### About this Activity
For Problem Set 4, we're stripping away a lot of the structure behind the problem and instead asking you to simply predict the type of trees (i.e. forest cover) from a series of environmental features.

### About the Dataset
You have been given two training documents - train-features.csv and train-outcomes - which contain the features (in the "features" file) and the outcomes (in the "outcomes" file) in the Data tab above (along with information about the features), with rows corresponding to cases. You have also been given test-features.csv with the test case features. Your objective is to provide a test-outcomes.csv file equivalent that predicts the outcomes for each case. See the Data page for full details.

### About Submissions
To submit a set of predictions, upload your properly formatted document in the Submit Predictions section. Use the sample in the Data section for guidance on formatting your submission. Check the Leaderboard section to see how you're doing!

You have to be logged in to Kaggle to submit, and Kaggle has some tricky rules in place to ensure each human only has one account. If your account is associated with your given name in the course roster or your campus username, I can easily link your activity to your grade. If your Kaggle account is a personal account, under a pseudonym, etc. that's fine - you'll just have to make that link in your brief description.

### Rules
Full details of how submissions work, etc. can be found in the Rules tab above as well as on Canvas. There are some important details to note here on the main page.

- You may only submit up to two predictions to Kaggle per day. Use internal validation processes (K-fold cross validation, etc) to optimize!
- Do not go find other copies of this dataset online. You can find and incorporate external data that can provide a benefit (e.g. if somehow Twitter sentiment or stock market analysis were to prove useful, which I doubt, you could add it to your modeling process), but if you find the *same* dataset, please do not use it in your model training.
- You are working on this homework alone. This is not a group assignment.
    - The rules for sharing and collaboration are somewhat relaxed on this assignment. You can share the tools, approaches and techniques that you are finding useful with others, e.g. "I found it helpful to use Classification Technique X" or "I dropped Feature A before I fit my data and got better outcomes". You can also choose not to share those insights with others, and instead hoard your succcesses.

Otherwise, this homework follows the same rules as other homework assignments - you should be working independently, using Piazza as a resource but not as a coding crutch. There are many approaches to solve this problem, and not everyone has to use the same one!

### Submissions to Grades

Outcomes will be calculated using F1 score, which will then be mapped to grade outcomes out of 100 Points. Your grade will be measured on Max(Public Score, Private Score). You do not have to submit anything to Canvas (no code, no writeup, etc.).

- Any submission < 14% F1 score: 0 Points
- 14% < 70% F1 score: 50 Points
- 70% < 80% F1 score: 70 Points
- 80% < 85% F1 score: 80 Points
- 85% < 91% F1 score: 90 Points
- F1 score > 91%: 100 Points
Submissions over 91% F1 score:
- For every 1% over 91%, you will receive 5 Bonus Points.
- For calculating these points, your score will be rounded down (e.g. an F1 score at 36.8% will not count as an F1 score at 37%

In addition, to foster a small spirit of competition, the top 25% of class submissions at the end of the competition will receive 10 Bonus Points
- You can be in the top 25% of class submissions on either the public or private leaderboards (or both) to get the 10 Bonus Points. These public / private bonus points will not stack, though they will combine with the over 91% F1 score bonus points.

### Acknowledgements
We thank the UCI Machine Learning Repository for access to this dataset.