Each project comes with 2-5 hours of micro-videos explaining the solution.
Code & Dataset
Get access to 50+ solved projects with iPython notebooks and datasets.
Add project experience to your Linkedin/Github profiles.
Understanding the problem Statement
Importing the dataset directly from Amazon AWS
What is Clustering
Performing basic EDA and Data-preprocessing
Plotting Boxplot and checking for identifying outliers
Fixing outliers using proper technique
Scaling and normalizing the dataset
Partition based methods, Hierarchical Methods, Model-based methods of clustering
Kmeans, k-median, k-mode agglomerative, divisive expectation-maximization based methods
Identifying different libraries used for Clustering
Steps involved in K-clustering
Applying different methods available for clustering
Applying the silhouette score on the clustering result
Visualizing the result by plotting graphs
Picking the best model for making predictions
Calculating probability related to testing data points for different clusters
The weekly sales transaction dataset consists of weekly purchased quantities of 800 products over 52 weeks. Normalised values are provided too. The objective of this data science project in R is to find out product bundles that can be put together on sale. Typically Market Basket Analysis was used to identify such bundles, here we are going to compare the relative importance of time series clustering in identifying product bundles.