import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.model_selection import GridSearchCV

# Load the housing data
df = pd.read_csv("RealEstateAU_1000_Samples.csv")

# Split the data into features and target
X = df.drop("price", axis=1)
y = df["price"]

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Define the Regression pipeline
reg_pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('regressor', LinearRegression())
])

# Define the Classification pipeline
clf_pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('classifier', SVC())
])

# Define the hyperparameters for the Regression pipeline
reg_parameters = {
    'regressor__fit_intercept': [True, False],
    'regressor__normalize': [True, False]
}

# Define the hyperparameters for the Classification pipeline
clf_parameters = {
    'classifier__kernel': ['linear', 'poly', 'rbf', 'sigmoid'],
    'classifier__C': [0.1, 1, 10, 100, 1000],
    'classifier__gamma': ['scale', 'auto']
}

# Use GridSearchCV to perform hyperparameter tuning on the Regression pipeline
reg_grid = GridSearchCV(reg_pipeline, reg_parameters, cv=5, scoring='neg_mean_squared_error', verbose=1)
reg_grid.fit(X_train, y_train)

# Use GridSearchCV to perform hyperparameter tuning on the Classification pipeline
clf_grid = GridSearchCV(clf_pipeline, clf_parameters, cv=5, scoring='accuracy', verbose=1)
clf_grid.fit(X_train, y_train)

# Print the best hyperparameters for the Regression pipeline
print("Best hyperparameters for Regression pipeline:", reg_grid.best_params_)

# Print the best hyperparameters for the Classification pipeline
print("Best hyperparameters for Classification pipeline:", clf_grid.best_params_)

# Predict the housing prices using the optimized Regression pipeline
y_pred_reg = reg_grid.predict(X_test)

# Predict the housing prices using the optimized Classification pipeline
y_pred_clf = clf_