Skip to content

Data analysis and pipelines

In genomic research I analyzed variants; in service work I compared audio, STT output, and delivery results

1 min read

In genomic research I analyzed variants; in service work I compared audio, STT output, and delivery results. Experience automating recurring analysis now informs my study of ingestion, transformation, and validation boundaries.

Pandas / Jupyter Notebook

Professional · Analyzed audio/STT output and delivery errors and prepared reports.

Python / cron / ETL

Professional · Automated recurring collection, preprocessing, and analysis to inform matching changes.

Samtools / Linux

Research · Preprocessed genomic data and worked with variant frequencies and annotation.

NumPy / Polars

Use and learning · Comparing array and table processing and transformation approaches.

Kafka / Airflow / dbt

Learning · Studying streaming, scheduling, transformation layers, and data quality checks.

Related project · GitHub