README.md

About data

Dataset 1

Create a model for predicting mortality caused by Heart Failure. (Labels are not balanced, consider using f1-score instead of accuracy) https://www.kaggle.com/andrewmvd/heart-failure-clinical-data

Dataset 2

Create a model for predicting complitacions during surgery. (Labels are not balanced, consider using f1-score instead of accuracy) https://www.kaggle.com/omnamahshivai/surgical-dataset-binary-classification

Setup

Create a virtual environment using virtualenv venv

Activate the virtual environment by running venv/bin/activate

On Windows use venv\Scripts\activate.bat

Install the dependencies using pip install -r requirements.txt

Check possibilities python main.py -h or run default python main.py

Example

1. Run in terminal python main.py -m DecisionTree -d data/dataset1.csv
2. This is what you get: Sample photo:

Limitations

1. Dataset must be preprocessed and cleaned (no missing values, no outliers, no duplicates).
2. Dataset must be in csv format.
3. Models solve the classification problem.
4. Available models: Decision Tree, Random Forest K-Nearest Neighbors

Future work

1. Add models: Logistic Regression, Support Vector Machine, Naive Bayes, K-Means, Linear SVM, and Gradient Boosting Classifier.
2. Add model manipulation: Grid Search, Cross Validation and Hyperparameter Tuning.
3. Add visualization.