from sklearn.datasets import load_boston
from sklearn.svm import SVR
from sklearn.metrics import mean_squared_error
from sklearn.metrics import r2_score
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
%matplotlib inline

#Data preparation. Boston Home Prices
data = load_boston()
X = data.data[:, [5,]] #Extract only the number of rooms as explanatory variables
y = data.target

#Separated into training data and test data
train_X, test_X = X[:400], X[400:]
train_y, test_y = y[:400], y[400:]

#SVR with modified hyperparameters(Support vector machine (kernel method))Learning at
model_s = SVR(C=1.0, kernel='rbf') #Uses rbf kernel with regularization parameter 1
model_s.fit(train_X, train_y)
#Prediction using learning data
s_pred = model_s.predict(train_X)
#Prediction using test data (prediction for unknown data)
s_pred_t = model_s.predict(test_X)

#graph display
fig, ax = plt.subplots()
ax.scatter(train_X, train_y, color='red', marker='s', label='data')
ax.plot(train_X, s_pred, color='blue', label='svr_rbf curve(train)')
ax.plot(test_X, s_pred_t, color='orange', label='svr_rbf curve(test)')
ax.legend()
plt.show()

print("○ Mean square error and coefficient of determination of training data")
print(mean_squared_error(train_y, s_pred))
print(r2_score(train_y, s_pred))
print("○ Mean square error and coefficient of determination of test data")
print(mean_squared_error(test_y, s_pred_t))
print(r2_score(test_y, s_pred_t))

Recommended Posts