feat: add genres information - missing and counts

    except (ValueError, SyntaxError):

        return {}

def parse_genres(x):

    """Parse genres from various formats"""

    if pd.isna(x):

        return []

    if isinstance(x, str):

        if x.startswith('[') and x.endswith(']'):

            try:

                return ast.literal_eval(x)

            except:

                # If it's just a comma-separated string

                return [genre.strip().strip('"').strip("'") for genre in x.strip('[]').split(',') if genre.strip()]

        elif ',' in x:

            return [genre.strip() for genre in x.split(',') if genre.strip()]

        else:

            return [x.strip()] if x.strip() else []

    elif isinstance(x, list):

        return x

    else:

        return []

df['tags'] = df['tags'].apply(parse_tags)

# Parse genres early in the pipeline

if 'genres' in df.columns:

    df['genres_parsed'] = df['genres'].apply(parse_genres)

    # Check for missing/empty genres

    print(f"\n--- GENRE MISSING VALUES ANALYSIS ---")

    original_nulls = df['genres'].isnull().sum()

    print(f"Original NULL values in genres: {original_nulls:,} ({original_nulls/len(df)*100:.1f}%)")

    empty_arrays = df['genres_parsed'].apply(lambda x: len(x) == 0 if isinstance(x, list) else True).sum()

    print(f"Empty genre arrays after parsing: {empty_arrays:,} ({empty_arrays/len(df)*100:.1f}%)")

    games_with_genres = df['genres_parsed'].apply(lambda x: len(x) > 0 if isinstance(x, list) else False).sum()

    print(f"Games with at least one genre: {games_with_genres:,} ({games_with_genres/len(df)*100:.1f}%)")

    # Show some examples of empty/problematic entries

    empty_mask = df['genres_parsed'].apply(lambda x: len(x) == 0 if isinstance(x, list) else True)

    if empty_mask.sum() > 0:

        print(f"\nSample of games with empty genres:")

        empty_sample = df[empty_mask][['name', 'genres', 'genres_parsed']].head(3)

        for idx, row in empty_sample.iterrows():

            print(f"  '{row['name']}': original='{row['genres']}', parsed={row['genres_parsed']}")

    # Count all genres immediately

    all_genres_debug = []

    for genres_list in df['genres_parsed']:

        if isinstance(genres_list, list):

            all_genres_debug.extend(genres_list)

    if all_genres_debug:

        genre_counts_debug = Counter(all_genres_debug)

        print(f"\nGenre counts (full dataset, before filtering):")

        for genre, count in genre_counts_debug.most_common(15):

            print(f"  {genre}: {count:,}")

        # Show genre distribution stats

        avg_genres_per_game = df['genres_parsed'].apply(lambda x: len(x) if isinstance(x, list) else 0).mean()

        print(f"\nAverage genres per game: {avg_genres_per_game:.2f}")

        # Show games with most genres

        max_genres = df['genres_parsed'].apply(lambda x: len(x) if isinstance(x, list) else 0).max()

        print(f"Maximum genres on a single game: {max_genres}")

        if max_genres > 0:

            multi_genre_games = df[df['genres_parsed'].apply(lambda x: len(x) if isinstance(x, list) else 0) == max_genres]

            print(f"Game(s) with {max_genres} genres:")

            for idx, row in multi_genre_games[['name', 'genres_parsed']].head(2).iterrows():

                print(f"  '{row['name']}': {row['genres_parsed']}")

    else:

        print("No genres found after parsing!")

else:

    print("No 'genres' column found in dataset!")

# --- 2. Handle price=0 ---

def clean_price(row):

    price = row['price']