Develop a machine learning model that can predict whether people have diabetes when their characteristics are specified

This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases.

The objective of the dataset is to diagnostically predict whether or not a patient has diabetes, based on certain diagnostic measurements included in the dataset. Several constraints were placed on the selection of these instances from a larger database. In particular, all patients here are females at least 21 years old of Pima Indian heritage.

The datasets consists of several medical predictor variables and one target variable, Outcome. Predictor variables includes the number of pregnancies the patient has had, their BMI, insulin level, age, and so on.

Number of Observation Units: 768

Variable Number: 9

Script Modes:

--no-debug: Runs full script
--no-tuning: Runs script without tuning
--model-history: Shows models parameters and RMSE scores

To run script with make commands first install MakeFile application on your IDE then run like:

run: Runs full script with tuning

debug: Runs script with debug mode (Set number of row option on scripts/config.file)

notuning: Runs script without tuning

req: Creates requirements.txt

install: Installs requirements.txt

models: Shows models parameters and RMSE scores

• diabetes-prediction.ipynb - Project Notebook

• main.py - Main script

• configs.py - Configuration Files (Grid & Project settings)

• model_history.py - Show model validation scores from model_info_data.json file

• preprocess.py - Data Preparation script

• train.py - Model Training with Debug option

• utils.py - Helper functions

• outputs - Output files, includes model pkl objects and model validation history

joblib==1.1.0
lightgbm==3.1.1
matplotlib==3.5.2
numpy==1.22.3
pandas==1.4.4
scikit_learn==1.1.2
seaborn==0.11.2
xgboost==1.5.0

• Oğuz Erdoğan - oguzerdo