Machine Learning Polynomial Regression

[braveYug]

Hello All,

I am facing some problem while implementing polynomial regression for my machine learning module. Part of my code is as below:

poly = PolynomialFeatures(degree = 4) 
X_poly = poly.fit_transform(X) 
lin = LinearRegression() 
lin.fit(X_poly, Y)
y_poly_pred = lin.predict(X_poly)
plt.scatter(X['Totalizer'], Y, color='red')
plt.plot(X['Totalizer'], y_poly_pred, color='b')
plt.title('Polynomial Regression')
plt.xlabel('Totalizer')
plt.ylabel('Temperature')
plt.show()

rmse = np.sqrt(mean_squared_error(Y,y_poly_pred))
r2 = r2_score(Y,y_poly_pred)
print(rmse)
print(r2)

Please also see attached picture :
   

My question is that my predicted values are completely in line with output(label) but still rmse and r2 are respectively 10.2 & 0.99. Why this rmse and r2 are showing in opposite direction that model is not tuned well? Am I missing something important?