From cddd6593fa2e3bc6c7ac573512361400e5283311 Mon Sep 17 00:00:00 2001
From: bhimmetoglu <burakhmmtgl@gmail.com>
Date: Thu, 3 Mar 2016 14:55:46 -0800
Subject: [PATCH] added files

---
 titanic/analysis-rf.R      |  66 ++++++
 titanic/clean.R            |   5 +
 titanic/predictions_rf.csv | 419 +++++++++++++++++++++++++++++++++++++
 3 files changed, 490 insertions(+)
 create mode 100644 titanic/analysis-rf.R
 create mode 100644 titanic/predictions_rf.csv

diff --git a/titanic/analysis-rf.R b/titanic/analysis-rf.R
new file mode 100644
index 0000000..62b60e0
--- /dev/null
+++ b/titanic/analysis-rf.R
@@ -0,0 +1,66 @@
+# Titanic Survival Analysis (Random Forest version)
+# Function:
+#     Read/clean train (clean.R)
+# 
+# Burak H. 
+library(caret); library(dplyr)
+
+# Go to working directory
+setwd("~/Coursera/projects/titanic")
+
+# Read the training and testing sets
+train0 <- read.csv("./data/train.csv")
+test0 <- read.csv("./data/test.csv")
+
+# Get the cleaned data
+fun.clean <- dget("clean.R")
+cleaned <- fun.clean(train0,test0)
+tr0 <- cleaned[[1]]; ts0 <- cleaned[[2]]
+
+# Further split the tr0 data into training and testing sets by Caret
+in.tr0 <- createDataPartition(tr0$Survived, p=0.7, list = FALSE)
+training <- tr0[in.tr0, ] 
+testing <- tr0[-in.tr0, ]
+
+# Train using random forests
+ctrl <- trainControl(allowParallel=T, method = "repeatedcv", number = 10, repeats = 10)
+modFit <- train(Survived ~ Sex + Age + Pclass + SibSp + Parch + Embarked + Fare + Title,
+                method = "rf", importance = TRUE, data = training, ntree = 500,
+                trControl = ctrl)
+
+# Predictions on the training set
+pred.tr <- predict(modFit, newdata = training)
+
+# Predict on the testing set
+pred0 <- predict(modFit, newdata = testing)
+
+# Confusion Matrices
+cm.test <- confusionMatrix(pred0, testing$Survived); cm.test$table
+cm.train <- confusionMatrix(pred.tr, training$Survived); cm.train$table
+
+# Now predict on the actual testing set (ts0)
+pred.ts0 <- predict(modFit, newdata = ts0)
+
+# Select Passanger ID and Survived to write into final table
+final <- data.frame(Survived = pred.ts0, PassengerId = ts0$PassengerId)
+write.csv(final, file = "predictions_rf.csv", row.names = FALSE, quote = FALSE)
+
+##### Boosting ####
+ctrl <- trainControl(method="boot")
+mod.gbm <- train(Survived ~ Sex + Age + Pclass + SibSp + Parch + Embarked + Fare,
+                method = "gbm", data = training,
+                trControl = ctrl, verbose = FALSE)
+
+# Predictions on the training set
+pred.tr.gbm <- predict(mod.gbm, newdata = training)
+
+# Predict on the testing set
+pred.ts.gbm <- predict(mod.gbm, newdata = testing)
+
+# Confusion Matrices
+cm.test <- confusionMatrix(pred0, testing$Survived); cm.test$table
+cm.train <- confusionMatrix(pred.tr, training$Survived); cm.train$table
+
+# Select Passanger ID and Survived to write into final table
+final <- data.frame(Survived = pred.ts0, PassengerId = ts0$PassengerId)
+write.csv(final, file = "predictions_rf.csv", row.names = FALSE, quote = FALSE)
diff --git a/titanic/clean.R b/titanic/clean.R
index d4892d8..56d5612 100644
--- a/titanic/clean.R
+++ b/titanic/clean.R
@@ -69,6 +69,8 @@ clean.tr <- function (train, test){
     titles[i] <- str_trim(strsplit(temp, split = ",")[[1]][2], "left")
   }
   # New data frame with a column = title
+  
+  # Change to factors
   ts2 <- mutate(test, Title = as.factor(titles))
 
   #Replce NA's with median age (this comes from train)
@@ -89,6 +91,9 @@ clean.tr <- function (train, test){
   ts2 <- mutate(ts2, binaryCabin = 1)
   ts2[ts2$Cabin == "", ]$binaryCabin = 0
   ts2 <- mutate(ts2, binaryCabin = factor(binaryCabin))
+
+  # There is one Title == Dona, replace it with Don (assume equivalence)
+  levels(ts2$Title) <- c("Col", "Don", "Dr", "Master", "Miss", "Mr", "Mrs", "Ms", "Rev")
       
   # Return the data.frames tr2 and ts2
   list(tr2,ts2)
diff --git a/titanic/predictions_rf.csv b/titanic/predictions_rf.csv
new file mode 100644
index 0000000..c854698
--- /dev/null
+++ b/titanic/predictions_rf.csv
@@ -0,0 +1,419 @@
+Survived,PassengerId
+0,892
+0,893
+0,894
+0,895
+0,896
+0,897
+0,898
+0,899
+1,900
+0,901
+0,902
+0,903
+1,904
+0,905
+1,906
+1,907
+0,908
+0,909
+0,910
+1,911
+1,912
+0,913
+1,914
+0,915
+1,916
+0,917
+1,918
+0,919
+0,920
+0,921
+0,922
+0,923
+0,924
+0,925
+1,926
+0,927
+0,928
+0,929
+0,930
+0,931
+0,932
+0,933
+0,934
+1,935
+1,936
+0,937
+0,938
+0,939
+1,940
+1,941
+0,942
+0,943
+1,944
+1,945
+0,946
+0,947
+0,948
+0,949
+0,950
+1,951
+0,952
+0,953
+0,954
+1,955
+1,956
+1,957
+1,958
+0,959
+0,960
+1,961
+1,962
+0,963
+0,964
+0,965
+1,966
+0,967
+0,968
+1,969
+0,970
+1,971
+1,972
+0,973
+0,974
+0,975
+0,976
+0,977
+1,978
+0,979
+1,980
+1,981
+0,982
+0,983
+1,984
+0,985
+0,986
+0,987
+1,988
+0,989
+0,990
+0,991
+1,992
+0,993
+0,994
+0,995
+0,996
+0,997
+0,998
+0,999
+0,1000
+0,1001
+0,1002
+1,1003
+1,1004
+1,1005
+1,1006
+0,1007
+0,1008
+1,1009
+0,1010
+1,1011
+1,1012
+0,1013
+1,1014
+0,1015
+0,1016
+0,1017
+0,1018
+1,1019
+0,1020
+0,1021
+0,1022
+0,1023
+0,1024
+0,1025
+0,1026
+0,1027
+0,1028
+0,1029
+0,1030
+0,1031
+0,1032
+1,1033
+0,1034
+0,1035
+0,1036
+0,1037
+0,1038
+0,1039
+0,1040
+0,1041
+1,1042
+0,1043
+0,1044
+0,1045
+0,1046
+0,1047
+1,1048
+0,1049
+0,1050
+1,1051
+1,1052
+1,1053
+1,1054
+0,1055
+0,1056
+0,1057
+0,1058
+0,1059
+1,1060
+0,1061
+0,1062
+0,1063
+0,1064
+0,1065
+0,1066
+1,1067
+1,1068
+1,1069
+1,1070
+1,1071
+0,1072
+0,1073
+1,1074
+0,1075
+1,1076
+0,1077
+1,1078
+0,1079
+0,1080
+0,1081
+0,1082
+0,1083
+0,1084
+0,1085
+1,1086
+0,1087
+1,1088
+0,1089
+0,1090
+0,1091
+1,1092
+1,1093
+1,1094
+1,1095
+0,1096
+0,1097
+1,1098
+0,1099
+1,1100
+0,1101
+0,1102
+0,1103
+0,1104
+1,1105
+0,1106
+0,1107
+1,1108
+0,1109
+1,1110
+0,1111
+1,1112
+0,1113
+1,1114
+0,1115
+1,1116
+0,1117
+0,1118
+1,1119
+0,1120
+0,1121
+0,1122
+1,1123
+0,1124
+0,1125
+1,1126
+0,1127
+1,1128
+0,1129
+1,1130
+1,1131
+1,1132
+1,1133
+0,1134
+0,1135
+1,1136
+0,1137
+1,1138
+0,1139
+1,1140
+0,1141
+1,1142
+0,1143
+1,1144
+0,1145
+0,1146
+0,1147
+0,1148
+0,1149
+1,1150
+0,1151
+0,1152
+0,1153
+1,1154
+1,1155
+0,1156
+0,1157
+0,1158
+0,1159
+0,1160
+0,1161
+0,1162
+0,1163
+1,1164
+1,1165
+0,1166
+1,1167
+0,1168
+0,1169
+0,1170
+0,1171
+0,1172
+1,1173
+1,1174
+0,1175
+1,1176
+0,1177
+0,1178
+0,1179
+0,1180
+0,1181
+0,1182
+0,1183
+0,1184
+0,1185
+0,1186
+0,1187
+1,1188
+0,1189
+0,1190
+0,1191
+0,1192
+0,1193
+0,1194
+0,1195
+1,1196
+1,1197
+1,1198
+0,1199
+0,1200
+0,1201
+0,1202
+0,1203
+0,1204
+1,1205
+1,1206
+1,1207
+0,1208
+0,1209
+0,1210
+0,1211
+0,1212
+0,1213
+0,1214
+0,1215
+1,1216
+0,1217
+1,1218
+0,1219
+0,1220
+0,1221
+1,1222
+0,1223
+0,1224
+1,1225
+0,1226
+0,1227
+0,1228
+0,1229
+0,1230
+0,1231
+0,1232
+0,1233
+0,1234
+1,1235
+1,1236
+0,1237
+0,1238
+1,1239
+0,1240
+1,1241
+1,1242
+0,1243
+0,1244
+0,1245
+1,1246
+0,1247
+1,1248
+0,1249
+0,1250
+0,1251
+0,1252
+1,1253
+1,1254
+0,1255
+1,1256
+0,1257
+0,1258
+0,1259
+1,1260
+0,1261
+0,1262
+1,1263
+0,1264
+0,1265
+1,1266
+1,1267
+0,1268
+0,1269
+0,1270
+0,1271
+0,1272
+0,1273
+0,1274
+0,1275
+0,1276
+1,1277
+0,1278
+0,1279
+0,1280
+0,1281
+0,1282
+1,1283
+0,1284
+0,1285
+0,1286
+1,1287
+0,1288
+1,1289
+0,1290
+0,1291
+1,1292
+0,1293
+1,1294
+0,1295
+0,1296
+0,1297
+0,1298
+0,1299
+1,1300
+1,1301
+1,1302
+1,1303
+0,1304
+0,1305
+1,1306
+0,1307
+0,1308
+1,1309