import numpy as np
from sklearn import datasets
from sklearn import preprocessing
from sklearn.utils import shuffle
from matplotlib import pyplot as plt

import math

np.set_printoptions(threshold=np.inf)


# load dataset
iris = datasets.load_iris()
X, labels = iris.data, iris.target
X, labels = shuffle(X, labels)
onehot_encoder = preprocessing.OneHotEncoder(sparse=False)
labels = labels.reshape(-1, 1)

# normalize input data
X = 2.0 * X / np.max(X) - 1.0
Y = onehot_encoder.fit_transform(labels)

# insert activation function and derivative here

# randomly initialize weights with mean 0


losses = []
for epoch in range(100):
    for j in range(len(X)):
        # forward pass

        # error
        error = ...

        # backward pass

        # weights update

    losses.append(np.sum(np.abs(error)))

plt.plot(losses)
plt.show()