In [ ]:

    

library(ggplot2)
library(dplyr)


    

In [ ]:

    

train <- read.csv("train.csv")


    

In [ ]:

    

str(train)


    

In [ ]:

    

test <- read.csv("test.csv")


    

In [ ]:

    

str(test)


    

In [ ]:

    

table(train$Survived)


    

In [ ]:

    

table(train$Survived, train$Sex)


    

In [ ]:

    

SexSurvived <- data.frame(Sex=c("female", "male"), Survived=c(t))


    

In [ ]:

    

processed <- train[,c("Survived", "Sex")]
str(processed)


    

In [ ]:

    

SexSurvived <- processed %>% group_by(Sex) %>% summarise(sum(Survived))
SexSurvived <- data.frame(SexSurvived)
names(SexSurvived)
str(SexSurvived)


    

In [ ]:

    

ggplot(SexSurvived, aes(x = Sex, y = sum.Survived.)) + geom_col(fill = "lightblue", colour = "black")


    

In [ ]:

    

processed <- train[,c("Survived", "Sex")]
str(processed)
SexSurvived <- processed %>% group_by(Sex) %>% count(Survived)
SexSurvived
SexSurvived <- as.data.frame(SexSurvived)
SexSurvived$Survived <- as.factor(SexSurvived$Survived)
str(SexSurvived)
ggplot(SexSurvived, aes(x = Sex, y = n, fill = Survived)) +
    geom_col(position = "dodge", colour = "black") + 
    scale_fill_brewer(palette = "Pastel2")


    

In [ ]:

    

genderSubmission <- read.csv("gender_submission.csv")


    

In [ ]:

    

str(genderSubmission)


    

In [ ]:

    

mySub <- genderSubmission
mySub$Survived <- 0


    

In [ ]:

    

str(mySub)


    

In [ ]:

    

mySub$Survived[test$Sex == "female"] <- 1


    

In [ ]:

    

str(mySub)


    

In [ ]:

    

sum(mySub$Survived != genderSubmission$Survived)


    

In [ ]:

    

write.csv(mySub, "MyGenderSubmission.csv", row.names = FALSE)


    

In [ ]:

    

summary(train)


    

In [ ]:

    

data <- train[,c("Survived", "Pclass")]
data1 <- data %>% group_by(Pclass) %>% count(Survived)
data1