Requirements

You are required to use the dataset contained within the file “Groceries data.csv” and then perform the following analysis by testing at least 2 classification algorithms and using Market basket analysis:

•             Perform an initial analysis of the data (EDA) using python in your Jupyter notebook. Discuss your findings and what relevance they might have on your planned classification algorithms and Market Basket analysis. [0-10]

•             Perform any preparation of the data, that you feel is necessary, using python in your Jupyter notebook. Explain your rationale behind your data preparation and how it will assist you.[0-20]

•             Create and implement Market Basket Analysis on the grocery dataset and discover the 5 most likely pairings of products.[0-35]

•             Make a classification of your choice using the dataset. Compare at least 2 different classification algorithms.  Comment on the accuracy differential between the training and testing set and any difference in the algorithms results[0-35]

Min Word count 1500 words, Not including references and code. All written work MUST be completed in Jupyter Notebook Markdown (please review “Jupyter Notebook Tutorial” Notes in Moodle if you are unsure of this).

Note

•             All written work MUST be completed in Jupyter Notebook Markdown (please review “Jupyter Notebook Tutorial” Notes in Moodle if you are unsure of this).

•             All data wrangling, analysis, and visualizations must be generated using python.

•             All Code must be included in code blocks (As normal). No other upload will be accepted.

•             All written work MUST be detailed in your Jupyter Markdown (NOT in code comments).