ajupton

big-data-engineering-project

Big Data Engineering practice project, including ETL with Airflow and Spark using AWS S3 and EMR

PySpark_guides

Reference and learning notebooks on the use of Spark for ML and analytical applications

archy-multilayer-nets

Mutlilayer Social Networks Created from Archaeological Data

Archytransmission

Files based on Eerkens and Bettinger (2008) statistical model for assessing cultural transmission from continuous archaeological data

LA_ICP_MS-Routines_FMNH

Routines to read and analyze LA-ICP-MS data from the Field Museum's Elemental Analysis Facility

Ceramic_Dashboard

Dashboard showing ceramic EDA and interaction network construction in the Late Prehistoric CIRV

Chicago_rideshare_at_scale

Forecasting rideshare demand in Chicago with AWS EMR and Pyspark

COVID-19

Visualizing and modeling the potential impacts of COVID-19

cRaggy_2018_submission

Submission to the Cascadia R Conf cRaggy

hike.pnw

Personalized PNW hiking trail recommendations

Data_Science_Challenge_Notebooks

Jupyter notebooks working through various data science challenges

deep-learning-practice

Repo showing practice deep learning applications/projects

deequ

Deequ is a library built on top of Apache Spark for defining "unit tests for data", which measure data quality in large datasets.

ER_sim

Network simulation function based on Erdős–Rényi model

pandas-profiling

Create HTML profiling reports from pandas DataFrame objects

Practice_Notebooks

Practicing Data Science Concepts in R and Python

Risk-Modeling-and-Fraud-Detection

Collection of resources for cutting edge approaches to risk modeling and fraud detection

websiteblogcode

Code for blogs @ andyupton.net

WIBD-Workshops-2018