Analytics and Data Analysis

Guidelines for data analysis, visualization, and Jupyter-based workflows using pandas, matplotlib, seaborn, and numpy. Prioritize readability, reproducibility, and vectorized operations.

Workflow: Exploratory Data Analysis Pipeline

1. Load and inspect — Read data with pd.read_csv() or appropriate loader, check .shape, .dtypes, .describe(), and .isnull().sum()
2. Clean and transform — Handle missing values, fix dtypes, rename columns, filter outliers using vectorized pandas operations
3. Explore relationships — Use .groupby(), .corr(), and cross-tabulations to identify patterns
4. Visualize findings — Create targeted plots with matplotlib/seaborn; label axes, add titles, use colorblind-friendly palettes
5. Validate results — Run statistical tests, report confidence intervals, verify assumptions
6. Document and share — Structure notebook with markdown sections, clear outputs before sharing, pin dependencies

Key Principles