|torrens university UniLearnO is not sponsored or endorsed by this college or university.
|Subject Code :
This Assessment focuses on the prediction of asteroid diameter sizes. Asteroids could cause immense damage if they collide with planet Earth. The extinction of dinosaurs has been attributed to an asteroid of 10 km diameter (Hartman, n.d.).
In this Assessment, you will create a regression model using statistical machine learning (ML) to accurately predict asteroid diameter using known observational features and asteroid dynamics. The National Aeronautics and Space Administration (NASA) Jet Propulsion Lab (JPL) Small-Body Database Search Engine (NASA, 2020b) provides feature and dynamic data for existing asteroids and comets.
1. Data set and Pre-Processing
1. Describe the data set (see Blakelobato, 2020d and the Centre for Near Earth Object Studies [CNEOS] glossary below) and any issues with the data upon visual inspection and using the Pandas head() function. It should be noted that pre-process and cleaning tasks have already been performed to resolve the majority of data issues. For example, the pre-processing of the database should have eliminated about half the columns by dropping duplicate columns, columns not relevant to asteroids, missing data, high cardinality columns, correlated columns and outliers in certain instances. Thus, you are not expected to undertake any major tasks in relation to cleaning the data, as this was taken into account in the data set you downloaded (Blakelobato, 2020b). However, you are encouraged to describe the data set and point out any aspects of the data worthy of further study.
2. Data Visualisation (Correlations and Two-Variable Plots)
1. Conduct an initial data exploration using only data visualisation. You should be able to review the correlations between the key attributes (see Blakelobato, 2020d) of the asteroid and your target for prediction. Using the seaborn library in Python, you can generate an annotated heatmap (see Figure 1, Basu, 2019) showing the variable correlation from most (+1) to none at all (–1). In addition to the heatmap, select at least three scatter plots to help highlight important features from the data set; for example, asteroid diameter (target variable) and absolute magnitude (H), asteroid geometric albedo and absolute magnitude (H), asteroid MOID and absolute magnitude (H) or number of observations used in the orbit fit (n_obs_used) and diameter.
3. Model Implementation
1. Create three models using the code and models provided by Blakelobato (2020a): Logistic Regression, Decision Tree and Random Forest.
2. Evaluate the performance metrics for each model to compare the different models. Use the table below to capture your metrics and comments. Explicitly identify the best model based on the metrics
4. Model Insights from Shapley Plots
1. Select a model and use Shapley plots to explain how your model makes predictions using the top three features.
2. Use the existing Shapley plots code to generate the top three features for increasing diameter prediction and the top feature for decreasing diameter. Comment on the most predictive features of the selected model using the Shapley plots.
This CLR 204 - Management has been solved by our PhD Experts at Unilearno. Our Assignment Writing Experts are efficient to provide a fresh solution to this question. We are serving more than 10000+ Students in Australia, UK and US by helping them to score HD in their academics. Our Experts are well trained to follow all marking rubrics and referencing style.
Be it a used or new solution, the quality of the work submitted by our assignment experts remains unhampered. You may continue to expect the same or even better quality with the used and new assignment solution files respectively. There’s one thing to be noticed that you could choose one between the two and acquire an HD either way. You could choose a new assignment solution file to get yourself an exclusive, plagiarism (with free Turnitin file), expert quality assignment or order an old solution file that was considered worthy of the highest distinction.
Eureka! You've stumped our genius minds (for now)! This exciting new question has our experts buzzing with curiosity. We can't wait to craft a fresh solution just for you!