I’m working with a large collection of scientific measurements and I need a Python-savvy analyst to turn the raw files into clear, reproducible insights. The job spans the full workflow: first cleaning and preprocessing the data, then running solid statistical analyses, and finally producing publication-ready visualisations. The raw data arrive as CSVs exported from laboratory equipment. I need you to: • Build robust preprocessing scripts (pandas / NumPy) to handle missing values, outliers and unit conversions. • Apply appropriate statistical tests and models with SciPy or statsmodels and summarise the findings in plain language. • Create concise, attractive plots—think matplotlib or seaborn—that I can drop straight into a report or slide deck. Deliverables • Well-commented Python scripts or Jupyter notebooks covering each step • A brief markdown or PDF report that explains methods, key statistics and interpretation of results • All generated figures saved as high-resolution PNG/SVG Everything should be reproducible on a fresh environment (requirements.txt or environment.yml appreciated). If you’re comfortable automating parts of the workflow or suggesting better tooling, I’m open to ideas. Looking forward to seeing how you can help make sense of this dataset.