import pandas as pd

# Read the housing dataset from the CSV file
data = pd.read_csv('Housing.csv')

# Explore the dataset
print(data.head())
print(data.shape)
print(data.describe())

import seaborn as sns
import matplotlib.pyplot as plt

# Use pairplots to visualize relationships between variables
sns.pairplot(data)
plt.show()

# Use boxplots to identify patterns or correlations
sns.boxplot(x='area', y='price', data=data)
plt.show()

# Map categorical variables to numerical values
data['furnishingstatus'] = data['furnishingstatus'].map({'furnished': 1, 'unfurnished': 0})

# Create dummy variables for the "furnishingstatus" feature
data = pd.get_dummies(data, columns=['furnishingstatus'], drop_first=True)

# Remove unnecessary variables from the dataset
data = data.drop('location', axis=1)

from sklearn.model_selection import train_test_split

# Split the dataset into training and testing sets using a 70:30 ratio
X = data.drop('price', axis=1)
y = data['price']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)

import statsmodels.api as sm

# Add a constant to the training data
X_train = sm.add_constant(X_train)

# Create a linear regression model using the training data
model = sm.OLS(y_train, X_train)

# Print the summary of the linear regression model
print(model.fit().summary())

from statsmodels.stats.outliers_influence import variance_inflation_factor
from sklearn.feature_selection import RFE

# Perform feature selection using variance inflation factor (VIF)
vif = pd.DataFrame()
vif['Features'] = X_train.columns
vif['VIF'] = [variance_inflation_factor(X_train.values, i) for i in range(X_train.shape[1])]

# Update the model by removing highly correlated or insignificant variables
X_train = X_train.drop(['feature1', 'feature2'], axis=1)

# Perform recursive feature elimination (RFE)
selector = RFE(model, n_features_to_select=5)
selector = selector.fit(X_train, y_train)

# Evaluate the model and calculate the VIFs for the final selected features
X_train_selected = X_train[X_train.columns[selector.support_]]
model_selected = sm.OLS(y_train, X_train_selected)
print(model_selected.fit().summary())

# Analyze the residuals of the model on the training data
residuals = model_selected.fit().resid
# Perform residual

 analysis here

from sklearn.preprocessing import StandardScaler

# Apply scaling on the test dataset
scaler = StandardScaler()
X_test_scaled = scaler.fit_transform(X_test)

# Make predictions using the final model on the test data
X_test_selected = X_test_scaled[:, selector.support_]
y_pred = model_selected.fit().predict(sm.add_constant(X_test_selected))

from sklearn.metrics import mean_squared_error, r2_score

# Compare the actual and predicted values using scatter plots
# Perform scatter plot here

# Evaluate the performance of the model using metrics such as RMSE and R-squared
rmse = mean_squared_error(y_test, y_pred, squared=False)
r2 = r2_score(y_test, y_pred)
print('RMSE:', rmse)
print('R-squared:', r2)