Advertisement
Guest User

Untitled

a guest
Aug 31st, 2015
65
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 2.39 KB | None | 0 0
  1. PassengerId = testData[1]
  2. testData = testData[-c(1, 8:11)]
  3.  
  4. testData$Sex = gsub("female", 1, testData$Sex)
  5. testData$Sex = gsub("^male", 0, testData$Sex)
  6.  
  7. test_master_vector = grep("Master.",testData$Name, fixed=TRUE)
  8. test_miss_vector = grep("Miss.", testData$Name, fixed=TRUE)
  9. test_mrs_vector = grep("Mrs.", testData$Name, fixed=TRUE)
  10. test_mr_vector = grep("Mr.", testData$Name, fixed=TRUE)
  11. test_dr_vector = grep("Dr.", testData$Name, fixed=TRUE)
  12.  
  13. for(i in test_master_vector) {
  14. testData[i, 2] = "Master"
  15. }
  16. for(i in test_miss_vector) {
  17. testData[i, 2] = "Miss"
  18. }
  19. for(i in test_mrs_vector) {
  20. testData[i, 2] = "Mrs"
  21. }
  22. for(i in test_mr_vector) {
  23. testData[i, 2] = "Mr"
  24. }
  25. for(i in test_dr_vector) {
  26. testData[i, 2] = "Dr"
  27. }
  28.  
  29. test_master_age = round(mean(testData$Age[testData$Name == "Master"], na.rm = TRUE), digits = 2)
  30. test_miss_age = round(mean(testData$Age[testData$Name == "Miss"], na.rm = TRUE), digits =2)
  31. test_mrs_age = round(mean(testData$Age[testData$Name == "Mrs"], na.rm = TRUE), digits = 2)
  32. test_mr_age = round(mean(testData$Age[testData$Name == "Mr"], na.rm = TRUE), digits = 2)
  33. test_dr_age = round(mean(testData$Age[testData$Name == "Dr"], na.rm = TRUE), digits = 2)
  34.  
  35. for (i in 1:nrow(testData)) {
  36. if (is.na(testData[i,4])) {
  37. if (testData[i, 2] == "Master") {
  38. testData[i, 4] = test_master_age
  39. } else if (testData[i, 2] == "Miss") {
  40. testData[i, 4] = test_miss_age
  41. } else if (testData[i, 2] == "Mrs") {
  42. testData[i, 4] = test_mrs_age
  43. } else if (testData[i, 2] == "Mr") {
  44. testData[i, 4] = test_mr_age
  45. } else if (testData[i, 2] == "Dr") {
  46. testData[i, 4] = test_dr_age
  47. } else {
  48. print(paste("Uncaught title at: ", i, sep=""))
  49. print(paste("The title unrecognized was: ", testData[i,2], sep=""))
  50. }
  51. }
  52. }
  53.  
  54. #We do a manual replacement here, because we weren't able to programmatically figure out the title.
  55. #We figured out it was 89 because the above print statement should have warned us.
  56. testData[89, 4] = test_miss_age
  57.  
  58. testData["Child"] = NA
  59.  
  60. for (i in 1:nrow(testData)) {
  61. if (testData[i, 4] <= 12) {
  62. testData[i, 7] = 1
  63. } else {
  64. testData[i, 7] = 2
  65. }
  66. }
  67.  
  68. testData["Family"] = NA
  69.  
  70. for(i in 1:nrow(testData)) {
  71. testData[i, 8] = testData[i, 5] + testData[i, 6] + 1
  72. }
  73.  
  74. testData["Mother"] = NA
  75.  
  76. for(i in 1:nrow(testData)) {
  77. if(testData[i, 2] == "Mrs" & testData[i, 6] > 0) {
  78. testData[i, 9] = 1
  79. } else {
  80. testData[i, 9] = 2
  81. }
  82. }
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement