Principal Component Analysis PCA Python Example Using SKLearn – V2


Learn how to run Principal Component Analysis (PCA) in Python using SKLearn. Learn when and how to use PCA in order to improve your Kmeans clustering results in Unsupervised Learning. Then, learn how to deploy your model using Power BI and how to analyse the traits of all your clusters and create valuable insights for the business. Real life example! Hope you enjoy this video!

Tutorial Overview:
1. What is Machine Learning in a nutshell
2. What is Unsupervised Learning (Supervised Vs Unsupervised Learning)
3. Problem formulation – What are we trying to solve?
4. Explaining how the whole automated process will work (Excel – SQL – Python – SQL – Power BI)
5. Loading the Raw Data into Python
6. Cleaning the Raw Data
7. What is Kmeans clustering
8. How to run Kmeans clustering using SKLean
6. What is Principal Component Analysis (PCA)
7. Who to run Kmeans and PCA together in Python
8. Ways to improve Kmeans results
9. Running Kmeans with optimal parameters
12. Creating the front end PowerBI Dashboard
13. Creating Insights from Clusters
14. Creating NPS analytics per Cluster
15. Discussing how these results can be used in real life

Data Analytics Course Link:
Promo: “FIRST100” for $50 off

Part 1 Video:

Yiannis GitHub – files:

Machine Learning Process:

How to download and install Python through Anaconda:

Numpy Tutorial:

Pandas Tutorial:

Joins / Merges Tutorial:

MatPlotLib Tutorial:

Seaborn Tutorial:

Machine Learning – Linear Regression Tutorial:

Machine Learning – Logistic Regression Tutorial:

Yiannis Pitsillides on Social Media:



Comment List

  • Data 360 YP
    November 28, 2020

    What do you think about these series of videos? Let me know your thoughts below! Thanks!

  • Data 360 YP
    November 28, 2020

    Hi, Not able to find your previous video… can you please share the link… Thanks

  • Data 360 YP
    November 28, 2020

    Thank you for this video. I still can't understand what you meant by this " the less principal components you have , the lower the interia will be after PCA" Can you elaborate more ? many thanks

  • Data 360 YP
    November 28, 2020

    In case you are using python 3.X:
    # Creating a df with the components and explained variance
    a = list(zip(range(0,n_components), pca.explained_variance_))

  • Data 360 YP
    November 28, 2020

    dude check this out
    there corona virus dashboard looks exactly like yours, they stole it

  • Data 360 YP
    November 28, 2020

    Excellent video Yiannis! Keep it up!

  • Data 360 YP
    November 28, 2020

    Brilliant! I was waiting for this! Thanks!

Write a comment