@ -129,6 +129,7 @@ pattern1 <- "%a, %d %b %Y %H:%M:%S"
 pattern2 <- "%d %b %Y %H:%M:%S"
 
 allparse.df$Date <- date.converter(allparse.df$Date, pattern1, pattern2)
+allparse.df$Date <- as.POSIXct(allparse.df$Date)
 
 # Convert emails and subjects to lower-case
 allparse.df$Subject <- tolower(allparse.df$Subject)
@@ -142,7 +143,7 @@ priority.df <- allparse.df[with(allparse.df, order(Date)), ]
 priority.train <- priority.df[1:(round(nrow(priority.df) / 2)), ]
 
 # The first step is to create rank weightings for all of the features.
-# We begin with the simpliest: who the email is from.
+# We begin with the simplest: who the email is from.
 
 # Calculate the frequency of correspondence with all emailers in the training set
 from.weight <- ddply(priority.train, .(From.EMail),

05-Regression/chapter05.R

@@ -18,6 +18,7 @@
 # Otherwise you will see errors when loading data or saving figures!
 
 library('ggplot2')
+dir.create("images")
 
 # First snippet
 ages <- read.csv(file.path('data', 'longevity.csv'))

06-Regularization/chapter06.R

@@ -18,6 +18,7 @@
 # Otherwise you will see errors when loading data or saving figures!
 
 library('ggplot2')
+library('Hmisc')
 
 # First snippet
 set.seed(1)

07-Optimization/chapter07.R

@@ -237,7 +237,7 @@ propose.modified.cipher <- function(cipher)
 # Seventeenth code snippet
 load(file.path('data', 'lexical_database.Rdata'))
 
-# Eighteength code snippet
+# Eighteenth code snippet
 lexical.database[['a']]
 lexical.database[['the']]
 lexical.database[['he']]

10-Recommendations/chapter10.R

@@ -143,7 +143,7 @@ row.names(user.package.matrix) <- user.package.matrix[, 1]
 user.package.matrix <- user.package.matrix[, -1]
 
 # Tenth code snippet
-similarities <- cor(user.package.matrix)
+suppressWarnings(similarities <- cor(user.package.matrix))
 
 nrow(similarities)
 #[1] 2487

11-SNA/02_twitter_net.R

@@ -65,10 +65,10 @@ user.net  <- set.vertex.attribute(user.net, "Label", value = get.vertex.attribut
 
 # Next, extract the 2-core, and remove pendants generated as a result
 user.cores <- graph.coreness(user.net, mode = "in")
-user.clean <- subgraph(user.net, which(user.cores > 1) - 1)
+user.clean <- induced.subgraph(user.net, which(user.cores > 1) - 1)
 
 # Finally, extract ego.net
-user.ego <- subgraph(user.net, c(0, neighbors(user.net, user, mode = "out")))
+user.ego <- induced.subgraph(user.net, c(0, neighbors(user.net, user, mode = "out")))
 
 # Add hierarchical clustering data to network
 user.sp <- shortest.paths(user.ego)

fast_check.R

@@ -39,7 +39,9 @@ source('chapter10.R')
 setwd('..')
 
 #setwd('11-SNA')
-#source('chapter09.R')
+#source('01_google_sg.R')
+#source('02_twitter_net.R')
+#source('03_twitter_rec.R')
 #setwd('..')
 
 setwd('12-Model_Comparison')

package_installer.R

@@ -33,7 +33,7 @@ cran.packages <- c("e1071",
                    "tm",
                    "XML")
 
-cat("This script will now attempt to install all of the R packages used in 'Machine Learning for Hackers'")
+cat("This script will now attempt to install all of the R packages used in 'Machine Learning for Hackers'\n")
 
 for(p in cran.packages) {
     if(!suppressWarnings(require(p, character.only = TRUE, quietly = TRUE))) {