R

• The World Bank - Global Database on Intergenerational Mobility (GDIM) - [R]
  • Techniques used: Clustering, choropleth visulaization, OLS
• Retail Data Set II Online from Dr. Daqing Chen, School of Engineering, London South Bank University - [R]
  • Techniques used: RFM analysis, heat map, segmentation, clustering, retention and lifetime value analysis

Python (from Coursera certifications)

• Introduction to Data Science Python
  • Simple regex
  • Simple data cleaning and analysis
  • Data analysis of renewable energy indicators
  • Correlation (pearsonr) of win/loss rate with population from the MLB, NBA, and NHL
• Data Representation
  • Visualization of record-breaking high and low temperatures in Ann Arbor on 2015 (year range 2005-2014)
• Applied Machine Learning
  • Training KNN classifier on breast cancer dataset from sklearn
  • Training decision tree, SVC, linear, and Lasso classifiers on the UCI Mushroom dataset
    [Link to dataset]
  • Training dummy and SVC classifiers on fraud data
  • Training random forest classifier to predict blight ticket violations
• Applied Text Mining
  • Cleaning and sorting datetimes
  • Text parsing, lemmatization, and spell-checking of Moby Dick
  • Machine learning using logistic regression and count vectorizer to predict spam messages
  • Machine learning to compare similarities between documents and assigning them the correct topics
• Applied Social Networks
  • Creating and manipulating graphs
  • Network Connectivity
  • Centrality of nodes, Scaled Page Rank algorithm, and HITS algorithm
  • Machine learning using logistic regression for predicting future connections between employees of a network (AUC score: 0.935)