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

# In[1]:


import os
import pandas as pd
import numpy as np
import sklearn
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.pipeline import make_pipeline


# In[2]:


train = pd.read_csv('train/train.tsv', header=None, sep='\t', error_bad_lines=False)
print(len(train))
train = train[:30000]


# In[3]:


x_train = train[4]
y_train = train[0]


# In[4]:


model = make_pipeline(TfidfVectorizer(), LinearRegression())
model.fit(x_train, y_train)


# In[5]:


def readFile(filename):
    result = []
    with open(filename, 'r', encoding="utf-8") as file:
        for line in file:
            text = line.split("\t")[0].strip()
            result.append(text)
    return result


# In[6]:


x_dev0 = readFile('dev-0/in.tsv')
dev_predicted =  model.predict(x_dev0)
with open('dev-0/out.tsv', 'wt') as f:
    for i in dev_predicted:
        f.write(str(i)+'\n')


# In[ ]:


x_dev1 = readFile('dev-0/in.tsv')
dev_predicted =  model.predict(x_dev1)
with open('dev-0/out.tsv', 'wt') as f:
    for i in dev_predicted:
        f.write(str(i)+'\n')


# In[ ]:


with open('test-A/in.tsv', 'r', encoding = 'utf-8') as f:
       x_test = f.readlines()
        
# x_test = pd.Series(x_test)
# x_test = vectorizer.transform(x_test)

test_predicted = model.predict(x_test)

with open('test-A/out.tsv', 'wt') as f:
    for i in test_predicted:
        f.write(str(i)+'\n')


# In[ ]:


get_ipython().system('jupyter nbconvert --to script run.ipynb')