EDA_2.py

# Detailed Missing Values Report
def missing_data_report(df):
    total = df.isnull().sum().sort_values(ascending=False)
    percent = (df.isnull().sum()/df.isnull().count()*100).sort_values(ascending=False)
    missing_df = pd.concat([total, percent], axis=1, keys=['Total Missing', 'Percent Missing (%)'])
    return missing_df[missing_df['Total Missing'] > 0]

print("\nMissing Data Report:")
print(missing_data_report(df))

# Visualizing Missing Data Patterns (Seaborn)
plt.figure(figsize=(10, 6))
sns.heatmap(df.isnull(), cbar=False, cmap='viridis')
plt.title('Missing Values Heatmap')
plt.show()

# You can also use missingno library for more advanced missing data visualizations
# !pip install missingno
# import missingno as msno
# msno.matrix(df, figsize=(10, 6), color=(0.2, 0.2, 0.2))
# plt.title('Missing Values Matrix (missingno)')
# plt.show()
# msno.bar(df, figsize=(10, 6), color='skyblue')
# plt.title('Missing Values Bar Plot (missingno)')
# plt.show()