fix: do price and playtime cleaning before summary

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

        print(f"\nAverage supported languages per game: {avg_languages_per_game:.2f}")

# --- 7. GENRES ANALYSIS (from original script) ---

# --- 9. GENRES ANALYSIS (from original script) ---

print(f"\n--- GENRES ANALYSIS ---")

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

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

        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}")

# --- 8. Pseudo-missing values analysis (zeros in numeric columns) ---

# --- 10. Pseudo-missing values analysis (zeros in numeric columns) ---

print("\n--- Potential pseudo-missing values (zeros in numeric columns) ---")

num_cols = df.select_dtypes(include=[np.number]).columns

zero_counts = (df[num_cols] == 0).sum().sort_values(ascending=False)

print(zero_counts)

# --- 9. COMPREHENSIVE MISSING VALUES SUMMARY ---

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

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)

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

# 0 playtime might mean missing if no one played / no data

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)

# --- 11. COMPREHENSIVE MISSING VALUES SUMMARY ---

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

print("COMPREHENSIVE MISSING VALUES SUMMARY")

print("="*60)