Based on what you’ve learned until now, use NumPy, pandas, matplotlib and seaborn to create a project of your choosing.
This project must at least satisfy the following minimum requirements:
-
Choose a public dataset that needs to clean and preprocess.
-
EDA
- Apply the essential EDA steps: head, shape, info, describe, and missing values.
- Apply the additional EDA steps based on your dataset needs.
-
Data Visualization
- Drive meaningful insights (at least 10 different charts, 5 of them are unique).
- Draw a subplot using the previous charts.
- Apply chart format including:
- Choose a specific style for your charts.
- Apply one color palette from your choice on all charts.
- Use title, x and y labels, font size, figure size, and legends.
-
Use pandas profiling.
-
Report your final conclusion and findings in one page (readme markdown file).
- Team members and their responsibilities.
- Introduction (problem, objectives).
- Dataset Overview and Source.
- Describe the final ten insights.
-
The Final presentation will be on Sunday (10 min for each group).
-
Due Date: Sat, 12 Aug, 11:00 pm
- Notebook file(.ipynb).
- Dataset file.
- README.md file.