Hi Data quest friends,
Here is my project on ebay used car listing dataset.
As with my other projects, any dataset and project that spark my interest, I am hoping to come back after data visualisation to have another go and enhancing it using the knowledge gained.
It would be great to receive feedback and comments on the following:
- Storytelling and flow
- Use of Numpy and Panda concepts
My Jupyter notebook file below:
Jupyer Notebook Viewer
Great job on the project. I see that you’ve tried going deep in to the data. That is an excellent start.
The following is my feedback (please click on each bullet point triangle to open the list of my suggestions)
Storytelling and Flow
- You’ve done a great job on this. I was able to follow the logical steps of reading, cleaning and analysing the data.
- I also like how you created the headings. It really brings out the data, especially the ones after cell. . I’m surprised that you haven’t kept the style throughout, like after cell  and cell. Any reason for the same?
- I noticed that you removed a lot of the price entries. You could remove more. Look for the word ‘schlacten’ in the listing name.
Use of Numpy and Pandas
- Your cleaning and your analysis speaks for your code. You’ve done well.
- Something I found confusing was when you used the parameter
normalise=True. I recommend that you multiply that value by 100. This could help readers understand better. When I first saw it, I was confused and wondered how you got such small fractional values, till I read what you wrote.
Hope to see your project with visualizations. Great job! Keep it going