[Udemy] Heart Attack and Diabetes Prediction Project in Apache Spark
What you’ll learn
On this course you’ll implement Spark Machine Studying Project 2 Mini Initiatives in Apache Spark utilizing Databricks Pocket book (Neighborhood version server)
Launching Apache Spark Cluster
Course of that knowledge utilizing a Machine Studying mannequin (Spark ML Library)
Apache Spark primary and Scala basic data is required and SQL Fundamentals together with Machine Studying fundamentals
Following browsers on Home windows, Linux or macOS desktop:
Google Chrome (Newest model), Firefox (Newest model), Safari (Newest model), Microsoft Edge* (Newest model)
Web Explorer 11* on Home windows 7, 8, or 10 (with newest Home windows updates utilized)
*You would possibly see efficiency degradation for some options on Microsoft Edge and Web Explorer.
On this Information science Machine Studying mission, we are going to create
1) Heart Illness Prediction
2) Diabetes Prediction
utilizing just a few algorithms of the predictive fashions.
- Discover Apache Spark and Machine Studying on the Databricks platform.
- Launching Spark Cluster
- Course of that knowledge utilizing a Machine Studying mannequin (Spark ML Library)
- Arms-on studying
- Actual time Use Case
- Create a Information Pipeline
- Publish the Project on Net to Impress your recruiter
- Graphical Illustration of Information utilizing Databricks pocket book.
- Rework structured knowledge utilizing SparkSQL and DataFrames
- Information exploration utilizing Apache Spark
1) Heart Illness Prediction utilizing Choice Tree Classification Mannequin
2) Diabetes Prediction utilizing Logistic Regression Mannequin and One-vs-Relaxation classifier (a.ok.a. One-vs-All) Mannequin
A Actual time Use Case on Apache Spark
Who this course is for:
- Newbie Apache Spark Developer, Bigdata Engineers or Builders, Software program Developer, Machine Studying Engineer, Information Scientist