# First, work individually Like a Sprint Challenge, work individually — until you make a submission that scores at least 60% accuracy on the public leaderboard. Also, for this first submission, do _not_ use online resources about the water pumps challenge, such as: - [DrivenData discussion forum](https://community.drivendata.org/c/pump-it-up-data-mining-the-water-table) - [DataCamp course](https://www.datacamp.com/community/open-courses/drivendata-water-pumps-challenge) # Then, work collaboratively After you make a submission that scores at least 60% accuracy on the public leaderboard, you are encouraged to collaborate with your cohort and use any online resources! You'll still submit your predictions individually. Also, you cannot use external data beyond what's provided here. But, you are free to discuss feature engineering ideas and modeling techniques. # Deliverables _The project has three parts. For each part, we've listed what's required to pass the Sprint Challenge, and what's recommended but not required._ ### Predictions Due Thursday at 4:15pm Pacific. Required: 60% accuracy on public leaderboard. Beat the majority class baseline. Work individually on this submission. Recommended: 80% accuracy on private leaderboard. Collaborate as a cohort for improved scores. ### Code Required: Write Python code to train your model and make predictions. Push your code to GitHub. Recommended: Format your notebook(s) with Markdown, comments, and visualizations. You could use this [style guide](https://www.dataquest.io/blog/data-science-project-style-guide/). ### Communication Required: Publish a blog post. Include 2+ visualizations. Recommended: Present to your cohort, up to 2 minutes. In your blog post, include 3+ visualizations, all with titles. Include at least one of these visualization types: - Partial dependence plot - Shapley values plot - Plot with explanatory title (full sentence communicating an insight you want your audience to know) plus additional text (subtitle and/or annotation) - Animation