Reference no: EM132956059
Protect Description
This course project aims at addressing an issue or gaining insight associated with the performance of predictive analysis within the civil arid environmental engineering field. The project will help you bring together many different demerits of the class and apply them to a particular topic of interest. In addition, you will gain experience in the iterative process of real-world data science analysis and develop a product, presentation, and report to add to your work portfolio.
Students will work Individually and report on the results of this data science project. PowerPoint (or similar platform) presentations should be no longer than 20 minutes in duration.
Project Goal:
The goal of the project is to develop a regression model to predict the compressive strength of the concrete. using Compressive strength groups: i) Low strength (≤5 MPa ii) Medium Strength ( 15 MPa < Comp. Strength ≤ 30 MPa) and iii) High Strength (> 30 MPa)., students should also build at least two classification models to classify the strength of concrete.
Elements of the Report for the Applied Project
1. Suggested content and order of the project written report (and presentation) are as follows: Abstracts provide a synopsis of your project in 250 words or less.
2. Introduction and Background: Introduce the project along with a description of the scope of activities. This should include a brief description of the projects a literature review of relevant past research and findings. Cite literature on civil and environmental engineering policies and methodologies that are relevant to your project
3. Predictive Problem and Approach: Introduce the Predictive problem of the project and solution strategy.
4. 'Data Analysis arid Results; Introduce and discuss the selected modeling methodology or methodologies in detail e.g._equations with reference(s) as well as training, validating, testing details). Appropriate tables and figures should be created according to the guidelines given in class for the completed projects. Also, provide a link to GitHub or include your code and data files in your project submission.
5. Potential Problems and Mitigation strategies: Identify potential problems that may be encountered in deploying the model and think & strategies that could be used to either avoid these problems or deal with their occurrences.
6. Conclusion: Provide a brief conclusion.
7. References.
Need the actual python file for this project just like the shown on your word documents. Need steps described, regression models, KNN models described.