Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 18 views

    Regression

    Uploaded by

    Anand Kumar

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Regression

    Uploaded by

    Anand Kumar
    18 views2 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    18 views2 pages

    Regression

    Uploaded by

    Anand Kumar

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    # Install and load the necessary package 'datarium' for the marketing dataset

    install.packages("datarium") # Install the datarium package


    library(datarium) # Load the datarium package

    # Load and inspect the marketing dataset


    data(package="datarium") # List datasets in the datarium package
    data("marketing") # Load the marketing dataset
    ?marketing # Get more information about the dataset
    View(marketing) # View the dataset in a tabular format
    str(marketing) # Check the structure of the dataset (variables and data types)
    summary(marketing) # Get summary statistics (mean, min, max, etc.) for the dataset
    plot(marketing, col="red") # Plot the dataset with red points to inspect relationships

    # Load the ggplot2 library for advanced visualizations


    library(ggplot2)

    # Install and load caTools to split the dataset into training and test sets
    install.packages("caTools") # Install the caTools package for data splitting
    library(caTools) # Load the caTools package

    # Split the dataset into training and testing subsets (80% for training, 20% for testing)
    set.seed(101) # Set a random seed to ensure reproducibility of the random split
    sample = sample.split(1:nrow(marketing), SplitRatio = 0.8) # Create a sample split (80%
    training, 20% testing)
    sample # Print the sample split to inspect the selection

    # Create the training and testing datasets based on the sample split
    train = subset(marketing, sample == TRUE) # Training set (80% of data)
    test = subset(marketing, sample == FALSE) # Testing set (20% of data)

    # Check the dimensions of the training and testing sets


    dim(train) # Check the number of rows and columns in the training set
    dim(test) # Check the number of rows and columns in the testing set

    # Build and evaluate a Simple Linear Regression (LR) model: Predict 'sales' based on
    'youtube' spend
    model1 <- lm(sales ~ youtube, data=train) # Fit a simple linear regression model using
    'youtube' as predictor
    summary(model1) # Display a summary of the linear regression model
    (coefficients, R-squared, etc.)
    pred1 <- predict(model1, test) # Predict sales using the trained model on the test
    data

    # Build and evaluate a Multiple Linear Regression (MLR) model: Predict 'sales' based on
    'youtube', 'facebook', and 'newspaper'
    model <- lm(sales ~ youtube + facebook + newspaper, data=train) # Fit a multiple linear
    regression model using multiple predictors
    summary(model) # Display a summary of the multiple linear
    regression model
    pred <- predict(model, test) # Predict sales using the multiple regression
    model on the test data

    # Prepare a new variable for plotting (x-axis as the sequence of test rows)
    x_axis <- seq(nrow(test)) # Create an x-axis variable representing row numbers of the test
    data

    # Combine the predictions and actual sales values into a data frame for easy comparison
    df <- data.frame(x_axis, pred, test$sales) # Combine x-axis, predicted sales, and actual
    sales into a data frame
    View(df) # View the resulting data frame with predictions and actual values

    # Create a line plot to compare the predicted sales vs. the actual sales using ggplot2
    g <- ggplot(df, aes(x=x_axis)) +
    geom_line(aes(y=pred, colour="Predicted")) + # Plot the predicted sales as a line
    geom_point(aes(x=x_axis, y=pred, colour="Predicted")) + # Plot the predicted sales as
    points
    geom_line(aes(y=test$sales, colour="Actual")) + # Plot the actual sales as a line
    geom_point(aes(x=x_axis, y=test$sales, colour="Actual")) + # Plot the actual sales as
    points
    scale_colour_manual("", values = c(Predicted="red", Actual="blue")) # Customize the
    colors of the lines and points

    You might also like