Skup podataka je California Housing, a cilj je predvideti cenu nekretnine.

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn import model_selection
from sklearn import datasets
from sklearn import preprocessing
from sklearn import metrics
from sklearn import svm

data = datasets.fetch_california_housing()
X = data.data
y = data.target

X_train_and_val, X_test, y_train_and_val, y_test = model_selection.train_test_split(
    X, y, test_size = 0.3, random_state = 7)

X_train, X_val, y_train, y_val = model_selection.train_test_split(
    X_train_and_val, y_train_and_val, train_size = 0.8, random_state = 7) 

scaler = preprocessing.StandardScaler()
scaler.fit(X_train)
X_train = scaler.transform(X_train)
X_val = scaler.transform(X_val)
X_test = scaler.transform(X_test)

Cs = [0.01, 0.05, 0.1, 0.5, 1, 5, 10]
gammas = [0.01, 0.05, 0.1, 0.5, 1, 5, 10]

best_mse = 10000
best_C = None
best_gamma = None

for C in Cs:
    for gamma in gammas:
        model = svm.SVR(kernel='rbf', gamma=gamma, C = C)
        model.fit(X_train, y_train)
        mse = metrics.mean_squared_error(y_val, model.predict(X_val))
        if mse < best_mse:
            best_mse = mse
            best_C = C
            best_gamma = gamma

print('Najbolji hiperparametri modela su: ', best_C, best_gamma)

Najbolji hiperparametri modela su:  5 0.5

print('Najmanja srednjekvadratna greska na validacionom skupu je: ', best_mse)

Najmanja srednjekvadratna greska na validacionom skupu je:  0.30594453711377617

best_model = svm.SVR(kernel='rbf', gamma=best_gamma, C=best_C)
best_model.fit(X_train, y_train)

SVR(C=5, gamma=0.5)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

metrics.mean_squared_error(y_test, best_model.predict(X_test))

0.30741759706586064

metrics.r2_score(y_test, best_model.predict(X_test))

0.7698766256707872