/Diabetes-Prediction

This is a Machine Learning model which predicts the presence of Diabetes in Patients

Primary LanguageJupyter NotebookMIT LicenseMIT

Diabetes Disease Prediction

This is a machine Learning mode which tries to determine if a person has a diabetes or not.

Data

The dataset is in comma seperated values (.csv) format and is included in teh code.

Packages Used

The following Packages were used

  • scikit-learn: To preprocess the data, initiate the model, split the data, cross-validate the data and score the model.
  • pandas: To import the dataset, change the dataset into a dataframe and view the data
  • seaborn & matplotlib: To visualize the data and to create heat maps to perform feature selection.

Model

Two models were used in this project:

  • The KNearestNeaighbor Classifier.
  • The Multi-Layer Perceptron Classifier.

Model Accuracy

  • The KNearestNeighborClassifier model recorded an accuracy of 72% on the test data.
  • The MultiLayerPerceptronClassifier model recorded an accuracy of 74% on the test data.