lw=3,
label=f"LR = 0.1, Final = {losses['LR=0.1'][-1]:.2f}")
plt.plot(xs,
losses['LR=0.01'],
lw=3,
label=f"LR = 0.01, Final = {losses['LR=0.01'][-1]:.2f}")
plt.plot(xs,
losses['LR=0.001'],
lw=3,
label=f"LR = 0.001, Final = {losses['LR=0.001'][-1]:.2f}")
plt.title('Loss per iteration (MSE) for different learning rates', size=20)
plt.xlabel('Iteration', size=14)
plt.ylabel('Loss', size=14)
plt.legend()
plt.show()
if __name__ == "__main__":
model = LinearRegression(lr=0.5)
model.fit(X_train, y_train, optimizer="adam")
preds = model.predict(X_test)
print(model._mean_squared_error(y_test, preds))
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
lr_model = LinearRegression()
lr_model.fit(X_train, y_train)
lr_preds = lr_model.predict(X_test)
print(mean_squared_error(y_test, lr_preds))
