Expertise in R, Python, Tableau, Matlab, SQL, SAS
Completed the following DATA SCIENCE projects:
Breast Cancer Diagnostics, Saint Peter’s University Feb’ 18
Employed Linear Discriminant Analysis, Logistic Regression and K-Nearest Neighbors algorithm in R (w/o using inbuilt functions for LDA, glm, and knn) to classify malignant vs benign breast tumors. Anomalies in the data were cleaned and then the dataset was reduced to significant dimensions which helped in predicting the correct diagnostics.
Expectation Maximization Algorithm for Gaussian Mixture Model Saint Peter’s University Feb’ 18
Hardcoded EM Algorithm for GMM in python to find the correct number of clusters and cluster membership for each observation in the dataset.
GISS Surface Temperature Analysis (GISTEMP), Saint Peter’s University Feb’ 18
Utilized NASA’s dataset for Surface Temperature Change to build a data visualization in Jupyter Notebook using Pandas and Plotly to show a time series mapping of temperature increase over past two centuries. Also presented a real time GIS mapping of temperature changes overtime to show how those factors change via different regions.
Crime Analysis in New York, Saint Peter’s University Dec’ 17
Presented a project using Data Visualization and Machine Learning on Crime Analysis in New York using python and Tableau. The project predicted an accuracy of 89% that a particular crime is likely to occur at a particular time at a particular location in New York.