import os

os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"

import tensorflow as tf

tf.get_logger().setLevel("ERROR")

x = tf.constant(3.0)

with tf.GradientTape() as tape:
    tape.watch(x)
    y = x * x + 2.0 * x

dy_dx = tape.gradient(y, x)

weight = tf.Variable(2.0, name="weight")
feature = tf.constant(3.0)
target = tf.constant(15.0)
optimizer = tf.keras.optimizers.SGD(learning_rate=0.05)

weight_before = float(weight.numpy())

with tf.GradientTape() as tape:
    prediction = weight * feature
    loss = tf.square(prediction - target)

gradients = tape.gradient(loss, [weight])
loss_before = float(loss.numpy())
optimizer.apply_gradients(zip(gradients, [weight]))

prediction_after = weight * feature
loss_after = tf.square(prediction_after - target)

print(f"TensorFlow {tf.__version__}")
print(f"dy/dx at x=3.0: {float(dy_dx.numpy()):.2f}")
print(f"weight before: {weight_before:.2f}")
print(f"loss before: {loss_before:.2f}")
print(f"gradient for weight: {float(gradients[0].numpy()):.2f}")
print(f"weight after: {float(weight.numpy()):.2f}")
print(f"loss after: {float(loss_after.numpy()):.2f}")
print(f"gradient connected: {gradients[0] is not None}")