With Selection, Slicing, Indexing and Filtering — In part 1 and part 2, we’ve learned how to inspect, describe and summarize a Pandas DataFrame. Today, we’ll learn how to extract a subset of a Pandas DataFrame. This is very useful because we often want to perform operations on subsets of our data. There are many different ways…

Reduce the size of your dataset while keeping as much of the variation as possible — In both Statistics and Machine Learning, the number of attributes, features or input variables of a dataset is referred to as its dimensionality. For example, let’s take a very simple dataset containing 2 attributes called Height and Weight. …

Choose the Right Laptop for Data Science and Machine Learning — If you’re learning Data Science and Machine Learning, you definitely need a laptop. This is because you need to write and run your own code to get hands-on experience. When you also consider portability, the laptop is the best option instead of a desktop. A traditional laptop may not be…

Avoid data leaking from the test set into the training set — Many of us are not aware of data leakage as this happens subtly. A golden rule exists when building ML and DL models: The same data used for training should not be used for testing. Instead, we should use two different sets of data for training and testing. Unfortunately, we…

Using the Functional API — Neural Networks and Deep Learning Course: Part 29 — Algorithms are useless if we ignore their practical applications. We’ve already discussed the principles behind autoencoders. It is time to discuss their practical applications. Before that, you should know how autoencoders are implemented in Keras. So, in this article, I will discuss the Keras implementation of autoencoders by building two…

Which one should you use when splitting your data? — In machine learning and deep learning, we often split our full dataset into train, validation and test sets. The training set is used for training (fitting) the model. The validation set is used for hyperparameter tuning. Finally, the test set is used for the final evaluation of the model. …

With the Keras functional API method — I like the people who keep things simple as much as possible. Python for loops are used for doing repetitive tasks efficiently with less code. Such a for loop can be used to efficiently build a stack of neural network layers. To demonstrate this for you, I will use a…

Understanding the principles behind autoencoders — Autoencoders (AEs) are a type of neural network architecture that is able to find a compressed representation of the input data such as image, video, text, speech, etc. Autoencoders fall under unsupervised learning algorithms as they learn the compressed representation of the data automatically from the input data without labels. Practical applications of autoencoders