src/analyze.py

#analyze.py
import pandas as pd
from ydata_profiling import ProfileReport

def analyze_csv(file_path):
    df = pd.read_csv(file_path)
    profile = ProfileReport(df, title="Profiling Report", minimal=True, explorative=True)

    summary = df.describe(include='all').to_dict()
    column_info = {
        col: {
            "dtype": str(df[col].dtype),
            "missing_pct": df[col].isnull().mean() * 100,
            "unique_vals": df[col].nunique(),
            "example_vals": df[col].dropna().unique()[:5].tolist()
        }
        for col in df.columns
    }

    return {
        "summary": summary,
        "columns": column_info,
        "shape": df.shape
    }