Santiago Humberto Londoño Restrepo's repositories
CheckPronunciationFlask
Check Pronunciation is a tool that allow to evaluate pronunciation in Spanish Language
UnitsTimePandasSeries
Python class that transforms a daily pandas series into pandas series with aggregated values depending on different units of time [weekly, monthly and yearly]
catboost
CatBoost is an open-source gradient boosting on decision trees library with categorical features support out of the box for Python, R
Cognitive-Speech-TTS
Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
datathon
Solución al desafio educativo propuesto por Datathon-2017.
ElectricityMarket-DataCamp
Code created to solve challenge sponsored by DataCamp, called: Understanding the Local Electricity Market
Final-Project---Practical-Machine-Learning---Data-Science-Specialization-by-Johns-Hopkins-University
Solution to Course Project for Practical Machine Learning Course
Gender-gap-in-entrepreneurship
Gender gap in entrepreneurship is a web application for those interested in analyzing Global Entrepreneurship Monitor (GEM) data from a gender perspective.
CompanyTests
Company tests that I have done to get a job
datasciencectacontent
repository for Community Mentor content related to the Johns Hopkins University Data Science Specialization on Coursera
docker-getting-started
Getting started with Docker
lisa
Lisa: a spanish chatbot based on Deep Q&A, the implementation of "A neural conversational model"
londoso.com
My personal website
machine-learning-course
R code for the assignments of Coursera machine learning course
myfirstmapLeaflet
Solution to the task of week 2 of the course Developing Data Products of the Johns Hopkins University offered through COURSERA.
papershiny
Repositorio para el artículo
PasosCrearRepo
Se describe el paso a paso y comandos git que uso frecuentemente para crear repositorios en sistemas de control de versiones.
Pyutilities
Repositorio con pruebas de concepto sobre uso de librerías en el mundo python
Robyn
Robyn is an experimental, automated and open-sourced Marketing Mix Modeling (MMM) package from Facebook Marketing Science. It uses various machine learning techniques (Ridge regression, multi-objective evolutionary algorithm for hyperparameter optimisation, gradient-based optimisation for budget allocation etc.) to define media channel efficiency and effectivity, explore adstock rates and saturation curves. It's built for granular datasets with many independent variables and therefore especially suitable for digital and direct response advertisers with rich dataset.
Rutilities
Repositorio con pruebas de concepto sobre uso de librerías en el mundo R
supervised-basico-admission-exams
Reto Colmbi-ia basico
Testhff
To do post request in flask app deployed in heroku