Language Breakdown
Lines of code distribution across 15 owned repositories
I-Shaped Developer
I-shapedSpecialist — deep expertise in Jupyter Notebook
Collaboration Network
Global Impact visualization
Repos
15
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Top Repositories
This project analyzes a telecom dataset to predict customer churn using multiple machine learning models. It includes data preprocessing, feature engineering, exploratory data analysis, and model comparison using metrics like recall, F1-score, and ROC-AUC.
2-layer neural network built from scratch using only NumPy. Implements forward pass, backpropagation, and gradient descent manually — no PyTorch or TensorFlow
Multi-class crop irrigation need classifier (Low / Medium / High) using LightGBM with target-encoded categorical interactions and soil-type feature crosses.
Batch, Stochastic, and Mini-batch Gradient Descent built from scratch in NumPy validated against sklearn.
Rain prediction on 145K Australian weather records using SVM with RBF kernel, SMOTE, and feature engineering. 82.8% accuracy.
Built an end-to-end machine learning pipeline for the Spaceship Titanic Kaggle competition, including data preprocessing, feature engineering, and model training using Logistic Regression, Decision Trees, Random Forest, and XGBoost, achieving ~81% accuracy and a Kaggle score of ~0.796.
Open Source Impact
Contributions to external projects
No external contributions found.