salma71

# Enable tab completion
source ~/git-completion.bash

# colors!
green="\[\033[0;32m\]"
blue="\[\033[0;34m\]"
purple="\[\033[0;35m\]"
reset="\[\033[0m\]"

# Change command prompt

salma71

# bash/zsh completion support for core Git.
#
# Copyright (C) 2006,2007 Shawn O. Pearce <spearce@spearce.org>
# Conceptually based on gitcompletion (http://gitweb.hawaga.org.uk/).
# Distributed under the GNU General Public License, version 2.0.
#
# The contained completion routines provide support for completing:
#
#    *) local and remote branch names
#    *) local and remote tag names

salma71

# bash/zsh git prompt support
#
# Copyright (C) 2006,2007 Shawn O. Pearce <spearce@spearce.org>
# Distributed under the GNU General Public License, version 2.0.
#
# This script allows you to see repository status in your prompt.
#
# To enable:
#
#    1) Copy this file to somewhere (e.g. ~/.git-prompt.sh).

salma71

# tabtab source for serverless package
# uninstall by removing these lines or running `tabtab uninstall serverless`
[ -f /Users/salma_elshahawy/Desktop/emicredit/node_modules/tabtab/.completions/serverless.bash ] && . /Users/salma_elshahawy/Desktop/emicredit/node_modules/tabtab/.completions/serverless.bash
# tabtab source for sls package
# uninstall by removing these lines or running `tabtab uninstall sls`
[ -f /Users/salma_elshahawy/Desktop/emicredit/node_modules/tabtab/.completions/sls.bash ] && . /Users/salma_elshahawy/Desktop/emicredit/node_modules/tabtab/.completions/sls.bash

salma71

# loading the required libraries
library(tidyverse)
library(dplyr)
library(ggplot)
library(readr)
library(caret)

# import train to R
train_df <- read.csv("train.csv", stringsAsFactors = FALSE)
head(train_df)

salma71

# Impute missing ages in Training data using caret

# picking only Age
train_df %>% select(-Ticket, -Name, -Cabin, -Embarked) -> train_ages
# use method bagImpute
pre_proc <- preProcess(train_ages, method = "bagImpute")
# predict Age
train_ages <- predict(pre_proc, train_ages)
# Append predicted age into train_df
train_df$Age <- train_ages$Age

salma71

salma71

# clean up NAs
sapply(train_df, function(x) sum(is.na(x)))
# PassengerId    Survived      Pclass        Name         Sex         Age       SibSp       Parch      Ticket        Fare 
#           0           0           0           0           0         177           0           0           0           0 
#       Cabin    Embarked 
#           0           0 

salma71

ggplot(train_df, mapping = aes(x = Survived, y = Age, fill = Survived)) + 
  geom_boxplot(outlier.colour = "red", outlier.shape = 5, outlier.size = 4) + 
  facet_wrap(~Sex)
  

salma71

# outlier detection and normalizing
outlier_norm <- function(x){
   qntile <- quantile(x, probs=c(.25, .75))
   caps <- quantile(x, probs=c(.05, .95))
   H <- 1.5 * IQR(x, na.rm = T)
   x[x < (qntile[1] - H)] <- caps[1]
   x[x > (qntile[2] + H)] <- caps[2]
   return(x)
}
train_df$Age=outlier_norm(train_df$Age)