import torch 
import torch.nn as nn
import numpy as np
import pandas as pd
from torch.autograd import Variable



class linearRegression(nn.Module):
   def __init__(self, input_dim, output_dim):
       super(linearRegression, self).__init__()
       self.linear = nn.Linear(input_dim, output_dim)
   def forward(self, x):
       out = self.linear(x)
       return out


inputDim = 1        
outputDim = 1       
model = linearRegression(inputDim, outputDim)
	
data = pd.read_csv('train/train.tsv',sep='\t',header=None)

y_values = data[0].tolist()
x_values = data[8].tolist()
        
x_train = np.array(x_values, dtype=np.float32)
x_train = x_train.reshape(-1, 1)
y_train = np.array(y_values, dtype=np.float32)
y_train = y_train.reshape(-1, 1)
	
if torch.cuda.is_available():
   model.cuda()

criterion = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.00001)
	


for epoch in range(1000):
    epoch += 1

    if torch.cuda.is_available():
        inputs = Variable(torch.from_numpy(x_train).cuda())
        labels = Variable(torch.from_numpy(y_train).cuda())
    else:
        inputs = Variable(torch.from_numpy(x_train))
        labels = Variable(torch.from_numpy(y_train))

optimizer.zero_grad()

outputs = model(inputs)
    
loss = criterion(outputs, labels)
    
loss.backward()

optimizer.step()


result = pd.read_csv('test-A/in.tsv',sep='\t',header=None)
end_x = result[7].tolist()
end_x = np.array(end_x, dtype=np.float32)
end_x = end_x.reshape(-1, 1)

predictions = model(torch.from_numpy(end_x).requires_grad_()).data.numpy()


output = open('test-A/out.tsv', 'w')
for p in predictions:
   output.write(str(p[0])+'\n')