KMeans Cluster Analysis: Data Science Project With Python

In this tutorial video using #python for data science, we are clustering customers using #KMeans #clustering and the essential Python libraries: pandas, scikit-learn and seaborn. I am walking you through a unique machine learning #project using the transactional data of online casino players, performing #featureengineering to convert customer transactional data to customer features. The first part of the #datascience #project can be watched here: Exploratory Data Analysis in Python: Data Science Project: https://youtu.be/Pi_OcqLzF64?si=NHrFYSGXZnwN6eL6 Contents: 00:00 - Introduction 02:23 - Data understanding 04:00 - Cluster analysis simply explained 05:11 - Feature engineering: for time series to customer features 18:02 - Join multiple pandas DataFrames 19:15 - Replace missing values with constant in pandas DataFrame 21:00 - Feature visualization with pairplot 23:07 - How to select the number of clusters for kmeans cluster analysis 24:42 - Elbow method for cluster selection 26:24 - Interpreting Silhouette plot 27:46 - Feature transformation with logarithm 28:35 - Cluster analysis 32:30 - Scatter plots 33:10 - Reverse the transformation for scale 38:43 - Conclusion Datasets: https://data.mendeley.com/datasets/9j5gcygnwg/1 Give a 🌟 to the code repository: https://github.com/giraffa-analytics/YT_casino_ml_project