Clasificación

Datasets para el ejercicio

• https://www.kaggle.com/c/titanic

library(dplyr)
library(ggplot2)
library(Amelia)

Loading required package: Rcpp
## 
## Amelia II: Multiple Imputation
## (Version 1.7.4, built: 2015-12-05)
## Copyright (C) 2005-2016 James Honaker, Gary King and Matthew Blackwell
## Refer to http://gking.harvard.edu/amelia/ for more information
## 

train<-read.csv("train.csv",stringsAsFactors = FALSE, na.strings = "")
test<-read.csv("test.csv",stringsAsFactors = FALSE, na.strings = "")

names(train)

 [1] "PassengerId" "Survived"    "Pclass"      "Name"        "Sex"        
 [6] "Age"         "SibSp"       "Parch"       "Ticket"      "Fare"       
[11] "Cabin"       "Embarked"   

names(test)

 [1] "PassengerId" "Pclass"      "Name"        "Sex"         "Age"        
 [6] "SibSp"       "Parch"       "Ticket"      "Fare"        "Cabin"      
[11] "Embarked"   

glimpse(train)

Observations: 891
Variables: 12
$ PassengerId (int) 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,...
$ Survived    (int) 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1...
$ Pclass      (int) 3, 1, 3, 1, 3, 3, 1, 3, 3, 2, 3, 1, 3, 3, 3, 2, 3, 2, 3, 3...
$ Name        (chr) "Braund, Mr. Owen Harris", "Cumings, Mrs. John Bradley (Fl...
$ Sex         (chr) "male", "female", "female", "female", "male", "male", "mal...
$ Age         (dbl) 22, 38, 26, 35, 35, NA, 54, 2, 27, 14, 4, 58, 20, 39, 14, ...
$ SibSp       (int) 1, 1, 0, 1, 0, 0, 0, 3, 0, 1, 1, 0, 0, 1, 0, 0, 4, 0, 1, 0...
$ Parch       (int) 0, 0, 0, 0, 0, 0, 0, 1, 2, 0, 1, 0, 0, 5, 0, 0, 1, 0, 0, 0...
$ Ticket      (chr) "A/5 21171", "PC 17599", "STON/O2. 3101282", "113803", "37...
$ Fare        (dbl) 7.2500, 71.2833, 7.9250, 53.1000, 8.0500, 8.4583, 51.8625,...
$ Cabin       (chr) NA, "C85", NA, "C123", NA, NA, "E46", NA, NA, NA, "G6", "C...
$ Embarked    (chr) "S", "C", "S", "S", "S", "Q", "S", "S", "S", "C", "S", "S"...

table(train$Survived,dnn = c("Survived"))

Survived
  0   1 
549 342 

prop.table(table(train$Survived,dnn = c("Survived")))

Survived
        0         1 
0.6161616 0.3838384 

prediccion 1

test$Survived<-rep(0,nrow(test))
glimpse(test)

Observations: 418
Variables: 12
$ PassengerId (int) 892, 893, 894, 895, 896, 897, 898, 899, 900, 901, 902, 903...
$ Pclass      (int) 3, 3, 2, 3, 3, 3, 3, 2, 3, 3, 3, 1, 1, 2, 1, 2, 2, 3, 3, 3...
$ Name        (chr) "Kelly, Mr. James", "Wilkes, Mrs. James (Ellen Needs)", "M...
$ Sex         (chr) "male", "female", "male", "male", "female", "male", "femal...
$ Age         (dbl) 34.5, 47.0, 62.0, 27.0, 22.0, 14.0, 30.0, 26.0, 18.0, 21.0...
$ SibSp       (int) 0, 1, 0, 0, 1, 0, 0, 1, 0, 2, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0...
$ Parch       (int) 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0...
$ Ticket      (chr) "330911", "363272", "240276", "315154", "3101298", "7538",...
$ Fare        (dbl) 7.8292, 7.0000, 9.6875, 8.6625, 12.2875, 9.2250, 7.6292, 2...
$ Cabin       (chr) NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "B45", NA,...
$ Embarked    (chr) "Q", "S", "Q", "S", "S", "S", "Q", "S", "C", "S", "S", "S"...
$ Survived    (dbl) 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0...

prediccion1<-data.frame(PassengerId = test$PassengerId,
                        Survived = test$Survived)
prediccion1

write.csv(prediccion1, file="allperish.csv",row.names = FALSE)

Prediccion 2

table(train$Survived,train$Sex)

   
    female male
  0     81  468
  1    233  109

\[Card(Sex_i \cap Survived_j )=\]

prop.table(table(train$Survived,train$Sex))

   
        female       male
  0 0.09090909 0.52525253
  1 0.26150393 0.12233446

\[P(Sex_i \cap Survived_j )\]

test$Survived<-ifelse(test = test$Sex=="female",
                      yes = 1,
                      no = 0)

prediccion2<-data.frame(PassengerId = test$PassengerId,
                        Survived = test$Survived)

write.csv(prediccion2, file = "swomen.csv",row.names = FALSE)

Predicción por regresión lineal

modelo1<-lm(data = train, formula = Survived ~ Pclass +
              Sex + Age+ SibSp, na.action = na.omit )
summary(modelo1)

Call:
lm(formula = Survived ~ Pclass + Sex + Age + SibSp, data = train, 
    na.action = na.omit)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.12371 -0.23934 -0.06484  0.22579  1.00073 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept)  1.396606   0.065609  21.287  < 2e-16 ***
Pclass      -0.205267   0.018769 -10.937  < 2e-16 ***
Sexmale     -0.486489   0.030527 -15.937  < 2e-16 ***
Age         -0.006557   0.001123  -5.839 8.01e-09 ***
SibSp       -0.054517   0.016230  -3.359 0.000824 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.3818 on 709 degrees of freedom
  (177 observations deleted due to missingness)
Multiple R-squared:  0.3997,    Adjusted R-squared:  0.3963 
F-statistic:   118 on 4 and 709 DF,  p-value: < 2.2e-16

test<-read.csv("test.csv",stringsAsFactors = FALSE, na.strings = "")
prediccion3<-predict(object = modelo1,newdata = test)
summary(prediccion3)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
-0.2369  0.1566  0.3799  0.4312  0.6678  1.0540      86 

hist(prediccion3)

prediccion3 <- ifelse(prediccion3>0.67, yes = 1, no = 0)
table(prediccion3)

prediccion3
  0   1 
337  81 

prediccion3 <- ifelse(is.na(prediccion3),yes = 0, no=prediccion3)
sum(is.na(prediccion3))

[1] 0

prediccion3 <- data.frame(PassengerId = test$PassengerId,
                          Survived = prediccion3) 

write.csv(prediccion3, file = "linreg.csv",row.names = FALSE)

prediccion3 %>% 
  arrange(Survived)%>%
  ggplot( aes(x=PassengerId, y=Survived))+
  geom_point()

missmap(train)

num_na <- function(x){
  sum(is.na(x))
}
sapply(train,num_na)

PassengerId    Survived      Pclass        Name         Sex         Age 
          0           0           0           0           0         177 
      SibSp       Parch      Ticket        Fare       Cabin    Embarked 
          0           0           0           0         687           0 
      Title       adult 
          0           0 

num_unico<-function(x){
  length(unique(x))
}
sapply(test,num_unico)

PassengerId      Pclass        Name         Sex         Age       SibSp 
        418           3         418           2          80           7 
      Parch      Ticket        Fare       Cabin    Embarked 
          8         363         170          77           3 

table(train$Embarked)

  C   Q   S 
168  77 644 

train$Embarked<-ifelse(is.na(train$Embarked),yes = "S",no = train$Embarked)

names(train)

 [1] "PassengerId" "Survived"    "Pclass"      "Name"        "Sex"        
 [6] "Age"         "SibSp"       "Parch"       "Ticket"      "Fare"       
[11] "Cabin"       "Embarked"   

train$Name[1:10]

 [1] "Braund, Mr. Owen Harris"                            
 [2] "Cumings, Mrs. John Bradley (Florence Briggs Thayer)"
 [3] "Heikkinen, Miss. Laina"                             
 [4] "Futrelle, Mrs. Jacques Heath (Lily May Peel)"       
 [5] "Allen, Mr. William Henry"                           
 [6] "Moran, Mr. James"                                   
 [7] "McCarthy, Mr. Timothy J"                            
 [8] "Palsson, Master. Gosta Leonard"                     
 [9] "Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)"  
[10] "Nasser, Mrs. Nicholas (Adele Achem)"                

train$Age[1:10]

 [1] 22 38 26 35 35 NA 54  2 27 14

x<-strsplit(train$Name[1],split = ",")
x<-x[[1]][2]
x<-trimws(x)
x<-strsplit(x,split = "[.]")
x[[1]][1]

[1] "Mr"

y<-strsplit(train$Name[1],split = "[.,]")
y[[1]]

[1] "Braund"       " Mr"          " Owen Harris"

title<-c()
for(i in train$Name){
  y<-strsplit(i,split = "[.,]")
  y<-y[[1]][2]
  title <- c(title,y)
}
title[1:15]

 [1] " Mr"     " Mrs"    " Miss"   " Mrs"    " Mr"     " Mr"     " Mr"    
 [8] " Master" " Mrs"    " Mrs"    " Miss"   " Miss"   " Mr"     " Mr"    
[15] " Miss"  

extract_title <- function(name){
  y<-strsplit(name,split = "[.,]")
  y<-y[[1]][2]
}
train$Title<-sapply(train$Name, FUN = extract_title,USE.NAMES = FALSE)
test$Title<-sapply(test$Name, FUN = extract_title,USE.NAMES = FALSE)

train$Title<-ifelse(trimws(train$Title) %in% c("Miss","Mlle", "Mme"),
                    yes = "Miss",
                    no =  train$Title)
test$Title<-ifelse(trimws(test$Title) %in% c("Miss","Mlle", "Mme"),
                    yes = "Miss",
                    no =  test$Title)
table(train$Title)

         Capt           Col           Don            Dr      Jonkheer 
            1             2             1             7             1 
         Lady         Major        Master            Mr           Mrs 
            1             2            40           517           125 
           Ms           Rev           Sir  the Countess          Miss 
            1             6             1             1           185 

train$adult<-ifelse(train$Age>12,yes = 1, no = 0)
test$adult<-ifelse(test$Age>12,yes = 1, no = 0)
table(train$Title,train$adult)

               
                  0   1
   Capt           0   1
   Col            0   2
   Don            0   1
   Dr             0   6
   Jonkheer       0   1
   Lady           0   1
   Major          0   2
   Master        36   0
   Mr             1 397
   Mrs            0 108
   Ms             0   1
   Rev            0   6
   Sir            0   1
   the Countess   0   1
  Miss           32 117

train$adult<-ifelse(is.na(train$Age) & trimws(train$Title) == "Master" ,
                    yes = 0,
                    no = ifelse(is.na(train$Age),
                                yes = 1,
                                no = train$adult)   
                    )
test$adult<-ifelse(is.na(test$Age) & trimws(test$Title) == "Master" ,
                    yes = 0,
                    no = ifelse(is.na(test$Age),
                                yes = 1,
                                no = test$adult)   
                    )

modelo2<-lm(data = train, formula = Survived ~ Pclass +
              Sex + adult+ SibSp+Embarked)
prediccion4<-predict(object = modelo2, newdata = test)
prediccion4 <- ifelse(prediccion4>0.5, yes = 1, no = 0)
prediccion4 <- ifelse(is.na(prediccion4),yes = 0, no=prediccion4)
prediccion4<-data.frame(PassengerId=test$PassengerId, 
                        Survived=prediccion4)