Skip to content

Abineshabee/Machine-Learning-Models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation


Machine Learning Models – Training Repository

This repository contains a collection of machine learning projects and experiments developed for learning and practicing machine learning algorithms.

The goal of this repository is to explore different datasets and implement classification and prediction models using Python and Jupyter Notebook.

Each project focuses on a different real-world dataset and demonstrates the workflow of

  • Data loading
  • Data preprocessing
  • Feature analysis
  • Model training
  • Model evaluation

This repository serves as a personal learning archive while studying machine learning concepts and model-building techniques.


Repository Structure

Machine-Learning-Models
│
├── DDoS_Attack
│   ├── DDos_Attack.ipynb
│   └── realtime_ddos_traffic_dataset.csv
│
├── SPAM_url
│   ├── spamURL.ipynb
│   └── url_spam_classification.csv
│
├── australia
│   ├── AUS_Rain.ipynb
│   └── weatherAUS.csv
│
├── diabetes
│   ├── diabetes.ipynb
│   └── diabetes.csv
│
├── sonar
│   ├── RM.ipynb
│   └── sonar_data.csv
│
├── vehicle
│   ├── Emission.ipynb
│   └── vehicle_emission_dataset.csv
│
└── README.md

Project Descriptions

1. DDoS Attack Detection

This project focuses on detecting Distributed Denial of Service (DDoS) attacks using machine learning.

Dataset

realtime_ddos_traffic_dataset.csv

The dataset contains network traffic features used to identify malicious traffic patterns.

Notebook

DDos_Attack.ipynb

The notebook demonstrates:

  • Network traffic analysis
  • Feature preprocessing
  • Machine learning model training
  • Detection of malicious traffic

Applications

  • Network intrusion detection
  • Cybersecurity monitoring
  • Real-time attack prevention

2. URL Spam Detection

This project detects whether a URL is spam or legitimate.

Dataset

url_spam_classification.csv

Contains features extracted from URLs such as:

  • Length of URL
  • Presence of suspicious characters
  • Domain features

Notebook

spamURL.ipynb

The notebook includes:

  • Feature extraction from URLs
  • Classification model training
  • Spam detection evaluation

Applications

  • Email filtering
  • Phishing detection
  • Website security

3. Australia Rain Prediction

This project predicts rainfall in Australia based on historical weather data.

Dataset

weatherAUS.csv

Contains meteorological data such as:

  • Temperature
  • Humidity
  • Wind speed
  • Rainfall records

Notebook

AUS_Rain.ipynb

The notebook demonstrates:

  • Weather data preprocessing
  • Feature engineering
  • Rain prediction model training

Applications

  • Weather forecasting
  • Agricultural planning
  • Climate analysis

4. Diabetes Prediction

This project predicts whether a patient is likely to have diabetes based on medical attributes.

Dataset

diabetes.csv

The dataset includes medical parameters such as:

  • Glucose level
  • Blood pressure
  • Insulin
  • BMI
  • Age

Notebook

diabetes.ipynb

The notebook includes:

  • Medical data preprocessing
  • Feature analysis
  • Binary classification model training

Applications

  • Healthcare diagnostics
  • Medical decision support
  • Preventive health analysis

5. Sonar Object Detection

This project predicts whether an object detected by sonar is a mine or a rock.

Dataset

sonar_data.csv

The dataset consists of sonar signal returns from different objects.

Notebook

RM.ipynb

The notebook demonstrates:

  • Signal feature analysis
  • Classification of sonar signals
  • Model evaluation

Applications

  • Naval defense systems
  • Underwater object detection
  • Marine robotics

6. Vehicle Emission Prediction

This project predicts vehicle emission levels based on engine and vehicle parameters.

Dataset

vehicle_emission_dataset.csv

The dataset contains information such as:

  • Engine size
  • Fuel type
  • Vehicle weight
  • Fuel consumption

Notebook

Emission.ipynb

The notebook demonstrates:

  • Environmental data analysis
  • Emission prediction models
  • Performance evaluation

Applications

  • Environmental monitoring
  • Vehicle regulation compliance
  • Emission control research

Machine Learning Workflow Used

Across the projects, a common ML workflow is followed:

Dataset Collection
       ↓
Data Cleaning
       ↓
Feature Selection
       ↓
Model Training
       ↓
Model Evaluation
       ↓
Prediction

Algorithms Explored

During experimentation, several machine learning algorithms may be used such as:

  • Logistic Regression
  • Decision Trees
  • Random Forest
  • K-Nearest Neighbors
  • Support Vector Machines
  • Naive Bayes

These algorithms are tested to understand their performance across different datasets.


Technologies Used

Technology Purpose
Python Programming language
Jupyter Notebook Experiment environment
Pandas Data manipulation
NumPy Numerical computation
Scikit-learn Machine learning models
Matplotlib Data visualization
Seaborn Statistical visualization

Learning Goals

This repository was created as part of a machine learning learning journey to understand:

  • Data preprocessing techniques
  • Feature engineering
  • Classification algorithms
  • Model evaluation metrics
  • Real-world datasets

It acts as a practice environment for building and testing machine learning models.


Future Improvements

Planned improvements include:

  • Adding deep learning models
  • Model deployment using Flask or FastAPI
  • Hyperparameter tuning
  • Performance benchmarking
  • Adding more datasets
  • Building end-to-end ML pipelines

Author

Abinesh N

GitHub https://github.com/Abineshabee


Releases

No releases published

Packages

 
 
 

Contributors