Ben Cooper

Time Series Analysis of Covid-19 Data

The data collected since the start of the novel Covid-19 pandemic offers an excellent opportunity to apply time series forecasting in unique ways.

I began by accessing the John Hopkin's Covid-19 world-wide dataset. This dataset is publicaly available on the Johns Hopkin's website and is also updated almost daily on Kaggle.

Target Enrichment and Phylogenomic Analysis

Target Enrichment and Extensive Population Sampling Help Untangle the Recent, Rapid Radiation of Oenothera Sect. Calylophus

This project was originally started as my thesis project at Northwestern University and culminated in publication in the Journal of Systematic Biology. It is an example of a fully end-to-end project I managed. From field collection, to wet lab genomic library construction, to bioinformatics and dataviz; I carried out all aspects of the project.

Recommender System

In this project, I explore six recommendation systems using the 1 millions songs dataset: popularity-based, user-user collaborative filtering, item-item collaborative filtering, matrix factorization, cluster-based, and content-based.

First, I perform an exploratory data analysis of the 1 million songs dataset, and then train, test, and evaluate the different recommendation algorithms based on prediction accuracy, RMSE, MAE and F1 metrics. I then build and test a hybrid recommendation system based on the best models identified in part I, and apply a weighted joiner function to construct the hybrid recommendations.

Predicting Customer Satisfaction

This project uses classification and regression methods (Random Forest, XGBoost, XGBoostRegressor) to predict customer satisfaction of customers riding the Shinkansen Bullet Train in Japan. This project was part of my submission for the Great Learning Spring 2023 Hack Linguist Hackathon Competition.

The dataset contains 23 customer experience and train/trip attribute features and is pre split into a train and test set. With my solution, I was able to predict customer satisfaction in the test set with >95% accuracy.

Project Title

Content Coming Soon...

Project Title

Content Coming Soon...

Regression

Content Coming Soon...

Time Series

Content Coming Soon...

Classification

Content Coming Soon...

Recommendation Systems

Content Coming Soon...

NLP

Content Coming Soon...

Deep Learning

Content Coming Soon...

Data Management

I have performed data management in many roles, as an assistant data manager for a regional office in the Dept. of the Interior (NPS), as well as in end to end scientific research projects. My expertise in data management includes TSQL, Python, and R programming languages, and using tools and software such as SQL database engines (Enterprise SQL, MySQL, Postgres), No-SQL (MongoDB), and tabular datasets (Excel, .csv, etc.).

I have worked on projects developing and deploying enterprise and spatial SQL databases, developing queries, views, and stored procedures for SQL and no-SQL databases, performing ETL (extract, transform, load) from legacy databases to SQL, and performing verification and validation on data.

Data Science

Content Coming Soon...

Software Engineering

Software engineering has been a pivotal component of my data science journey and in many ways, my journey as a data scientist began with software engineering. Like many data scientists, much of the work I do leverages jupyter notebooks for EDA. However, my experience in software engineering means that I can not only interface with software engineers, but I also have the experience needed for building and deploying end to end data science pipelines.

My first software engineering project, and my first coding project in general, was a mobile ArcGIS app I built while working for the National Park Service. The app was built in Microsoft JavaScript and Visual Basic and ran on the old ArcPad environmental on Trimbles and other handheld windows-based GPS units. More recently in a software engineering course at the UMN, I worked with a three other students to build a PPALMS quiz generator for learning management systems (with UI) in Python.

Web Development

I am fairly new to web development, but enjoy the app development and visualization aspects of webpage development. I started out with wordpress sites and now use Django and Jekyll for my builds.

I built this website using the python3 Django library. Django was easy to use for me because it uses python, which is my favorite language to program in. However, using Django did not eliminate the need for extensive html and CSS to build a mobile compatible, functioning, and formatted site.

The project links on this site are hosted by Github, and I used Jekyll to build these pages. Jekyll made it possible for me to create pages using converted markdown files. These files I created from data science projects developed in jupyter notebooks, and then converted with a custom nbconvert template.

I have also used wordpress to build sites, but I much prefer the freedom that a language based web app platform gives.

Data Visualization

Content Coming Soon...

Systematic Biology

Target Enrichment and Extensive Population Sampling Help Untangle the Recent, Rapid Radiation of Oenothera Sect. Calylophus

Oenothera sect. Calylophus is a North American group of 13 recognized taxa in the evening primrose family (Onagraceae) with an evolutionary history that may include independent origins of bee pollination, edaphic endemism, and permanent translocation heterozygosity. Like other groups that radiated relatively recently and rapidly, taxon boundaries within Oenothera sect. Calylophus have remained challenging to circumscribe. In this study, we used target enrichment, flanking noncoding regions, gene tree/species tree methods, tests for gene flow modified for target-enrichment data, and morphometric analysis to reconstruct phylogenetic hypotheses, evaluate current taxon circumscriptions, and examine character evolution in Oenothera sect. Calylophus . Because sect. Calylophus comprises a clade with a relatively restricted geographic range, we were able to extensively sample across the range of geographic, edaphic, and morphological diversity in the group. We found that the combination of exons and flanking noncoding regions led to improved support for species relationships. We reconstructed potential hybrid origins of some accessions and note that if processes such as hybridization are not taken into account, the number of inferred evolutionary transitions may be artificially inflated. We recovered strong evidence for multiple evolutionary origins of bee pollination from ancestral hawkmoth pollination, edaphic specialization on gypsum, and permanent translocation heterozygosity. This study applies newly emerging techniques alongside dense infraspecific sampling and morphological analyses to effectively reconstruct the recalcitrant history of a rapid radiation.