For this coursework you must submit 2 separate files (separate submission links on Moodle for each file): •

For this coursework you must submit 2 separate files (separate submission links on Moodle for each file): • a PDF document containing your final report. • a zip file containing your code both as a .ipynb workbook and as a PDF exported from collab. Detailed Specification This Coursework is to be completed individually. You are working as a Data Scientist for a (fictitious) manufacturing company who makes metal parts for various industries. They have been experimenting with a new metal alloy that should have superior properties to the one they are currently using; however, in practice they have been finding it is very sensitive to changes in the processing parameters causing defects to form. If these defects reach a certain size, they severely impact the lifespan of the metal parts, meaning the entire part must be scrapped as defective. However, the process of measuring a parts lifespan is a slow, destructive, and expensive process, so the company are hoping you can create a Machine Learning solution that allows them to estimate the lifespan of a part based on the more easily recorded parameters, which the company hopes to use to refine their production process. A secondary objective for the company is for you to create a Machine Learning solution that can use the provided scans to automatically classify whether a part is defective or not, as they are currently having to do this manually. The company has collected two sets of data: 1. A table of processing parameters and measurements taken from the completed parts. 2. A collection of images from scanning the surface of the completed parts. Both sets of data provided have been cleaned (so there is no need to check for incorrect, duplicate, or missing data) with labels/lifespan measurements attached to prepare the data for the supervised learning tasks. Data To complete this assignment, you must use the data provided on Moodle: Dataset 1 URL: https://moodlecurrent.gre.ac.uk/mod/resource/view…. Dataset 2 URL: https://moodlecurrent.gre.ac.uk/mod/resource/view…. Also provided on Moodle are more detailed descriptions of the datasets, which it is recommended you read to aid in your understanding of the problem domain. Submissions based on other data will not be marked and will receive 0 marks. Note: This data was created specifically for this assessment and is entirely synthetic. More information check the file attached