R Programming Assignment Solution on Pop and GDP

library(readr)
gdp <- read_csv("pop-gdp.csv")
dim(gdp)

#Renaming the columns

names(gdp)[2] <- "Pop"
names(gdp)[3] <- "GDP"
colnames(gdp)

#scatter plot
library(ggplot2)
ggplot(gdp, aes(x = GDP, y = Year))+geom_point()

ggplot(gdp, aes(x = Pop, y = Year))+geom_point()

library(dplyr)
R1 <- gdp %>%
 filter(between(Year, 1947, 1964))
R1

R2 <- gdp %>%
  filter(between(Year, 1972, 1990))
R2

R3 <- gdp %>%
  filter(between(Year, 1998, 2014))
R3

#Years 1955 and 1960 are missing in R1
# for GDP

lm.fit <- lm(GDP ~ Year, data = R1)
lm.fit

newdata = data.frame(Year = 1955)
p1 <- predict(lm.fit, newdata)  

newdata1 = data.frame(Year = 1960)
p2 <- predict(lm.fit, newdata1)    

# for Pop

lm.fit1 <- lm(Pop ~ Year, data = R1)
lm.fit1

newdata2 = data.frame(Year = 1955)
p3 <- predict(lm.fit1, newdata2)  

newdata3 = data.frame(Year = 1960)
p4 <- predict(lm.fit1, newdata3)    

#################

new_row_1 <- c(1955, p1, p3)
new_row_2 <- c(1960, p2, p4)
R1 <- rbind(R1, new_row_1, new_row_2) %>% arrange(Year)

# Scatter plot of enhanced R1

ggplot(R1, aes(x = GDP, y = Year))+geom_point()

ggplot(R1, aes(x = Pop, y = Year))+geom_point()

# As we can see that these points are totally differnet from the linear trend in the data