[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291110-105":59,"doc-detail-291110-en":135},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":128,"head_meta":130,"extra_data":132,"updated_unix":134},105,"en","configuration-manual-msc-research-project-data-analytics-291110","Configuration Manual - MSc Research Project Data Analytics","","Configuration Manual for an MSc Research Project in Data Analytics, authored by Aishwarya Rani Gopal under supervisor Mayank Jain. The manual explains the hardware and software setup to reproduce the research, focusing on Google Colab and required packages. It outlines Python library installation/import steps, describes dataset preparation using Irish and OSHA data sources loaded via Google Drive, and details preprocessing workflows including one-hot encoding, decision-tree feature selection, MinMax scaling, and class balancing with SMOTE and RUS. It also summarizes the model-building approach using multiple machine learning algorithms.",{"@graph":69,"@context":127},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/configuration-manual-msc-research-project-data-analytics-291110/291110/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/configuration-manual-msc-research-project-data-analytics-291110/291110.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-08","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119,123],{"name":110,"@type":111,"acceptedAnswer":112},"What is the purpose of the Configuration Manual?","Question",{"text":113,"@type":114},"The manual aims to explain the hardware and software setups needed to duplicate the research, including the steps to execute the code and the applications/packages required.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which datasets are used, and how are they loaded into the environment?",{"text":118,"@type":114},"The manual uses two datasets: an Irish dataset from the Irish Government website and an OSHA dataset from Kaggle. The files are loaded in Google Drive and accessed in Google Colab by mounting the drive.",{"name":120,"@type":111,"acceptedAnswer":121},"How is data preprocessing and class balancing performed?",{"text":122,"@type":114},"Missing values are removed, categorical variables are encoded with one-hot encoding, feature selection is done using a decision tree classifier, and feature scaling uses MinMax scaling. Class imbalance is addressed with SMOTE and RUS resampling techniques.",{"name":124,"@type":111,"acceptedAnswer":125},"Which machine learning algorithms are evaluated in model building?",{"text":126,"@type":114},"Six experiments are described using five algorithms: SVM, Adaboost, XG Boost, Naive Bayes, and Multi-Layer Perceptron (MLP). Models are tested with feature-selected and class-balanced datasets for both Irish and OSHA datasets.","https://schema.org",{"og:url":83,"og:type":129,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":131,"canonical":83},"index,follow",{"doc_id":133,"site_id":62},291110,1789643484,{"code":4,"msg":5,"data":136},{"doc_id":133,"user_id":137,"nickname":92,"user_avatar":138,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":139,"file_id":140,"file_url":141,"file_type":142,"file_size":143,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":44,"language":144,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":145,"faqs":146,"seo_title":147,"seo_description":67,"update_tm":134,"read_time":148,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","Configuration Manual  \nMSc Research Project Data Analytics  \nAishwarya Rani Gopal  \nStudent ID: 21226105  \nSchool of Computing National College of Ireland  \nSupervisor: Mayank Jain  \nNational College of Ireland Project Submission Sheet School of Computing  \n| Student Name: | Aishwarya Rani Gopal |\n| --- | --- |\n| Student ID: | 21226105 |\n| Programme: | Data Analytics |\n| Year: | 2023 |\n| Module: | MSc Research Project |\n| Supervisor: | Mayank Jain |\n| Submission Due Date: | 14/12/2023 |\n| Project Title: | Configuration Manual |\n| Word Count: | 820 |\n| Page Count: | 7 |\n\nI 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.  \nALL 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.  \n\n| Signature: | Aishwarya Rani Gopal |\n| --- | --- |\n| Date: | 29th January 2024 |\n\nPLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST:  \n\n| Attach a completed copy of this sheet to each project (including multiple copies) . | □ |\n| --- | --- |\n| Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | □ |\n| 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. | □ |\n\nAssignments that are submitted to the Programme Coordinator office must be placed into the assignment box located outside the office.  \n\n| Office Use Only |  |\n| --- | --- |\n| Signature: |  |\n| Date: |  |\n| Penalty Applied (if applicable): |  |\n\nConfiguration Manual  \nAishwarya Rani Gopal  \n21226105  \n1 Introduction  \nThe main objective of this manual is to explain the hardware and software setups required to duplicate the research in the future. This paper describes the steps necessary to execute the code along with the applications and packages required.  \n2 System Configuration  \nThis section discusses the hardware and software configurations of the project.  \n2.1 Hardware Configuration  \nThe Hardware configuration of the project is mention in Figure 1 .  \nFigure 1: Hardware Specification  \n2.2 Software Configuration  \nGoogle Colab 1 is easy to use. Using a Google account sign-in, Google Colab can be accessed. Required files can be imported into Google Drive and can be accessed using Google Colab. It integrates smoothly with various Google services and supports GPU and TPU acceleration, making it an ideal platform for machine learning and data analysis projects (Figure 2) . Other Software like Microsoft Excel is used for initial data exploration. Lifetime of the VM is 12hrs.  \nFigure 2: Software Specification  \n3 Python Libraries  \nThree Colab notebooks have been used for this project as shown in Figure 3 .  \n• Data Visualization-DataVisualize Irish.ipynb is used to perform Exhaustive Exploratory Data Analysis  \n• Modelling for Irish Dataset-ModelBuilding Irish.ipynb is used in Data Preparation and Model Building for Irish Dataset.  \n• Model Building for OSHA Dataset-ModelBuilding OSHA.ipynb is used in Data Preparation and Model Building for OSHA Dataset.  \n1[https://colab.research.google.com/](https://colab.research.google.com/)  \nFigure 3: Colab Files  \n3.1 Installing Libraries  \nThe Figure 4 shows the code snippet to installation of all the required libraries used in the research.  \nFigure 4: Libraries installation  \n3.2 Importing Libraries  \nThe Figure 5 shows the code snippet to Import the downloaded libraries used in the research.  \nFigure 5: Importing Libraries  \n4 Project Development  \n4.1 Data Preparation  \nThis research uses two datasets. Irish Datase","cbCaipJ190PdoDwu","https://ap.wps.com/l/cbCaipJ190PdoDwu","pdf",1081529,"English","# 1 Introduction\n# 2 System Configuration\n## 2.1 Hardware Configuration\n## 2.2 Software Configuration\n# 3 Python Libraries\n## 3.1 Installing Libraries\n## 3.2 Importing Libraries\n# 4 Project Development\n## 4.1 Data Preparation\n## 4.2 Data Handling\n# 5 Model Building","[{\"question\":\"What is the purpose of the Configuration Manual?\",\"answer\":\"The manual aims to explain the hardware and software setups needed to duplicate the research, including the steps to execute the code and the applications/packages required.\"},{\"question\":\"Which datasets are used, and how are they loaded into the environment?\",\"answer\":\"The manual uses two datasets: an Irish dataset from the Irish Government website and an OSHA dataset from Kaggle. The files are loaded in Google Drive and accessed in Google Colab by mounting the drive.\"},{\"question\":\"How is data preprocessing and class balancing performed?\",\"answer\":\"Missing values are removed, categorical variables are encoded with one-hot encoding, feature selection is done using a decision tree classifier, and feature scaling uses MinMax scaling. Class imbalance is addressed with SMOTE and RUS resampling techniques.\"},{\"question\":\"Which machine learning algorithms are evaluated in model building?\",\"answer\":\"Six experiments are described using five algorithms: SVM, Adaboost, XG Boost, Naive Bayes, and Multi-Layer Perceptron (MLP). Models are tested with feature-selected and class-balanced datasets for both Irish and OSHA datasets.\"}]","Configuration Manual - MSc Research Project Data Analytics | PDF",23]