feat: look for free to play in tags and also genres

# --- 7. Handle price=0 (BEFORE comprehensive summary) ---

def clean_price(row):

    """

    Cleans the price column. If price is 0, checks if 'Free to Play' is

    present in either tags or genres. If not, the price is set to NaN.

    """

    price = row['price']

    tags = row['tags']

    genres = row['genres_parsed']

    if price == 0:

        if isinstance(tags, dict) and any(t.lower() == "free to play" for t in tags.keys()):

            return 0  # true free to play

        # Check if 'Free to Play' is in tags (case-insensitive)

        is_free_in_tags = isinstance(tags, dict) and any(t.lower() == "free to play" for t in tags.keys())

        # Check if 'Free to Play' is in genres (case-insensitive)

        is_free_in_genres = isinstance(genres, list) and any(g.lower() == "free to play" for g in genres)

        # If it's marked as Free to Play in either tags or genres, keep the price at 0

        if is_free_in_tags or is_free_in_genres:

            return 0  # It's a genuinely free-to-play game

        else:

            return np.nan  # treat as missing

            # If price is 0 but not marked as F2P, treat it as missing data

            return np.nan

    return price

# Overwrite original price column

# Overwrite original price column with cleaned data

df['price'] = df.apply(clean_price, axis=1)

# --- 8. Clean playtime columns (BEFORE comprehensive summary) ---

    missing_pct = (missing_count / len(df)) * 100

    print(f"{col:35}: {missing_count:8,} ({missing_pct:5.1f}%)")

# --- 10. Handle price=0 (from original script) ---

def clean_price(row):

    price = row['price']

    tags = row['tags']

    if price == 0:

        if isinstance(tags, dict) and any(t.lower() == "free to play" for t in tags.keys()):

            return 0  # true free to play

        else:

            return np.nan  # treat as missing

    return price

# Overwrite original price column

df['price'] = df.apply(clean_price, axis=1)

# --- 11. Clean playtime columns (from original script) ---

playtime_cols = ['average_playtime_forever', 'median_playtime_forever',

                 'average_playtime_2weeks', 'median_playtime_2weeks']

for col in playtime_cols:

    df[col] = df[col].replace(0, np.nan)

# --- 12. REMOVE ROWS WITH NaN VALUES IN KEY COLUMNS ---

print("\n" + "="*60)

print("FILTERING DATASET FOR COMPLETE KEY COLUMNS")