Kaggle-Titanic-Caret-1
Ming Si
June 07 2018
Titanic competition from Kaggle. Part 1, Missing data is imputed using
- kNN in the preProcess function in the Caret
- median imputation in the preProcess function in the Caret
- mice package
library(tidyverse)
library(DataExplorer)
library(lubridate)
library(pander)
library(data.table)
library(grid)
library(gridExtra)
library(mice)
library(caret)1 Loading the data
titanic.train <- read_csv("train.csv",col_names = TRUE)
titanic.test <- read_csv("test.csv",col_names = TRUE)Add Survived column to the test dataset to match the column in the train dataset
2 Combining train and test
Combine train and test dataset for cleaning
## Warning in if (attr(list(...)[[1]], "class") == "mids")
## return(rbind.mids(...)) else return(base::rbind(...)): the condition has
## length > 1 and only the first element will be used## [1] "PassengerId" "Pclass" "Name" "Sex" "Age"
## [6] "SibSp" "Parch" "Ticket" "Fare" "Cabin"
## [11] "Embarked" "Survived"2.1 Convert variable to factors
Using map function in the Purrr package to convert multiple variables into factor at once
factor_variable <- c("Survived","Pclass","Sex","Embarked")
titanic[factor_variable] <- map(titanic[factor_variable],as.factor)
str(titanic)## Classes 'tbl_df', 'tbl' and 'data.frame': 1309 obs. of 12 variables:
## $ PassengerId: int 892 893 894 895 896 897 898 899 900 901 ...
## $ Pclass : Factor w/ 3 levels "1","2","3": 3 3 2 3 3 3 3 2 3 3 ...
## $ Name : chr "Kelly, Mr. James" "Wilkes, Mrs. James (Ellen Needs)" "Myles, Mr. Thomas Francis" "Wirz, Mr. Albert" ...
## $ Sex : Factor w/ 2 levels "female","male": 2 1 2 2 1 2 1 2 1 2 ...
## $ Age : num 34.5 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 : chr "330911" "363272" "240276" "315154" ...
## $ Fare : num 7.83 7 9.69 8.66 12.29 ...
## $ Cabin : chr NA NA NA NA ...
## $ Embarked : Factor w/ 3 levels "C","Q","S": 2 3 2 3 3 3 2 3 1 3 ...
## $ Survived : Factor w/ 2 levels "0","1": NA NA NA NA NA NA NA NA NA NA ...
## - attr(*, "spec")=List of 2
## ..$ cols :List of 11
## .. ..$ PassengerId: list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ Pclass : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ Name : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ Sex : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ Age : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ SibSp : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ Parch : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ Ticket : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ Fare : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ Cabin : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ Embarked : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## ..$ default: list()
## .. ..- attr(*, "class")= chr "collector_guess" "collector"
## ..- attr(*, "class")= chr "col_spec"2.2 Exploratory Data
check on missing values in multiple columns in the data frame
method is from https://sebastiansauer.github.io/sum-isna/
## $PassengerId
## [1] 0
##
## $Pclass
## [1] 0
##
## $Name
## [1] 0
##
## $Sex
## [1] 0
##
## $Age
## [1] 263
##
## $SibSp
## [1] 0
##
## $Parch
## [1] 0
##
## $Ticket
## [1] 0
##
## $Fare
## [1] 1
##
## $Cabin
## [1] 1014
##
## $Embarked
## [1] 2
##
## $Survived
## [1] 4183 Variable explanation
Variable Name Description Survived Survived (1) or died (0) Pclass Passenger’s class Name Passenger’s name Sex Passenger’s sex Age Passenger’s age SibSp Number of siblings/spouses aboard Parch Number of parents/children aboard Ticket Ticket number Fare Fare Cabin Cabin Embarked Port of embarkation
4 Remove “unuseful” variable
The following variables might not be relevant for survival, remove for this try.
Name, Ticket, Fare, Cabin, Embark.
Fare and cabin might be correspond with Pclass
titanic.2 is the dataset without Name,ticket, Fare, Carbon and Embarked variables.
## [1] "PassengerId" "Pclass" "Sex" "Age" "SibSp"
## [6] "Parch" "Survived"## $PassengerId
## [1] 0
##
## $Pclass
## [1] 0
##
## $Sex
## [1] 0
##
## $Age
## [1] 263
##
## $SibSp
## [1] 0
##
## $Parch
## [1] 0
##
## $Survived
## [1] 418Now only Age variable has missing values.
5 Missing Value Imputation
Age distribution
5.1 Knn - preProcess Caret Package
The knn in preProcess in the Caret Package transforms the data.
titanic.kNN is the dataset processed by preProcess function in the Caret.
## [1] "PassengerId" "Pclass" "Sex" "Age" "SibSp"
## [6] "Parch" "Survived"AgePredict <- preProcess(method ="knnImpute",x =titanic.2[,-c(1,7)])
titanic.kNN <- predict(AgePredict,newdata=titanic.2)
summary(titanic.kNN$Age)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -2.061342 -0.546789 0.077626 -0.000672 0.355144 3.477218After using knnImpute in the preProcess function in the caret. the Age data is transformed.
5.2 Median Impute Caret
titanic.median is the median impute using Caret
AgePredict <- preProcess(method ="medianImpute",x =titanic.2[,-c(1,7)])
titanic.median <- predict(AgePredict,newdata=titanic.2)
plot_histogram(titanic.median$Age)
check on the difference between original data,titanic.2 and the median imputed data titanic.median
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.17 22.00 28.00 29.50 35.00 80.00## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.17 21.00 28.00 29.88 39.00 80.00 2635.3 MICE package for imputation
Introduction mice https://www.rdocumentation.org/packages/mice/versions/3.0.0/topics/mice https://datascienceplus.com/imputing-missing-data-with-r-mice-package/
## [1] "PassengerId" "Pclass" "Sex" "Age" "SibSp"
## [6] "Parch" "Survived"use micepackage to impute missing value in Age variable, method = rf is random forest.
mice imputation has two steps.
1st step, micefunction. 2nd step, completefiction.
##
## iter imp variable
## 1 1 Age
## 1 2 Age
## 1 3 Age
## 1 4 Age
## 1 5 Age
## 2 1 Age
## 2 2 Age
## 2 3 Age
## 2 4 Age
## 2 5 Age
## 3 1 Age
## 3 2 Age
## 3 3 Age
## 3 4 Age
## 3 5 Age
## 4 1 Age
## 4 2 Age
## 4 3 Age
## 4 4 Age
## 4 5 Age
## 5 1 Age
## 5 2 Age
## 5 3 Age
## 5 4 Age
## 5 5 AgeThe micecomplete dataset only have 5 variable, PassengerID and Survived variables are removed by mice
## 'data.frame': 1309 obs. of 5 variables:
## $ Pclass: Factor w/ 3 levels "1","2","3": 3 3 2 3 3 3 3 2 3 3 ...
## $ Sex : Factor w/ 2 levels "female","male": 2 1 2 2 1 2 1 2 1 2 ...
## $ Age : num 34.5 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 ...compare data imputed with original data
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.17 21.00 28.00 29.45 37.00 80.00## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.17 21.00 28.00 29.88 39.00 80.00 263Assign Age variable in the micecomplete dataset into titanic.mice Age variable. Now titanic.mice dataset has 7 variables.
## [1] FALSE
export mice dataset