New solution for the problem in the video: "Make our poor calssification model work for a regression dataset"

[mmaksi]

The provided solution in the course for the mentioned video section 2: Neural Network Calssiifcation in TensorFlow doesn't work for some reason. So I figured out this solution instead:

# Set random seed
tf.random.set_seed(42)

# Create some regression data
X_regression = np.arange(0, 1000, 5)
y_regression = np.arange(100, 1100, 5) # y = X + 100

# Split it into training and test sets
X_reg_train = X_regression[:150]
X_reg_test = X_regression[150:]
y_reg_train = y_regression[:150]
y_reg_test = y_regression[150:]

# Create a simple neural network model
model = tf.keras.Sequential([
    tf.keras.layers.Input(shape=(1,)),  # Input layer with 1 feature
    tf.keras.layers.Dense(64, activation='relu'),  # Hidden layer with 64 units and ReLU activation
    tf.keras.layers.Dense(1)  # Output layer with 1 unit (regression)
])

# Compile the model
model.compile(optimizer='adam', loss='mean_squared_error')

# Train the model on the training data
model.fit(X_reg_train, y_reg_train, epochs=50, batch_size=32, verbose=2)