# this is a recap

# a training pipeline generally consists of 3 steps:
# 1. Design model (input, output size, forward pass (layers))
# 2. Construct loss and optimizer
# 3. Training loop
#     - forward pass: compute prediction
#     - backward pass: gradient computation
#     - update parameters

# (iterate step 3)

import torch
import torch.nn as nn

X = torch.tensor([[1], [2], [3], [4]], dtype=torch.float32)
Y = torch.tensor([[3], [6], [9], [12]], dtype=torch.float32)

X_test = torch.tensor([5], dtype=torch.float32)

n_samples, n_features = X.shape
input_size = output_size = n_features

learning_rate = 0.01
n_iter = 100


model = nn.Linear(input_size, output_size, bias=False)
loss = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)

print(f'Prediction before training: f(5) = {model(X_test).item():.3f}')
for epoch in range(n_iter):
    Y_pred = model(X)
    l = loss(Y, Y_pred)
    l.backward()
    optimizer.step()
    optimizer.zero_grad()

    [w] = model.parameters()
    w = w.item()

    if epoch % 10 == 0:
        print(f'Epoch {epoch}: w = {w:.3f}, loss = {l:.5f}')

print(f'Prediction after training: f(5) = {model(X_test).item():.3f}')