- Experience working with data
- A drive to learn
- Not required to know SQL, Python or R
- Module 1 - Overview of Data Analytic Problems
- Module 2 - Extract: Data types, Databases and importing data.
- Module 3 - Transformation: SQL Practice: Case When, Group By
- Module 4 - Transofmration: SQL Interactive Class
- Module 5 - Aggregation: SQL Jobs, SQL Views, Order of Operations - Assignment #2
- Module 6 - Aggregation: Introduction to Python, Data types, pandas
- Module 7 - Aggregation: Pandas common functions.
- Module 8 - Performance Optimizations - Loops, functions
Technology used
- SQL, Python (pandas, SQLAlchemy, pymysql)
- Pandas group-by,
- MySQL Server, MySQL Workbench
- Database Administration Strategies
Twitch Streamer Analytics - Famerly
A passion project that involves scheduled data extraction through an API request, retreiving and analyzing collected data and presenting the results in an easy-to-consume format.
Technology Used
- AWS RDS & EC2 Server
- Python/pandas/SQL stack
- Modules: requests, json, twitch-python-client
Kaggle Competitions/Machine Learning - Kaggle
About 80 percent of adults experience low back pain at some point in their lifetimes. It is the most common cause of job-related disability and a leading contributor to missed work days. -National Institute of Health
Utilizing technology to enhance the lives of people always has, and always be my life's mission. If we could produce a model which accurately predicts low back pain, then perhaps anatomical measurements could be examined more routinely as an indicator of back health.
- Low Back Pain Algorithm - 85% accuracy with Support Vector Machine
Technology used
- Language: Python
- Data Transformation: pandas, numpy
- Machine Learning: keras, scikit-learn
- Visualization: seaborn
Sentiment Analysis on Student Feedback - GCP NLP API
Every year, CMCC sends out an anonymous 'Exit Interview' to the graduating class to gather feedback, extract trends among the responses and use the trends to improve the experience each year. This presents an ideal problem for Natural Language Processesing within the domain of Machine Learn to tackle as we have a dataset of open-text and the need to extract insights about it.
Technology used
- Python
- pandas
- natural language API
- Google Cloud
Dashboard Automation - Google Data Studio | PowerBI
Automated Benchmark.
Technology used
- Medical Records
- Python
- Modules: pandas, pygsheets
Custom Sign Up App - PowerApps | Sharepoint
Aligning the busy schedules
Technology used
- Microsoft PowerApps
- Microsoft Sharepoint
- Microsoft PowerBI
- Microsoft Flow