Feature Analysis

import pandas as pd
import numpy as np

# Top correlations with target (medv)
correlations = {
    'rm': 0.696,        # Positive: More rooms
    'zn': 0.360,        # Positive: Large lots
    'b': 0.333,         # Positive: Demographics
    'dis': 0.250,       # Positive: Distance to work
    'chas': 0.175,      # Positive: River proximity
    'age': -0.377,      # Negative: Older homes
    'rad': -0.382,      # Negative: Highway access
    'crim': -0.388,     # Negative: Crime
    'nox': -0.427,      # Negative: Pollution
    'tax': -0.469,      # Negative: Property tax
    'indus': -0.484,    # Negative: Industrial area
    'ptratio': -0.508,  # Negative: School quality
    'lstat': -0.738     # Negative: Low income %
}

House Price ≈ 
  Space + Income Level + School Quality 
  + Environmental Quality + Safety 
  - Cost Burden

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Load dataset
df = pd.read_csv('BostonHousing.csv')

# Calculate correlation matrix
corr_matrix = df.corr()

# Plot heatmap
plt.figure(figsize=(12, 10))
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', center=0)
plt.title('Boston Housing - Feature Correlation Matrix')
plt.tight_layout()
plt.show()

# Show top correlations with target
target_corr = corr_matrix['medv'].drop('medv').sort_values(ascending=False)
print("\nTop correlations with medv:")
print(target_corr)