Configuration Manual - How to run the code - MSc Research Project Data Analytics

Sep 17, 2026

Uploaded by Eliana

Configuration Manual for an MSc Research Project in Data Analytics submitted in 2023. It certifies research referencing and the required referencing standard, and includes an attachment and checklist section for Moodle submission and keeping a hard copy. The manual describes the project structure and contents, focusing on package and library setup, Kaggle notebook execution versus local installation, system and hardware prerequisites, and the data analysis workflow. It covers EDA, pre-processing, feature engineering, data splitting, and implementation and evaluation of multiple machine learning models for predicting hospital readmissions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Contents

1 Introduction

2 Packages and Libraries

3 System and Software specification

4 Data Analysis

5 Simple Machine learning models

6 Neural Networks

7 How to run the code

7.1 Kaggle Notebook

7.2 Jupyter Notebook

Configuration Manual MSc Research Project Data Analytics Zainab Makrani Student ID: 22190082 School of Computing National College of Ireland Supervisor: Jorge Basilio National College of Ireland Project Submission Sheet School of Computing | Student Name: | Zainab Makrani | | --- | --- | | Student ID: | 22190082 | | Programme: | Data Analytics | | Year: | 2023 | | Module: | MSc Research Project | | Supervisor: | Jorge Basilio | | Submission Due Date: | 15/12/2023 | | Project Title: | Configuration Manual | | Word Count: | XXX | | Page Count: | 9 | I hereby certify that the information contained in this (my submission) is information pertaining to research I conducted for this project. All information other than my own contribution will be fully referenced and listed in the relevant bibliography section at the rear of the project. ALL internet material must be referenced in the bibliography section. Students are required to use the Referencing Standard specified in the report template. To use other author’s written or electronic work is illegal (plagiarism) and may result in disciplinary action. | Signature: | | | --- | --- | | Date: | 13th December 2023 | PLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST: | Attach a completed copy of this sheet to each project (including multiple copies) . | □ | | --- | --- | | Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | □ | | You must ensure that you retain a HARD COPY of the project, both foryour own reference and in case a project is lost or mislaid. It is not sufficient to keep a copy on computer. | □ | Assignments that are submitted to the Programme Coordinator office must be placed into the assignment box located outside the office. | Office Use Only | | | --- | --- | | Signature: | | | Date: | | | Penalty Applied (if applicable): | | Configuration Manual Zainab Makrani 22190082 Contents 1 Introduction 2 2 Packages and Libraries 2 3 System and Software specification 3 3.1 Hardware specifications for local environment ............... 3 4 Data Analysis 3 4.1 EDA ...................................... 4 4.2 Pre-processing ................................. 5 4.3 Feature Engineering .............................. 6 4.4 Splitting data ................................. 7 5 Simple Machine learning models 7 6 Neural Networks 8 7 How to run the code 9 7.1 Kaggle Notebook ............................... 9 7.2 Jupyter Notebook ............................... 9 1 Introduction This document discusses how the machine learning models are implemented for prediction of readmissions. The total code consists of 8 ML models which are differentiated between simple ML models and Neural networks. Each model is trined and used for prediction and then evaluated. The code is developed on kaggle IDE and is best to run it there, however, an alternative is to run it on local environment. Each of these ways is discussed in details in this manual. 2 Packages and Libraries This is contained in the utilities section of the code whic first checks the version of python implemented and neccessary pip installments Figure 1: Version and Pip install commands The utilities also contain the libraries that are later implemented to create necessary machine learning methods. Figure 2: Python Libraries implemented 3 System and Software specification To build this project on kaggle, u will need to create a kaggle account to run the kaggle notebook 1 . Based on their technical specifications, 2 , each notebook is allocated; 1. 12 hours of execution time for CPU and GPU ran sessions while providing 9hrs for TPU sessions. 2. 20GB automatically saving disk space 3. Scratchpad disk space which is not saved outside the current session. To build this on a local environment, the prerequisites is that python 3 is installed and set up to the path 3 . 3.1 Hardware specificati

FAQs

What is the document’s purpose and scope?

The document explains how machine learning models are implemented to predict hospital readmissions, including setup, execution approaches, and evaluation of multiple models and neural networks.

What are the system and software requirements for running the project on Kaggle and locally?

For Kaggle, a Kaggle account is needed and execution-time and disk-space limits are stated. For local use, Python 3 must be installed and configured to the system path.

How is the data analysis workflow organized before model training?

The manual outlines loading data for EDA with visual checks, then proceeds to pre-processing, feature engineering, and splitting data into training and testing sets.

Sep 17, 2026

Uploaded by Eliana