LIS 4317 Final Project: Fuel Economy Data from the U.S Dept. of Energy

 

LIS 4317 Final Project: Fuel Economy Data from the U.S Dept. of Energy

Investigating the association between vehicle features and CO2 emissions in a dataset comprising fuel efficiency data is the issue statement for my final project. The objective is to ascertain the extent to which CO2 emissions differ among various vehicle classes. In order to evaluate the effects of automobiles on the environment and pinpoint possible areas where fuel efficiency regulations could be strengthened, further investigation is essential. The idea suggests that specific vehicle classes, like larger cars or ones with bigger engines, might have more CO2 emissions than other car classes.

This issue is set within the larger framework of transportation research and environmental sustainability. The relationship between vehicle characteristics and emissions, particularly CO2 emissions, has been well studied in the past. Numerous techniques, such as statistical evaluations and graphics, have been used to investigate these connections. For example, to see how emissions vary amongst various car models, researchers have employed bar charts, box plots, and scatter plots. Additionally, research in this field has looked into how regulations and technology developments can lower the emissions from vehicles.

A bar plot showing the distribution of CO2 emissions by vehicle class is made using a visual analytics technique in order to solve the issue. To get the average CO2 emissions for each vehicle type, the dataset is first analyzed. Subsequently, the box plot is created using the R ggplot2 library, where the y-axis represents CO2 emissions and the x-axis represents vehicle class. This method facilitates insights into possible trends or patterns by providing an easy-to-understand graphic representation of the variations in CO2 emissions across various vehicle classes.

Overall, this solution offers a structured and informative approach to examining the relationship between vehicle characteristics and CO2 emissions, contributing to the broader understanding of environmental sustainability in the automotive industry. The visual representation accurately portrays the data without distortion, resulting in a low lie factor. There are no unnecessary or excessive decorative elements in the visualization, ensuring clarity and focus on the data. The visualizations adheres to best practices outlined by Stephen Few, such as clear labeling, appropriate use of color, and minimal distractions. It fits into the best practices outlined in our textbook for effective visual analysis.

LIS 4317: Module #13 Assignment

 

Module 13 Assignment

A powerful visual representation of random sampling from a uniform distribution is provided by the animation produced with the animation package and the R programming language. The animation shows a plot of ten randomly selected values from the uniform distribution in each frame. The y-axis boundaries are always set between 0 and 1 to facilitate comparisons. As the animation goes on, viewers will be able to see how the generated numbers are distributed randomly and with variability; some frames show clustered dots, while others show a more scattered distribution. An interactive and dynamic element can be added to presentations, blog posts, or instructional materials by saving the animation as a GIF. This makes it easily shareable and a useful tool for presenting ideas connected to random sampling. 

The plot() method is used to create scatter plots, and the Sys.sleep() function adds a little delay between frames to make sure the animation is visible. The code uses a loop to generate each frame. Finally, to make sharing and distribution of the visual presentation simple, the animation is saved as a GIF file using the saveGIF() function. The concept of random sampling is clearly communicated by this straightforward yet powerful animation, which also improves R data display.

LIS 4317: Module # 12

 

Module # 12

I was able to install and load the necessary packages, such as GGally, igraph, and ggplot2, for network visualization. The network was successfully visualized using the ggnet2 function from the GGally package, and the erdos.renyi.game function from the igraph package was successfully used to generate a random network. Because of this, the random network may be successfully visualized using ggnet2, giving rise to a rudimentary depiction of the network topology.

Throughout the procedure, there were a number of difficulties and mistakes. I first ran into issues when trying to use functions from the network package, like rgraph and as.network, because I was using the wrong functions and didn't have the necessary dependencies. Moreover, I have made the mistake of applying functions from the network and SNA packages when they are not required for the visualization process, which has caused confusion and needless difficulties.

Despite several significant obstacles and setbacks along the road, the process of developing the social network visualization was ultimately successful. These challenges offered priceless teaching moments and emphasized how crucial it is to pay close attention to function usage, package dependencies, and error interpretation during the development process.