# This R script will run on our backend. You can write arbitrary code here!

# Many standard libraries are already installed, such as randomForest
library('ggthemes') # visualization
library('scales') # visualization
library('dplyr') # data manipulation
library('mice') # imputatio
library(randomForest)
library('ggplot2')

# The train and test data is stored in the ../input directory
train <- read.csv("../input/train.csv")
test  <- read.csv("../input/test.csv")

full  <- bind_rows(train, test) # bind training & test data

# check data
str(full)

print(full$Name)


# Grab title from passenger names
full$Title <- gsub('(.*, )|(\\..*)', '', full$Name)

# Show title counts by sex
table(full$Sex, full$Title)


# Titles with very low cell counts to be combined to "rare" level
rare_title <- c('Dona', 'Lady', 'the Countess','Capt', 'Col', 'Don', 
                'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer')

# Also reassign mlle, ms, and mme accordingly
full$Title[full$Title == 'Mlle']        <- 'Miss' 
full$Title[full$Title == 'Ms']          <- 'Miss'
full$Title[full$Title == 'Mme']         <- 'Mrs' 
full$Title[full$Title %in% rare_title]  <- 'Rare Title'

# Show title counts by sex again
table(full$Sex, full$Title)




full$Surname <- gsub('(,.*)','',full$Name)

print(full$Surname)



# Create a family size variable including the passenger themselves
full$Fsize <- full$SibSp + full$Parch + 1

# Create a family variable 
full$Family <- paste(full$Surname, full$Fsize, sep='_')



# Use ggplot2 to visualize the relationship between family size & survival
ggplot(full[1:891,], aes(x = Fsize, fill = factor(Survived))) +
  geom_bar(stat='count', position='dodge') +
  scale_x_continuous(breaks=c(1:11)) +
  labs(x = 'Family Size') +
  theme_few()




# Discretize family size
full$FsizeD[full$Fsize == 1] <- 'singleton'
full$FsizeD[full$Fsize < 5 & full$Fsize > 1] <- 'small'
full$FsizeD[full$Fsize > 4] <- 'large'

# Show family size by survival using a mosaic plot
mosaicplot(table(full$FsizeD, full$Survived), main='Family Size by Survival', shade=TRUE)



cat(paste('We will infer their values for **embarkment** based on present data that we can imagine may be relevant: **passenger class** and **fare**. We see that they paid<b> $', full[c(62, 830), 'Fare'][[1]][1], '</b>and<b> $', full[c(62, 830), 'Fare'][[1]][2], '</b>respectively and their classes are<b>', full[c(62, 830), 'Pclass'][[1]][1], '</b>and<b>', full[c(62, 830), 'Pclass'][[1]][2], '</b>. So from where did they embark?'))



# We can inspect the train data. The results of this are printed in the log tab below
summary(train)


a<-array(1:10)

# Here we will plot the passenger survival by class
train$Survived <- factor(train$Survived, levels=c(1,0))
levels(train$Survived) <- c("Survived", "Died")
train$Pclass <- as.factor(train$Pclass)
levels(train$Pclass) <- c("1st Class", "2nd Class", "3rd Class")

png("1_survival_by_class.png", width=800, height=600)
mosaicplot(train$Pclass ~ train$Survived, main="Passenger Survival by Class",
           color=c("#8dd3c7", "#fb8072"), shade=FALSE,  xlab="", ylab="",
           off=c(0), cex.axis=1.4)
dev.off()