A framework for prototyping and benchmarking imputation methods

Simple and automatic data cleaning in one line of code! It performs one-hot encoding, date & time casting to datetime dtype, detects binary columns, safely convert non-numeric columns to numeric dtypes, cleaning dirty/empty values, normalizing values and removing unwanted columns all in one line of code. Get your data ready for model training an…

NLPiper is a package that agglomerates different NLP tools and applies their transformations in the target document.

A Python Library for the Generation of Artificial Missing Data

A clean and modular pipeline for preprocessing the Food-101 dataset using both folder-based and CSV-based workflows.

All the scripts to prepare the Courtois-Neuromod dataset

Scripts for pre-processing eye-tracker data from pupil cloud

Audio Pattern Recognition project - Music Genres Classification

Explore your favorite anime with this interactive search app! 🚀 This project leverages Weaviate for vector search and Gradio for a seamless user interface. Using embeddings from a custom anime dataset, you can perform quick and accurate similarity searches for anime titles

animal-behavior-preprocessing is a Python repository to preprocess animal behavior data. It works on the output spreadsheets from video-tracking of animal body parts with LEAP or DeepLabCut. It applies a Median Filter, an Ensemble Kalman Filter, transforms data to joint angles and computes their Morlet Wavelet Spectra.

Python toolkit for preprocessing data for the City Controller's Gun Violence Dashboard

A library that provides template code for Python development to shorten the project development cycle.

Functionality to preprocess and analyse multi-omics data

This project uses the S.Y. 2020-2021 DepEd Schools Masterlist that contains 64,000+ school information across the Philippines, including location, sectors, and classification details.

An AI-powered resume and job description matching application using natural language processing and machine learning techniques. This application provides intelligent analysis of resume-job compatibility with detailed scoring and recommendations.

MNIST is a Dataset for images of handwritten digits Classification with KNN by extracting features using centroid

BigKinds Data Analysis Toolkit for python

this was a academic project that showcase my pre&post ML model knowledge such as, data collection, data preprocessing, AI model training( ML) and finetune the model

PickMyModel is an end to end AutoML and meta-learning system that automatically analyzes user-uploaded datasets, recommends suitable models based on learned patterns from previous datasets. The system extracts rich statistical meta features, applies reusable preprocessing pipelines and trains and evaluates multiple models.