Code

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# Load the housing dataset
data = pd.read_csv('/Users/mohamedkamara/Library/Containers/com.microsoft.Excel/Data/Downloads/housing.csv')

# Drop rows with missing values
data = data.dropna()

# Separate features (X) and target variable (y)
X = data.drop('median_house_value', axis=1)
y = data['median_house_value']

# Encode categorical features using one-hot encoding
data_encoded = pd.get_dummies(data, columns=['ocean_proximity'])

# Split the encoded data into features and target variable
X = data_encoded.drop('median_house_value', axis=1)
y = data_encoded['median_house_value']

# Split data into training and testing sets (80% train, 20% test)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train the Linear Regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Make predictions on the test set
predictions = model.predict(X_test)

# Evaluate model performance using Mean Squared Error
mse = mean_squared_error(y_test, predictions)
print(f"Mean Squared Error: {mse}")

# Visualizing: Scatter Plot of actual vs predicted house values
plt.figure(figsize=(8, 6))
plt.scatter(y_test, predictions, alpha=0.5)
plt.xlabel('Actual House Value')
plt.ylabel('Predicted House Value')
plt.title('Actual vs Predicted House Values')
plt.grid(True)
plt.show()

# Visualizing: Histogram of median_house_value
plt.figure(figsize=(8, 6))
plt.hist(data['median_house_value'], bins=30, color='skyblue', edgecolor='black')
plt.xlabel('Median House Value')
plt.ylabel('Frequency')
plt.title('Distribution of Median House Values')
plt.grid(True)
plt.show()

# Visualizing: Histograms of numerical features
numerical_features = X.select_dtypes(include=['float64', 'int64']).columns

# Set up subplots for each feature
fig, axes = plt.subplots(nrows=3, ncols=3, figsize=(15, 10))
fig.subplots_adjust(hspace=0.5, wspace=0.5)

for i, column in enumerate(numerical_features):
    row = i // 3
    col = i % 3
    ax = axes[row, col]

    X[column].plot(kind='hist', ax=ax, bins=20)
    ax.set_title(column)
    ax.set_xlabel('Value')
    ax.set_ylabel('Frequency')

plt.tight_layout()
plt.show()