Data Science Portfolio Spreadsheets I've Known and Loved

Gauging Debate

Elections! Tweets! Sentiment!

Methods
Tech
NLP
Spark
Sentiment Analysis
Kafka
AWS
Flask
Plot.ly
Streaming Data

SEE:Net

MIT's Social Evolution Experiment

Methods
Tech
Network Graphs
Python
Correlation
Flask
UX/UI
D3
Sensor Data

HelloMarc.us

Robot Predicts Hollywood Box Office

Methods
Tech
LDA
Python
MCMC
Flask
Ridge Regression
D3

Chicago's Lead Problem

Data Science for Public Health

Methods
Tech
Spectral Clustering
R
GAM
Python
Geospatial Analysis
Shiny
Random Forests

Lead Inspection App

Helping City Health Officials

Methods
Tech
Time Series
D3
Geotagging
AJAX
PHP
PostgreSQL
Sensor Data

March Madness Magic

Predicting the NCAA Tournament

Methods
Tech
GLM
R
Boosting
gbm package
Neural Nets
nnet package
Ensemble methods

Innovation Mining

Experimentally-Induced Creativity

Methods
Tech
Network Analysis
R
Text Mining
tm package
LASSO
glmnet package
Permutation Testing
Qualtrics

Red Team vs Blue Team

US Senate Network Analysis

Methods
Tech
Network Graphs
Python
Spanning Trees
NetworkX
Matplotlib

In Search Of Delicious

Collaborative Filtering With Yelp Data

Methods
Tech
KNN
Python
Matrix Factorization
MRJob
Gibbs Sampling
AWS

Research Portfolio Data Science Meets Science Science

Depression/Instagram

Blue Selfie, Sad Selfie?

Methods
Tech
Bayesian GLM
Python
Sentiment Analysis
SQLite3
Random Forests
R
Face Detection
Qualtrics
Image analysis
mTurk

Twitter & Mental Health

Screening Mental Health With Tweets

Methods
Tech
HMM
Python
Random Forests
SQLite3
Sentiment Analysis
Qualtrics
mTurk

Diabetes Time Warp

Altered Time Affects Blood Sugar

Methods
Tech
ANOVA
Javascript
Regression
R