Understanding the datasets
In this chapter, we are using two datasets, as follows:
E-commerce item data
Book-Crossing dataset
e-commerce Item Data
This dataset contains data items taken from actual stock keeping units (SKUs). It is from an outdoor apparel brand's product catalog. We are building the recommendation engine for this outdoor apparel brand's product catalog. You can access the dataset by using this link: https://www.kaggle.com/cclark/product-item-data/data.
This dataset contains 500 data items. There are two columns in the dataset.
ID: This column indicates the indexing of the data item. In layman's terms, it is the serial number of the dataset.
Description: This column has all the necessary descriptions about the products, and we need to use this data to build the recommendation engine.
You can refer to the following figure:
Figure 4.3: Snippet of the e-commerce item data
As you can see, the description column has textual data, and we need to process this textual dataset in order to...
