davidfrisch / cw_data_eng_2

This repository contains coursework from the Data Engineering 2 module, which focuses on analysing customer service calls to improve service quality.

Description

This repository contains coursework from the Data Engineering 2 module, which focuses on analysing customer service calls to improve service quality. The report outlines a workflow that was tested on 621 audio files over a 24-hour period to identify and analyse unsatisfactory conversations between agents and customers.

Requirements for setup

• Have the same public and private ssh key of the Client VM and the Clusters VMs in the ~/.ssh folder of the host.
• Have a GitHub Personal Access Token (PAT) given in the zip folder of the coursework submission.
• Have a HuggingFace API key given in the zip folder of the coursework submission.

Guides

• To read the report of the coursework, please visit DataEng2_CW.pdf.
• To read the setup guide, please visit setup_guide.md.
• To read the startup guide, please visit startup_guide.md.

Example

• To see an example of the platform, please visit ec2-3-10-170-172.eu-west-2.compute.amazonaws.com.