{"id":15208072,"url":"https://github.com/atheeralzhrani/data-science-projects","last_synced_at":"2026-03-09T19:08:51.084Z","repository":{"id":254815626,"uuid":"837103633","full_name":"AtheerAlzhrani/data-science-projects","owner":"AtheerAlzhrani","description":"This repository contains my data science projects, where I utilized tools and libraries such as Spark, Python,  Pandas, NumPy, SQLite, Matplotlib, Seaborn, and performed Exploratory Data Analysis .","archived":false,"fork":false,"pushed_at":"2024-09-09T07:47:12.000Z","size":1603,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-06T17:15:38.031Z","etag":null,"topics":["data-engineering","data-preprocessing","data-science","data-visualization","exploratory-data-analysis","matplotlib","pandas","python","python-lambda","seaborn","spark"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AtheerAlzhrani.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-02T08:11:58.000Z","updated_at":"2024-09-09T07:47:16.000Z","dependencies_parsed_at":"2024-08-28T16:46:33.199Z","dependency_job_id":"fe2b9099-0013-46c4-a61b-dfedc682a763","html_url":"https://github.com/AtheerAlzhrani/data-science-projects","commit_stats":{"total_commits":31,"total_committers":1,"mean_commits":31.0,"dds":0.0,"last_synced_commit":"bdf64b9e4807a40dd7d6f112cfc244c1ffde13a5"},"previous_names":["atheeralzhrani/data-science-projects"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AtheerAlzhrani%2Fdata-science-projects","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AtheerAlzhrani%2Fdata-science-projects/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AtheerAlzhrani%2Fdata-science-projects/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AtheerAlzhrani%2Fdata-science-projects/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AtheerAlzhrani","download_url":"https://codeload.github.com/AtheerAlzhrani/data-science-projects/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242250926,"owners_count":20096897,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["data-engineering","data-preprocessing","data-science","data-visualization","exploratory-data-analysis","matplotlib","pandas","python","python-lambda","seaborn","spark"],"created_at":"2024-09-28T07:00:59.543Z","updated_at":"2026-03-09T19:08:51.016Z","avatar_url":"https://github.com/AtheerAlzhrani.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Data-Science-Projects\nThis repository contains my data science projects, where I utilized tools and libraries such as Spark, Python, Pandas, NumPy, Matplotlib, Seaborn, and performed Exploratory Data Analysis (EDA) and more, to perform data preprocessing, visualization, and model building.\n\n# Project2\nThis project provides a comprehensive analysis of the AI-powered job market, including data preprocessing, exploratory data analysis, visualizations, and predictive modeling using a combination of encoded categorical features and scaled salary data. The model's performance was evaluated using RMSE and visualized using a scatter plot. Further steps include finetune the model and exploring additional features to improve prediction accuracy.\n# Project1\nThe project involved analyzing a Telco customer dataset with 21 features on 7043 customers. I used Spark for dataset manipulation and user churn forecasting, with the Naive Bayes model achieving 70.55% accuracy and an F1 score of 0.6741.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatheeralzhrani%2Fdata-science-projects","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatheeralzhrani%2Fdata-science-projects","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatheeralzhrani%2Fdata-science-projects/lists"}