Brunopaes / nasa-asteroids

This project aims to classify, based on morphological and physical attributes, the Nasa's monitored asteroids hazardousness.

Asteroids_Nasa

This project aims to classify, based on morphological and physical attributes, the Nasa's monitored asteroids hazardousness. This binary classification project was made in python 3.6.

---

Project Structure - Directories

• Data: datasets directory;
• Scripts: python scripts directory;
• reports: pyplots, docs and reports.

---

Requirements

This project, as dependencies, require the following python libraries:

• scikit-learn;
• pandas;

To install them, in your anaconda envoironment or virtual envoironment, run the following command:

  pip install sklearn pandas

---

Sklearn Models

• Random Forest.
  • model arguments:
    • n_arguments: 100;
    • rest: default.

---

Results

Models Accuracy

1. The Random Forest model assertiveness rate was: 99.89 %.
2. The dumb algorithm assertiveness rate was 18.55 %. - independent of attributes, the model always infers True.

Confusion Matrix

	Hazardous	Not Hazardous
Hazardous	764	0
Not Hazardous	1	173

---

References

Nasa Asteroid's Dataset:

• https://www.kaggle.com/shrutimehta/nasa-asteroids-classification/

---