Kristin Mussar's repositories
ICU_predictions
Predicting the length of stay in the ICU using the MIMIC-III database
covid19_datathon
Group project in association with MIT's COVID-19 Datathon
Udemy_Data_Science_Exercises
Worksheets from the Python for Data Science and Machine Learning Bootcamp course from Udemy
AI_for_Medicine
Notebooks used in AI for Medicine Specialization courses
bioinformatics_specialization
Files in association with the Genomic Data Science Specialization from Johns Hopkins
TwitterFlu
Separating Semantic Meaning in Health-Related Tweets
Whale_Call_Detection
Classify audio files as either North Atlantic Right Whales or not
American_Time_Use_Survey
Analysis of the American Time Use Survey from the Bureau of Labor Statistics
Breast_Cancer_Prediction
Wisconsin Diagnostic Dataset from Scikit learn
chocolate_ratings
Analyze a database of different varieties of dark chocolate, their origins, and their ratings to determine what makes a great chocolate.
Ecommerce_data_linear_regression
practice exercise_ analysis of ecommerce data to inform business strategy
Iris_flower_classification
classification of flowers into 3 species using petal and sepal measurements
kmussar.github.io
my blog
KNN_excercise
Analysis of artificially generated data
Lending_Club_Predictions
Predict if people will default on their loans
mimic-code
MIMIC Code Repository: Code shared by the research community for the MIMIC-III database
Modeling_Ad_Clicks
Created an accurate model to predict whether or not a user will click on an ad from this company based on their demographics, the time of day, and day of week
NYC_Metro_Marketing_Optimization
Project to optimize MTA station marketing
R_intro
four week intro to R: basic syntax, data manipulation, data viz
scanpy-tutorials
Scanpy Tutorials.
SQL_practice-1
A collection of SQL practice problems for interviews
style_sheet
A basic style sheet example
Superhero_Storyline_Generator
This project scrapes the storylines of Marvel movies from IMDB, feeds them to a Markov Chain, and generates potential new plot lines based on the previous movie synopses. See the "expanded-functionality" branch for an additional feature.
ThinkStats2
Text and supporting code for Think Stats, 2nd Edition
titanic_kaggle
First machine learning project with Kaggle - predicting the likelihood of passengers to survive the titanic sinking