I'm trying to run an svm on the titanic data set but I've run into an issue with the predict function.
svm.iceberg <- svm(Survived ~ Pclass+Sex+SibSp+Parch+Ticket+Fare+Cabin+Embarked+Surname+Age_Range, data = train.iceberg)
svm.prediction <- predict(svm.iceberg, newdata = test.iceberg) #prediction
I'm receiving the following error:
Error in names(ret2) <- rowns :'names' attribute [418] must be the same length as the vector [0]
I think the error is a result of when I made the factor levels the same for the train and test data for a few variables (here is the code I used):
test.iceberg$Name <- factor(test.iceberg$Name,levels =levels(train.iceberg$Name))
test.iceberg$Ticket <- factor(test.iceberg$Ticket,levels =levels(train.iceberg$Ticket))
test.iceberg$Cabin <- factor(test.iceberg$Cabin,levels =levels(train.iceberg$Cabin))
test.iceberg$Surname <- factor(test.iceberg$Ticket,levels =levels(train.iceberg$Surname))
Here is the train data frame:
str(train.iceberg)
'data.frame': 891 obs. of 14 variables:
$ PassengerId: int 1 2 3 4 5 6 7 8 9 10 ...
$ Survived : int 0 1 1 1 0 0 0 0 1 1 ...
$ Pclass : Factor w/ 3 levels "1","2","3": 3 1 3 1 3 3 1 3 3 2 ...
$ Name : Factor w/ 891 levels "Abbing, Mr. Anthony",..: 109 191 354 273 16 555 516 625 413 577 ...
$ Sex : Factor w/ 2 levels "female","male": 2 1 1 1 2 2 2 2 1 1 ...
$ Age : num 22 38 26 35 35 NA 54 2 27 14 ...
$ SibSp : int 1 1 0 1 0 0 0 3 0 1 ...
$ Parch : int 0 0 0 0 0 0 0 1 2 0 ...
$ Ticket : Factor w/ 681 levels "110152","110413",..: 524 597 670 50 473 276 86 396 345 133 ...
$ Fare : num 7.25 71.28 7.92 53.1 8.05 ...
$ Cabin : Factor w/ 147 levels "A10","A14","A16",..: NA 82 NA 56 NA NA 130 NA NA NA ...
$ Embarked : Factor w/ 3 levels "C","Q","S": 3 1 3 3 3 2 3 3 3 1 ...
$ Surname : Factor w/ 667 levels "Abbing","Abbott",..: 74 137 252 199 12 410 379 464 293 427 ...
$ Age_Range : num 4 4 4 4 4 NA 4 2 4 3 ...
This caused a lot of NA's in the test data frame as can be seen below:
> str(test.iceberg) #
'data.frame': 418 obs. of 14 variables:
$ PassengerId: int 892 893 894 895 896 897 898 899 900 901 ...
$ Survived : int NA NA NA NA NA NA NA NA NA NA ...
$ Pclass : Factor w/ 3 levels "1","2","3": 3 3 2 3 3 3 3 2 3 3 ...
$ Name : Factor w/ 891 levels "Abbing, Mr. Anthony",..: 434 NA NA NA NA NA 178 NA NA NA ...
$ Sex : Factor w/ 2 levels "female","male": 2 1 2 2 1 2 1 2 1 2 ...
$ Age : num 34 47 62 27 22 14 30 26 18 21 ...
$ SibSp : int 0 1 0 0 1 0 0 1 0 2 ...
$ Parch : int 0 0 0 0 1 0 0 1 0 0 ...
$ Ticket : Factor w/ 681 levels "110152","110413",..: NA NA NA NA 252 NA NA 159 NA 520 ...
$ Fare : num 7.83 7 9.69 8.66 12.29 ...
$ Cabin : Factor w/ 147 levels "A10","A14","A16",..: NA NA NA NA NA NA NA NA NA NA ...
$ Embarked : Factor w/ 3 levels "C","Q","S": 2 3 2 3 3 3 2 3 1 3 ...
$ Surname : Factor w/ 667 levels "Abbing","Abbott",..: NA NA NA NA NA NA NA NA NA NA ...
$ Age_Range : num 5 6 8 5 5 3 5 5 3 5 ...
Here is a sample of the data:
dput((droplevels(head(train.iceberg,100))))
structure(list(PassengerId = 1:100, Survived = c(0L, 1L, 1L,
1L, 0L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 1L, 0L, 1L, 0L,
1L, 0L, 1L, 1L, 1L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 1L, 1L, 0L, 0L,
0L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 1L, 0L, 0L, 0L,
0L, 1L, 1L, 0L, 1L, 1L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 1L, 1L,
0L, 1L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 1L, 1L, 0L, 1L, 1L,
0L, 1L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L,
0L), Pclass = structure(c(3L, 1L, 3L, 1L, 3L, 3L, 1L, 3L, 3L,
2L, 3L, 1L, 3L, 3L, 3L, 2L, 3L, 2L, 3L, 3L, 2L, 2L, 3L, 1L, 3L,
3L, 3L, 1L, 3L, 3L, 1L, 1L, 3L, 2L, 1L, 1L, 3L, 3L, 3L, 3L, 3L,
2L, 3L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 2L, 1L, 1L, 2L,
3L, 2L, 3L, 3L, 1L, 1L, 3L, 1L, 3L, 2L, 3L, 3L, 3L, 2L, 3L, 2L,
3L, 3L, 3L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 1L, 2L, 3L, 3L, 3L, 1L,
3L, 3L, 3L, 1L, 3L, 3L, 3L, 1L, 1L, 2L, 2L), .Label = c("1",
"2", "3"), class = "factor"), Name = structure(c(12L, 22L, 41L,
32L, 2L, 61L, 56L, 72L, 48L, 64L, 79L, 11L, 80L, 4L, 95L, 42L,
75L, 99L, 94L, 55L, 33L, 9L, 58L, 86L, 73L, 7L, 27L, 31L, 70L,
90L, 92L, 87L, 34L, 98L, 59L, 43L, 54L, 14L, 93L, 65L, 1L, 91L,
51L, 52L, 24L, 76L, 53L, 69L, 78L, 6L, 74L, 66L, 39L, 28L, 71L,
100L, 77L, 67L, 97L, 36L, 83L, 45L, 40L, 84L, 89L, 62L, 68L,
21L, 3L, 50L, 47L, 37L, 44L, 19L, 10L, 60L, 88L, 63L, 13L, 26L,
96L, 81L, 57L, 15L, 46L, 8L, 29L, 85L, 30L, 16L, 18L, 5L, 17L,
23L, 20L, 82L, 35L, 38L, 25L, 49L), .Label = c("Ahlin, Mrs. Johan (Johanna Persdotter Larsson)",
"Allen, Mr. William Henry", "Andersson, Miss. Erna Alexandra",
"Andersson, Mr. Anders Johan", "Andreasson, Mr. Paul Edvin",
"Arnold-Franchi, Mrs. Josef (Josefine Franchi)", "Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)",
"Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)", "Beesley, Mr. Lawrence",
"Bing, Mr. Lee", "Bonnell, Miss. Elizabeth", "Braund, Mr. Owen Harris",
"Caldwell, Master. Alden Gates", "Cann, Mr. Ernest Charles",
"Carrau, Mr. Francisco M", "Celotti, Mr. Francesco", "Chaffee, Mr. Herbert Fuller",
"Christmann, Mr. Emil", "Chronopoulos, Mr. Apostolos", "Coxon, Mr. Daniel",
"Crease, Mr. Ernest James", "Cumings, Mrs. John Bradley (Florence Briggs Thayer)",
"Dean, Mr. Bertram Frank", "Devaney, Miss. Margaret Delia", "Doling, Mrs. John T (Ada Julia Bone)",
"Dowdell, Miss. Elizabeth", "Emir, Mr. Farred Chehab", "Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)",
"Ford, Mr. William Neal", "Fortune, Miss. Mabel Helen", "Fortune, Mr. Charles Alexander",
"Futrelle, Mrs. Jacques Heath (Lily May Peel)", "Fynney, Mr. Joseph J",
"Glynn, Miss. Mary Agatha", "Goldschmidt, Mr. George B", "Goodwin, Master. William Frederick",
"Goodwin, Miss. Lillian Amy", "Greenfield, Mr. William Bertram",
"Harper, Mrs. Henry Sleeper (Myna Haxtun)", "Harris, Mr. Henry Birkhardt",
"Heikkinen, Miss. Laina", "Hewlett, Mrs. (Mary D Kingcome) ",
"Holverson, Mr. Alexander Oskar", "Hood, Mr. Ambrose Jr", "Icard, Miss. Amelie",
"Ilett, Miss. Bertha", "Jenkin, Mr. Stephen Curnow", "Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",
"Kantor, Mr. Sinai", "Kink, Mr. Vincenz", "Kraeff, Mr. Theodor",
"Laroche, Miss. Simonne Marie Anne Andree", "Lennon, Mr. Denis",
"Mamee, Mr. Hanna", "Masselmani, Mrs. Fatima", "McCarthy, Mr. Timothy J",
"McDermott, Miss. Brigdet Delia", "McGowan, Miss. Anna \"Annie\"",
"Meyer, Mr. Edgar Joseph", "Moen, Mr. Sigurd Hansen", "Moran, Mr. James",
"Moubarek, Master. Gerios", "Moutal, Mr. Rahamin Haim", "Nasser, Mrs. Nicholas (Adele Achem)",
"Nicola-Yarred, Miss. Jamila", "Nosworthy, Mr. Richard Cater",
"Novel, Mr. Mansouer", "Nye, Mrs. (Elizabeth Ramell)", "O'Driscoll, Miss. Bridget",
"O'Dwyer, Miss. Ellen \"Nellie\"", "Ostby, Mr. Engelhart Cornelius",
"Palsson, Master. Gosta Leonard", "Palsson, Miss. Torborg Danira",
"Panula, Master. Juha Niilo", "Rice, Master. Eugene", "Rogers, Mr. William John",
"Rugg, Miss. Emily", "Samaan, Mr. Youssef", "Sandstrom, Miss. Marguerite Rut",
"Saundercock, Mr. William Henry", "Sheerlinck, Mr. Jan Baptist",
"Shorney, Mr. Charles Joseph", "Sirayanian, Mr. Orsen", "Skoog, Master. Harald",
"Slocovski, Mr. Selman Francis", "Sloper, Mr. William Thompson",
"Spencer, Mrs. William Augustus (Marie Eugenie)", "Staneff, Mr. Ivan",
"Stewart, Mr. Albert A", "Todoroff, Mr. Lalio", "Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)",
"Uruchurtu, Don. Manuel E", "Vander Planke, Miss. Augusta Maria",
"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)", "Vestrom, Miss. Hulda Amanda Adolfina",
"Waelens, Mr. Achille", "West, Miss. Constance Mirium", "Wheadon, Mr. Edward H",
"Williams, Mr. Charles Eugene", "Woolner, Mr. Hugh"), class = "factor"),
Sex = structure(c(2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L,
1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L,
2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L,
1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L
), .Label = c("female", "male"), class = "factor"), Age = c(22,
38, 26, 35, 35, NA, 54, 2, 27, 14, 4, 58, 20, 39, 14, 55,
2, NA, 31, NA, 35, 34, 15, 28, 8, 38, NA, 19, NA, NA, 40,
NA, NA, 66, 28, 42, NA, 21, 18, 14, 40, 27, NA, 3, 19, NA,
NA, NA, NA, 18, 7, 21, 49, 29, 65, NA, 21, 28, 5, 11, 22,
38, 45, 4, NA, NA, 29, 19, 17, 26, 32, 16, 21, 26, 32, 25,
NA, NA, 1, 30, 22, 29, NA, 28, 17, 33, 16, NA, 23, 24, 29,
20, 46, 26, 59, NA, 71, 23, 34, 34), SibSp = c(1L, 1L, 0L,
1L, 0L, 0L, 0L, 3L, 0L, 1L, 1L, 0L, 0L, 1L, 0L, 0L, 4L, 0L,
1L, 0L, 0L, 0L, 0L, 0L, 3L, 1L, 0L, 3L, 0L, 0L, 0L, 1L, 0L,
0L, 1L, 1L, 0L, 0L, 2L, 1L, 1L, 1L, 0L, 1L, 0L, 0L, 1L, 0L,
2L, 1L, 4L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 1L, 5L, 0L, 0L, 1L,
3L, 0L, 1L, 0L, 0L, 4L, 2L, 0L, 5L, 0L, 1L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 3L, 1L, 0L, 3L, 0L, 0L, 0L, 1L,
1L, 0L, 0L, 0L, 0L, 0L, 1L), Parch = c(0L, 0L, 0L, 0L, 0L,
0L, 0L, 1L, 2L, 0L, 1L, 0L, 0L, 5L, 0L, 0L, 1L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 1L, 5L, 0L, 2L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 0L, 0L, 0L, 0L, 0L, 0L,
1L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 2L, 2L, 0L, 0L, 0L, 2L, 0L,
1L, 0L, 0L, 2L, 0L, 0L, 2L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 3L, 0L, 2L, 0L, 0L, 0L, 0L, 2L, 0L,
0L, 0L, 1L, 1L, 0L), Ticket = structure(c(71L, 82L, 95L,
7L, 64L, 36L, 11L, 58L, 52L, 15L, 88L, 4L, 72L, 49L, 59L,
20L, 67L, 18L, 44L, 23L, 16L, 19L, 37L, 5L, 58L, 48L, 22L,
13L, 40L, 55L, 83L, 80L, 41L, 74L, 84L, 6L, 28L, 69L, 45L,
24L, 68L, 8L, 57L, 92L, 39L, 89L, 63L, 9L, 26L, 56L, 34L,
70L, 81L, 31L, 2L, 12L, 76L, 30L, 78L, 79L, 27L, 3L, 62L,
50L, 85L, 25L, 75L, 91L, 33L, 35L, 77L, 79L, 90L, 29L, 10L,
53L, 54L, 65L, 21L, 61L, 46L, 47L, 38L, 1L, 93L, 32L, 96L,
94L, 13L, 42L, 43L, 51L, 97L, 73L, 60L, 66L, 86L, 87L, 14L,
17L), .Label = c("113059", "113509", "113572", "113783",
"113788", "113789", "113803", "11668", "14311", "1601", "17463",
"19947", "19950", "231919", "237736", "239865", "244367",
"244373", "248698", "248706", "248738", "2631", "2649", "2651",
"2661", "2662", "2669", "2677", "2680", "2697", "2926", "3101278",
"3101281", "3101295", "315151", "330877", "330923", "330932",
"330958", "330959", "335677", "343275", "343276", "345763",
"345764", "345767", "345779", "347077", "347082", "347088",
"347466", "347742", "348123", "349208", "349216", "349237",
"349253", "349909", "350406", "364500", "364516", "36973",
"370371", "373450", "374746", "374910", "382652", "7546",
"A./5. 2152", "A/4. 39886", "A/5 21171", "A/5. 2151", "C.A. 2315",
"C.A. 24579", "C.A. 29395", "C.A. 31026", "C.A. 33111", "C.A. 34651",
"CA 2144", "PC 17569", "PC 17572", "PC 17599", "PC 17601",
"PC 17604", "PC 17605", "PC 17754", "PC 17759", "PP 9549",
"S.C./A.4. 23567", "S.O.C. 14879", "S.P. 3464", "SC/Paris 2123",
"SO/C 14885", "SOTON/OQ 392086", "STON/O2. 3101282", "W./C. 6608",
"W.E.P. 5734"), class = "factor"), Fare = c(7.25, 71.2833,
7.925, 53.1, 8.05, 8.4583, 51.8625, 21.075, 11.1333, 30.0708,
16.7, 26.55, 8.05, 31.275, 7.8542, 16, 29.125, 13, 18, 7.225,
26, 13, 8.0292, 35.5, 21.075, 31.3875, 7.225, 263, 7.8792,
7.8958, 27.7208, 146.5208, 7.75, 10.5, 82.1708, 52, 7.2292,
8.05, 18, 11.2417, 9.475, 21, 7.8958, 41.5792, 7.8792, 8.05,
15.5, 7.75, 21.6792, 17.8, 39.6875, 7.8, 76.7292, 26, 61.9792,
35.5, 10.5, 7.2292, 27.75, 46.9, 7.2292, 80, 83.475, 27.9,
27.7208, 15.2458, 10.5, 8.1583, 7.925, 8.6625, 10.5, 46.9,
73.5, 14.4542, 56.4958, 7.65, 7.8958, 8.05, 29, 12.475, 9,
9.5, 7.7875, 47.1, 10.5, 15.85, 34.375, 8.05, 263, 8.05,
8.05, 7.8542, 61.175, 20.575, 7.25, 8.05, 34.6542, 63.3583,
23, 26), Cabin = structure(c(NA, 11L, NA, 7L, NA, NA, 16L,
NA, NA, NA, 19L, 6L, NA, NA, NA, NA, NA, NA, NA, NA, NA,
14L, NA, 2L, NA, NA, NA, 8L, NA, NA, NA, 5L, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, 13L, NA, 4L, 9L, NA, NA, NA, NA, NA, 3L, 10L, NA,
NA, NA, 18L, NA, NA, NA, NA, NA, NA, NA, NA, 17L, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 8L, NA, NA, NA, 15L,
NA, NA, NA, 1L, 12L, NA, NA), .Label = c("A5", "A6", "B28",
"B30", "B78", "C103", "C123", "C23 C25 C27", "C52", "C83",
"C85", "D10 D12", "D33", "D56", "E31", "E46", "F G73", "F33",
"G6"), class = "factor"), Embarked = structure(c(3L, 1L,
3L, 3L, 3L, 2L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 2L,
3L, 3L, 1L, 3L, 3L, 2L, 3L, 3L, 3L, 1L, 3L, 2L, 3L, 1L, 1L,
2L, 3L, 1L, 3L, 1L, 3L, 3L, 1L, 3L, 3L, 1L, 1L, 2L, 3L, 2L,
2L, 1L, 3L, 3L, 3L, 1L, 3L, 1L, 3L, 3L, 1L, 3L, 3L, 1L, NA,
3L, 3L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 1L, 1L, 3L, 3L), .Label = c("C", "Q", "S"
), class = "factor"), Surname = structure(c(11L, 21L, 38L,
30L, 2L, 58L, 53L, 69L, 45L, 61L, 75L, 10L, 76L, 3L, 90L,
39L, 71L, 94L, 89L, 52L, 31L, 8L, 55L, 82L, 69L, 6L, 26L,
29L, 67L, 86L, 88L, 83L, 32L, 93L, 56L, 40L, 51L, 13L, 89L,
62L, 1L, 87L, 48L, 49L, 23L, 72L, 50L, 66L, 74L, 5L, 70L,
63L, 36L, 27L, 68L, 95L, 73L, 64L, 92L, 34L, 79L, 42L, 37L,
80L, 85L, 59L, 65L, 20L, 3L, 47L, 44L, 34L, 41L, 18L, 9L,
57L, 84L, 60L, 12L, 25L, 91L, 77L, 54L, 14L, 43L, 7L, 28L,
81L, 29L, 15L, 17L, 4L, 16L, 22L, 19L, 78L, 33L, 35L, 24L,
46L), .Label = c("Ahlin", "Allen", "Andersson", "Andreasson",
"Arnold-Franchi", "Asplund", "Backstrom", "Beesley", "Bing",
"Bonnell", "Braund", "Caldwell", "Cann", "Carrau", "Celotti",
"Chaffee", "Christmann", "Chronopoulos", "Coxon", "Crease",
"Cumings", "Dean", "Devaney", "Doling", "Dowdell", "Emir",
"Faunthorpe", "Ford", "Fortune", "Futrelle", "Fynney", "Glynn",
"Goldschmidt", "Goodwin", "Greenfield", "Harper", "Harris",
"Heikkinen", "Hewlett", "Holverson", "Hood", "Icard", "Ilett",
"Jenkin", "Johnson", "Kantor", "Kink", "Kraeff", "Laroche",
"Lennon", "Mamee", "Masselmani", "McCarthy", "McDermott",
"McGowan", "Meyer", "Moen", "Moran", "Moubarek", "Moutal",
"Nasser", "Nicola-Yarred", "Nosworthy", "Novel", "Nye", "O'Driscoll",
"O'Dwyer", "Ostby", "Palsson", "Panula", "Rice", "Rogers",
"Rugg", "Samaan", "Sandstrom", "Saundercock", "Sheerlinck",
"Shorney", "Sirayanian", "Skoog", "Slocovski", "Sloper",
"Spencer", "Staneff", "Stewart", "Todoroff", "Turpin", "Uruchurtu",
"Vander Planke", "Vestrom", "Waelens", "West", "Wheadon",
"Williams", "Woolner"), class = "factor"), Age_Range = c(4,
4, 4, 4, 4, NA, 4, 2, 4, 3, 2, 4, 4, 4, 3, 4, 2, NA, 4, NA,
4, 4, 3, 4, 2, 4, NA, 3, NA, NA, 6, NA, NA, 8, 5, 6, NA,
5, 3, 3, 6, 5, NA, 2, 3, NA, NA, NA, NA, 3, 2, 5, 6, 5, 8,
NA, 5, 5, 2, 2, 5, 5, 6, 2, NA, NA, 5, 3, 3, 5, 5, 3, 5,
5, 5, 5, NA, NA, 1, 5, 5, 5, NA, 5, 3, 5, 3, NA, 5, 5, 5,
5, 6, 5, 7, NA, 9, 5, 5, 5)), .Names = c("PassengerId", "Survived",
"Pclass", "Name", "Sex", "Age", "SibSp", "Parch", "Ticket", "Fare",
"Cabin", "Embarked", "Surname", "Age_Range"), row.names = c(NA,
100L), class = "data.frame")
