Inspiration
The Quick Release Vehicle Bill of Materials dataset contains data entry information of the engineers releasing their parts into the Bill of Materials (BoM). However, engineers have been releasing parts into the BoM without checking the data quality first. As a result, we have been hired to sort out the data and try to identify any patterns and issues in the data and report back to the company.
What it does
We did an exploratory analysis project on this given dataset with various charts and plots to recognize any trends and violations within the data of the Bill of Materials.
We wanted to figure out if we could find out if it was the employees or something beyond them that was causing all these data entry violations in the dataset. This project visualizes key trends and big discrepancies that we noticed among the data.
How we built it
We built this project using pandas to load the data into a dataframe and visualize the data and created charts using the plotly library.
Challenges we ran into
Since, it was our first datathon, we ran into many challenges including cleaning up the data. It was difficult to create an algorithm that would correctly first check if the parent key of a part matched the parent entry in the dataset. Since the dataset was so large and the structure of the part hierarchy was so complex, it required an advanced data structure to accommodate the complex system in the BoM.
Log in or sign up for Devpost to join the conversation.