[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290526-105":59,"doc-detail-290526-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","configuration-manual-msc-research-project-data-analytics-student-submission-sheet","Configuration Manual - MSc Research Project Data Analytics - Student Submission Sheet","","MSc Research Project “Configuration Manual” documents how to replicate a coffee-quality prediction study in a specified computing environment. It records the software and hardware setup, including Python and PyCharm versions, and describes dataset acquisition from Kaggle, combining Arabica and Robusta CSV files into a unified dataset. The manual then covers exploratory data analysis, library installation, target distribution visualization, preprocessing steps such as missing-value handling, and feature engineering using one-hot encoding for categorical variables. It concludes with model implementation details for Random Forest, GBM, SVR, and a hybrid approach.",{"@graph":69,"@context":123},[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-student-submission-sheet/290526/",{"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-student-submission-sheet/290526.png","ImageObject",300,407,{"name":92,"@type":93},"Noah","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-28","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is included in the configuration manual to replicate the study?","Question",{"text":113,"@type":114},"It includes a snapshot of the code for constructed models, exploratory data analysis, assessment and data import/preprocessing, plus essential hardware and tools needed for the specified environment.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Where was the dataset obtained and how was it prepared?",{"text":118,"@type":114},"The dataset was obtained from the Kaggle platform, with separate CSV files for Arabica and Robusta. Both files were combined and renamed as “Coffee” for the study.",{"name":120,"@type":111,"acceptedAnswer":121},"What preprocessing steps and feature engineering techniques are described?",{"text":122,"@type":114},"The manual describes handling missing values and performing feature engineering using one-hot encoding for categorical variables.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290526,1789641939,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":41,"preview_page_count":4},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Configuration Manual  \nMSc Research Project Data Analytics  \nMethmi Kaveesha Melewwe Thantrige  \nStudent ID: x22156879  \nSchool of Computing National College of Ireland  \nSupervisor: Prof. Jorge Basilio  \nNational College of Ireland Project Submission Sheet School of Computing  \n| Student Name: | Methmi Kaveesha Melewwe Thantrige |\n| --- | --- |\n| Student ID: | x22156879 |\n| Programme: | Data Analytics |\n| Year: | 2023-2024 |\n| Module: | MSc Research Project |\n| Supervisor: | Prof. Jorge Basilio |\n| Submission Due Date: | 31st January 2024 |\n| Project Title: | Configuration Manual |\n| Word Count: | 628 |\n| Page Count: | 10 |\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: | Methmi Kaveesha Melewwe Thantrige |\n| --- | --- |\n| Date: | 31st 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  \nMethmi Kaveesha Melewwe Thantrigex22156879  \n1 Introduction  \nAll the information required for replicating the study’s results in a particular environment is included in the configuration manual. Provided is a snapshot of the code for all constructed models, exploratory data analysis, assessment, and data import and preprocessing as well as essential hardware and tools.  \nThe structure of the report is as follows: In Section 2, there is information on the environment’s setup. Section 3 goes into depth on data collection. Section 4 covers exploratory data analysis and data pre-processing. Section 5 contains information on data splitting for the training and testing stages. Section 6 includes information on each model developed, as well as findings and graphics.  \n2 Section 2  \nInformation regarding the environment setup specifically required software and hardware is mentioned in this section.  \n2.1 Hardware Requirement  \nThe hardware requirement needed is shown in below Figures 1 and 2 .  \nFigure 1: Hardware Requirement  \nFigure 2: Software Requirement  \n2.2 Software Requirement  \n1. Python (Version 3.7.13)  \n2. PyCharm IDE (2022.3.1) -PyCharm is a popular integrated development environment (IDE) specifically designed for Python development. Developed by JetBrains, PyCharm provides a robust and feature-rich environment for Python programmers, offering tools to streamline the coding, testing, and debugging processes. The IDE supports a wide range of Python frameworks, including Django, Flask, and more. Key features include intelligent code completion, syntax highlighting, integrated testing tools, version control integration (such as Git), and powerful debugging capabilities JetBrains (2021) .  \n3 Data Collection  \nThe dataset was obtained from the Kaggle platform which is an open-source website CQI Dataset: [https://www. kaggle. com/datasets/volpatto/coffee-quality-database-from-cqi](https://www. kaggle. com/datasets/volpatto/coffee","cbCaivNycs7mL9wJ","https://ap.wps.com/l/cbCaivNycs7mL9wJ","pdf",1290006,12,"English","# 1 Introduction\n# 2 Section 2\n## 2.1 Hardware Requirement\n## 2.2 Software Requirement\n# 3 Data Collection\n# 4 Data Exploration\n## 4.1 Loading Data\n## 4.2 Exploratory Data Analysis\n## 4.3 Data Preprocessing\n# 5 Model Implementation\n## 5.1 Random Forest\n## 5.2 Gradient Boosting Machine (GBM)\n## 5.3 Support Vector Regression (SVR)\n## 5.4 Hybrid Model","[{\"question\":\"What is included in the configuration manual to replicate the study?\",\"answer\":\"It includes a snapshot of the code for constructed models, exploratory data analysis, assessment and data import/preprocessing, plus essential hardware and tools needed for the specified environment.\"},{\"question\":\"Where was the dataset obtained and how was it prepared?\",\"answer\":\"The dataset was obtained from the Kaggle platform, with separate CSV files for Arabica and Robusta. Both files were combined and renamed as “Coffee” for the study.\"},{\"question\":\"What preprocessing steps and feature engineering techniques are described?\",\"answer\":\"The manual describes handling missing values and performing feature engineering using one-hot encoding for categorical variables.\"}]","Configuration Manual - MSc Research Project Data Analytics - Student Submission Sheet | PDF"]