change UB Exam Dataset to Local Exam Dataset

UBOdin · May 18, 2017 · a1a40a7 · a1a40a7
1 parent 4f0342f
commit a1a40a7
Show file tree

Hide file tree

Showing 15 changed files with 79 additions and 79 deletions.
diff --git a/data/modules.csv b/data/modules.csv
@@ -2,45 +2,45 @@ Regularization,Dataset,Metric,Silhouette,BetaCV,DunnIndex
 No Regularization,IIT Bombay Dataset,Aouiche,0.1235358,0.5766875,0.1428571
 No Regularization,IIT Bombay Dataset,Aligon,0.3141606,0.5440821,0.1
 No Regularization,IIT Bombay Dataset,Makiyama,0.13533,0.664748,0.0741799
-No Regularization,UB Exam Dataset,Aouiche,0.07935877,0.9231208,0.2
-No Regularization,UB Exam Dataset,Aligon,0.1304497,0.8644934,0.5
-No Regularization,UB Exam Dataset,Makiyama,0.09405354,0.8968658,0.2301996
+No Regularization,Local Exam Dataset,Aouiche,0.07935877,0.9231208,0.2
+No Regularization,Local Exam Dataset,Aligon,0.1304497,0.8644934,0.5
+No Regularization,Local Exam Dataset,Makiyama,0.09405354,0.8968658,0.2301996
 No Regularization,PhoneLab-Google+,Aouiche,0.03618038,0.8934701,0.5
 No Regularization,PhoneLab-Google+,Aligon,0.06388966,0.9024188,0.5
 No Regularization,PhoneLab-Google+,Makiyama,0.1167357,0.8795412,0.2462216
 Naming,IIT Bombay Dataset,Aouiche,0.1669147,0.4963258,0.1666667
 Naming,IIT Bombay Dataset,Aligon,0.3697328,0.4765228,0.1
 Naming,IIT Bombay Dataset,Makiyama,0.1712637,0.6056812,0.0513167
-Naming,UB Exam Dataset,Aouiche,0.1726122,0.8177304,0.1666667
-Naming,UB Exam Dataset,Aligon,0.2543268,0.733504,0.3333333
-Naming,UB Exam Dataset,Makiyama,0.2684318,0.6965586,0.08146848
+Naming,Local Exam Dataset,Aouiche,0.1726122,0.8177304,0.1666667
+Naming,Local Exam Dataset,Aligon,0.2543268,0.733504,0.3333333
+Naming,Local Exam Dataset,Makiyama,0.2684318,0.6965586,0.08146848
 Naming,PhoneLab-Google+,Aouiche,0.03535551,0.8936538,0.5
 Naming,PhoneLab-Google+,Aligon,0.06260814,0.9036594,0.5
 Naming,PhoneLab-Google+,Makiyama,0.1127893,0.8855078,0.2462216
 Expression Standardization,IIT Bombay Dataset,Aouiche,0.1224014,0.6047874,0.1428571
 Expression Standardization,IIT Bombay Dataset,Aligon,0.2993084,0.5636266,0.1
 Expression Standardization,IIT Bombay Dataset,Makiyama,0.1363646,0.6599014,0.0741799
-Expression Standardization,UB Exam Dataset,Aouiche,0.08419705,0.9225258,0.2
-Expression Standardization,UB Exam Dataset,Aligon,0.08806635,0.9113887,0.3888889
-Expression Standardization,UB Exam Dataset,Makiyama,0.07635507,0.9195338,0.2600599
+Expression Standardization,Local Exam Dataset,Aouiche,0.08419705,0.9225258,0.2
+Expression Standardization,Local Exam Dataset,Aligon,0.08806635,0.9113887,0.3888889
+Expression Standardization,Local Exam Dataset,Makiyama,0.07635507,0.9195338,0.2600599
 Expression Standardization,PhoneLab-Google+,Aouiche,0.1188399,0.8847059,0.8
 Expression Standardization,PhoneLab-Google+,Aligon,0.09856893,0.8975172,0.5
 Expression Standardization,PhoneLab-Google+,Makiyama,0.1184555,0.8789764,0.3333333
 FROM-nested Subquery,IIT Bombay Dataset,Aouiche,0.1092233,0.585477,0.1428571
 FROM-nested Subquery,IIT Bombay Dataset,Aligon,0.3040806,0.5455569,0.1
 FROM-nested Subquery,IIT Bombay Dataset,Makiyama,0.1645668,0.6473655,0.0741799
-FROM-nested Subquery,UB Exam Dataset,Aouiche,0.07851794,0.9240567,0.2
-FROM-nested Subquery,UB Exam Dataset,Aligon,0.1323939,0.8655788,0.5
-FROM-nested Subquery,UB Exam Dataset,Makiyama,0.1216638,0.8640163,0.1835034
+FROM-nested Subquery,Local Exam Dataset,Aouiche,0.07851794,0.9240567,0.2
+FROM-nested Subquery,Local Exam Dataset,Aligon,0.1323939,0.8655788,0.5
+FROM-nested Subquery,Local Exam Dataset,Makiyama,0.1216638,0.8640163,0.1835034
 FROM-nested Subquery,PhoneLab-Google+,Aouiche,0.03618038,0.8934701,0.5
 FROM-nested Subquery,PhoneLab-Google+,Aligon,0.06444628,0.9018627,0.5
 FROM-nested Subquery,PhoneLab-Google+,Makiyama,0.1155413,0.8813375,0.3333333
 UNION Pull-out,IIT Bombay Dataset,Aouiche,0.1255522,0.5773791,0.1428571
 UNION Pull-out,IIT Bombay Dataset,Aligon,0.3170179,0.5432966,0.1
 UNION Pull-out,IIT Bombay Dataset,Makiyama,0.139807,0.6644235,0.0741799
-UNION Pull-out,UB Exam Dataset,Aouiche,0.07935877,0.9231208,0.2
-UNION Pull-out,UB Exam Dataset,Aligon,0.1285675,0.8660956,0.5
-UNION Pull-out,UB Exam Dataset,Makiyama,0.09405354,0.8968658,0.2301996
+UNION Pull-out,Local Exam Dataset,Aouiche,0.07935877,0.9231208,0.2
+UNION Pull-out,Local Exam Dataset,Aligon,0.1285675,0.8660956,0.5
+UNION Pull-out,Local Exam Dataset,Makiyama,0.09405354,0.8968658,0.2301996
 UNION Pull-out,PhoneLab-Google+,Aouiche,0.03618038,0.8934701,0.5
 UNION Pull-out,PhoneLab-Google+,Aligon,0.06372295,0.9022875,0.5
 UNION Pull-out,PhoneLab-Google+,Makiyama,0.1155413,0.8813375,0.3333333
diff --git a/data/result.csv b/data/result.csv
@@ -5,12 +5,12 @@ IIT Bombay Dataset,FALSE,Aligon,0.3143479,0.5448168,0.1
 IIT Bombay Dataset,TRUE,Aligon,0.3485726,0.4825776,0.1
 IIT Bombay Dataset,FALSE,Aouiche,0.1235358,0.5766875,0.1428571
 IIT Bombay Dataset,TRUE,Aouiche,0.1273715,0.5236675,0.2
-UB Exam Dataset,FALSE,Makiyama,0.09405354,0.8968658,0.2301996
-UB Exam Dataset,TRUE,Makiyama,0.3033892,0.6454333,0.08146848
-UB Exam Dataset,FALSE,Aligon,0.1310474,0.86316,0.5
-UB Exam Dataset,TRUE,Aligon,0.2307616,0.7602108,0.25
-UB Exam Dataset,FALSE,Aouiche,0.07935877,0.9231208,0.2
-UB Exam Dataset,TRUE,Aouiche,0.2356835,0.7466782,0.1666667
+Local Exam Dataset,FALSE,Makiyama,0.09405354,0.8968658,0.2301996
+Local Exam Dataset,TRUE,Makiyama,0.3033892,0.6454333,0.08146848
+Local Exam Dataset,FALSE,Aligon,0.1310474,0.86316,0.5
+Local Exam Dataset,TRUE,Aligon,0.2307616,0.7602108,0.25
+Local Exam Dataset,FALSE,Aouiche,0.07935877,0.9231208,0.2
+Local Exam Dataset,TRUE,Aouiche,0.2356835,0.7466782,0.1666667
 PocketData-Google+,FALSE,Makiyama,0.1167357,0.8795412,0.2462216
 PocketData-Google+,TRUE,Makiyama,0.1146658,0.8845571,0.3333333
 PocketData-Google+,FALSE,Aligon,0.06302234,0.903197,0.5

diff --git a/figure/compare_betacv.pdf b/figure/compare_betacv.pdf
diff --git a/figure/compare_dunn.pdf b/figure/compare_dunn.pdf
diff --git a/figure/compare_silhouette.pdf b/figure/compare_silhouette.pdf
diff --git a/figure/module.pdf b/figure/module.pdf
diff --git a/figure/sil_bombay_Aligon.pdf b/figure/sil_bombay_Aligon.pdf
diff --git a/figure/sil_bombay_Aligon_regularization.pdf b/figure/sil_bombay_Aligon_regularization.pdf
diff --git a/figure/sil_googleplus_Aligon.pdf b/figure/sil_googleplus_Aligon.pdf
diff --git a/figure/sil_googleplus_Aligon_regularization.pdf b/figure/sil_googleplus_Aligon_regularization.pdf
diff --git a/figure/sil_ub_Aligon.pdf b/figure/sil_ub_Aligon.pdf
diff --git a/figure/sil_ub_Aligon_regularization.pdf b/figure/sil_ub_Aligon_regularization.pdf
diff --git a/script_figure_2.R b/script_figure_2.R
@@ -1,36 +1,29 @@
 # set working directory
 #setwd("~/Downloads/EttuBench")
 
-# load two files evaluation.R and utils.R
-source(file = "./evaluation.R")
-source(file = "./utils.R")
-
 # load supporting libraries
-library(cluster)
-library(factoextra)
-library(RColorBrewer)
-
-dataset <- read.csv(file = "./data/bombay_queries.csv", header = TRUE, sep = "\t")
-
-distMat <- readDistMat("./data/bombay_aligon.csv")
-silhouettePlot(distMat, dataset$label, "./figure/sil_bombay_Aligon.pdf")
-
-distMat <- readDistMat("./data/bombay_aligon_regularization.csv")
-silhouettePlot(distMat, dataset$label, "./figure/sil_bombay_Aligon_regularization.pdf")
-
-dataset <- read.csv(file = "./data/ub_queries.csv", header = TRUE, sep = "\t")
-
-distMat <- readDistMat("./data/ub_aligon.csv")
-silhouettePlot(distMat, dataset$label, "./figure/sil_ub_Aligon.pdf")
-
-distMat <- readDistMat("./data/ub_aligon_regularization.csv")
-silhouettePlot(distMat, dataset$label, "./figure/sil_ub_Aligon_regularization.pdf")
-
-dataset <- read.csv(file = "./data/googleplus_queries.csv", header = TRUE, sep = "\t")
-
-distMat <- readDistMat("./data/googleplus_aligon.csv")
-silhouettePlot(distMat, dataset$label, "./figure/sil_googleplus_Aligon.pdf")
-
-distMat <- readDistMat("./data/googleplus_aligon_regularization.csv")
-silhouettePlot(distMat, dataset$label, "./figure/sil_googleplus_Aligon_regularization.pdf")
-
+library(ggplot2)
+
+comparison <- read.csv(file = "./data/result.csv", header = TRUE)
+comparison$dataset <- factor(comparison$dataset, 
+                             levels = c("IIT Bombay Dataset", 
+                                        "Local Exam Dataset", 
+                                        "PocketData-Google+"))
+
+ggplot(data = comparison, aes(x = metric, y = silhouette, fill = regularization)) + 
+  geom_bar(position="dodge", stat="identity") + facet_grid(~ dataset) + 
+  ylab("Average Silhouette Coefficient") + xlab("Metric") + 
+  theme_bw(base_size = 18) + theme(legend.position = "top") + scale_fill_grey() +
+  ggsave(filename = "./figure/compare_silhouette.pdf")
+
+ggplot(data = comparison, aes(x = metric, y = beta_cv, fill = regularization)) + 
+  geom_bar(position="dodge", stat="identity") + facet_grid(~ dataset) + 
+  ylab("Average Silhouette Coefficient") + xlab("Metric") + 
+  theme_bw(base_size = 18) + theme(legend.position = "top") + scale_fill_grey() +
+  ggsave(filename = "./figure/compare_betacv.pdf")
+
+ggplot(data = comparison, aes(x = metric, y = dunn, fill = regularization)) + 
+  geom_bar(position="dodge", stat="identity") + facet_grid(~ dataset) + 
+  ylab("Average Silhouette Coefficient") + xlab("Metric") + 
+  theme_bw(base_size = 18) + theme(legend.position = "top") + scale_fill_grey() +
+  ggsave(filename = "./figure/compare_dunn.pdf")
diff --git a/script_figure_3.R b/script_figure_3.R
@@ -1,29 +1,36 @@
 # set working directory
 #setwd("~/Downloads/EttuBench")
 
+# load two files evaluation.R and utils.R
+source(file = "./evaluation.R")
+source(file = "./utils.R")
+
 # load supporting libraries
-library(ggplot2)
-
-comparison <- read.csv(file = "./data/result.csv", header = TRUE)
-comparison$dataset <- factor(comparison$dataset, 
-                             levels = c("IIT Bombay Dataset", 
-                                        "UB Exam Dataset", 
-                                        "PocketData-Google+"))
-
-ggplot(data = comparison, aes(x = metric, y = silhouette, fill = regularization)) + 
-  geom_bar(position="dodge", stat="identity") + facet_grid(~ dataset) + 
-  ylab("Average Silhouette Coefficient") + xlab("Metric") + 
-  theme_bw(base_size = 18) + theme(legend.position = "top") + scale_fill_grey() +
-  ggsave(filename = "./figure/compare_silhouette.pdf")
-
-ggplot(data = comparison, aes(x = metric, y = beta_cv, fill = regularization)) + 
-  geom_bar(position="dodge", stat="identity") + facet_grid(~ dataset) + 
-  ylab("Average Silhouette Coefficient") + xlab("Metric") + 
-  theme_bw(base_size = 18) + theme(legend.position = "top") + scale_fill_grey() +
-  ggsave(filename = "./figure/compare_betacv.pdf")
-
-ggplot(data = comparison, aes(x = metric, y = dunn, fill = regularization)) + 
-  geom_bar(position="dodge", stat="identity") + facet_grid(~ dataset) + 
-  ylab("Average Silhouette Coefficient") + xlab("Metric") + 
-  theme_bw(base_size = 18) + theme(legend.position = "top") + scale_fill_grey() +
-  ggsave(filename = "./figure/compare_dunn.pdf")
+library(cluster)
+library(factoextra)
+library(RColorBrewer)
+
+dataset <- read.csv(file = "./data/bombay_queries.csv", header = TRUE, sep = "\t")
+
+distMat <- readDistMat("./data/bombay_aligon.csv")
+silhouettePlot(distMat, dataset$label, "./figure/sil_bombay_Aligon.pdf")
+
+distMat <- readDistMat("./data/bombay_aligon_regularization.csv")
+silhouettePlot(distMat, dataset$label, "./figure/sil_bombay_Aligon_regularization.pdf")
+
+dataset <- read.csv(file = "./data/ub_queries.csv", header = TRUE, sep = "\t")
+
+distMat <- readDistMat("./data/ub_aligon.csv")
+silhouettePlot(distMat, dataset$label, "./figure/sil_ub_Aligon.pdf")
+
+distMat <- readDistMat("./data/ub_aligon_regularization.csv")
+silhouettePlot(distMat, dataset$label, "./figure/sil_ub_Aligon_regularization.pdf")
+
+dataset <- read.csv(file = "./data/googleplus_queries.csv", header = TRUE, sep = "\t")
+
+distMat <- readDistMat("./data/googleplus_aligon.csv")
+silhouettePlot(distMat, dataset$label, "./figure/sil_googleplus_Aligon.pdf")
+
+distMat <- readDistMat("./data/googleplus_aligon_regularization.csv")
+silhouettePlot(distMat, dataset$label, "./figure/sil_googleplus_Aligon_regularization.pdf")
+
diff --git a/script_figure_4.R b/script_figure_4.R
@@ -12,7 +12,7 @@ comparison$Regularization <- factor(comparison$Regularization,
                                                "FROM-nested Subquery",
                                                "UNION Pull-out"))
 comparison$Dataset <- factor(comparison$Dataset, 
-                             levels = c("IIT Bombay Dataset", "UB Exam Dataset",
+                             levels = c("IIT Bombay Dataset", "Local Exam Dataset",
                                         "PhoneLab-Google+"))
 
 # individual module analysis