I am David Raymond Kearney, political economist by training, data scientist by profession.
As a data scientist, I create automated member and provider engagement campaigns that leverage e-mail, IVR, SMS and live calls to increase medication adherence.
I also design experiments and employ randomized control trials to improve campaigns by identifying the most effective campaign variants, and productionlize machine learning models to identify members at risk of behaving in a way that contributes to poor health outcomes and most likely to benefit from campaigns.
I got my Ph.D. at Duke University, where my research focused on applying econometric and statistical techniques to explain and predict the allocation of fiscal transfers.
This site, will cover spark, h2o. hive and data science using python.
Posts
Stock Market Analysis of Microsoft, Zoom, and Snowflake
Using the Quandl API and Pandas Datareader API to call Microsoft, Apple, Zoom, Snowflake stocks and other finance data
Evaluating Distributions and generating Experimental Crosstabs for the Evaluation of Experiments as well as Experimental Comparisons with T-Tests, Purpose Assumptions, Corrections and Implementations in Python
Evaluating Distributions and generating experimental Crosstabs for the evaluation of Experiments
Using Dask with dask.bag and regex to parse Notes from the Underground from project gutenberg
Friday links
Using Dask with dask.bag and regex to parse The Brothers Karamazov from project gutenberg
Linear Regression using Dask Data Frames
Using dask_ml.preprocessing and OneHotEncoder for categorical encoding with Dask
Moving Dask XGboost with Fiscal Data, saving and loading Dask XGboost models
Visualizing Operations with Dask Dataframes on Fiscal Data
Monday links
Moving Fiscal Data from a sqlite db to a dask dataframe
Working with dask data frames. Reading Fiscal Data from a sqlite db to a dask dataframe. Computing, visualizing and groupby with dask dataframes. Using dask.distributed locally.
Moving fiscal data from a pandas dataframe to a sqlite local database