Accelerated Exploratory Data Analysis with pandas on NVIDIA GPUs | Accelerated Data Science Series

NVIDIA RAPIDS accelerates your data science and exploratory data analysis (EDA) without changing a single line of code. In this example, you will see how to build a pandas application that processes over 45M rows, speed it by 28x faster on GPUs and visualize the large dataset interactively. Learn three new data science skills as you get started with the pandas library: Data preparation: Loading and transforming a large dataset in pandas with operations such as filter and merge. Interactive dashboards: Building a dashboard and running it with GPUs to render large datasets with low latency. Google Colab: Using NVIDIA GPUs and RAPIDS libraries with pandas out of the box on Google Colab. 00:03 - Introduction 00:45 – Data Preparation and Exploration 07:30 – Interactive Dashboard 08:25 – Demo: Interactive Dashboard 09:28 – Building the Accelerated Interactive Dashboard 13:23 – Tips for Running Demo in Google Colab 15:36 – Conclusion 📗 Run this demo yourself on Google Colab: https://colab.research.google.com/gist/will-hill/aa24c3ffe1428c005af3793fcacf9bd2/cudf_pandas_opencellid_demo.ipynb ➡️ Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl ➡️ Read and subscribe to the NVIDIA Technical Blog: https://nvda.ws/3XHae9F #datascience #dataanalytics #pandas #machinelearning #RAPIDS RAPIDS cuDF, pandas, real-time analytics, dataframe, NVIDIA, Data Analytics, Data Science, CPU/GPU Interoperability, GPU-Accelerated, GPU