mieszkania5/mieszkania5.ipynb

import torch 
import pandas
import numpy
from torch.autograd import Variable

class LinearRegressionModel(torch.nn.Module): 
    def __init__(self): 
        super(LinearRegressionModel, self).__init__() 
        self.linear = torch.nn.Linear(1, 1)
    def forward(self, x): 
        y_pred = self.linear(x) 
        return y_pred 

train_data=pandas.read_csv('C:/Users/eryk6/PycharmProjects/mieszkania5/train/train.tsv',sep='\t',header=None)

x=train_data[0].tolist()
x = [str(train_data).replace(' ', '') for train_data in x]

y=train_data[8].tolist()
y = [str(train_data).replace(' ', '') for train_data in y]

x=numpy.array(x, dtype=numpy.float32)
y=numpy.array(y, dtype=numpy.float32)

x = x.reshape(-1, 1)
y = y.reshape(-1, 1)

model = LinearRegressionModel()
criterion = torch.nn.MSELoss() 
optimizer = torch.optim.SGD(our_model.parameters(), lr = 0.000000000001 ) 

for i in range(500): 
    input = Variable(torch.from_numpy(x))
    pred_y = model(input)
    optimizer.zero_grad()
    loss = criterion(pred_y, Variable(torch.from_numpy(y))) 
    optimizer.zero_grad() 
    loss.backward() 
    optimizer.step()

test_A_in = pandas.read_csv('C:/Users/eryk6/PycharmProjects/mieszkania5/test-A/in.tsv',sep='\t',header=None)
x = test_A_in[7].tolist()
x = numpy.array(x, dtype=numpy.float32)
x = x.reshape(-1, 1)

y = model(Variable(torch.from_numpy(x))).data.numpy()
out = open('C:/Users/eryk6/PycharmProjects/mieszkania5/test-A/out.tsv', 'w')
for i in y:
    out.write(str(i[0])+'\n')
out.close()

dv_in = pandas.read_csv('C:/Users/eryk6/PycharmProjects/mieszkania5/dev-0/in.tsv',sep='\t',header=None)
x = dv_in[7].tolist()
x = numpy.array(x, dtype=numpy.float32)
x = x.reshape(-1, 1)

y = model(Variable(torch.from_numpy(x))).data.numpy()
output = open('C:/Users/eryk6/PycharmProjects/mieszkania5/dev-0/out.tsv', 'w')
for i in y:
    output.write(str(i[0])+'\n')
output.close()