hera94 / market-basket-analysis-instacart

Market-Basket-Analysis-Instacart

This project implements a dashboard using R Shiny Dashboard Library. The dasboard represents a market basket analysis of Instacart. It allows the user to specify the data source that will be used to produce Descriptive and Prescriptive Data Analytics. The prescriptive data analytics implements an Apriori Algorithm with the flexibility of changing the algorithm parameters through the dashboard.

Getting Started

• To clone (download the repository), open Git Bash (for Windows users), terminal for Linux/Mac users and run the following commands:

$ cd DIRECTORY
example:
$ cd Desktop
$ git clone https://github.com/Hera94/Market-Basket-Analysis-Instacart

Prerequisites

• Install R and R Studio. A helpful link: https://courses.edx.org/courses/UTAustinX/UT.7.01x/3T2014/56c5437b88fa43cf828bff5371c6a924/
• Download and Install Git Bash (for windows users)

User Manual

Use the sidebar through the different tabs of the dashboard

• Upload Tables - this tab is used to define the folder(directory) where all the data files are found. please choose the folder "instacart-market-basket-analysis".
• Tables - this tab helps to take a glance at the data of each dataset.
• Descriptive Data Analytics- this tab has four subtabs representing descriptive graphs of the dataset.
• Prescriptive Data Analytics- this tab implements a Market Basket Analysis. The Apriori algorithm is made interactive as the user has controls to change the parameters of the algorithm. Also, the user can choose if he wants to do the Apriori per product, per Aisle, or per Department. The user will see the marketing insights, Association rule scatterplots, association rule graph and association rules.

Tips

• Check Screenshots.pdf for screenshots of the dashboard
• if the libraries used are not installed, uncomment the code for installing those packages.
• It is recommended to set the default browser to Google Chrome and once you run the app, click on "Open in Browser".

References

The dataset was taken from Kaggle posted by Instacart: https://www.kaggle.com/c/instacart-market-basket-analysis/data

market-basket-analysis-instacart's Issues

good day Author, based on the git clone results, there are some errors due to limited LFS bandwidth

During cloning the project, the git clone message revealed that This repository is over its data quota, and the author should purchase more data packs to allow us who clone your project to restore access. I understand it is not necessary for you to purchase more data packs for us. But May I know, rather than the solution above, are there any methods to retrieved the locked LFS files in the csv? Such as attaching the copy of zip folders of those csv files in your repo? Hope to hear from you soon. By the way, I'm doing this because I refer this repo to do my university project. Lots of thanks in advance.

Upload tables not responding

I have installed all the packages and while I have executed and clicked on Upload Tables>Chosse Folder and select the folder with the CSV file, there is no response for the server. It's still saying uploading tables.

Note: I can see the aisles.csv in the Content tab