book edits

.gitignore

@@ -2,4 +2,4 @@
 .dropbox
 code_check*
 nohup.out
-+*.pdf
+*.pdf

01-Introduction/ufo_sightings.R

@@ -19,7 +19,7 @@
 # All rights reserved.
 
 # NOTE: If you are running this in the R console you must use the 'setwd' command to set the 
-# working directory for the console to whereever you have saved this file prior to running.
+# working directory for the console to wherever you have saved this file prior to running.
 # Otherwise you will see errors when loading data or saving figures!
 
 # Load libraries and data
@@ -119,7 +119,6 @@ head(ufo.us)
 quick.hist <- ggplot(ufo.us, aes(x = DateOccurred)) +
   geom_histogram() + 
   scale_x_date(breaks = "50 years")
-
 ggsave(plot = quick.hist,
        filename = file.path("images", "quick_hist.pdf"),
        height = 6,

02-Exploration/chapter02.R

@@ -393,7 +393,11 @@ logit.model <- glm(Male ~ Weight + Height,
 
 ggplot(heights.weights, aes(x = Height, y = Weight)) +
   geom_point(aes(color = Gender, alpha = 0.25)) +
+<<<<<<< HEAD
+  scale_alpha(guide= "none") + 
+=======
   scale_alpha(guide = "none") + 
+>>>>>>> jmw/master
   scale_color_manual(values = c("Male" = "black", "Female" = "gray")) +
   theme_bw() +
   stat_abline(intercept = -coef(logit.model)[1] / coef(logit.model)[2],

03-Classification/email_classify.R

@@ -45,7 +45,7 @@ ex1 <- ggplot(val, aes(x, V2)) +
   geom_jitter(aes(shape = as.factor(V3)),
                   position = position_jitter(height = 2)) +
   scale_shape_discrete(guide = "none", solid = FALSE) +
-  geom_hline(aes(yintercept = c(10,30), linetype = 2)) +
+  geom_hline(aes(yintercept = c(10,30)), linetype = 2) +
   theme_bw() +
   xlab("X") +
   ylab("Y")

06-Regularization/chapter06.R

@@ -331,6 +331,7 @@ rmse <- function(y, h)
 }
 
 # Twenty-second code snippet
+
 library('glmnet')
 
 glmnet.fit <- with(training.df, glmnet(poly(X, degree = 10), Y))

07-Optimization/chapter07.R

@@ -76,15 +76,15 @@ a.error <- function(a)
 }
 
 # Seventh code snippet
-curve(sapply(x, function (a) {a.error(a)}), from = -1000, to = 1000)
+curve(sapply(x, function (a) {a.error(a)}), from = -1000, to = 1000, ylab = "Squared Error")
 
 # Eighth code snippet
 b.error <- function(b)
 {
   return(squared.error(heights.weights, 0, b))
 }
 
-curve(sapply(x, function (b) {b.error(b)}), from = -1000, to = 1000)
+curve(sapply(x, function (b) {b.error(b)}), from = -1000, to = 1000, ylab = "Squared Error")
 
 # Ninth code snippet
 ridge.error <- function(heights.weights, a, b, lambda)
@@ -124,13 +124,13 @@ a.ridge.error <- function(a, lambda)
 {
   return(ridge.error(heights.weights, a, 0, lambda))
 }
-curve(sapply(x, function (a) {a.ridge.error(a, lambda)}), from = -1000, to = 1000)
+curve(sapply(x, function (a) {a.ridge.error(a, lambda)}), from = -1000, to = 1000, ylab = "Ridge Error")
 
 b.ridge.error <- function(b, lambda)
 {
   return(ridge.error(heights.weights, 0, b, lambda))
 }
-curve(sapply(x, function (b) {b.ridge.error(b, lambda)}), from = -1000, to = 1000)
+curve(sapply(x, function (b) {b.ridge.error(b, lambda)}), from = -1000, to = 1000, ylab = "Ridge Error")
 
 # Twelfth code snippet
 absolute.error <- function(heights.weights, a, b)
@@ -146,7 +146,7 @@ a.absolute.error <- function(a)
   return(absolute.error(heights.weights, a, 0))
 }
 
-curve(sapply(x, function (a) {a.absolute.error(a)}), from = -1000, to = 1000)
+curve(sapply(x, function (a) {a.absolute.error(a)}), from = -1000, to = 1000, ylab = "Absolute Error")
 
 # Fourteenth code snippet
 english.letters <- c('a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k',

09-MDS/chapter09.R

@@ -83,6 +83,7 @@ ex.dist
 ex.mds <- cmdscale(ex.dist)
 plot(ex.mds, type = 'n')
 text(ex.mds, c('A', 'B', 'C', 'D'))
+grid()
 
 # Seventh code snippet
 library('foreign')
@@ -183,15 +184,15 @@ head(rollcall.mds[[1]])
 cong.110 <- rollcall.mds[[9]]
 
 base.110 <- ggplot(cong.110, aes(x = x, y = y)) +
-  scale_size(to = c(2,2), legend = FALSE) +
-  scale_alpha(legend = FALSE) + theme_bw() +
-  opts(axis.ticks = theme_blank(),
-       axis.text.x = theme_blank(),
-       axis.text.y = theme_blank(),
-       title = "Roll Call Vote MDS Clustering for 110th U.S. Senate",
-       panel.grid.major = theme_blank()) +
+  scale_size(range = c(2,2), guide="none") +
+  scale_alpha(guide = "none") + theme_bw() +
+  theme(axis.ticks = element_blank(),
+       axis.text.x = element_blank(),
+       axis.text.y = element_blank(),
+       panel.grid.major = element_blank()) +
   xlab("") +
   ylab("") +
+  ggtitle("Roll Call Vote MDS Clustering for 110th U.S. Senate") + 
   scale_shape(name = "Party", breaks = c("100", "200", "328"),
               labels = c("Dem.", "Rep.", "Ind."), solid = FALSE) +
   scale_color_manual(name = "Party", values = c("100" = "black",
@@ -213,14 +214,14 @@ print(base.110 + geom_text(aes(color = party,
 all.mds <- do.call(rbind, rollcall.mds)
 all.plot <- ggplot(all.mds, aes(x = x, y = y)) +
   geom_point(aes(shape = party, alpha = 0.75, size = 2)) +
-  scale_size(to = c(2, 2), legend = FALSE) +
-  scale_alpha(legend = FALSE) +
+  scale_size(range = c(2, 2), guide="none") +
+  scale_alpha(guide="none") +
   theme_bw() +
-  opts(axis.ticks = theme_blank(),
-       axis.text.x = theme_blank(),
-       axis.text.y = theme_blank(),
-       title = "Roll Call Vote MDS Clustering for U.S. Senate (101st - 111th Congress)",
-       panel.grid.major = theme_blank()) +
+  theme(axis.ticks = element_blank(),
+       axis.text.x = element_blank(),
+       axis.text.y = element_blank(),
+       panel.grid.major = element_blank()) +
+       ggtitle("Roll Call Vote MDS Clustering for U.S. Senate (101st - 111th Congress)") +
        xlab("") +
        ylab("") +
        scale_shape(name = "Party",
@@ -243,14 +244,14 @@ for(i in 1:length(rollcall.mds))
 
   # Build base plot
   mds.plot <- ggplot(mds, aes(x = x, y = y)) +
-    scale_size(to = c(2, 2), legend = FALSE) +
-    scale_alpha(legend = FALSE) +
+    scale_size(range = c(2, 2), guide="none") +
+    scale_alpha(guide="none") +
     theme_bw() +
-    opts(axis.ticks = theme_blank(), 
-         axis.text.x = theme_blank(),
-         axis.text.y = theme_blank(),
-         title = plot.title,
-         panel.grid.major = theme_blank()) +
+    theme(axis.ticks = element_blank(), 
+         axis.text.x = element_blank(),
+         axis.text.y = element_blank(),
+         panel.grid.major = element_blank()) +
+         ggtitle(plot.title) + 
     xlab("") +
     ylab("")
 

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)

package_installer.R

@@ -1,4 +1,4 @@
-# File-Name:       package_installer.R           
+# Name:       package_installer.R           
 # Date:            2012-02-10                         
 # Author:          Drew Conway (drew.conway@nyu.edu)
 # Purpose:         Install all of the packages needed for the Machine Learning for Hackers case studies
@@ -45,3 +45,4 @@ for(p in cran.packages) {
 
 print("### All required packages installed ###")
 
+