cicada ML.py

import os
import pandas as pd
import numpy as np
import networkx as nx
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import random
import numpy as np
import matplotlib.pyplot as plt
import numpy as np
from matplotlib import pyplot
from math import cos, sin, atan
import numpy as np
from math import exp
from random import seed
from random import random
import gym
import tensorflow as tf
from tensorflow.keras import layers
import numpy as np
import matplotlib.pyplot as plt
import torch 
import sklearn
# Requests allows us to make HTTP requests which we will use to get data fro
import requests
# Pandas is a software libray written for the python programming language f
import pandas as pd
# NumPy is a library for the python programming language, adding support for
import numpy as np
# Datetime is a library that allows us to represent dates
import datetime
# Setting this option will print all collumns of a dataframe 
pd.set_option('display.max_columns', None)
# Setting this  option will print all of the data in a feature
pd.set_option('display.max_columns', None)

flifht_url="https://github.com/ChineseGLUE/ChineseGLUE.git"

response = requests.get(flifht_url)

response.content

data=response.json
data

# Use json_normalize meethod to convert the json result into a dataframe
data = pd.json_normalize

zip_file = keras.utils.get_file(
    fname="cora.tgz",
    origin="https://linqs-data.soe.ucsc.edu/public/lbc/cora.tgz",
    extract=True,
)
data_dir = os.path.join(os.path.dirname(zip_file), "cora")

zip_file = keras.utils.get_file(
    fname="cora.tgz",
    origin="https://github.com/minimaxir/ml-data-generator.git",
    extract=True,
)
data_dir = os.path.join(os.path.dirname(zip_file), "cora")

zip_file = keras.utils.get_file(
    fname="cora.tgz",
    origin="https://github.com/WenjieDu/TSDB.git",
    extract=True,
)
data_dir = os.path.join(os.path.dirname(zip_file), "cora")

citations = pd.read_csv(
    os.path.join(data_dir, "cora.cites"),
    sep="\t",
    header=None,
    names=["target", "source"],
)
print("Citations shape:", citations.shape)

citations.sample(frac=1).head()

column_names = ["paper_id"] + [f"term_{idx}" for idx in range(1433)] + ["subject"]
papers = pd.read_csv(
    os.path.join(data_dir, "cora.content"), sep="\t", header=None, names=column_names,
)
print("Papers shape:", papers.shape)

print(papers.sample(5).T)

print(papers.subject.value_counts())

class_values = sorted(papers["subject"].unique())
class_idx = {name: id for id, name in enumerate(class_values)}
paper_idx = {name: idx for idx, name in enumerate(sorted(papers["paper_id"].unique()))}

papers["paper_id"] = papers["paper_id"].apply(lambda name: paper_idx[name])
citations["source"] = citations["source"].apply(lambda name: paper_idx[name])
citations["target"] = citations["target"].apply(lambda name: paper_idx[name])
papers["subject"] = papers["subject"].apply(lambda value: class_idx[value])

plt.figure(figsize=(10, 10))
colors = papers["subject"].tolist()
cora_graph = nx.from_pandas_edgelist(citations.sample(n=1500))
subjects = list(papers[papers["paper_id"].isin(list(cora_graph.nodes))]["subject"])
nx.draw_spring(cora_graph, node_size=15, node_color=subjects)

train_data, test_data = [], []

for _, group_data in papers.groupby("subject"):
    # Select around 50% of the dataset for training.
    random_selection = np.random.rand(len(group_data.index)) <= 0.5
    train_data.append(group_data[random_selection])
    test_data.append(group_data[~random_selection])

train_data = pd.concat(train_data).sample(frac=1)
test_data = pd.concat(test_data).sample(frac=1)

print("Train data shape:", train_data.shape)
print("Test data shape:", test_data.shape)

hidden_units = [32, 32]
learning_rate = 0.01
dropout_rate = 0.5
num_epochs = 300
batch_size = 256

# Initialize a network
def initialize_network(n_inputs, n_hidden, n_outputs):
	network = list()
	hidden_layer = [{'weights':[random() for i in range(n_inputs + 1)]} for i in range(n_hidden)]
	network.append(hidden_layer)
	output_layer = [{'weights':[random() for i in range(n_hidden + 1)]} for i in range(n_outputs)]
	network.append(output_layer)
	return network

plt.style.use('seaborn')
plt.figure(figsize=(8,4))
def SigmoidBinary(t):
    return 1/(1+np.exp(-t))
t = np.linspace(-5, 5)
plt.plot(t, SigmoidBinary(t))
plt.title('Binary Sigmoid Activation Function')
plt.show()

class Neuron():
    def __init__(self, x, y):
        self.x = x
        self.y = y

    def draw(self):
        circle = pyplot.Circle((self.x, self.y), radius=neuron_radius, fill=False)
        pyplot.gca().add_patch(circle)


class Layer():
    def __init__(self, network, number_of_neurons, weights):
        self.previous_layer = self.__get_previous_layer(network)
        self.y = self.__calculate_layer_y_position()
        self.neurons = self.__intialise_neurons(number_of_neurons)
        self.weights = weights

    def __intialise_neurons(self, number_of_neurons):
        neurons = []
        x = self.__calculate_left_margin_so_layer_is_centered(number_of_neurons)
        for iteration in range(number_of_neurons):
            neuron = Neuron(x, self.y)
            neurons.append(neuron)
            x += horizontal_distance_between_neurons
        return neurons

    def __calculate_left_margin_so_layer_is_centered(self, number_of_neurons):
        return horizontal_distance_between_neurons * (number_of_neurons_in_widest_layer - number_of_neurons) / 2

    def __calculate_layer_y_position(self):
        if self.previous_layer:
            return self.previous_layer.y + vertical_distance_between_layers
        else:
            return 0

    def __get_previous_layer(self, network):
        if len(network.layers) > 0:
            return network.layers[-1]
        else:
            return None

    def __line_between_two_neurons(self, neuron1, neuron2, linewidth):
        angle = atan((neuron2.x - neuron1.x) / float(neuron2.y - neuron1.y))
        x_adjustment = neuron_radius * sin(angle)
        y_adjustment = neuron_radius * cos(angle)
        line_x_data = (neuron1.x - x_adjustment, neuron2.x + x_adjustment)
        line_y_data = (neuron1.y - y_adjustment, neuron2.y + y_adjustment)
        line = pyplot.Line2D(line_x_data, line_y_data, linewidth=linewidth)
        pyplot.gca().add_line(line)

    def draw(self):
        for this_layer_neuron_index in range(len(self.neurons)):
            neuron = self.neurons[this_layer_neuron_index]
            neuron.draw()
            if self.previous_layer:
                for previous_layer_neuron_index in range(len(self.previous_layer.neurons)):
                    previous_layer_neuron = self.previous_layer.neurons[previous_layer_neuron_index]
                    weight = self.previous_layer.weights[this_layer_neuron_index, previous_layer_neuron_index]
                    self.__line_between_two_neurons(neuron, previous_layer_neuron, weight)


class NeuralNetwork():
    def __init__(self):
        self.layers = []

    def add_layer(self, number_of_neurons, weights=None):
        layer = Layer(self, number_of_neurons, weights)
        self.layers.append(layer)

    def draw(self):
        for layer in self.layers:
            layer.draw()
        pyplot.axis('scaled')
        pyplot.show()


if __name__ == "__main__":
    vertical_distance_between_layers = 20
    horizontal_distance_between_neurons = 3
    neuron_radius = 0.5
    number_of_neurons_in_widest_layer = 20
    network = NeuralNetwork()
    # weights to convert from 100 outputs to 100 (decimal digits to their binary representation)
    weights1 = np.array([\
                         [0,0,0,0,0,0,0,0,1,1],\
                         [0,0,0,0,1,1,1,1,0,0],\
                         [0,0,1,1,0,0,1,1,0,0],\
                         [0,1,0,1,0,1,0,1,0,1]])
    network.add_layer(10, weights1)
    network.add_layer(4)
    network.draw()

from projectq import MainEngine
from projectq.ops import All, CNOT, H, Measure, X, Z

quantum_engine = MainEngine()


def create_bell_pair(quantum_engine):
    # Newly created Qubits are in the base state of 0,
    qubit_one = quantum_engine.allocate_qubit()
    qubit_two = quantum_engine.allocate_qubit()
    H | qubit_one
    # Measure | qubit_one
    # qubit_one_val = int(qubit_one)

    CNOT | (qubit_one, qubit_two)
    # Measure | qubit_two
    # cnot_val = int(qubit_two)

    return qubit_one, qubit_two

def create_message(quantum_engine='', qubit_one='', message_value=0):
    qubit_to_send = quantum_engine.allocate_qubit()
    if message_value == 1:
        '''
        setting the qubit to positive if message_value is 1
        by flipping the base state with a Pauli-X gate.
        '''
        X | qubit_to_send

    # entangle the original qubit with the message qubit
    CNOT | (qubit_to_send, qubit_one)

    '''
    1 - Put the message qubit in superposition
    2 - Measure out the two values to get the classical bit value
        by collapsing the state.
    '''
    H | qubit_to_send
    Measure | qubit_to_send
    Measure | qubit_one

    # The qubits are now turned into normal bits we can send through classical channels
    classical_encoded_message = [int(qubit_to_send), int(qubit_one)]

    return classical_encoded_message


def message_reciever(quantum_engine, message, qubit_two):
    '''
    Pauli-X and/or Pauli-Z gates are applied to the Qubit,
    conditionally on the values in the message.
    '''
    if message[1] == 1:
        X | qubit_two
    if message[0] == 1:
        Z | qubit_two

    '''
    Measuring the Qubit and collapsing the state down to either 1 or 0
    '''
    Measure | qubit_two

    quantum_engine.flush()

    received_bit = int(qubit_two)
    return received_bit


qubit_one, qubit_two = create_bell_pair(quantum_engine)
classical_encoded_message = create_message(
    quantum_engine=quantum_engine, qubit_one=qubit_one, message_value=0)

print('classical_encoded_message = ', classical_encoded_message)

received_bit = message_reciever(
    quantum_engine=quantum_engine, message=classical_encoded_message, qubit_two=qubit_two)

print('received_bit = ', str(received_bit))


def send_receive(bit=0, quantum_engine=''):
    # Create bell pair
    qubit_one, qubit_two = create_bell_pair(quantum_engine)
    # entangle the bit with the first qubit
    classical_encoded_message = create_message(
        quantum_engine=quantum_engine, qubit_one=qubit_one, message_value=bit)
    # print('send_bit = ', classical_encoded_message)
    # Teleport the bit and return it back
    received_bit = message_reciever(
        quantum_engine, classical_encoded_message, qubit_two)
    # print('received_bit = ', received_bit)
    return received_bit


message = 'HelloWorld'
binary_encoded_message = [bin(ord(x))[2:].zfill(8) for x in message]
print('Message to send: ', message)
print('Binary message to send: ', binary_encoded_message)

received_bytes_list = []
for letter in binary_encoded_message:
    received_bits = ''
    for bit in letter:
        received_bits = received_bits + \
            str(send_receive(int(bit), quantum_engine))
    received_bytes_list.append(received_bits)

binary_to_string = ''.join([chr(int(x, 2)) for x in received_bytes_list])
print('Received Binary message: ', received_bytes_list)
print('Received message: ', binary_to_string)

quantum_engine.flush()


# bin_mess = 'a'
# print(ord(bin_mess))
# print(bin(ord(bin_mess)))
# print(bin(ord(bin_mess))[2:])
# print(bin(ord(bin_mess))[2:].zfill(8))

# bin_result = bin(ord(bin_mess))[2:].zfill(8)
# print(chr(int(bin_result, 2)))

import numpy as np
import matplotlib.pyplot as plt
from qutip import *
# Generate a random quantum state vector
num_qubits = 1  # Number of qubits
state = rand_ket(2 ** num_qubits)

# Visualize the state using a 3D plot
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
sphere = Bloch(axes=ax)
sphere.add_states(state)
sphere.show()
import numpy as np
import matplotlib.pyplot as plt
from qutip import *
# Generate a random quantum state vector
num_qubits = 1  # Number of qubits
state = rand_ket(2 ** num_qubits)

# Alternatively, visualize the state using a Bloch sphere representation
bloch = Bloch()
bloch.add_states(state)
bloch.show()

# Show the plots
plt.show()

from random import seed
from random import random

# Initialize a network
def initialize_network(n_inputs, n_hidden, n_outputs):
	network = list()
	hidden_layer = [{'weights':[random() for i in range(n_inputs + 1)]} for i in range(n_hidden)]
	network.append(hidden_layer)
	output_layer = [{'weights':[random() for i in range(n_hidden + 1)]} for i in range(n_outputs)]
	network.append(output_layer)
	return network

seed(1)
network = initialize_network(2, 1, 2)
for layer in network:
	print(layer)

# Calculate neuron activation for an input
def activate(weights, inputs):
	activation = weights[-1]
	for i in range(len(weights)-1):
		activation += weights[i] * inputs[i]
	return activation

# Transfer neuron activation
def transfer(activation):
	return 1.0 / (1.0 + exp(-activation))

# Forward propagate input to a network output
def forward_propagate(network, row):
	inputs = row
	for layer in network:
		new_inputs = []
		for neuron in layer:
			activation = activate(neuron['weights'], inputs)
			neuron['output'] = transfer(activation)
			new_inputs.append(neuron['output'])
		inputs = new_inputs
	return inputs

from math import exp

# Calculate neuron activation for an input
def activate(weights, inputs):
	activation = weights[-1]
	for i in range(len(weights)-1):
		activation += weights[i] * inputs[i]
	return activation

# Transfer neuron activation
def transfer(activation):
	return 1.0 / (1.0 + exp(-activation))

# Forward propagate input to a network output
def forward_propagate(network, row):
	inputs = row
	for layer in network:
		new_inputs = []
		for neuron in layer:
			activation = activate(neuron['weights'], inputs)
			neuron['output'] = transfer(activation)
			new_inputs.append(neuron['output'])
		inputs = new_inputs
	return inputs

# test forward propagation
network = [[{'weights': [0.13436424411240122, 0.8474337369372327, 0.763774618976614]}],
		[{'weights': [0.2550690257394217, 0.49543508709194095]}, {'weights': [0.4494910647887381, 0.651592972722763]}]]
row = [1, 0, None]
output = forward_propagate(network, row)
print(output)

# Calculate the derivative of an neuron output
def transfer_derivative(output):
	return output * (1.0 - output)

# Backpropagate error and store in neurons
def backward_propagate_error(network, expected):
	for i in reversed(range(len(network))):
		layer = network[i]
		errors = list()
		if i != len(network)-1:
			for j in range(len(layer)):
				error = 0.0
				for neuron in network[i + 1]:
					error += (neuron['weights'][j] * neuron['delta'])
				errors.append(error)
		else:
			for j in range(len(layer)):
				neuron = layer[j]
				errors.append(neuron['output'] - expected[j])
		for j in range(len(layer)):
			neuron = layer[j]
			neuron['delta'] = errors[j] * transfer_derivative(neuron['output'])

# Calculate the derivative of an neuron output
def transfer_derivative(output):
	return output * (1.0 - output)

# Backpropagate error and store in neurons
def backward_propagate_error(network, expected):
	for i in reversed(range(len(network))):
		layer = network[i]
		errors = list()
		if i != len(network)-1:
			for j in range(len(layer)):
				error = 0.0
				for neuron in network[i + 1]:
					error += (neuron['weights'][j] * neuron['delta'])
				errors.append(error)
		else:
			for j in range(len(layer)):
				neuron = layer[j]
				errors.append(neuron['output'] - expected[j])
		for j in range(len(layer)):
			neuron = layer[j]
			neuron['delta'] = errors[j] * transfer_derivative(neuron['output'])

# test backpropagation of error
network = [[{'output': 0.7105668883115941, 'weights': [0.13436424411240122, 0.8474337369372327, 0.763774618976614]}],
		[{'output': 0.6213859615555266, 'weights': [0.2550690257394217, 0.49543508709194095]}, {'output': 0.6573693455986976, 'weights': [0.4494910647887381, 0.651592972722763]}]]
expected = [0, 1]
backward_propagate_error(network, expected)
for layer in network:
	print(layer)

# Update network weights with error
def update_weights(network, row, l_rate):
	for i in range(len(network)):
		inputs = row[:-1]
		if i != 0:
			inputs = [neuron['output'] for neuron in network[i - 1]]
		for neuron in network[i]:
			for j in range(len(inputs)):
				neuron['weights'][j] -= l_rate * neuron['delta'] * inputs[j]
			neuron['weights'][-1] -= l_rate * neuron['delta']

# Train a network for a fixed number of epochs
def train_network(network, train, l_rate, n_epoch, n_outputs):
	for epoch in range(n_epoch):
		sum_error = 0
		for row in train:
			outputs = forward_propagate(network, row)
			expected = [0 for i in range(n_outputs)]
			expected[row[-1]] = 1
			sum_error += sum([(expected[i]-outputs[i])**2 for i in range(len(expected))])
			backward_propagate_error(network, expected)
			update_weights(network, row, l_rate)
		print('>epoch=%d, lrate=%.3f, error=%.3f' % (epoch, l_rate, sum_error))


# Initialize a network
def initialize_network(n_inputs, n_hidden, n_outputs):
	network = list()
	hidden_layer = [{'weights':[random() for i in range(n_inputs + 1)]} for i in range(n_hidden)]
	network.append(hidden_layer)
	output_layer = [{'weights':[random() for i in range(n_hidden + 1)]} for i in range(n_outputs)]
	network.append(output_layer)
	return network

# Calculate neuron activation for an input
def activate(weights, inputs):
	activation = weights[-1]
	for i in range(len(weights)-1):
		activation += weights[i] * inputs[i]
	return activation

# Transfer neuron activation
def transfer(activation):
	return 1.0 / (1.0 + exp(-activation))

# Forward propagate input to a network output
def forward_propagate(network, row):
	inputs = row
	for layer in network:
		new_inputs = []
		for neuron in layer:
			activation = activate(neuron['weights'], inputs)
			neuron['output'] = transfer(activation)
			new_inputs.append(neuron['output'])
		inputs = new_inputs
	return inputs

# Calculate the derivative of an neuron output
def transfer_derivative(output):
	return output * (1.0 - output)

# Backpropagate error and store in neurons
def backward_propagate_error(network, expected):
	for i in reversed(range(len(network))):
		layer = network[i]
		errors = list()
		if i != len(network)-1:
			for j in range(len(layer)):
				error = 0.0
				for neuron in network[i + 1]:
					error += (neuron['weights'][j] * neuron['delta'])
				errors.append(error)
		else:
			for j in range(len(layer)):
				neuron = layer[j]
				errors.append(neuron['output'] - expected[j])
		for j in range(len(layer)):
			neuron = layer[j]
			neuron['delta'] = errors[j] * transfer_derivative(neuron['output'])

# Update network weights with error
def update_weights(network, row, l_rate):
	for i in range(len(network)):
		inputs = row[:-1]
		if i != 0:
			inputs = [neuron['output'] for neuron in network[i - 1]]
		for neuron in network[i]:
			for j in range(len(inputs)):
				neuron['weights'][j] -= l_rate * neuron['delta'] * inputs[j]
			neuron['weights'][-1] -= l_rate * neuron['delta']

# Train a network for a fixed number of epochs
def train_network(network, train, l_rate, n_epoch, n_outputs):
	for epoch in range(n_epoch):
		sum_error = 0
		for row in train:
			outputs = forward_propagate(network, row)
			expected = [0 for i in range(n_outputs)]
			expected[row[-1]] = 1
			sum_error += sum([(expected[i]-outputs[i])**2 for i in range(len(expected))])
			backward_propagate_error(network, expected)
			update_weights(network, row, l_rate)
		print('>epoch=%d, lrate=%.3f, error=%.3f' % (epoch, l_rate, sum_error))

# Test training backprop algorithm
seed(1)
dataset = [[2.7810836,2.550537003,0],
	[1.465489372,2.362125076,0],
	[3.396561688,4.400293529,0],
	[1.38807019,1.850220317,0],
	[3.06407232,3.005305973,0],
	[7.627531214,2.759262235,1],
	[5.332441248,2.088626775,1],
	[6.922596716,1.77106367,1],
	[8.675418651,-0.242068655,1],
	[7.673756466,3.508563011,1]]
n_inputs = len(dataset[0]) - 1
n_outputs = len(set([row[-1] for row in dataset]))
network = initialize_network(n_inputs, 2, n_outputs)
train_network(network, dataset, 0.5, 200000, n_outputs)
for layer in network:
	print(layer)

problem = "Pendulum-v1"
env = gym.make(problem)

num_states = env.observation_space.shape[0]
print("Size of State Space ->  {}".format(num_states))
num_actions = env.action_space.shape[0]
print("Size of Action Space ->  {}".format(num_actions))

upper_bound = env.action_space.high[0]
lower_bound = env.action_space.low[0]

print("Max Value of Action ->  {}".format(upper_bound))
print("Min Value of Action ->  {}".format(lower_bound))

class OUActionNoise:
    def __init__(self, mean, std_deviation, theta=0.15, dt=1e-2, x_initial=None):
        self.theta = theta
        self.mean = mean
        self.std_dev = std_deviation
        self.dt = dt
        self.x_initial = x_initial
        self.reset()

    def __call__(self):
        # Formula taken from https://www.wikipedia.org/wiki/Ornstein-Uhlenbeck_process.
        x = (
            self.x_prev
            + self.theta * (self.mean - self.x_prev) * self.dt
            + self.std_dev * np.sqrt(self.dt) * np.random.normal(size=self.mean.shape)
        )
        # Store x into x_prev
        # Makes next noise dependent on current one
        self.x_prev = x
        return x

    def reset(self):
        if self.x_initial is not None:
            self.x_prev = self.x_initial
        else:
            self.x_prev = np.zeros_like(self.mean)

class Buffer:
    def __init__(self, buffer_capacity=100000, batch_size=64):
        # Number of "experiences" to store at max
        self.buffer_capacity = buffer_capacity
        # Num of tuples to train on.
        self.batch_size = batch_size

        # Its tells us num of times record() was called.
        self.buffer_counter = 0

        # Instead of list of tuples as the exp.replay concept go
        # We use different np.arrays for each tuple element
        self.state_buffer = np.zeros((self.buffer_capacity, num_states))
        self.action_buffer = np.zeros((self.buffer_capacity, num_actions))
        self.reward_buffer = np.zeros((self.buffer_capacity, 1))
        self.next_state_buffer = np.zeros((self.buffer_capacity, num_states))

    # Takes (s,a,r,s') obervation tuple as input
    def record(self, obs_tuple):
        # Set index to zero if buffer_capacity is exceeded,
        # replacing old records
        index = self.buffer_counter % self.buffer_capacity

        self.state_buffer[index] = obs_tuple[0]
        self.action_buffer[index] = obs_tuple[1]
        self.reward_buffer[index] = obs_tuple[2]
        self.next_state_buffer[index] = obs_tuple[3]

        self.buffer_counter += 1

    # Eager execution is turned on by default in TensorFlow 2. Decorating with tf.function allows
    # TensorFlow to build a static graph out of the logic and computations in our function.
    # This provides a large speed up for blocks of code that contain many small TensorFlow operations such as this one.
    @tf.function
    def update(
        self, state_batch, action_batch, reward_batch, next_state_batch,
    ):
        # Training and updating Actor & Critic networks.
        # See Pseudo Code.
        with tf.GradientTape() as tape:
            target_actions = target_actor(next_state_batch, training=True)
            y = reward_batch + gamma * target_critic(
                [next_state_batch, target_actions], training=True
            )
            critic_value = critic_model([state_batch, action_batch], training=True)
            critic_loss = tf.math.reduce_mean(tf.math.square(y - critic_value))

        critic_grad = tape.gradient(critic_loss, critic_model.trainable_variables)
        critic_optimizer.apply_gradients(
            zip(critic_grad, critic_model.trainable_variables)
        )

        with tf.GradientTape() as tape:
            actions = actor_model(state_batch, training=True)
            critic_value = critic_model([state_batch, actions], training=True)
            # Used `-value` as we want to maximize the value given
            # by the critic for our actions
            actor_loss = -tf.math.reduce_mean(critic_value)

        actor_grad = tape.gradient(actor_loss, actor_model.trainable_variables)
        actor_optimizer.apply_gradients(
            zip(actor_grad, actor_model.trainable_variables)
        )

    # We compute the loss and update parameters
    def learn(self):
        # Get sampling range
        record_range = min(self.buffer_counter, self.buffer_capacity)
        # Randomly sample indices
        batch_indices = np.random.choice(record_range, self.batch_size)

        # Convert to tensors
        state_batch = tf.convert_to_tensor(self.state_buffer[batch_indices])
        action_batch = tf.convert_to_tensor(self.action_buffer[batch_indices])
        reward_batch = tf.convert_to_tensor(self.reward_buffer[batch_indices])
        reward_batch = tf.cast(reward_batch, dtype=tf.float32)
        next_state_batch = tf.convert_to_tensor(self.next_state_buffer[batch_indices])

        self.update(state_batch, action_batch, reward_batch, next_state_batch)


# This update target parameters slowly
# Based on rate `tau`, which is much less than one.
@tf.function
def update_target(target_weights, weights, tau):
    for (a, b) in zip(target_weights, weights):
        a.assign(b * tau + a * (1 - tau))

def get_actor():
    # Initialize weights between -3e-3 and 3-e3
    last_init = tf.random_uniform_initializer(minval=-0.003, maxval=0.003)

    inputs = layers.Input(shape=(num_states,))
    out = layers.Dense(256, activation="relu")(inputs)
    out = layers.Dense(256, activation="relu")(out)
    outputs = layers.Dense(1, activation="tanh", kernel_initializer=last_init)(out)

    # Our upper bound is 2.0 for Pendulum.
    outputs = outputs * upper_bound
    model = tf.keras.Model(inputs, outputs)
    return model


def get_critic():
    # State as input
    state_input = layers.Input(shape=(num_states))
    state_out = layers.Dense(16, activation="relu")(state_input)
    state_out = layers.Dense(32, activation="relu")(state_out)

    # Action as input
    action_input = layers.Input(shape=(num_actions))
    action_out = layers.Dense(32, activation="relu")(action_input)

    # Both are passed through seperate layer before concatenating
    concat = layers.Concatenate()([state_out, action_out])

    out = layers.Dense(256, activation="relu")(concat)
    out = layers.Dense(256, activation="relu")(out)
    outputs = layers.Dense(1)(out)

    # Outputs single value for give state-action
    model = tf.keras.Model([state_input, action_input], outputs)

    return model

def policy(state, noise_object):
    sampled_actions = tf.squeeze(actor_model(state))
    noise = noise_object()
    # Adding noise to action
    sampled_actions = sampled_actions.numpy() + noise

    # We make sure action is within bounds
    legal_action = np.clip(sampled_actions, lower_bound, upper_bound)

    return [np.squeeze(legal_action)]

std_dev = 0.2
ou_noise = OUActionNoise(mean=np.zeros(1), std_deviation=float(std_dev) * np.ones(1))

actor_model = get_actor()
critic_model = get_critic()

target_actor = get_actor()
target_critic = get_critic()

# Making the weights equal initially
target_actor.set_weights(actor_model.get_weights())
target_critic.set_weights(critic_model.get_weights())

# Learning rate for actor-critic models
critic_lr = 0.002
actor_lr = 0.001

critic_optimizer = tf.keras.optimizers.Adam(critic_lr)
actor_optimizer = tf.keras.optimizers.Adam(actor_lr)

total_episodes = 100
# Discount factor for future rewards
gamma = 0.99
# Used to update target networks
tau = 0.005

buffer = Buffer(50000, 64)

# Make a prediction with a network
def predict(network, row):
	outputs = forward_propagate(network, row)
	return outputs.index(max(outputs))

from math import exp

# Calculate neuron activation for an input
def activate(weights, inputs):
	activation = weights[-1]
	for i in range(len(weights)-1):
		activation += weights[i] * inputs[i]
	return activation

# Transfer neuron activation
def transfer(activation):
	return 1.0 / (1.0 + exp(-activation))

# Forward propagate input to a network output
def forward_propagate(network, row):
	inputs = row
	for layer in network:
		new_inputs = []
		for neuron in layer:
			activation = activate(neuron['weights'], inputs)
			neuron['output'] = transfer(activation)
			new_inputs.append(neuron['output'])
		inputs = new_inputs
	return inputs

# Make a prediction with a network
def predict(network, row):
	outputs = forward_propagate(network, row)
	return outputs.index(max(outputs))

# Test making predictions with the network
dataset = [[2.7810836,2.550537003,0],
	[1.465489372,2.362125076,0],
	[3.396561688,4.400293529,0],
	[1.38807019,1.850220317,0],
	[3.06407232,3.005305973,0],
	[7.627531214,2.759262235,1],
	[5.332441248,2.088626775,1],
	[6.922596716,1.77106367,1],
	[8.675418651,-0.242068655,1],
	[7.673756466,3.508563011,1]]
network = [[{'weights': [-1.482313569067226, 1.8308790073202204, 1.078381922048799]}, {'weights': [0.23244990332399884, 0.3621998343835864, 0.40289821191094327]}],
	[{'weights': [2.5001872433501404, 0.7887233511355132, -1.1026649757805829]}, {'weights': [-2.429350576245497, 0.8357651039198697, 1.0699217181280656]}]]
for row in dataset:
	prediction = predict(network, row)
	print('Expected=%d, Got=%d' % (row[-1], prediction))

def run_experiment(model, x_train, y_train):
    # Compile the model.
    model.compile(
        optimizer=keras.optimizers.Adam(learning_rate),
        loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
        metrics=[keras.metrics.SparseCategoricalAccuracy(name="acc")],
    )
    # Create an early stopping callback.
    early_stopping = keras.callbacks.EarlyStopping(
        monitor="val_acc", patience=50, restore_best_weights=True
    )
    # Fit the model.
    history = model.fit(
        x=x_train,
        y=y_train,
        epochs=num_epochs,
        batch_size=batch_size,
        validation_split=0.15,
        callbacks=[early_stopping],
    )

    return history

def display_learning_curves(history):
    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15, 5))

    ax1.plot(history.history["loss"])
    ax1.plot(history.history["val_loss"])
    ax1.legend(["train", "test"], loc="upper right")
    ax1.set_xlabel("Epochs")
    ax1.set_ylabel("Loss")

    ax2.plot(history.history["acc"])
    ax2.plot(history.history["val_acc"])
    ax2.legend(["train", "test"], loc="upper right")
    ax2.set_xlabel("Epochs")
    ax2.set_ylabel("Accuracy")
    plt.show()

def create_ffn(hidden_units, dropout_rate, name=None):
    fnn_layers = []

    for units in hidden_units:
        fnn_layers.append(layers.BatchNormalization())
        fnn_layers.append(layers.Dropout(dropout_rate))
        fnn_layers.append(layers.Dense(units, activation=tf.nn.gelu))

    return keras.Sequential(fnn_layers, name=name)

feature_names = list(set(papers.columns) - {"paper_id", "subject"})
num_features = len(feature_names)
num_classes = len(class_idx)

# Create train and test features as a numpy array.
x_train = train_data[feature_names].to_numpy()
x_test = test_data[feature_names].to_numpy()
# Create train and test targets as a numpy array.
y_train = train_data["subject"]
y_test = test_data["subject"]

def create_baseline_model(hidden_units, num_classes, dropout_rate=0.2):
    inputs = layers.Input(shape=(num_features,), name="input_features")
    x = create_ffn(hidden_units, dropout_rate, name=f"ffn_block1")(inputs)
    for block_idx in range(4):
        # Create an FFN block.
        x1 = create_ffn(hidden_units, dropout_rate, name=f"ffn_block{block_idx + 2}")(x)
        # Add skip connection.
        x = layers.Add(name=f"skip_connection{block_idx + 2}")([x, x1])
    # Compute logits.
    logits = layers.Dense(num_classes, name="logits")(x)
    # Create the model.
    return keras.Model(inputs=inputs, outputs=logits, name="baseline")


baseline_model = create_baseline_model(hidden_units, num_classes, dropout_rate)
baseline_model.summary()

history = run_experiment(baseline_model, x_train, y_train)

display_learning_curves(history)

_, test_accuracy = baseline_model.evaluate(x=x_test, y=y_test, verbose=0)
print(f"Test accuracy: {round(test_accuracy * 100, 2)}%")

def generate_random_instances(num_instances):
    token_probability = x_train.mean(axis=0)
    instances = []
    for _ in range(num_instances):
        probabilities = np.random.uniform(size=len(token_probability))
        instance = (probabilities <= token_probability).astype(int)
        instances.append(instance)

    return np.array(instances)


def display_class_probabilities(probabilities):
    for instance_idx, probs in enumerate(probabilities):
        print(f"Instance {instance_idx + 1}:")
        for class_idx, prob in enumerate(probs):
            print(f"- {class_values[class_idx]}: {round(prob * 100, 2)}%")

new_instances = generate_random_instances(num_classes)
logits = baseline_model.predict(new_instances)
probabilities = keras.activations.softmax(tf.convert_to_tensor(logits)).numpy()
display_class_probabilities(probabilities)

# Create an edges array (sparse adjacency matrix) of shape [2, num_edges].
edges = citations[["source", "target"]].to_numpy().T
# Create an edge weights array of ones.
edge_weights = tf.ones(shape=edges.shape[1])
# Create a node features array of shape [num_nodes, num_features].
node_features = tf.cast(
    papers.sort_values("paper_id")[feature_names].to_numpy(), dtype=tf.dtypes.float32
)
# Create graph info tuple with node_features, edges, and edge_weights.
graph_info = (node_features, edges, edge_weights)

print("Edges shape:", edges.shape)
print("Nodes shape:", node_features.shape)

def create_gru(hidden_units, dropout_rate):
    inputs = keras.layers.Input(shape=(2, hidden_units[0]))
    x = inputs
    for units in hidden_units:
      x = layers.GRU(
          units=units,
          activation="tanh",
          recurrent_activation="sigmoid",
          return_sequences=True,
          dropout=dropout_rate,
          return_state=False,
          recurrent_dropout=dropout_rate,
      )(x)
    return keras.Model(inputs=inputs, outputs=x)


class GraphConvLayer(layers.Layer):
    def __init__(
        self,
        hidden_units,
        dropout_rate=0.2,
        aggregation_type="mean",
        combination_type="concat",
        normalize=False,
        *args,
        **kwargs,
    ):
        super().__init__(*args, **kwargs)

        self.aggregation_type = aggregation_type
        self.combination_type = combination_type
        self.normalize = normalize

        self.ffn_prepare = create_ffn(hidden_units, dropout_rate)
        if self.combination_type == "gru":
            self.update_fn = create_gru(hidden_units, dropout_rate)

    def prepare(self, node_repesentations, weights=None):
        # node_repesentations shape is [num_edges, embedding_dim].
        messages = self.ffn_prepare(node_repesentations)
        if weights is not None:
            messages = messages * tf.expand_dims(weights, -1)
        return messages

    def aggregate(self, node_indices, neighbour_messages, node_repesentations):
        # node_indices shape is [num_edges].
        # neighbour_messages shape: [num_edges, representation_dim].
        # node_repesentations shape is [num_nodes, representation_dim]
        num_nodes = node_repesentations.shape[0]
        if self.aggregation_type == "sum":
            aggregated_message = tf.math.unsorted_segment_sum(
                neighbour_messages, node_indices, num_segments=num_nodes
            )
        elif self.aggregation_type == "mean":
            aggregated_message = tf.math.unsorted_segment_mean(
                neighbour_messages, node_indices, num_segments=num_nodes
            )
        elif self.aggregation_type == "max":
            aggregated_message = tf.math.unsorted_segment_max(
                neighbour_messages, node_indices, num_segments=num_nodes
            )
        else:
            raise ValueError(f"Invalid aggregation type: {self.aggregation_type}.")

        return aggregated_message

    def update(self, node_repesentations, aggregated_messages):
        # node_repesentations shape is [num_nodes, representation_dim].
        # aggregated_messages shape is [num_nodes, representation_dim].
        if self.combination_type == "gru":
            # Create a sequence of two elements for the GRU layer.
            h = tf.stack([node_repesentations, aggregated_messages], axis=1)
        elif self.combination_type == "concat":
            # Concatenate the node_repesentations and aggregated_messages.
            h = tf.concat([node_repesentations, aggregated_messages], axis=1)
        elif self.combination_type == "add":
            # Add node_repesentations and aggregated_messages.
            h = node_repesentations + aggregated_messages
        else:
            raise ValueError(f"Invalid combination type: {self.combination_type}.")

        # Apply the processing function.
        node_embeddings = self.update_fn(h)
        if self.combination_type == "gru":
            node_embeddings = tf.unstack(node_embeddings, axis=1)[-1]

        if self.normalize:
            node_embeddings = tf.nn.l2_normalize(node_embeddings, axis=-1)
        return node_embeddings

    def call(self, inputs):
        """Process the inputs to produce the node_embeddings.

        inputs: a tuple of three elements: node_repesentations, edges, edge_weights.
        Returns: node_embeddings of shape [num_nodes, representation_dim].
        """

        node_repesentations, edges, edge_weights = inputs
        # Get node_indices (source) and neighbour_indices (target) from edges.
        node_indices, neighbour_indices = edges[0], edges[1]
        # neighbour_repesentations shape is [num_edges, representation_dim].
        neighbour_repesentations = tf.gather(node_repesentations, neighbour_indices)

        # Prepare the messages of the neighbours.
        neighbour_messages = self.prepare(neighbour_repesentations, edge_weights)
        # Aggregate the neighbour messages.
        aggregated_messages = self.aggregate(
            node_indices, neighbour_messages, node_repesentations
        )
        # Update the node embedding with the neighbour messages.
        return self.update(node_repesentations, aggregated_messages)