LIS 4317

  This week, I explored R animations using Yihui Xie's (animation) package, as highlighted on Yihui's blog and Bryan's R-bloggers post. The goal was to create a basic animation and understand how visualization can evolve dynamically with data. I created a simple animated scatter plot where random points appear and change across 10 frames. The animation simulates data fluctuation over time, using the savegif() function. Each frame displays a new set of random points with vibrant colors for visual clarity. This kind of animation can be incredibly useful when demonstrating changes over time, such as stock trends, simulation outputs, or even the convergence of algorithms. What I found compelling was how easy it was to implement — a few lines of code produced an engaging visualization. The animation output was saved as a GIF, making it easy to embed in websites or presentations. This simple tool opens up creative possibilities for storytelling with data something static chart...

  This week, I explored the basics of Social Network Analysis by creating my first network visualization using RStudio and the ggnet2 package. Here’s what I learned during the process. What Worked: Installing the necessary libraries (GGally, network, sna, and ggplot2) was smooth. I was able to generate a basic network and customize it by adjusting node size, color, and edge width. What Didn’t Work: At first, I forgot to convert the matrix created by rgraph() into a network object using the network() function, which caused an error in ggnet2. Another issue I faced was with labeling nodes—I initially tried to use numbers instead of letters, which didn’t render appropriately until I used network.vertex.names(). Key Takeaways: "ggnet2" is a powerful yet beginner-friendly tool for network visualization in R. This would be useful for presenting real-world social networks like Twitter conversations or organizational structures. R Studio Code: # Install necessary packages (run on...

Dot Dash Plot in ggplot2 This graph titled "Dot Dash Plot in ggplot2" illustrates the trend of budget expenditures over a series of years ranging approximately from 1967 to 1977 . The x-axis represents the Year , while the y-axis indicates Budget Expenditures . The data points are connected using a dot-dash line , with each point clearly marked to emphasize individual yearly values. The overall trend shows a sharp increase in expenditures from 1967 to around 1970, followed by fluctuations with minor increases and decreases through the mid-1970s. The plot peaks just before 1976 and then declines slightly toward 1977. The use of a grey background and dashed lines provides a clear, visual contrast that helps highlight the progression and variability of the data over time.

Color Gradient Based on a Continuous Variable Style : Scatter Plot with a color gradient (based on a continuous variable qsec). Do you like the visualization? Why? Yes. The color gradient from yellow to dark blue effectively shows the variation in quarter-mile time across points. It’s visually appealing and functionally informative. Is the Headline Accurate? Yes. The title "Quarter-Mile Time Gradient on MPG vs Weight" is accurate, clearly describing the visual mapping. Does the visualization support the title narrative? Yes. The scatter plot shows mpg vs wt and color encodes qsec, aligning with the title. Does the visualization lie? No. It presents data truthfully and avoids distortions. Unnecessary Graphic Elements? No unnecessary elements. Clean and focused on the data. Like or Dislike (Design, Color, Layout)? Like. The yellow-to-dark blue gradient is effective for continuous data, and the layout is clean. CODE: ggplot(mtcars, aes(x = wt, y = mpg, color = qs...

Multivariate visualization is an effective way to explore relationships between multiple variables simultaneously. In this graph, we inputted: X-axis : Horsepower (hp ) Y-axis : Miles per gallon (mpg) Color : Number of cylinders (cyl) Size : Weight (wt) The patterns identified are: Cars with higher horsepower tend to have lower fuel efficiency. Heavier cars (more prominent points) usually have more cylinders. The distinction between different cylinder groups can be observed through color. 5 Design Principles Alignment The axes and labels are well-aligned, ensuring readability. The legend is positioned appropriately to avoid clutter. Repetition The same color scheme is used consistently for cylinder categories. Labels and formatting maintain consistency across variables. Contrast The different colors for cylinder groups provide clear differentiation. The white background ensures the data stands out. Proximity Related elements (title, labels, legend) are...

In this post, I analyze relationships within the mtcars dataset using scatter plots with regression lines, following Stephen Few’s recommendations for effective visual analytics. The goal is to explore how miles per gallon (mpg) correlates with horsepower (hp) and weight (wt) while maintaining clarity and ease of comparison through a grid layout. After creating the code, and reviewing the data some findings are: MPG vs Horsepower : The scatter plot shows a negative correlation —as horsepower increases, fuel efficiency (mpg) decreases. MPG vs Weight : A similar negative correlation is observed—heavier cars tend to have lower fuel efficiency. Both relationships align with expectations in automotive performance, where higher power and heavier weight generally lead to higher fuel consumption. Stephen Few emphasizes clarity, simplicity, and effective comparison in visual analytics. His recommendation to use a grid layout enhances comparative analysis by keeping related visualizatio...