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

# In[2]:


import torch
import gensim.downloader as downloader
import pandas as pd
import csv
from nltk.tokenize import word_tokenize as tokenize
import numpy as np


# In[7]:


class NeuralNetworkModel(torch.nn.Module):
    
    def __init__(self, input_size, hidden_size, num_classes):
        super(NeuralNetworkModel, self).__init__()
        self.fc1 = torch.nn.Linear(input_size,hidden_size)
        self.fc2 = torch.nn.Linear(hidden_size,num_classes)
        
    def forward(self,x):
        x = self.fc1(x)
        x = torch.relu(x)
        x = self.fc2(x)
        x = torch.sigmoid(x)
        return x


# In[4]:


w2v = downloader.load('word2vec-google-news-300')


# In[9]:


#model + settings

nn = NeuralNetworkModel(300,300,1)
crit = torch.nn.BCELoss()
opti = torch.optim.SGD(nn.parameters(), lr=0.08)
BATCH_SIZE = 5
epochs = 5


# In[12]:


#trening

#wczytanie danych
train_data_in = pd.read_csv('train/in.tsv.xz', compression='xz', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\t', nrows=3000)
train_data_ex = pd.read_csv('train/expected.tsv', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\t', nrows=3000)

#preprocessing
train_in = train_data_in[0].str.lower()
train_in = [tokenize(line) for line in train_in]
train_in = [np.mean([w2v[x] for x in data if x in w2v] or [np.zeros(300)], axis=0) for data in train_in]
train_ex = train_data_ex[0]

for epoch in range(epochs):
    nn.train()
    for i in range(0,train_data_ex.shape[0],BATCH_SIZE):
        x = train_in[i:i + BATCH_SIZE]
        x = torch.tensor(x)
        y = train_ex[i:i + BATCH_SIZE]
        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1,1)
        
        opti.zero_grad()
        y_pred = nn(x.float())
        loss = crit(y_pred,y)
        loss.backward()
        opti.step()


# In[27]:


#dev-0 predict

#wczytanie danych
dev0_data = pd.read_csv('dev-0/in.tsv.xz', compression='xz', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\t')
dev0_data = dev0_data[0].str.lower()
dev0_data = [tokenize(line) for line in dev0_data]
dev0_data = [np.mean([w2v[x] for x in data if x in w2v] or [np.zeros(300)], axis=0) for data in dev0_data]

dev0_y=[]
nn.eval()
with torch.no_grad():
    for i in range(0, len(dev0_data), BATCH_SIZE):
        x = dev0_data[i:i + BATCH_SIZE]
        x = torch.tensor(x)
        dev0_y_pred = nn(x.float())

        dev0_y_prediction = (dev0_y_pred > 0.5)
        dev0_y.extend(dev0_y_prediction)
        
#zapis wyników
np.asarray(dev0_y, dtype=np.int32).tofile('dev-0/out.tsv', sep='\n')


# In[28]:


#test-A predict

#wczytanie danych
testA_data = pd.read_csv('test-A/in.tsv.xz', compression='xz', header=None, quoting=csv.QUOTE_NONE, sep='\t')
testA_data = testA_data[0].str.lower()
testA_data = [tokenize(line) for line in testA_data]
testA_data = [np.mean([w2v[x] for x in data if x in w2v] or [np.zeros(300)], axis=0) for data in testA_data]

testA_y=[]
nn.eval()
with torch.no_grad():
    for i in range(0, len(testA_data), BATCH_SIZE):
        x = testA_data[i:i + BATCH_SIZE]
        x = torch.tensor(x)
        testA_y_pred = nn(x.float())

        testA_y_prediction = (testA_y_pred > 0.5)
        testA_y.extend(testA_y_prediction)
        
#zapis wyników
np.asarray(testA_y, dtype=np.int32).tofile('test-A/out.tsv', sep='\n')