library("ggplot2")
library("gplots")
library("glmnet")
library("MASS")
library("tidyverse")
library("dplyr")
library("reshape")
library("ggpubr")
library("glmnet")
library("reshape2")
library("heatmaply")
library("dummies")
library("dplyr")
library("tidyr")
library("ggplot2")
library("caTools")
library("caret")
library("ROCR")
library("ggpubr")

Reading Data

rm(list=ls())
students_math<-read.csv("/Users/kayhanbabakan/OneDrive/Analytics Edge Project/student-mat.csv",sep = ";")
students_por<-read.csv("/Users/kayhanbabakan/OneDrive/Analytics Edge Project/student-por.csv", sep = ";")
students_both<-read.csv("/Users/kayhanbabakan/OneDrive/Analytics Edge Project/studentsinboth.csv", sep = ",")

Pre-Processing

students_math$school = as.factor(students_math$school)
students_math$sex = as.factor(students_math$sex)
students_math$address = as.factor(students_math$address)
students_math$famsize = as.factor(students_math$famsize)
students_math$Fjob = as.factor(students_math$Fjob)
students_math$Mjob = as.factor(students_math$Mjob)
students_math$reason = as.factor(students_math$reason)
students_math$guardian = as.factor(students_math$guardian)
students_math$schoolsup = as.factor(students_math$schoolsup)
students_math$famsup = as.factor(students_math$famsup)
students_math$paid = as.factor(students_math$paid)
students_math$activities = as.factor(students_math$activities)
students_math$nursery = as.factor(students_math$nursery)
students_math$higher = as.factor(students_math$higher)
students_math$internet = as.factor(students_math$internet)
students_math$higher = as.factor(students_math$higher)
students_math$romantic = as.factor(students_math$romantic)
students_math$Pstatus = as.factor(students_math$Pstatus)

Coliniearity testing

students_mathonly = select(students_math,-c(G1,G2))
students_mathonly2 = model.matrix(~.,data=students_mathonly)
ggcorr(students_mathonly2,size=2)+
  theme(axis.text.x = element_text(angle = 90, hjust = 1))

WalcxDalc = ggplot(students_mathonly)+
  geom_bar(aes(Walc,Dalc),stat="identity")

MeduxFedu=ggplot(students_mathonly)+
  geom_bar(aes(as.factor(Medu),fill=as.factor(Fedu)),stat="count")

ggarrange(WalcxDalc,MeduxFedu,legend = "top")

Initial indications

#grade above percetnage
FailuresxG3=ggplot(students_mathonly,aes(x=failures,fill=G3<=10))+
  geom_histogram(binwidth=1,position='fill')

FamrelxG3=ggplot(students_mathonly,aes(x=famrel,fill=G3<=10))+
  geom_histogram(binwidth=1,position='fill')

GooutxG3= ggplot(students_mathonly,aes(x=goout,fill=G3<=10))+
  geom_histogram(binwidth=1,position='fill')

StudytimexG3=ggplot(students_mathonly,aes(x=studytime,fill=G3<=10))+
  geom_histogram(binwidth=1,position='fill')

RomanticxG3=ggplot(students_mathonly,aes(x=romantic,fill=G3<=10))+
  geom_bar(position='fill')

AbsencesxG3= ggplot(students_mathonly, aes(absences, G3,colour = sex))+
  geom_point()+
  xlab("absences")+
  ylab("3Q Grades")

ggarrange(FailuresxG3,FamrelxG3,GooutxG3,StudytimexG3,RomanticxG3,AbsencesxG3,legend = "top")

Linear Modeling

set.seed(1)
split = createDataPartition(students_mathonly$G3, p = 0.65, list = FALSE) 
math.train = students_mathonly[split,]
math.test = students_mathonly[-split,]

math.lm = lm(G3~+sex+famsize+Medu+failures+romantic, data = math.train)
summary(math.lm)

Call:
lm(formula = G3 ~ +sex + famsize + Medu + failures + romantic, 
    data = math.train)

Residuals:
     Min       1Q   Median       3Q      Max 
-12.6879  -2.0789   0.3121   2.8798   8.8798 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)   8.2935     0.8126  10.207  < 2e-16 ***
sexM          0.7410     0.5389   1.375 0.170348    
famsizeLE3    1.1845     0.5864   2.020 0.044453 *  
Medu          0.9133     0.2537   3.600 0.000383 ***
failures     -1.8348     0.3681  -4.984 1.16e-06 ***
romanticyes  -1.2107     0.5581  -2.169 0.030981 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 4.265 on 253 degrees of freedom
Multiple R-squared:  0.196, Adjusted R-squared:  0.1802 
F-statistic: 12.34 on 5 and 253 DF,  p-value: 1.017e-10

Stepwise variable reduction linear output basis standard threshold