Part 41 How to Choose the Number of Clusters

Statistics,
Data Science,
Python,
machine learning,
Benefits of Data Science,
Linear regression,
Multiple Linear Regression,
Logistic Regression,
Cluster Analysis,
K-Means Clustering,
Other Types of Clustering
Popular Data Science Tools,
Careers in Data Science,
Descriptive Statistics,
OLS,
R-Squared,
Test for Significance of the Model (F-Test),
Linearity,
No Endogeneity,
Normality and Homoscedasticity,
Multicollinearity,

[@jamesnewport4198]

Really useful explanation, thank you

[@sachinhota1473]

A very clear explanation of Elbow method used to identify k in k-means clustering.
Thanks a lot !!!

[@thangtran145]

Absolutely wonderful explanation! Really helpful guys! Please keep it up!

[@xiaoqizheng7476]

thanks a lot! very clear and interesting explanation!

[@nicorubino5636]

Thanks for sharing this! ☺

[@avnerbatat5103]

great explanation

[@vitorribeirosa]

Thanks for your explanation.
You clarified my doubts.

[@gregmaland5318]

Very well done!

[@luciferjohn8971]

Nice explanation.
Just one thing Could you please explain what is (x)
Are these the data points?

[@mazi082]

x is the numeric columns selected from the dataframe (iloc or loc method). Remember you cant use a catagroical columns for this exercise.
Aslo when plotting the KMeans clusters, you should use numeric columns only (remeber to comvert x to numpy arrray, e,g x.to_numpy()

[@slartidan]

Can we use an equation to find the "ellbow", or is it necessary a human decision? Maybe the "derivation" can help?

[@user-jp4ep9ht1o]

👍

[@Rahul-qe9gc]

What about Silhouette score and Visualization?

[@Axiom23573]

Monotonously Decreasing Function 😂