Merge branch 'master' of github.com:johnmyleswhite/ML_for_Hackers

.gitignore

@@ -2,3 +2,4 @@
 .dropbox
 code_check*
 nohup.out
++*.pdf

01-Introduction/data/ufo/16154.yaml

@@ -3,7 +3,7 @@ infochimps_schema:
   title: Infochimps Simple Schema (ICSS)
   version: 0.1.1
   generated_at: Wed Oct 20 14:34:20 +0000 2010
-  url: "http://www.infochimps.com/datasets/60000-documented-ufo-sightings-with-text-descriptions-and-metada.yaml"
+  url: "http://infochimps.com/datasets/d60000-documented-ufo-sightings-with-text-descriptions-and-metad.yaml"
   description: >-
     This is an Infochimps Simple Schema (ICSS).
 
@@ -24,7 +24,7 @@ dataset:
   title:               60,000+ Documented UFO Sightings With Text Descriptions And Metadata
   subtitle:            ~
   main_link:           ~
-  url:                 "http://www.infochimps.com/datasets/60000-documented-ufo-sightings-with-text-descriptions-and-metada"
+  url:                 "http://infochimps.com/datasets/d60000-documented-ufo-sightings-with-text-descriptions-and-metad"
   created_at:          "Wed Oct 20 04:49:06 UTC 2010"
   updated_at:          "Wed Oct 20 04:50:01 UTC 2010"  
   tags:              [ alien,aliens,awesome,database,ET,extra-terrestrial,flying,ship,sighting,space,tsv,ufo,unidentified-flying-objec ]

02-Exploration/chapter02.R

@@ -372,7 +372,7 @@ ggplot(heights.weights[1:2000, ], aes(x = Height, y = Weight)) +
 # Visualize how gender depends on height and weight.
 ggplot(heights.weights, aes(x = Height, y = Weight)) +
   geom_point(aes(color = Gender, alpha = 0.25)) +
-  scale_alpha(legend = FALSE) + 
+  scale_alpha(guide = "none") + 
   scale_color_manual(values = c("Male" = "black", "Female" = "gray")) +
   theme_bw()
 
@@ -393,7 +393,7 @@ logit.model <- glm(Male ~ Weight + Height,
 
 ggplot(heights.weights, aes(x = Height, y = Weight)) +
   geom_point(aes(color = Gender, alpha = 0.25)) +
-  scale_alpha(legend = FALSE) + 
+  scale_alpha(guide = "none") + 
   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

@@ -44,7 +44,7 @@ val <- data.frame(cbind(x, rbind(y1, y2, y3)),
 ex1 <- ggplot(val, aes(x, V2)) +
   geom_jitter(aes(shape = as.factor(V3)),
                   position = position_jitter(height = 2)) +
-  scale_shape_discrete(legend = FALSE, solid = FALSE) +
+  scale_shape_discrete(guide = "none", solid = FALSE) +
   geom_hline(aes(yintercept = c(10,30), linetype = 2)) +
   theme_bw() +
   xlab("X") +
@@ -302,20 +302,18 @@ class.df$Class <- as.logical(as.numeric(class.df$Class))
 class.df$Type <- as.factor(class.df$Type)
 
 # Create final plot of results
-class.plot <- ggplot(class.df, aes(x = Pr.HAM, Pr.SPAM)) +
+class.plot <- ggplot(class.df, aes(x = log(Pr.HAM), log(Pr.SPAM))) +
     geom_point(aes(shape = Type, alpha = 0.5)) +
     stat_abline(yintercept = 0, slope = 1) +
-    scale_x_log10() +
-    scale_y_log10() +
     scale_shape_manual(values = c("EASYHAM" = 1,
                                   "HARDHAM" = 2,
                                   "SPAM" = 3),
                        name = "Email Type") +
-    scale_alpha(legend = FALSE) +
+    scale_alpha(guide = "none") +
     xlab("log[Pr(HAM)]") +
     ylab("log[Pr(SPAM)]") +
     theme_bw() +
-    opts(axis.text.x = theme_blank(), axis.text.y = theme_blank())
+    theme(axis.text.x = element_blank(), axis.text.y = element_blank())
 ggsave(plot = class.plot,
        filename = file.path("images", "03_final_classification.pdf"),
        height = 10,

04-Ranking/priority_inbox.R

@@ -7,7 +7,7 @@
 #                   the simple work counts used in Chapter 3.
 # Data Used:       Email messages contained in ../../03-Classification/code/data/
 #                   source: http://spamassassin.apache.org/publiccorpus/
-# Packages Used:   tm, ggplot2
+# Packages Used:   tm, ggplot2, plyr
 
 # All source code is copyright (c) 2012, under the Simplified BSD License.  
 # For more information on FreeBSD see: http://www.opensource.org/licenses/bsd-license.php
@@ -24,6 +24,7 @@
 # Load libraries
 library('tm')
 library('ggplot2')
+library('plyr')
 
 # Set the global paths
 data.path <- file.path("..", "03-Classification", "data")
@@ -161,12 +162,12 @@ from.scales <- ggplot(from.ex) +
                 color = "darkblue")) +
   scale_x_continuous(breaks = 1:nrow(from.ex), labels = from.ex$From.EMail) +
   coord_flip() +
-  scale_fill_manual(values = c("lightgrey" = "lightgrey"), legend = FALSE) +
-  scale_color_manual(values = c("darkblue" = "darkblue"), legend = FALSE) +
+  scale_fill_manual(values = c("lightgrey" = "lightgrey"), guide = "none") +
+  scale_color_manual(values = c("darkblue" = "darkblue"), guide = "none") +
   ylab("Number of Emails Received (truncated at 6)") +
   xlab("Sender Address") +
   theme_bw() +
-  opts(axis.text.y = theme_text(size = 5, hjust = 1))
+  theme(axis.text.y = element_text(size = 5, hjust = 1))
 ggsave(plot = from.scales,
        filename = file.path("images", "0011_from_scales.pdf"),
        height = 4.8,
@@ -188,7 +189,7 @@ from.rescaled <- ggplot(from.weight, aes(x = 1:nrow(from.weight))) +
   xlab("") +
   ylab("Number of emails Receieved") +
   theme_bw() +
-  opts(axis.text.y = theme_blank(), axis.text.x = theme_blank())
+  theme(axis.text.y = element_blank(), axis.text.x = element_blank())
 ggsave(plot = from.rescaled,
        filename = file.path("images", "0012_from_rescaled.pdf"),
        height = 4.8,
@@ -423,7 +424,7 @@ priority.threshold <- median(train.ranks.df$Rank)
 threshold.plot <- ggplot(train.ranks.df, aes(x = Rank)) +
   stat_density(aes(fill="darkred")) +
   geom_vline(xintercept = priority.threshold, linetype = 2) +
-  scale_fill_manual(values = c("darkred" = "darkred"), legend = FALSE) +
+  scale_fill_manual(values = c("darkred" = "darkred"), guide = "none") +
   theme_bw()
 ggsave(plot = threshold.plot,
        filename = file.path("images", "01_threshold_plot.pdf"),
@@ -455,7 +456,7 @@ testing.plot <- ggplot(subset(final.df, Type == "TRAINING"), aes(x = Rank)) +
   stat_density(data = subset(final.df, Type == "TESTING"),
                aes(fill = Type, alpha = 0.65)) +
   geom_vline(xintercept = priority.threshold, linetype = 2) +
-  scale_alpha(legend = FALSE) +
+  scale_alpha(guide = "none") +
   scale_fill_manual(values = c("TRAINING" = "darkred", "TESTING" = "darkblue")) +
   theme_bw()
 ggsave(plot = testing.plot,

05-Regression/chapter05.R

@@ -173,6 +173,7 @@ top.1000.sites <- read.csv(file.path('data', 'top_1000_sites.tsv'),
 
 ggplot(top.1000.sites, aes(x = PageViews, y = UniqueVisitors)) +
   geom_point()
+ggsave(file.path("images", "page_views_vs_visitors.pdf"))
 
 # Eighteenth snippet
 ggplot(top.1000.sites, aes(x = PageViews)) +
@@ -185,11 +186,13 @@ ggplot(top.1000.sites, aes(x = log(PageViews))) +
 # Twentieth snippet
 ggplot(top.1000.sites, aes(x = log(PageViews), y = log(UniqueVisitors))) +
   geom_point()
+ggsave(file.path("images", "log_page_views_vs_log_visitors.pdf"))
 
 # Twenty-first snippet
 ggplot(top.1000.sites, aes(x = log(PageViews), y = log(UniqueVisitors))) +
   geom_point() +
   geom_smooth(method = 'lm', se = FALSE)
+ggsave(file.path("images", "log_page_views_vs_log_visitors_with_lm.pdf"))
 
 # Twenty-second snippet
 lm.fit <- lm(log(PageViews) ~ log(UniqueVisitors),

08-PCA/chapter08.R

@@ -49,7 +49,7 @@ correlations <- as.numeric(cor.matrix)
 ggplot(data.frame(Correlation = correlations),
   aes(x = Correlation, fill = 1)) +
   geom_density() +
-  opts(legend.position = 'none')
+  theme(legend.position = 'none')
 
 # Sixth code snippet
 pca <- princomp(date.stock.matrix[,2:ncol(date.stock.matrix)])
@@ -77,7 +77,7 @@ loadings <- as.numeric(principal.component)
 ggplot(data.frame(Loading = loadings),
   aes(x = Loading, fill = 1)) +
   geom_density() +
-  opts(legend.position = 'none')
+  them(legend.position = 'none')
 
 # Tenth code snippet
 market.index <- predict(pca)[, 1]

12-Model_Comparison/chapter12.R

@@ -43,6 +43,7 @@ mean(with(df, svm.predictions == Label))
 #[1] 0.7204
 
 # Third code snippet
+library("reshape")
 df <- cbind(df,
             data.frame(Logit = ifelse(predict(logit.fit) > 0, 1, 0),
                        SVM = ifelse(predict(svm.fit) > 0, 1, 0)))

fast_check.R

@@ -0,0 +1,47 @@
+setwd('01-Introduction')
+source('ufo_sightings.R')
+setwd('..')
+
+setwd('02-Exploration')
+source('chapter02.R')
+setwd('..')
+
+setwd('03-Classification')
+source('email_classify.R')
+setwd('..')
+
+setwd('04-Ranking')
+source('priority_inbox.R')
+setwd('..')
+
+setwd('05-Regression')
+source('chapter05.R')
+setwd('..')
+
+setwd('06-Regularization')
+source('chapter06.R')
+setwd('..')
+
+setwd('07-Optimization')
+source('chapter07.R')
+setwd('..')
+
+setwd('08-PCA')
+source('chapter08.R')
+setwd('..')
+
+setwd('09-MDS')
+source('chapter09.R')
+setwd('..')
+
+setwd('10-Recommendations')
+source('chapter10.R')
+setwd('..')
+
+#setwd('11-SNA')
+#source('chapter09.R')
+#setwd('..')
+
+setwd('12-Model_Comparison')
+source('chapter12.R')
+setwd('..')

package_installer.R

@@ -16,13 +16,16 @@
 # Create a vector containing all of the packages that will be used in the case studies
 # (in no particular order)
 
-cran.packages <- c("ggplot2",
+cran.packages <- c("e1071",
+                   "ggplot2",
                    "glmnet",
+                   "Hmisc",
                    "igraph",
                    "lme4",
                    "lubridate",
                    "plyr",
                    "RCurl",
+                   "reshape",
                    "RJSONIO",
                    "scales"
                    "tm",