This repository contains beginner-to-intermediate level machine learning projects implemented in Python using Jupyter Notebooks. Each project demonstrates a core ML concept, using real-world or well-known datasets.
https://github.com/chirayu08/ML-basic-codes
Implements a basic feedforward neural network from scratch with manual backpropagation. No libraries like TensorFlow or PyTorch are used — ideal for learning core neural net mechanics.
📁 Artificial Neural Network using Back propagation algorithm.ipynb
Builds a decision tree using the ID3 algorithm and information gain to classify whether to play based on weather features. Implemented from scratch.
📁 ID3 algorithm-weather-dataset.ipynb
Applies linear regression on the IRIS dataset to predict flower measurements. Includes MSE evaluation and model interpretation.
📁 Linear regression on IRIS dataset.ipynb
Trains a logistic regression model on the scikit-learn digits dataset to recognize handwritten digits (0–9). Includes data visualization and performance metrics.
📁 Logistic Regression for digit recognition.ipynb
Uses a Random Forest classifier to predict survival outcomes on the Titanic dataset. Includes preprocessing, model training, and feature importance plotting.
📁 Random Forest Titanic dataset.ipynb
Implements multi-class classification using Support Vector Machines (SVMs). Explores one-vs-rest or one-vs-one strategies.
📁 SVM Multiclass classification.ipynb
Applies SVM with RBF kernel to classify digits using the scikit-learn digits dataset. Includes classification report and digit visualization.
📁 Support Vector Machine for digit recognition.ipynb
Implements a Gaussian Naive Bayes classifier on numeric data. Evaluates using accuracy score and confusion matrix.
📁 naïve Bayesian Classifier .ipynb
Performs K-Means clustering, likely on the Iris dataset. Demonstrates unsupervised learning with centroid visualization and optional label comparison.
📁 one clustering algorithm.ipynb