ium_444421/evaluation.py

#!/usr/bin/env python
# coding: utf-8

# In[ ]:


import numpy as np
import pandas as pd
from sklearn.metrics import accuracy_score
import torch
from torch import nn, optim
import torch.nn.functional as F
import matplotlib.pyplot as plt


# In[ ]:


class Net(nn.Module):
    def __init__(self, n_features):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(n_features, 5)
        self.fc2 = nn.Linear(5, 3)
        self.fc3 = nn.Linear(3, 1)
    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        return torch.sigmoid(self.fc3(x))


# In[ ]:


X_test = pd.read_csv('X_test.csv')
y_test = pd.read_csv('y_test.csv')


# In[ ]:


X_test = torch.from_numpy(np.array(X_test)).float()
y_test = torch.squeeze(torch.from_numpy(y_test.values).float())


# In[ ]:


device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
X_test = X_test.to(device)
y_test = y_test.to(device)


# In[ ]:


net = torch.load('model.pth')


# In[ ]:


y_pred = net(X_test)
y_pred = y_pred.ge(.5).view(-1).cpu()
y_test = y_test.cpu()


# In[ ]:


accuracy = accuracy_score(y_test, y_pred)
with open('build_accuracy.txt', 'a') as file:
    file.write(str(accuracy))
    file.write('\n')


# In[ ]:


with open('build_accuracy.txt') as file:
    acc = [float(line.rstrip()) for line in file]
    
builds = list(range(1, len(acc) + 1))

plt.xlabel('build')
plt.ylabel('accuracy')
plt.plot(builds, acc, 'ro')
plt.show()
plt.savefig('bilds_accuracy.jpg')