fix: dont remove rows that have nan in 2weeks playtimes (too many nans)

print("\n--- Reviews overview ---")

print(df[['num_reviews_total', 'pct_pos_total']].describe())

# --- 6. REMOVE ROWS WITH ANY NaN VALUES ---

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

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

print("REMOVING ROWS WITH ANY NaN VALUES")

print("REMOVING ROWS WITH NaN IN KEY COLUMNS")

print("="*60)

print(f"Original dataset size: {df.shape[0]:,} rows, {df.shape[1]} columns")

print(f"Rows with any NaN: {df.isnull().any(axis=1).sum():,}")

# Remove all rows that have at least one NaN value

df_complete = df.dropna()

print(f"Complete dataset size: {df_complete.shape[0]:,} rows, {df_complete.shape[1]} columns")

# Key columns we need for analysis

key_columns = ['price', 'average_playtime_forever', 'median_playtime_forever']

# Check missing values in key columns

print(f"\nMissing values in key columns:")

for col in key_columns:

    missing_count = df[col].isnull().sum()

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

    print(f"  {col}: {missing_count:,} ({missing_pct:.1f}%)")

# Remove rows that have NaN in any of the key columns

df_complete = df.dropna(subset=key_columns)

print(f"\nFiltered dataset size: {df_complete.shape[0]:,} rows, {df_complete.shape[1]} columns")

print(f"Data retention: {len(df_complete)/len(df)*100:.1f}%")

# --- 7. ANALYSIS ON COMPLETE DATASET ---

# Show how many rows still have NaN in 2-week columns (this is fine)

two_week_cols = ['average_playtime_2weeks', 'median_playtime_2weeks']

for col in two_week_cols:

    if col in df_complete.columns:

        missing_2week = df_complete[col].isnull().sum()

        missing_2week_pct = (missing_2week / len(df_complete)) * 100

        print(f"Remaining NaN in {col}: {missing_2week:,} ({missing_2week_pct:.1f}%) - OK to keep")

# --- 7. ANALYSIS ON FILTERED DATASET ---

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

print("ANALYSIS ON COMPLETE DATASET (NO NaN VALUES)")

print("ANALYSIS ON FILTERED DATASET (KEY COLUMNS COMPLETE)")

print("="*60)

# Analysis for average_playtime_forever

print(f"Games with >1000 reviews: {(df_complete['num_reviews_total'] > 1000).sum():,} ({(df_complete['num_reviews_total'] > 1000).mean()*100:.1f}%)")

print(f"Games with >90% positive reviews: {(df_complete['pct_pos_total'] > 90).sum():,} ({(df_complete['pct_pos_total'] > 90).mean()*100:.1f}%)")

# --- 8. Visualization Examples (Complete Dataset) ---

# --- 8. Visualization Examples (Filtered Dataset) ---

fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2, figsize=(15, 12))

# Distribution of prices

df_complete['price'].plot(kind='hist', bins=50, logy=True, title="Price Distribution (Complete Dataset)", ax=ax1)

df_complete['price'].plot(kind='hist', bins=50, logy=True, title="Price Distribution (Filtered Dataset)", ax=ax1)

ax1.set_xlabel("Price ($)")

ax1.set_ylabel("Count (log scale)")

# Distribution of average playtime (in hours, log scale)

playtime_hours_plot = playtime_hours[playtime_hours > 0]  # Remove any remaining zeros

playtime_hours_plot.plot(kind='hist', bins=50, logx=True, logy=True, 

                        title="Average Playtime Distribution (Complete Dataset)", ax=ax2)

                        title="Average Playtime Distribution (Filtered Dataset)", ax=ax2)

ax2.set_xlabel("Average Playtime (hours, log scale)")

ax2.set_ylabel("Count (log scale)")

ax3.set_yscale("log")

ax3.set_xlabel("Average Playtime (hours, log)")

ax3.set_ylabel("Total Reviews (log)")

ax3.set_title("Playtime vs Reviews (Complete Dataset)")

ax3.set_title("Playtime vs Reviews (Filtered Dataset)")

# Price vs Reviews (for paid games)

paid_mask = df_complete['price'] > 0

    ax4.set_yscale("log")

    ax4.set_xlabel("Price ($, log)")

    ax4.set_ylabel("Total Reviews (log)")

    ax4.set_title("Price vs Reviews - Paid Games (Complete Dataset)")

    ax4.set_title("Price vs Reviews - Paid Games (Filtered Dataset)")

plt.tight_layout()

plt.show()

# --- 9. Language & Tag exploration (Complete Dataset) ---

# --- 9. Language & Tag exploration (Filtered Dataset) ---

# Top supported languages

lang_counts = Counter([lang for langs in df_complete['supported_languages'] for lang in langs])

print("\n--- Top supported languages (Complete Dataset) ---")

print("\n--- Top supported languages (Filtered Dataset) ---")

print(pd.Series(lang_counts).sort_values(ascending=False).head(10))

# Top tags

tag_counts = Counter([tag for tags in df_complete['tags'] for tag in tags.keys()])

print("\n--- Top tags (Complete Dataset) ---")

print("\n--- Top tags (Filtered Dataset) ---")

print(pd.Series(tag_counts).sort_values(ascending=False).head(10))