DS510 - Final Project

# Read CSV file into a data frame data <- read.csv("ds510_mpg.csv", header = TRUE, col.names = c("mpg", "cylinder", "displacement", "horsepower", "weight", "acceleration", "model_year", "origin", "car_name")) data

# Read CSV file into a data frame data <- read.csv("ds510_mpg.csv", header = TRUE, col.names = c("mpg", "cylinder", "displacement", "horsepower", "weight", "acceleration", "model_year", "origin", "car_name")) # Create a subset of the data frame of only the first 300 records data <- data[1:300, ] # Drop specified columns given categorical nature columns_to_drop <- c("origin", "car_name") data <- data[, !(names(data) %in% columns_to_drop)] # Change model_year format from YY to YYYY data$model_year <- as.numeric(paste0("19", data$model_year)) # Change the data type of the "horsepower" column to integer data$horsepower <- as.integer(data$horsepower) # Display the first few rows of the data #head(data) #Simple Linear Regression Analysis m_cylinder <- lm(mpg ~ cylinder, data = data) m_dis <- lm(mpg ~ displacement, data = data) m_hp <- lm(mpg ~ horsepower, data = data) m_weight <- lm(mpg ~ weight, data = data) m_accel <- lm(mpg ~ acceleration, data = data) m_year <- lm(mpg ~ model_year, data = data) summary(m_cylinder) summary(m_dis) summary(m_hp) summary(m_weight) summary(m_accel) summary(m_year) # Multiple Linear Regression Analysis based on coefficients which had the strongest correlations in prior analysis model <- lm(mpg ~ cylinder + displacement + horsepower + weight + acceleration , data = data) # Display summary of the regression model summary(model) # Display Multiple Linear Regression Equation cat("Linear Regression Equation:\n") cat(paste("mpg =", round(coefficients(model)[1], 4))) for (i in 2:length(coefficients(model))) { cat(paste("+ (", round(coefficients(model)[i], 4), "*", names(coefficients(model)[i]),")")) } cat("\n") # Read CSV file into a data frame data_test <- read.csv("ds510_mpg.csv", header = TRUE, col.names = c("mpg", "cylinder", "displacement", "horsepower", "weight", "acceleration", "model_year", "origin", "car_name")) # Use the model to predict mpg for the remaining 98 samples data_test <- data_test[301:398,] columns_to_drop <- c("origin", "car_name","model_year") data_test <- data_test[, !(names(data_test) %in% columns_to_drop)] data_test$horsepower <- as.integer(data_test$horsepower) # Predict mpg using the trained model predicted_mpg <- predict(model, newdata = data_test) #create data frame of actual and predicted values values <- data.frame(actual=data_test$mpg, predicted= predicted_mpg) #plot predicted vs. actual values plot(x=values$predicted, y=values$actual, xlab='Predicted Values', ylab='Actual Values', main='Predicted vs. Actual Values - Test Sample') #add diagonal line for estimated regression line abline(a=0, b=1) # Calculate residuals residuals <- data_test$mpg - predicted_mpg #Residual Plot par(mfrow = c(1, 2)) # Set up a 1x2 plotting grid plot(predicted_mpg, residuals, main = "Residual Plot", xlab = "Predicted MPG", ylab = "Residuals", pch = 16, col = "blue") abline(h = 0, col = "red", lty = 2) # Add a reference line #Histogram of Residuals hist(residuals, main = "Histogram of Residuals", xlab = "Residuals", col = "lightblue", border = "black")