Principal Component Analysis

Linear Algebra for Data Science in R

Eric Eager

Data Scientist at Pro Football Focus

Big Data

head(select(combine, height:shuttle))

  height weight forty vertical bench broad_jump three_cone shuttle
1     71    192  4.38     35.0    14        127       6.71    3.98
2     73    298  5.34     26.5    27         99       7.81    4.71
3     77    256  4.67     31.0    17        113       7.34    4.38
4     74    198  4.34     41.0    16        131       6.56    4.03
5     76    257  4.87     30.0    20        118       7.12    4.23
6     78    262  4.60     38.5    18        128       7.53    4.48

nrow(combine)

Big Data - Redundancy

Principal Component Analysis

One of the more-useful methods from applied linear algebra
Non-parametric way of extracting meaningful information from confusing data sets
Uncovers hidden, low-dimensional structures that underlie your data
These structures are more-easily visualized and are often interpretable to content experts

Principal Component Analysis - Motivating Example

Let's practice!

Linear Algebra for Data Science in R