confusion-matrix-analysis

A clear and interpretable baseline for predicting drug categories using patient features and a Decision Tree classifier. Designed to be interview-friendly, with emphasis on clarity, step-by-step decisions, and interpretability

the code uses KNN, Gaussian Naive Bayes & SVM to classify images. It preprocesses, normalizes data, applies PCA , computes accuracy, precision etc. It evaluates k-NN using Euclidean distance & cosine similarity, visualizing results with line plots, 3D scatter plots, & confusion matrices to demonstrate classifier performance.

This project analyzes app reviews using sentiment classification powered by DistilBERT. It employs machine learning and natural language processing (NLP) techniques to determine sentiment as positive, neutral, or negative. The analysis provides valuable insights into user feedback for app improvement.

This is a production-ready, end-to-end system developed to detect and classify racist tweets using advanced Natural Language Processing (NLP) techniques. Built on top of BERTweet (vinai/bertweet-base) and fine-tuned with a robust, k-fold cross-validation training pipeline, powered by streamlit UI!

Rust-based CNN for garbage classification into 6 categories with high accuracy on GPU.

Binary and multiclass classification on workplace service requests. Logistic regression, decision tree and random forest in Scikit-learn pipelines with decision threshold tuning to manage false-positive vs false-negative trade-off for SLA breach prediction

This project implements the classical LeNet-5 CNN for MNIST digit classification using PyTorch. It covers a complete pipeline from data preprocessing to deployment. The model achieves ~98.8% test accuracy, showing the strong effectiveness of early CNN architectures for image classification.