hellomlorg / breast-cancer-prediction-using-julia

code and data for breast cancer prediction

breast-cancer-prediction-using-julia

Requirements

You will first need to install julia in your system to run this code along side the various Libraries used in this project. You also need jupyter notebook to run this ipynb file. The packages needed are mentioned below.

1. DataFrames
2. CSV
3. Plots
4. Statistics
5. StatsPlots
6. Pkg
7. Pandas

Dataset

The dataset used in this project was taken from kaggle available at https://www.kaggle.com/uciml/breast-cancer-wisconsin-data and can also be found on UCI Machine Learning Repository at https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Diagnostic%29.

Accuracy

The accuracy of the model varies each time you train it from 70 to 90 percent reason being that it was only trained using a RandomForestClassifier. You can try applying various other models for better accuracy and/or do feature scaling and/or feature engineering.

Understanding the code

You can understand more on how this model works from the article I have written in helloml available at https://helloml.org/breast-cancer-prediction-using-julia/.

How to run the code

Clone this repo and then use the Jupyter Notebook to open the ipynb file.