Скачать с ютуб Real Time vs Near Real Time [DATA SCIENCE AT SCALE WITH VERTICAPY] в хорошем качестве

Real Time vs Near Real Time [DATA SCIENCE AT SCALE WITH VERTICAPY]

Different Data Science Projects have different time constraints. Sometimes it is needed to act fast in order to avoid the worst. But for many use-cases, we don’t need an instant response. Does Real-Time really exist? When to do Real-Time or Near Real Time? What type of Data Preparation we need in order to deploy our work. In this video, we will answer to all those questions. Hands-on: We will implement two Random Forest Classifier models to detect Credit Card Fraud: one for real-time and one for near real-time analytics. We will export the first one to independent Python code using the to_python function. Chapters: 0:00 Intro 0:55 Real-Time - Example 1:46 Near Real-Time - Example 2:29 Flexible Time Constraint - Example 2:52 Time Constraint Categories 4:03 Best Practices 5:16 Hands-on 9:28 Thank-you VerticaPy Installation Guide: https://www.vertica.com/python/instal... Notebook: https://github.com/vertica/VerticaPy/... Dataset: https://www.kaggle.com/dmirandaalves/... Presenter: Badr Ouali VerticaPy Website: https://www.vertica.com/python/ LinkedIN:   / verticapy   Music: https://www.bensound.com - Creative Minds Photos: https://www.unsplash.com software: #verticapy #vertica topics: #realtime #nearrealtime #datascience #machinelearning