Run exploratory data analysis and visualizations

Perform exploratory data analysis, visualization, statistical tests, and reporting

Exploratory investigation of datasets when the question is broad (profile, compare, find patterns) vs narrow hypothesis testing

• · raw dataset or model output
• · question/hypothesis to investigate
• · expected output format (notebook/report)

• · distribution plots, correlation matrices
• · statistical test results with p-values
• · markdown report with narrative insights and visuals

• · pandas
• · scipy
• · matplotlib/seaborn
• · Jupyter notebooks

• · data accessible and loadable
• · question specific enough for EDA

• · dataset too large to load in memory
• · missing values too prevalent
• · hypothesis requires domain knowledge not in data

• · reads .describe(), .info(), .corr() systematically
• · identifies outliers with IQR/z-score
• · tests for stationarity in time series
• · visualization best practices explicit