R Bridge Course Final Project

Introduction:

This is the final project for the Bridge course to demonstrate the skills learned through the 3 weeks course. The dataset “Credit Card” will be used for the analysis. The main functions will be applied to analyze the dataset such as mean(), median(), mode(), summary() as well as graphic tools (ggplot2 library).

Question for analysis: Does expenditure proportionally increase with income?

Load data and summary of the data:

The dataset is loaded from the Github repository. Columns from 2 to 7 are used.

#install.packages("plyr")
#library(plyr)

## Reading .csv from Github
CreditCard <- read.csv("https://raw.githubusercontent.com/deepasharma06/R-HW3/main/CreditCard.csv", 
stringsAsFactors = FALSE)
summary(CreditCard)

##        X              card              reports             age         
##  Min.   :   1.0   Length:1319        Min.   : 0.0000   Min.   : 0.1667  
##  1st Qu.: 330.5   Class :character   1st Qu.: 0.0000   1st Qu.:25.4167  
##  Median : 660.0   Mode  :character   Median : 0.0000   Median :31.2500  
##  Mean   : 660.0                      Mean   : 0.4564   Mean   :33.2131  
##  3rd Qu.: 989.5                      3rd Qu.: 0.0000   3rd Qu.:39.4167  
##  Max.   :1319.0                      Max.   :14.0000   Max.   :83.5000  
##      income           share            expenditure          owner          
##  Min.   : 0.210   Min.   :0.0001091   Min.   :   0.000   Length:1319       
##  1st Qu.: 2.244   1st Qu.:0.0023159   1st Qu.:   4.583   Class :character  
##  Median : 2.900   Median :0.0388272   Median : 101.298   Mode  :character  
##  Mean   : 3.365   Mean   :0.0687322   Mean   : 185.057                     
##  3rd Qu.: 4.000   3rd Qu.:0.0936168   3rd Qu.: 249.036                     
##  Max.   :13.500   Max.   :0.9063205   Max.   :3099.505                     
##    selfemp            dependents         months         majorcards    
##  Length:1319        Min.   :0.0000   Min.   :  0.00   Min.   :0.0000  
##  Class :character   1st Qu.:0.0000   1st Qu.: 12.00   1st Qu.:1.0000  
##  Mode  :character   Median :1.0000   Median : 30.00   Median :1.0000  
##                     Mean   :0.9939   Mean   : 55.27   Mean   :0.8173  
##                     3rd Qu.:2.0000   3rd Qu.: 72.00   3rd Qu.:1.0000  
##                     Max.   :6.0000   Max.   :540.00   Max.   :1.0000  
##      active      
##  Min.   : 0.000  
##  1st Qu.: 2.000  
##  Median : 6.000  
##  Mean   : 6.997  
##  3rd Qu.:11.000  
##  Max.   :46.000

colnames(CreditCard) <- c("card", "reports", "age", "income", "share", "expenditure", "owner")
summary(CreditCard)

##       card          reports               age              income       
##  Min.   :   1.0   Length:1319        Min.   : 0.0000   Min.   : 0.1667  
##  1st Qu.: 330.5   Class :character   1st Qu.: 0.0000   1st Qu.:25.4167  
##  Median : 660.0   Mode  :character   Median : 0.0000   Median :31.2500  
##  Mean   : 660.0                      Mean   : 0.4564   Mean   :33.2131  
##  3rd Qu.: 989.5                      3rd Qu.: 0.0000   3rd Qu.:39.4167  
##  Max.   :1319.0                      Max.   :14.0000   Max.   :83.5000  
##      share         expenditure            owner               NA           
##  Min.   : 0.210   Min.   :0.0001091   Min.   :   0.000   Length:1319       
##  1st Qu.: 2.244   1st Qu.:0.0023159   1st Qu.:   4.583   Class :character  
##  Median : 2.900   Median :0.0388272   Median : 101.298   Mode  :character  
##  Mean   : 3.365   Mean   :0.0687322   Mean   : 185.057                     
##  3rd Qu.: 4.000   3rd Qu.:0.0936168   3rd Qu.: 249.036                     
##  Max.   :13.500   Max.   :0.9063205   Max.   :3099.505                     
##       NA                  NA               NA               NA        
##  Length:1319        Min.   :0.0000   Min.   :  0.00   Min.   :0.0000  
##  Class :character   1st Qu.:0.0000   1st Qu.: 12.00   1st Qu.:1.0000  
##  Mode  :character   Median :1.0000   Median : 30.00   Median :1.0000  
##                     Mean   :0.9939   Mean   : 55.27   Mean   :0.8173  
##                     3rd Qu.:2.0000   3rd Qu.: 72.00   3rd Qu.:1.0000  
##                     Max.   :6.0000   Max.   :540.00   Max.   :1.0000  
##        NA        
##  Min.   : 0.000  
##  1st Qu.: 2.000  
##  Median : 6.000  
##  Mean   : 6.997  
##  3rd Qu.:11.000  
##  Max.   :46.000

# Q1: Data Exploration:
mean_age <- mean(CreditCard[,3])
median_age <- median(CreditCard[,3])
mean_income <- mean(CreditCard[,4])
median_income <- median(CreditCard[,4])
mean_expenditure <- mean(CreditCard[,6])
median_expenditure <- median(CreditCard[,6])

print(sprintf("Mean age is %f, median age %f", mean_age, median_age))

## [1] "Mean age is 0.456406, median age 0.000000"

print(sprintf("Mean income is %f, median income %f", mean_income, median_income))

## [1] "Mean income is 33.213103, median income 31.250000"

print(sprintf("Mean expediture is %f, median expenditure %f", mean_expenditure, median_expenditure))

## [1] "Mean expediture is 0.068732, median expenditure 0.038827"

## Q2: Data Wrangling / creating new data frame with a new order of data
# CreditCard
CreditCard_new <- CreditCard[order(CreditCard$income, decreasing = TRUE),]

#Q2: Data Wrangling / Renaming columns

names(CreditCard_new)[names(CreditCard_new)=="card"] <- "Card#"
names(CreditCard_new)[names(CreditCard_new)=="reports"] <- "Reports"
names(CreditCard_new)[names(CreditCard_new)=="age"] <- "Age_in_Years"
names(CreditCard_new)[names(CreditCard_new)=="income"] <- "Income_in_1000"
names(CreditCard_new)[names(CreditCard_new)=="expenditure"] <- "Expenditure_in_1000"
# print (CreditCard_new)

#Analyze a subset of data with a certain column value greater than a specified value (in this example, the Income_in_1000 > 50)
CreditCard_new1 = subset(CreditCard_new, Income_in_1000>50)
summary(CreditCard_new1)

##      Card#          Reports           Age_in_Years   Income_in_1000 
##  Min.   :  82.0   Length:84          Min.   :0.000   Min.   :50.33  
##  1st Qu.: 418.5   Class :character   1st Qu.:0.000   1st Qu.:52.94  
##  Median : 734.5   Mode  :character   Median :0.000   Median :55.12  
##  Mean   : 713.8                      Mean   :0.369   Mean   :57.34  
##  3rd Qu.:1038.5                      3rd Qu.:0.000   3rd Qu.:60.44  
##  Max.   :1299.0                      Max.   :6.000   Max.   :83.50  
##      share        Expenditure_in_1000     owner              NA           
##  Min.   : 1.450   Min.   :0.0001091   Min.   :   0.00   Length:84         
##  1st Qu.: 2.500   1st Qu.:0.0008000   1st Qu.:   0.00   Class :character  
##  Median : 3.700   Median :0.0227894   Median :  72.47   Mode  :character  
##  Mean   : 4.232   Mean   :0.0439334   Mean   : 175.47                     
##  3rd Qu.: 5.318   3rd Qu.:0.0625904   3rd Qu.: 213.09                     
##  Max.   :12.500   Max.   :0.2975549   Max.   :3099.51                     
##      NA.1                NA.2            NA.3             NA.4     
##  Length:84          Min.   :0.000   Min.   :  1.00   Min.   :0.00  
##  Class :character   1st Qu.:0.000   1st Qu.: 38.75   1st Qu.:0.75  
##  Mode  :character   Median :1.000   Median :120.00   Median :1.00  
##                     Mean   :0.881   Mean   :149.10   Mean   :0.75  
##                     3rd Qu.:1.000   3rd Qu.:240.00   3rd Qu.:1.00  
##                     Max.   :4.000   Max.   :540.00   Max.   :1.00  
##       NA.5      
##  Min.   : 0.00  
##  1st Qu.: 3.00  
##  Median : 6.50  
##  Mean   : 8.06  
##  3rd Qu.:13.00  
##  Max.   :44.00

#Note: the Income_in_1000 Min value is 50.33 so the subset is correct.

#Q3: Install ggplot package
installed.packages("ggplot2")

##      Package LibPath Version Priority Depends Imports LinkingTo Suggests
##      Enhances License License_is_FOSS License_restricts_use OS_type Archs
##      MD5sum NeedsCompilation Built

library(ggplot2)

# #Q3: Scatter Plot
ggplot(CreditCard_new1, aes(x=Income_in_1000, y=Expenditure_in_1000)) + geom_point(color="red", size = 1, alpha=1) + scale_x_continuous("Income_in_1000$") + scale_y_continuous("Expenditure_in_1000$") + theme_minimal()

# Analysis: We see that the higher plots of expenditure is towards the lower income range.

#Q3: Boxplot / of report in the x axis and Expenditure in Y axis

crop=ggplot(data=CreditCard_new1, mapping=aes(x=Reports, y=Expenditure_in_1000))+geom_boxplot()
crop

#Q3: Adding Mean value to the Box Plot (purple point)

ggplot(CreditCard_new1, aes(x=Income_in_1000, y=Expenditure_in_1000, fill = Income_in_1000)) + 
  geom_boxplot() +
  stat_summary(fun = "mean", geom = "point", shape = 10,
               size = 1, color = "Purple")

## Warning: Continuous x aesthetic -- did you forget aes(group=...)?

# The purple points shows the mean value of expenditure for each range of income. We can see that the means are higher towards the left where the income is lower.

#A3 - Histogram of data - Expenditure_in_1000

ggplot(data = CreditCard_new1, aes(x = Income_in_1000)) + geom_histogram(bins = 10)

#A3 - Histogram of data - Expenditure_in_1000

ggplot(data = CreditCard_new1, aes(x = Expenditure_in_1000)) + geom_histogram(bins = 10)

#Q4: Linera regression of expenditure and Income 

ggplot(data=CreditCard_new1, aes(x=Expenditure_in_1000, y=Income_in_1000, group=1)) +
  geom_line()+
  geom_smooth(method='lm') 

## `geom_smooth()` using formula 'y ~ x'

Conclusion:

Based on the linear regression plot of income vs. Expenditure, it can be seen that expediture does decrease with decreasing income but the decrease is not seen to be proportional. The decrease in expenditure is slower as compared to the decrease in income which would mean that peopel with lower income spent a higher portion of their income. This makes sense econimically because the minimum cost of living remains the same irrespective of the income level and hence people with lower income will have to spent higher percentage of their income to meet that minimum.