Q: What are the two basic categories of machine learning and how do they differ from each other?
A: Machine learning can be broadly categorized into supervised and unsupervised learning. In the case of supervised learning, the model is trained based on the historical data, which is treated as the version of truth, termed training data. In the case of unsupervised learning, the algorithm derives inferences based on the input data, without labeled training data. The hidden patterns within the datasets are derived on the fly.
Q: Why is the Spark programming model suitable for machine learning with big datasets?
A: Spark is a general-purpose computation engine based on the fundamentals of distributed resilient computing. The large datasets are seamlessly distributed across cluster nodes for faster model generation and execution. Most of the underlying details are hidden from the data science engineer and hence there is a very limited learning curve involved in implementing...