81 lines
2.2 KiB
Python
81 lines
2.2 KiB
Python
|
import numpy as np
|
||
|
import pandas as pd
|
||
|
import torch
|
||
|
import torch.nn as tnn
|
||
|
|
||
|
filedir = '/home/ubuntu/Pulpit/TAU/mieszkania5'
|
||
|
#train size
|
||
|
learningRate = 0.0001
|
||
|
epochs = 10000
|
||
|
#treainfile
|
||
|
trainfile = filedir + '/train/train.tsv'
|
||
|
#data files
|
||
|
dev0in = filedir + '/dev-0/in.tsv'
|
||
|
dev0out = filedir + '/dev-0/out.tsv'
|
||
|
testAin = filedir + '/test-A/in.tsv'
|
||
|
testAout = filedir + '/test-A/out.tsv'
|
||
|
|
||
|
|
||
|
class linearRegression(tnn.Module):
|
||
|
def __init__(self, dim_i, dim_o):
|
||
|
super(linearRegression, self).__init__()
|
||
|
self.linear = tnn.Linear(dim_i, dim_o)
|
||
|
|
||
|
def forward(self, x):
|
||
|
out = self.linear(x)
|
||
|
return out
|
||
|
|
||
|
model = linearRegression(1, 1)
|
||
|
device = torch.device('cpu')
|
||
|
model.to(device)
|
||
|
print('model regresji gotowy')
|
||
|
|
||
|
#dane do treningu
|
||
|
trainfile_read = pd.raed_csv(trainfile, sep='\t', header=None, index_col=None)
|
||
|
train_data_sizes = np.array(trainfile_read[8].tolist(), dtype=np.float32).reshape(-1, 1)
|
||
|
train_data_prices = np.array(trainfile_read[0].tolist(), dtype=np.float32).reshape(-1, 1)
|
||
|
|
||
|
#dane do przewidywania
|
||
|
devfile_read = pd.raed_csv(dev0in, sep='\t', header=None, index_col=None)
|
||
|
testfile_in = pd.raed_csv(testAin, sep='\t', header=None, index_col=None)
|
||
|
dev_data_sizes = np.array(devfile_read[7].tolist(), dtype=np.float32)
|
||
|
test_data_sizes = np.array(testfile_in[7].tolist(), dtype=np.float32)
|
||
|
criterion = tnn.MSELoss()
|
||
|
optimizer = torch.optim.SGD(model.parameters(), lr=learningRate)
|
||
|
|
||
|
print('dane wczytane')
|
||
|
|
||
|
#trening
|
||
|
for epoch in range(epochs):
|
||
|
inputs = torch.from_numpy(train_data_sizes)
|
||
|
labels = torch.from_numpy(train_data_prices)
|
||
|
|
||
|
optimizer.zero_grad()
|
||
|
|
||
|
outputs = model(inputs)
|
||
|
|
||
|
loss = criterion(outputs, labels)
|
||
|
|
||
|
loss.backward()
|
||
|
|
||
|
optimizer.step()
|
||
|
print('trening zakonczony')
|
||
|
#przewidywanie ceny
|
||
|
|
||
|
predicted = model(torch.from_numpy(dev_data_sizes).requires_grad_()).data.numpy()
|
||
|
|
||
|
print('zapisywanie wyników dev-0')
|
||
|
|
||
|
dev_of = open(dev0out, 'w')
|
||
|
for i in predicted:
|
||
|
dev_of.write(str(i[0])+'\n')
|
||
|
dev_of.close()
|
||
|
|
||
|
predicted = model(torch.from_numpy(test_data_sizes).requires_grad_()).data.numpy()
|
||
|
|
||
|
print('zapisywanie wyników test-A')
|
||
|
|
||
|
test_of = open(testAout, 'w')
|
||
|
for i in predicted:
|
||
|
test_of.write(str(i[0])+'\n')
|
||
|
test_of.close()
|