I have a working Python script that already tackles a portion of my scientific-data analysis, but it needs a full refresh so it can: • clean and preprocess raw experimental files (handling missing values, unit conversions, outlier checks) • run the required statistical analyses (descriptive stats, hypothesis testing, regression where relevant) • generate clear, publication-quality visualisations of the results The current code is organised in a single file. I want it refactored into well-named functions or classes, documented with concise docstrings, and wrapped in a short Jupyter notebook that demonstrates the new workflow from import to final figure. Please keep any existing logic that is still valid but feel free to streamline it with modern libraries—pandas, NumPy, SciPy, matplotlib or seaborn are all fine. Deliverables 1. Updated .py module(s) with preprocessing, stats, and plotting functions 2. Example Jupyter notebook that runs end-to-end on sample data I will supply 3. Brief README outlining dependencies and execution steps 4. Comments or inline notes highlighting any assumptions or edge-case handling you added I will test the code on a fresh environment; it should execute without errors and reproduce the notebook’s figures. If everything works and the results match my benchmark calculations, the task is complete.