import pandas as pd

df = pd.DataFrame({
    'Name': ['John', 'Sarah', 'Mike', 'Emma', None],
    'Age': [25, 30, None, 35, 28],
    'City': ['NYC', 'LA', 'NYC', 'Chicago', 'LA'],
    'Salary': [50000, 60000, 55000, 70000, 45000]
})

def data_overview(df):
    print("=" * 40)
    print("DATA OVERVIEW")
    print("=" * 40)
    print(f"Rows: {len(df)}")
    print(f"Columns: {len(df.columns)}")
    print(f"\nColumn names: {list(df.columns)}")
    print(f"\nData types:")
    print(df.dtypes)

data_overview(df)

def missing_report(df):
    print("=" * 40)
    print("MISSING DATA")
    print("=" * 40)
    missing = df.isna().sum()
    pct = (missing / len(df)) * 100

    report = pd.DataFrame({
        'Missing': missing,
        'Percent': pct
    })
    print(report[report['Missing'] > 0])
    print(f"\nTotal missing values: {missing.sum()}")

missing_report(df)

def numeric_summary(df):
    print("=" * 40)
    print("NUMERIC COLUMNS")
    print("=" * 40)
    numeric_cols = df.select_dtypes(include=['number']).columns

    for col in numeric_cols:
        print(f"\n{col}:")
        print(f"  Mean: {df[col].mean():.2f}")
        print(f"  Median: {df[col].median():.2f}")
        print(f"  Min: {df[col].min()}")
        print(f"  Max: {df[col].max()}")

numeric_summary(df)

def categorical_summary(df):
    print("=" * 40)
    print("CATEGORICAL COLUMNS")
    print("=" * 40)
    cat_cols = df.select_dtypes(include=['object']).columns

    for col in cat_cols:
        print(f"\n{col}:")
        print(f"  Unique values: {df[col].nunique()}")
        print(f"  Most common: {df[col].mode()[0]}")
        print(f"  Value counts:")
        print(df[col].value_counts().head(5).to_string())

categorical_summary(df)

def full_eda_report(df):
    print("\n" + "=" * 50)
    print("EXPLORATORY DATA ANALYSIS REPORT")
    print("=" * 50)

    # 1. Overview
    print(f"\n1. DATA SHAPE")
    print(f"   Rows: {len(df)}")
    print(f"   Columns: {len(df.columns)}")

    # 2. Missing data
    print(f"\n2. MISSING DATA")
    missing = df.isna().sum()
    if missing.sum() > 0:
        for col in df.columns:
            if missing[col] > 0:
                pct = (missing[col] / len(df)) * 100
                print(f"   {col}: {missing[col]} ({pct:.1f}%)")
    else:
        print("   No missing values!")

    # 3. Numeric columns
    print(f"\n3. NUMERIC SUMMARY")
    print(df.describe().round(2))

    # 4. Categorical columns
    print(f"\n4. CATEGORICAL SUMMARY")
    for col in df.select_dtypes(include=['object']).columns:
        print(f"\n   {col}:")
        print(df[col].value_counts().to_string())

    # 5. Correlations
    print(f"\n5. CORRELATIONS")
    numeric_df = df.select_dtypes(include=['number'])
    if len(numeric_df.columns) > 1:
        print(numeric_df.corr().round(2))

    print("\n" + "=" * 50)
    print("END OF REPORT")
    print("=" * 50)

# Run the report
full_eda_report(df)

import sys

# Save print output to file
with open('eda_report.txt', 'w') as f:
    # Redirect print to file
    old_stdout = sys.stdout
    sys.stdout = f
    full_eda_report(df)
    sys.stdout = old_stdout

print("Report saved to eda_report.txt")