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

# Load packages
library('ggplot2') # visualization
library('ggthemes') # visualization
library('scales') # visualization
library('dplyr') # data manipulation
library('mice') # imputation
library('randomForest') # classification algorithm

# The train and test data is stored in the ../input directory
train <- read.csv('../input/train.csv', stringsAsFactors = F)
test  <- read.csv('../input/test.csv', stringsAsFactors = F)

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

# check data
str(full)

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

# 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)

# Finally, grab surname from passenger name
full$Surname <- sapply(full$Name,  
                      function(x) strsplit(x, split = '[,.]')[[1]][1])
                      
# 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='_')

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


# Create a Deck variable. Get passenger deck A - F:
full$Deck<-factor(sapply(full$Cabin, function(x) strsplit(x, NULL)[[1]][1]))

# Since their fare was $80 for 1st class, they most likely embarked from 'C'
full$Embarked[c(62, 830)] <- 'C'

# Replace missing fare value with median fare for class/embarkment
full$Fare[1044] <- median(full[full$Pclass == '3' & full$Embarked == 'S', ]$Fare, na.rm = TRUE)

# Make variables factors into factors
factor_vars <- c('PassengerId','Pclass','Sex','Embarked',
                 'Title','Surname','Family','FsizeD')

full[factor_vars] <- lapply(full[factor_vars], function(x) as.factor(x))

# Set a random seed
set.seed(129)

# Perform mice imputation, excluding certain less-than-useful variables:
mice_mod <- mice(full[, !names(full) %in% c('PassengerId','Name','Ticket','Cabin','Family','Surname','Survived')], method='rf')

# Save the complete output 
mice_output <- complete(mice_mod)


# Replace Age variable from the mice model.
full$Age <- mice_output$Age

# Show new number of missing Age values
sum(is.na(full$Age))

# Create the column child, and indicate whether child or adult
full$Child[full$Age < 18] <- 'Child'
full$Child[full$Age >= 18] <- 'Adult'

# Show counts
table(full$Child, full$Survived)

# Adding Mother variable
full$Mother <- 'Not Mother'
full$Mother[full$Sex == 'female' & full$Parch > 0 & full$Age > 18 & full$Title != 'Miss'] <- 'Mother'

# Show counts
table(full$Mother, full$Survived)

# Finish by factorizing our two new factor variables
full$Child  <- factor(full$Child)

full$Mother <- factor(full$Mother)

md.pattern(full)

# Split the data back into a train set and a test set
train <- full[1:891,]
test <- full[892:1309,]

# Set a random seed
set.seed(754)

# Build the model (note: not all possible variables are used)
rf_model <- randomForest(factor(Survived) ~ Pclass + Sex + Age + SibSp + Parch + 
                                            Fare + Embarked + Title + 
                                            FsizeD + Child + Mother,
                                            data = train)
                                            
# Get importance
importance    <- importance(rf_model)
varImportance <- data.frame(Variables = row.names(importance), 
                            Importance = round(importance[ ,'MeanDecreaseGini'],2))

# Create a rank variable based on importance
rankImportance <- varImportance %>%
  mutate(Rank = paste0('#',dense_rank(desc(Importance))))

# Predict using the test set
prediction <- predict(rf_model, test)

# Save the solution to a dataframe with two columns: PassengerId and Survived (prediction)
solution <- data.frame(PassengerID = test$PassengerId, Survived = prediction)

# Write the solution to file
write.csv(solution, file = 'rf_mod_Solution.csv', row.names = F)