Visit SSDS at: https://ssds.stanford.edu/
I am an instructor, researcher, and data scientist with 15 years’ experience across learning design and pedagogy, instruction, cross-functional collaboration for data science projects, project management, consultation, and mentorship. At Stanford, I lead a team that upskills and reskills students, faculty, and staff in group and personal settings (online and offline) to help them be successful in their computational research projects through workshops, consultations, specialized trainings, curriculum development, mentoring, and coaching using a variety of pedagogical and methodological resources that emphasize critical thinking and data skills.
Additionally, I cultivate successful cross-functional collaborations across campus as well as with external stakeholders to leverage data science and artificial intelligence to optimize workflows and processes for research teams. My personal research interests span machine learning applications to bioarchaeology and international conflict, teaching pedagogy, deep learning, and computational text analysis/natural language processing.
Currently working on:
- Ecological effects of chlorinated water, disease, and conflict in Northwest Syria
- Health, agriculture, and armed conflict in Syria and Yemen
- How to use administrative data to better understand student, faculty, and staff data science needs
- Machine learning to better understand perioperative depression
- Postoperative complications in young female diabetics
I can help with:
- R/RStudio/Tidyverse, Python/Jupyter Notebooks, Bash, Git/GitHub, SQLite, Microsoft Excel, Qualtrics, Google Suite
- Data preparation: text, image, quantitative, machine/deep learning, data imputation
- Data visualization: ggplot2, geospatial mapping, matplotlib, seaborn, plotly, altair, geopandas, gnuplot
- Machine learning: caret, SuperLearner, H2O, scikit-learn, tensorflow, pytorch, keras, regression (lm, glm, penalized, step, spline, hinge), classification, tree-based methods, confusion matrix derivations, cross-validation
- Deep learning: quantitative, text, image, MLP, GAN, RNN, CNN, LSTM, transfer learning
- Text: mining, classification, word embeddings, topic modeling (assisted/anchored/weighted/neural), sentiment analysis, semantic structure/analysis
- Unsupervised methods/dimension reduction: PCA, MCA, CCA, tSNE, UMAP, clustering
- API access, social network data, webscraping
- Categorical data analysis
- Time series, forecasting
- Survey design and analysis
- Bloomberg Terminal
- PhD, Anthropology, Southern Illinois University Carbondale
- MA, Anthropology, Wichita State University
- BS, Anthropology, Michigan State University
Weng A and Muzzall E. 2022. Working with messy time series data in Python Jupyter Book. https://roflauren-roflauren.github.io/GearUp-MessyData/intro.html
Muzzall E and Weng A. 2022. Text Analysis and Machine Learning Jupyter Book. https://eastbayev.github.io/SSDS-TAML/intro.html.
Muzzall E. 2017. Ensemble machine learning for sex prediction of a worldwide craniometric dataset. https://github.com/EastBayEv/Ensemble-machine-learning-for-sex-prediction-of-a-worldwide-craniometric-dataset.