Use the Fama-French 5-Factor Model plus momentum to identify undervalued stocks, analyze alpha, and measure return contributions in Python

				
					import requests
import zipfile
import io
import re
import pandas as pd
import yfinance as yf

class FamaFrenchDownloader:
    """Downloads and processes Fama-French 5-factor data (daily)."""

    FF5_URL = "https://mba.tuck.dartmouth.edu/pages/faculty/ken.french/ftp/F-F_Research_Data_5_Factors_2x3_daily_CSV.zip"

    @staticmethod
    def download_ff5():
        """Fetches and extracts F-F 5-Factor data from the web."""
        response = requests.get(FamaFrenchDownloader.FF5_URL)
        with zipfile.ZipFile(io.BytesIO(response.content)) as z:
            file_name = z.namelist()[0]
            with z.open(file_name) as f:
                return f.read().decode("utf-8").splitlines()

    @staticmethod
    def parse_ff5_data():
        """Extracts and cleans F-F 5-Factor data."""
        lines = FamaFrenchDownloader.download_ff5()

        # Keep only data lines (starting with 8-digit dates)
        data_lines = [line for line in lines if re.match(r'^\s*\d{8}', line)]

        # Read into DataFrame
        df = pd.read_csv(io.StringIO("\n".join(data_lines)), sep=r"\s*,\s*", header=None, engine="python")

        # Assign column names
        df.columns = ["Date", "MKT_RF", "SMB", "HML", "RMW", "CMA", "RF"]

        # Convert date column
        df["Date"] = pd.to_datetime(df["Date"], format="%Y%m%d", errors="coerce")

        # Convert numeric columns
        df.iloc[:, 1:] = df.iloc[:, 1:].apply(pd.to_numeric, errors="coerce")

        return df

# Usage (Fixed)
ff5_df = FamaFrenchDownloader.parse_ff5_data()
ff5_df