Bufan ZengUse Parquet for Big Data StorageDue to the portable nature, comma-separated values(csv) format is the most popular format for tabular data. If I were to list three tabular…Jun 28, 20181Jun 28, 20181
Bufan ZengModel-based Collaborative Filtering in IBM Watson Studio (Scala Notebook + Spark)Collaborative Filtering(CF) is a very popular machine learning algorithm in recommendation systems. Unlike content-based recommendation…May 29, 2018May 29, 2018
