https://github.com/soumyaco/kneighbors-classifier-diabetes

Diabetes prediction using KNN-Classifier algorithm. Step by step guided notebook
https://github.com/soumyaco/kneighbors-classifier-diabetes

data-science data-visualization diabetes-dateset-analysis diabetes-prediction knn-classification machine-learning-algorithms python3

Last synced: 10 days ago
JSON representation

Diabetes prediction using KNN-Classifier algorithm. Step by step guided notebook

• Host: GitHub
• URL: https://github.com/soumyaco/kneighbors-classifier-diabetes
• Owner: SoumyaCO
• License: gpl-3.0
• Created: 2023-08-17T15:26:16.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-08-18T19:32:37.000Z (over 1 year ago)
• Last Synced: 2024-10-25T11:49:58.443Z (about 2 months ago)
• Topics: data-science, data-visualization, diabetes-dateset-analysis, diabetes-prediction, knn-classification, machine-learning-algorithms, python3
• Language: Jupyter Notebook
• Homepage: https://www.kaggle.com/code/soumyadipbhat/knn-diabetes-classification
• Size: 853 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  



# Predicting Diabetes using KNeighborsClassifier.

![accuracy vs n_neighbors graph](https://github.com/SoumyaCO/KNeighbors-classifier-diabetes/blob/main/knn-image.png)

### 1. 🎯 Aim: 

Train a model with the diabetes data to predict a patient has diabetes or not.

### 2. 📚 Concepts Covered:

* Data Manupulation

* Feature Engineering

* Scaling a dataset

* Hyperparameter tuning with `GridSearchCV`

* `confusion_matix`

* F1_score, precision

* Data Visualization

### 3. 🔎 Approach: 

> * Importing the data

> * Understanding the features

> * Cleaning the data

> * Scale and Impute the data

> * Instantiate a `KNeighborsClassifier()` model from `sklearn.neighbors`

> * To have the right number of `n_neighbors` performed `GridSearchCV`

> * After getting the `grid.best_params_` visualized `confusion_matrix`

> * Calculated Precision, Recall, F1_score

> * Lastly visualized a accuracy vs n_neighbors plot

👉 In the notebook I've provided detailed codes and concepts. If you like it please give a star ⭐️

❗If you are trying it in **google colab** you have to upload the dataset [dibetes.csv]

🧑🏻‍💻 My Profile:

> * [🔗LinkedIn ](https://www.linkedin.com/in/soumyadip-bhattacharjya-993974234/)

> * [🔗 Kaggle](https://www.kaggle.com/soumyadipbhat)