Dimensionality reduction using PCA
In real-world data, there are a vast number of features and it is hard to analyze or visualize this tremendous amount of data. Hence we use Dimensionality Reduction in Data Preprocessing stage to discard redundant features.
Dimensionality reduction means projecting data to a lower-dimensional space, which makes it easier for analyzing and visualizing data. However, the reduction of dimension requires a trade-off between accuracy (high dimensions) and interpretability (low dimensions).
But the key is to retain maximum variance features and reduce redundant features.

#dimensionality-reduction #data-science #principal-component #apc #machine-learning