#!/usr/bin/python3

import torch
import pandas as pd
from sklearn.model_selection import train_test_split


data = pd.read_csv('iris.data',sep = ',', header = None)
data[5] = data[4].apply(lambda x: 1 if x == 'Iris-versicolor' else 0)


x = torch.tensor(data[[0,1,2,3]].values, dtype=torch.float)
y = torch.tensor(data[5], dtype=torch.float)

y = y.reshape(100,1)

X_train, X_test, y_train, y_test = train_test_split(x,y, random_state = 42)

class Network(torch.nn.Module):

    def __init__(self):
        super(Network, self).__init__()
        self.fc = torch.nn.Linear(4,1)

    def forward(self,x):
        x = self.fc(x)
        x = torch.nn.functional.sigmoid(x)

        return x

network = Network()
optimizer = torch.optim.SGD(network.parameters(), lr=0.002)
criterion = torch.nn.BCELoss()

samples_in_batch = 5

for epoch in range(3000):

    network.train()
    for i in range(0,len(X_train),samples_in_batch):
        batch_x = X_train[i:i+samples_in_batch]
        batch_y = y_train[i:i+samples_in_batch]
        optimizer.zero_grad()
        ypredicted = network(batch_x)

        loss = criterion(ypredicted,batch_y)

        loss.backward()
        optimizer.step()


    network.eval()
    predicted_correct = 0
    loss_sum = 0
    for i in range(0,len(X_test),samples_in_batch):
        batch_x = X_test[i:i+samples_in_batch]
        batch_y = y_test[i:i+samples_in_batch]
        optimizer.zero_grad()
        ypredicted = network(batch_x)

        loss_sum += criterion(ypredicted,batch_y)

        predicted_correct +=  sum(((ypredicted > 0.5) == batch_y)).item()

    accuracy = 100 * predicted_correct / len(y_test)
    print('{:.3}'.format(loss.item()), "\t => ",  accuracy, '% accuracy')