MwansaMwango / machine-learning-challenge

Machine learning models capable of classifying candidate exoplanets from the deep space NASA Kepler Telescope raw dataset.

Machine Learning - Exoplanet Exploration

Background

Over a period of nine years in deep space, the NASA Kepler space telescope has been out on a planet-hunting mission to discover hidden planets outside of our solar system.

To help process this data, you will create machine learning models capable of classifying candidate exoplanets from the raw dataset.

1. Preprocess the raw data
2. Tune the models
3. Compare two or more models

---

Approach

Preprocess the Data

• Preprocess the dataset prior to fitting the model.
• Perform feature selection and remove unnecessary features.
• Use MinMaxScaler to scale the numerical data.
• Separate the data into training and testing data.

Tune Model Parameters

• Use GridSearch to tune model parameters.
• Tune and compare at least two different classifiers.

Reporting

• For the first model, we used Random Forest Classifier with hyper-parameters optmised using GridSearchCV.

---

Resources

• Exoplanet Data Source

• Scikit-Learn Tutorial Part 1

• Scikit-Learn Tutorial Part 2

• Grid Search

---