{"id":21232554,"url":"https://github.com/essien1990/apache-spark","last_synced_at":"2026-04-14T23:32:10.590Z","repository":{"id":107274824,"uuid":"418145636","full_name":"essien1990/Apache-Spark","owner":"essien1990","description":"Batch Processing using Apache Spark and Python for data exploration","archived":false,"fork":false,"pushed_at":"2021-10-17T14:27:51.000Z","size":12,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-15T21:25:24.556Z","etag":null,"topics":["apache-spark","jupyter-lab","jupyter-notebook","pyspark","pyspark-sql","python3"],"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/essien1990.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":"2021-10-17T13:47:42.000Z","updated_at":"2022-05-23T10:49:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"39037314-dac3-454f-a017-4e18ecad9b43","html_url":"https://github.com/essien1990/Apache-Spark","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/essien1990/Apache-Spark","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/essien1990%2FApache-Spark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/essien1990%2FApache-Spark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/essien1990%2FApache-Spark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/essien1990%2FApache-Spark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/essien1990","download_url":"https://codeload.github.com/essien1990/Apache-Spark/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/essien1990%2FApache-Spark/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31819718,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T18:05:02.291Z","status":"ssl_error","status_checked_at":"2026-04-14T18:05:01.765Z","response_time":153,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["apache-spark","jupyter-lab","jupyter-notebook","pyspark","pyspark-sql","python3"],"created_at":"2024-11-20T23:53:08.572Z","updated_at":"2026-04-14T23:32:10.557Z","avatar_url":"https://github.com/essien1990.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Apache Spark Using Python3 for data analysis\n - Batch Processing using Apache Spark and Python3 for data exploration\n - Dataset was downloded from https://www.kaggle.com/\n - Focusing on Pyspark SQL libraries\n    - from pyspark.sql.types import BooleanType\n    - from pyspark.sql.functions import udf\n    - from pyspark.sql import functions as F\n    - from pyspark.sql import SparkSession\n    - from pyspark.sql import Window\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fessien1990%2Fapache-spark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fessien1990%2Fapache-spark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fessien1990%2Fapache-spark/lists"}