import numpy as np
from sklearn.datasets import make_blobs

def make_blocks(n_samples=20, centers=2, n_features=3):
    x, y = make_blobs(n_samples=n_samples, centers=centers, n_features=n_features, random_state=42)
    y = y[:, np.newaxis]  # Adding a new axis to make it compatible with the network architecture
    return x, y

def sigmoid(x):
    return 1 / (1 + np.exp(-x))

def sigmoid_derivative(x):
    return x * (1 - x)

input_neurons = 3
hidden_neurons = 3
output_neurons = 1

np.random.seed(42)

weights_input_hidden = np.random.rand(input_neurons, hidden_neurons)
bias_hidden = np.zeros((1, hidden_neurons))

weights_hidden_output = np.random.rand(hidden_neurons, output_neurons)
bias_output = np.zeros((1, output_neurons))

learning_rate = 0.01
epochs = 100

x, y = make_blocks(n_samples=20, centers=2, n_features=3)

for epoch in range(epochs):
    hidden_layer_input = np.dot(x, weights_input_hidden) + bias_hidden
    hidden_layer_output = sigmoid(hidden_layer_input)

    output_layer_input = np.dot(hidden_layer_output, weights_hidden_output) + bias_output
    predicted_output = sigmoid(output_layer_input)

    error = y - predicted_output

    output_error = error * sigmoid_derivative(predicted_output)
    hidden_layer_error = output_error.dot(weights_hidden_output.T) * sigmoid_derivative(hidden_layer_output)

    weights_hidden_output += hidden_layer_output.T.dot(output_error) * learning_rate
    bias_output += np.sum(output_error, axis=0, keepdims=True) * learning_rate

    weights_input_hidden += x.T.dot(hidden_layer_error) * learning_rate
    bias_hidden += np.sum(hidden_layer_error, axis=0, keepdims=True) * learning_rate

hidden_layer_input = np.dot(x, weights_input_hidden) + bias_hidden
hidden_layer_output = sigmoid(hidden_layer_input)

output_layer_input = np.dot(hidden_layer_output, weights_hidden_output) + bias_output
predicted_output = sigmoid(output_layer_input)

predicted_output = np.round(predicted_output)

accuracy = np.mean(predicted_output == y)

print("Predicted Output:")
print(predicted_output)
print("\nTrue Output:")
print(y)
print("\nAccuracy: {:.2%}".format(accuracy))