Convert a css file to a dictionary to be used with AI/ML (MFA)

create_dictionary.py

import csv

def create_hebrew_dictionary(
    input_csv="hebrew_frequency.csv",
    output_dict="hebrew_dictionary.txt"
):
    """
    Reads the CSV file from the scrape script and creates
    a Hebrew -> Transliteration dictionary (or any mapping you choose).
    Saves it in a simple text file for demonstration.
    """
    # Adjust these column names/indexes based on the CSV from step 1
    # E.g., if your headers are: ["Rank", "Hebrew", "Transliteration", "Part of Speech", "English"]
    # We might want: Hebrew -> Transliteration

    # hebrew_col_name = "Hebrew"
    hebrew_col_name = "Transliteration"
    translit_col_name = "Transliteration"

    # Load the CSV
    with open(input_csv, "r", encoding="utf-8") as f:
        reader = csv.DictReader(f)
        # Confirm the columns exist
        if hebrew_col_name not in reader.fieldnames or translit_col_name not in reader.fieldnames:
            raise ValueError(f"CSV missing required columns {hebrew_col_name} or {translit_col_name}")

        # Build a dictionary in Python (Hebrew -> Transliteration)
        hebrew_dict = {}
        for row in reader:
            hebrew_word = row[hebrew_col_name].strip()
            transliteration = row[translit_col_name].strip()
            # Store in a Python dict
            if hebrew_word:
                hebrew_dict[hebrew_word] = transliteration

    # Save dictionary to a text file
    with open(output_dict, "w", encoding="utf-8") as out_f:
        for hebrew_word, transliteration in hebrew_dict.items():
            line = f"{hebrew_word} : {transliteration}\n"
            out_f.write(line)

    print(f"Dictionary file saved to {output_dict}")


if __name__ == "__main__":
    create_hebrew_dictionary("hebrew_frequency.csv", "hebrew_dictionary.txt")