Eric Blander
Data Science | Data Engineering | Python Development
Twitter Sentiment Analysis: #Masks
- Scraped and cleaned 150 million tweets containing the word ‘mask’ over COVID-19
- Implemented natural language processing (NLP) models to analyze sentiment
- Cleaned and combined 18 datasets into one set of 50 million information packets
- Implemented KNN, Random Forest, and XGBoost models to detect malicious activity
Regression Analysis of Housing Prices
- Created features based on limited information about houses in King’s County
- Implemented linear and logistic regression models to accurately predict prices
- Exploratory data analysis of half a billion leaked passwords
- Used statistical analysis to systematically determine features of weak passwords
