Taming Big Data with Apache Spark and Python
Taming big data with ApacheSpark and Python - hands on!
After you`ve learned everything you need to analyze data and try your hand at open competitions, start looking for a job. Independent confirmation of your qualifications will be an advantage.
Computers learn to act on their own, we no longer need to write detailed instructions for performing certain tasks. Therefore, machine learning is of great importance for almost any field, but above all it will work well where there is Data Science.
The first step in learning machine learning is to become familiar with its three main forms.
1) Supervised learning is the most advanced form of machine learning. The idea is to build a function that predicts target marks for new data based on historical data for which we know the "correct" values (target labels). Historical data is tagged. Labeling (assignment to a class) means that you have a specific output value for each line of data. This is the essence of the algorithm.
2) Learning without a teacher. We don't have tagged variables, but a lot of raw data. This allows you to identify what are called patterns in the historical inputs, as well as draw interesting insights from a general perspective. So there is no output here, only the pattern visible in the uncontrolled input. The beauty of unsupervised learning is that it lends itself to many combinations of patterns, so these algorithms are more complex.
3) Reinforcement learning is applied when you have an algorithm with examples that are not labeled, as in unsupervised learning. However, you can supplement the example with positive or negative responses according to the solutions suggested by the algorithm. Reinforcement learning is about applications for which an algorithm must make decisions that have consequences. It's like learning through trial and error. An interesting example of reinforcement learning is when computers learn to play video games on their own.
What to read
- Taming Big Data with Apache Spark and Python by Frank Kane
- Supervised and unsupervised algorithms in machine learning. Easy to understand and concise explanations of the types of machine learning algorithms.
- Visualization in machine learning. Excellent visualization to help you understand how machine learning is used.