natc79 Goto Github PK

airplaneaccidents

Analysis of data on airplane accidents in the US

bikerentalpredictions

Identifying the best model for predicting bike rentals in DC 2011-2012.

boardgamereviews

Analysis of data from BoardGameGeeks

corporacionfavorita

Forecasting Corporacion Favorita product sales. Exploratory forecasting of sales for ~4000 products across 54 grocery stores.

educationalachievement

Analysis on Civil Rights Data on Educational Achievement and Opportunities (2013-2014)

egyptjobdata

Scraping and analysis of Egypt Job websites to gather information on labor market demands.

flowerimageclassifier

Pytorch flower image classifier. Final project for Udacity's Pytorch Challenge Scholarship.

gendergaps-collegegraduates

Gender statistics on college graduates 1970-2012

hackernewsdata

Article popularity on Hacker News 2006-2015

highvaluemerchants

Examines various models for predicting high value merchants using transaction data from an online payments platform.

intldevengagement

Facebook data is used to examine post content of organizations and factors that affect follower engagement.

jeopardystrategies

Examine strategies for winning on Jeopardy by parsing question, answer and associated value amounts.

lendingclubloans

Compressing Lending Club data from 2007-2011

menajobdata

Scrape and process job data from selected MENA countries.

moviereviews

Movie reviews from 4 different movie review services through 2015.

natc79.github.io

nyc-highschools

Determining the best performing NYC high schools (2012)

parlai

A framework for training and evaluating AI models on a variety of openly available dialog datasets.

pubmed

Download and process documents from PubMed

recentcollegegrads

Analyzes data on recent college graduates from 2012-2014.

startupfunding

Optimizing storage and analysis of data from Crunchbase (through 2013).

starwarsfans

Analysis of online survey data of Star Wars Fans run in 2014

stockmarketpredictions

Time series data on the S&P 500 used to predict future S&P 500 prices.

stockprices

Analyzing daily stock price data over 2007-2017 using hash, arrays and lists.

thanksgivingdinner-stats

Thanksgiving dinner statistics from an online survey run in 2015.

us-births

Statistics on US births from 2004-2014

us-deaths

Explores data on US gun deaths from 2012-2014.

wikipages

Scrape html Wiki Pages and optimize speed of processing using thread and process pools.

worldfactbook

Analysis of CIA sponsored data on population, land area etc. over time.

zillowhousing

Initial data compression and analysis on Zillow Housing Data from Kaggle 2017 competition.