👨💻 This repository contains code for evaluating various machine learning models for binary classification.
🔍 Features used for the models are selected through the Feature Importance method using Random Forest.
The dataset is loaded from "FMat.pkl", and features are extracted for training and testing.
Categorical data is encoded using LabelEncoder, and features are normalized.
The dataset is split into training and testing sets (80% training, 20% testing) with a random seed of 42.
The following models are evaluated:
- K-Nearest Neighbors (KNN)
- Logistic Regression
- Naive Bayes
- Decision Tree
- Random Forest
- LightGBM
- XGBoost
Model performance is assessed using:
- F1-score
- Area Under the Curve (AUC)
Results for each model are displayed, including F1-score and AUC. 🚀
Use this code to evaluate the performance of various machine learning models for binary classification tasks. Explore and modify the code for your datasets and model evaluations. 📚
For more details, refer to the code comments and documentation. Feel free to adapt and improve it for your specific needs. 😊