All posts

Evaluating impact of interventions

Protect yourself from costly bandits

Deep learning in R

Keras, the LEGO of deep learning

Classification of spreadsheets

Helping a machine to make sense of tabular data

t-Distributed Stochastic Neighbor Embedding

Visualising high-dimensional datasets

Principal Component Analysis

Summarising data using fewer features

Mastering Bayes

Are you Frequently A / B testing?

Agent Based Modelling

The game of life

Deploying a model

How to show off your random forest

Shiny interactive map app development

The dangers of cherry picking evidence

It's if_else statements all the way down...

How to tidy up multiple if and else if statements

Dealing with dates

Easy date aggregations

Monster Hunting with XGBoost

The prize winning, scalable, portable and distributed Gradient Boosting algorithm

Newyearal Networks

Back to basics with Artificial Neural Networks

Genetic programming in space

A supervised learning method motivated by an analogy to biological evolution

Test Driven Development

Letting testthat do the heavy lifting

Sold!

Advanced Regression techniques for predicting house prices

Sparking your interest in a dry subject

Using Spark and R for regression of concrete strength

The Fast and the Furiously Frugal

Quick and easy classification

Regime Switching Model

Forecasting regime changes in market turbulence

A pipe dream

Complex decisions made simple

Phat Maps

Mapping obesity in the UK

Discrete Time Markov Chains

My data science journey is a Markov Chain

map_df()

Combining objects as data_frames in purrr

Nearest neighbour methods

A simple non-linear classifier using nearest-neighbour averaging

The Game of Kaggle

Predicting survival of passengers on the Titanic

Getting to grips with 'Elements of statistical learning'

Linear models and least squares

Predicting virtual hat sales in Dota 2

Working with time series data and basic forecasting

The magic of neural networks

Student attainment prediction with neural networks

The Hadley Effect

What happens when Hadley reads your blog

Iteratively applying models

Using dplyr, broom, and purrr to make life easy

Assessing classifier performance

Evaluating performance of supervised learning tools

Support vector machines for forest fire prediction

Predicting forest fire scale using support vector machines

Logistic regression for student performance prediction

Predicting student end of year performance using logistic regression

Lookup tables

Using character matching for quick lookups

Student performance in Portugal

Predicting student performance using CART

Measuring light with a Raspberry Pi

A year's data collected with a simple LDR based light sensor

Raspberry Pi MQTT broker

Setting up minibian

IoT with the ESP8266

A low cost Wi-Fi serial module

Sensing temperature with a Raspberry Pi

A year of measurements

Measuring obsession

Home monitoring with Raspberry Pis

Unsupervised learning with K-means

A simple implementation

Reproducible journal articles

Writing papers for peer review with knitr

Visualising FAO data

Making bubble maps in R

Growing up

Using classes in R

Elastic-net regularisation

Using R package glmnet for regularisation

SylvaSense Part II

Adding temperature monitoring to the equation

SylvaSense Part I

Using an arduino for environmental sensing

Regularised linear regression

Adding regularisation to vectorised linear regression

Too hot to cycle?

Do Londoners and New Yorkers disagree?

Writing a PhD thesis in LaTeX and R

Some lessons learned the hard way

Handwriting recognition with logistic regression

Simple multiclass classification

Non-linear classification with logistic regression

Implementing regularisation and feature mapping

Implementing vectorised logistic regression

Comparing vectorised methods with general linear models

Multivariate linear regression

Feature scaling and gradient descent

Linear regression with gradient descent

Linear regression the machine learning way

Gradient descent in R

Implementing gradient decsent in R

Finding the right blogging platform

Blogger, WordPress, Jekyll?

LondonR 2014 - ggvis

ggvis workshop at LondonR by Aimee Gott

Do women take the scenic route or do men cycle faster?

Using the Google routing API via ggmap

Is CitiBike an old boy's club?

Gender differences in the New York cycle hire data