Question 1

The dataset comprises records of commuter journeys. The data dictionary of this dataset is depicted in Appendix 1.

The Python codes are to be expressed in text format and must be included, with the correct indentation(s), in all the answers in the report. Screenshots of the codes are not permitted and will not be marked.

The corresponding Jupyter notebook must also be submitted.

(a) In the dataset, ‘-’, ‘–’, and ‘?’ are considered as missing values, and the variable columns of the dataset are noted as in the data dictionary in order. As part of data preparation, read the dataset in as a Pandas dataframe, with the above considerations.

(b) Identify the variable columns which have missing values. As part of data preparation, implement ways to treat them, and explain your rationale. State any interesting observation(s).

(c) As part of data preparation, identify three (3) other data quality issues in the data. Similarly, suggest and implement ways to treat them, and explain your rationale.

(d) Develop a user-defined function that will print the hour, expressed in the 12-hour clock format (e.g., 12am, 1pm), whereby the highest number of commuters start their journey.

(e) Write Python code to create appropriate visualizations of the commuter data. Analyze the results and then discuss three (3) interesting insights.