mavillan

py-hausdorff

Fast computation of Hausdorff distance in Python

tsforest

Time series forecasting with tree ensembles

m5-forecasting-accuracy

Solution to Kaggle's M5 Forecasting Accuracy Competition

mahts

Model Agnostic Hierarchical Time Series in Python

walmart-data-science-test-2018

Desafío para postulantes a prácticas de data science en Walmart Chile 2018

yolanda

Codebase for MeLi 2021 data challenge

ACNM

Advanced Computational Numerical Methods course at UTFSM

jane-street-market-prediction

Solution to Kaggle's M5 Jane street market prediction

mavillan.github.io.old

amex-default-prediction

Codebase for Kaggle's AMEX default prediction competition

ashrae

Codebase for Kaggle's ASHRAE Great Energy Predictor 2019 competition

condor_tensorflow

CONditionals for Ordinal Regression and classification in tensorflow

docker-airflow

Docker Apache Airflow

ds-competition-template

Template repo for data science competitions

gb-vpp

Solution to Kaggle's google brain - ventilator pressure prediction challenge

google_quest_challenge

Codebase for Kaggle competition: Google Quest QA labeling

HDMClouds

A Hierarchical Decomposition of Molecular Clouds

icr-identify-age-related-conditions

Codebase for Kaggle's ICR - Identifying Age-Related Conditions

indoor-location-navigation

Codebase for Kaggle's indoor location navigation competition

LightGBM

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

lofo-importance

Leave One Feature Out Importance

master-thesis-utfsm

mavillan

mavillan.github.io

My personal blog

multiverse

Dockerfile for building an Ubuntu 16.04 image with the full stack of Python data science packages

nonconformist

Python implementation of the conformal prediction framework.

optuna

A hyperparameter optimization framework

prophet

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

pytorch-axe

Minimalist interfaces to train pytorch models with less boilerplate code

ubiquant-market-prediction

Codebase for Kaggle's ubiquant market prediction competition