graph TD
    A[Raw Data] --> B[Ingest + Validate Schema]
    B --> C[Clean: Missing Values, Outliers, Types]
    C --> D[Exploratory Data Analysis]
    D --> E[Distribution Assessment]
    E --> F{Parametric Assumptions Met?}
    F -->|Yes| G[Parametric Tests]
    F -->|No| H[Non-Parametric Tests]
    G --> I[Effect Size + Confidence Intervals]
    H --> I
    I --> J[Publication Visualization]
    J --> K[Reproducible Report]

import pandas as pd
import numpy as np
from scipy import stats
import seaborn as sns
import matplotlib.pyplot as plt

def analysis_pipeline(filepath: str) -> dict:
    df = pd.read_csv(filepath)

    report = {
        "shape": df.shape,
        "missing": df.isnull().sum().to_dict(),
        "dtypes": df.dtypes.astype(str).to_dict(),
    }

    numeric_cols = df.select_dtypes(include=[np.number]).columns
    for col in numeric_cols:
        stat, p = stats.shapiro(df[col].dropna()[:5000])
        report[f"{col}_normality"] = {"statistic": stat, "p_value": p, "normal": p > 0.05}

    return report

def compare_groups(df: pd.DataFrame, value_col: str, group_col: str) -> dict:
    groups = [g[value_col].dropna() for _, g in df.groupby(group_col)]

    normality_ok = all(stats.shapiro(g[:5000]).pvalue > 0.05 for g in groups)
    _, levene_p = stats.levene(*groups)
    homoscedastic = levene_p > 0.05

    if normality_ok and homoscedastic:
        stat, p = stats.f_oneway(*groups) if len(groups) > 2 else stats.ttest_ind(*groups)
        test_name = "ANOVA" if len(groups) > 2 else "t-test"
    else:
        stat, p = stats.kruskal(*groups)
        test_name = "Kruskal-Wallis"

    effect = compute_cohens_d(groups[0], groups[1]) if len(groups) == 2 else compute_eta_squared(groups)

    return {"test": test_name, "statistic": stat, "p_value": p, "effect_size": effect}

def publication_figure(df: pd.DataFrame, x: str, y: str, output: str):
    fig, ax = plt.subplots(figsize=(3.5, 3))  # Single-column journal width
    sns.boxplot(data=df, x=x, y=y, palette="colorblind", ax=ax)
    ax.set_xlabel(x.replace("_", " ").title())
    ax.set_ylabel(y.replace("_", " ").title())
    sns.despine()
    fig.tight_layout()
    fig.savefig(output, dpi=300, bbox_inches="tight")
    plt.close(fig)