Comparative Analysis of ML and DL Models to Predict Water Quality - Configuration Manual

Sep 17, 2026

Uploaded by Theodora

Project submission sheet and configuration manual for an MSc Research Project in Data Analytics. Provides author and academic details, submission and certification statements, and a checklist for attaching hard copy and Moodle receipt. Includes instructions for running two notebooks that implement machine learning and deep learning pipelines for water potability prediction, listing required Python packages, system requirements, key hyperparameter categories, and the notebook execution workflow. Results and evaluation plots are saved for review and include accuracy and confusion-matrix reporting.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Project Submission Sheet

Certification and Referencing Requirements

Submission Checklist

System Setup and Execution

Required Python Packages

System Requirements

Hyperparameters Overview

Execution Steps

References

Configuration Manual MSc Research Project Data Analytics Pooja Sree Maniga Student ID: 23243236 School of Computing National College of Ireland Supervisor: Dr. Anu Sahni National College of Ireland MSc Project Submission Sheet School of Computing Pooja Sree Maniga Student Name: Student ID: …23243236 Programme: Data Analytics Year: 2024 . . Module: …Msc in Research Project . Lecturer: Dr. Anu Sahni Submission Due Date: 12/12/2024 Project Title: …Comparative Analysis of ML and DL Models to Predict water quality Word Count: 689 Page Count: 4 . . 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: Poojasree Maniga Date: 12/12/2024 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 for your 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 Pooja Sree Maniga 23243236 1 Section 1 The provided notebooks implement machine learning (ML) and deep learning (DL) pipelines for water potability prediction using structured datasets. The ML notebook focuses on models like Random Forest, XGBoost, and Decision Tree, with extensive hyperparameter tuning and evaluation metrics like accuracy and confusion matrices. The DL notebook, on the other hand, leverages deep learning architectures, likely incorporating TensorFlow or PyTorch, and includes provisions for GPU utilization through CUDA settings. Both notebooks use common preprocessing steps such as label encoding and dataset splitting. 2 Section 2 The following Python packages are required to run the notebooks 􀁸 General Libraries: pandas, numpy, matplotlib, seaborn pip install pandas numpy matplotlib seaborn 􀁸 Machine Learning Frameworks: o scikit-learn: For preprocessing, training, and evaluation of ML models. o xgboost: For XGBoost-specific implementations. pip install scikit-learn xgboost 􀁸 Deep Learning Frameworks: pip install tensorflow torch 3 System Requirements To run these notebooks efficiently, ensure the system meets the following specifications: 􀁸 Processor: Minimum quad-core CPU. 􀁸 RAM: At least 8 GB, 16 GB recommended. 􀁸 GPU: CUDA-enabled GPU for deep learning tasks. 􀁸 Storage: At least 1 GB of free disk space for datasets and intermediate files. 4 Hyperparameters Machine Learning models: 􀁸 Grid Search Parameters: o Random Forest: n_estimators, max_depth, entropy o XGBoost: n_estimators o Decision Tree: max_depth o Logistic Regression: Regularization parameter C Deep Learning models: 􀁸 Hyperparameters: o Batch size o Learning rate o Number of epochs 5 Execution 1) Load dataset 2) Perform necessary preprocessing steps such as Label encoding for categorical data 3) Split data into training and test sets 4) Select and Train Models o For example, training random forest model 􀁸 For Logistic regression

FAQs

What notebooks are included for the water potability prediction pipeline?

The configuration manual describes two notebooks: one for machine learning models (e.g., Random Forest, XGBoost, Decision Tree) and one for deep learning architectures using a framework such as TensorFlow or PyTorch, with GPU/CUDA provisions.

Which Python packages are required to run the notebooks?

General libraries listed include pandas, numpy, matplotlib, and seaborn. The setup also requires scikit-learn and xgboost for ML, and tensorflow and torch for deep learning.

What are the minimum system requirements to run the deep learning notebooks efficiently?

The document specifies a minimum quad-core CPU, at least 8 GB RAM (16 GB recommended), a CUDA-enabled GPU, and at least 1 GB free disk space for datasets and intermediate files.

Sep 17, 2026

Uploaded by Theodora