ffineis

Cover_letter_classification

Classify the efficacy of certain cover letters with Multinomial Naive Bayes

health_weather

Kinsa Health Weather Map data scraper

ncaa_quarterbacks

A web scraping project to track NCAA football players and to determine if the position of quarterback is equitably distributed by race.

nurcs-singularity

Singularity documentation and build files for Northwestern University's Research Computing Services and the Quest HPC

AlwaysSunnyDataset

Dataset of It's Always Sunny In Philadelphia

Azure-Databricks-Dev-Ops

Complete end to end sample of doing DevOps with Azure Databricks

dask-lightgbm

databases_workshop

RCS Intro to Databases workshop materials

deepbind-docker

Docker image for the DeepBind method.

Energyrisk_GIT

fbboost

R package providing Xgboost tree-ensemble embedding capabilities along with functions altering the traditional Xgboost/caret training API that provides more simple grid-searching capabilities.

FBEraser

Programatically delete your Facebook posts

ffineis.github.io

Typical blog of a loudmouthed data scientist

git-intro

Git/Github Intro

Greeble_image_learning

Use a labeled set of Greebles as an alternative tutorial dataset for image classification methods

Healthcare_Prediction

Prediction of healthcare coverage from analysis of 2009-2011 American Community Survey data

HLMr

Low key replace HLM software with shiny app whaaaaat

HPCExampleAssignment

Hi-Perm Computing Example Assignment 1

ieee-cis-fraud-detection

IEEE-CIS Fraud Detection Kaggle competition code, illustration of massive Sklearn Pipelines

imbalanced_classifier_app

Streamlit app to visualize the effect of imbalanced class data on binary classifier models.

intro_Socrata

Various scripts for analyzing data hosted by Socrata

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.

NATS

Neural Abstractive Text Summarization with Sequence-to-Sequence Models

photo_kaggle

Attempt at old Kaggle competition: https://www.kaggle.com/c/PhotoQualityPrediction/

scdlintrend

Repo for Effect Sizes in SCD Studies with Trend analysis

scikit-learn

scikit-learn: machine learning in Python

Smisc

Sego Miscellaneous: A collection of functions for statistical computing and data manipulation in R

stat_350_final

Final Project for NU STAT 350 Winter 2018

SuperSight

SuperSight is a static dashboard generator made for Matplotlib plots. It uses Jinja2, Bootstrap 4, MathJax and Gutenberg CSS !

sam-twilio-sms-to-sqs

SAM application for 2-way SMS messaging using the Twilio python SDK