neural_network_scratch.py

neural_network_scratch.py

import numpy as np, sys
import pandas as pd

# Ler o arquivo CSV
df = pd.read_csv('diabetes.csv')

# Extrair os dados para feature_set e labels
feature_set = feature_set = df.drop('diabetico', axis=1).values
labels = df['diabetico'].values.reshape(-1, 1)

np.random.seed(42)
weights = np.random.rand(3,1)
bias = np.random.rand(1)
lr = 0.05

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


def sigmoid_der(x):
    return sigmoid(x)*(1-sigmoid(x))

for epoch in range(20000):
    inputs = feature_set

    # feedforward passo 1
    XW = np.dot(feature_set, weights) + bias

    #feedforward passo 2
    z = sigmoid(XW)

    # backpropagation passo 1
    error = z - labels

    # backpropagation passo 2
    dcost_dpred = error
    dpred_dz = sigmoid_der(z)

    z_delta = dcost_dpred * dpred_dz

    inputs = feature_set.T
    weights -= lr * np.dot(inputs, z_delta)

    for num in z_delta:
        bias -= lr * num
        
single_point = np.array([0,1,0]) #np.array([1,0,0])
result = sigmoid(np.dot(single_point, weights) + bias)
print(result)

# Limiar para converter a saída da rede neural em 0 ou 1
limiar = 0.5

# Verificar se a previsão é maior que o limiar
resultado = 1 if result[0] > limiar else 0

print(resultado)