The dataset is derived from the study *[In Silico Design of 2D and 3D Covalent Organic Frameworks for Methane Storage Applications](https://archive.materialscloud.org/record/2018.0003/v2)*, which presents a database of 69,840 COFs, designed using 666 unique organic linkers and evaluated with four synthesis methods. Grand-canonical Monte Carlo simulations were used to calculate methane storage, highlighting COFs that surpass the performance of existing materials.

Participants will leverage this dataset to develop predictive models, advancing the design of high-performing COFs for methane storage applications.

---

## Files

- **`train.csv`**: Contains the training dataset with feature variables and the target variable (`highUptake_mol`).
- **`test.csv`**: The test dataset for which participants will generate predictions.
- **`sample_submission.csv`**: A sample file showing the expected format for submission.

---

## Columns

Below are the key features in the dataset:

- **`voidFraction`**: Porosity or percentage of void space in the material.
- **`supercellVolume`**: Volume of the supercell structure used for modeling.
- **`density`**: Density of the material.
- **`cell_a`, `cell_b`, `cell_c`**: Dimensions of the supercell structure in angstroms.
- **`alpha_deg`, `beta_deg`, `gamma_deg`**: Angles (in degrees) of the supercell structure.
- **`num_carbon`, `num_fluorine`, etc.**: Counts of specific atoms within the material (e.g., carbon, fluorine).
- **`largest_incl_sphere`**: Diameter of the largest sphere that fits inside the material.
- **`largest_free_sphere`**: Diameter of the largest sphere that can move freely within the material.
- **`largest_incl_sphere_along_path`**: Diameter of the largest sphere that fits along a path in the material.
- **`highUptake_mol` (Target Variable)**: Methane absorption capacity of the material (target variable to predict).

---

## What You Need to Do

- **Train**: Use the features in `train.csv` to model `highUptake_mol`.
- **Predict**: Generate methane uptake predictions for `test.csv`.
- **Submit**: Format predictions as per `sample_submission.csv` and submit your results.