Libraries: Pandas, Numpy, Seaborn, Matplotlib, nltk, sklearn
Using tutorials built a Naive Bayes classifier to predict sentiment from thousands of Twitter tweets.
Learnt data cleaning and manipulation to turn raw data tweets and extract useful key words and phrases Used matplotlib for data visualization (ie. histogram of total length of tweets, number of negative / positive reviews)
Applied Learnings from past project to scrape and analyze customer review data in (reviews.py) to gain insights on a company's brand image and customer experiences from ReviewPilot
Visualized Key words into a wordcloud