PCA. Theory, uses and implementation.

---

Work by: Momchil Georgiev

Personal email: [email protected]

Every work cited in this project has been acquired legally through public domains such as university websites, online publications and personal/company blogs.

Description

During my course in data science I had the pleasure to work on a short project about PCA. I wanted to share what I have done and perhaps "shine a little light" on the subject while giving my own spin.

This notebook is mainly designed for people who have just started studying programming and data science. I have tried to explain everything as simple as I can and if it gets technical - there are always sources to read that explain it in more detail.

With that out of the way. Enjoy!

Contents:

1. Project Motive

2. PCA and the theory behind it:

2.1 Standardize the data

2.1.1 Calculating the mean

2.1.2 Calculating the variance

2.1.3 Calculating standard deviation

2.2 Eigenvectors and eigenvalues of the covariance matrix

3. Some other examples of PCA:

3.1 Breast cancer dataset

3.2 Eigenfaces

4. Conclusion

5. References

6. Bibliography

> Rest of the project is in PCA.ipynb