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

# In[1]:


import pandas as pd
import numpy as np
from pathlib import Path
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
from sklearn.linear_model import LinearRegression


# ## TRENING

# In[2]:


NAMES = ["Price","Mileage","Year","Brand","EngineType","EngineCapacity"]
TRAIN_BASE = pd.read_csv("train/train.tsv", sep ='\t', names=NAMES)


# In[3]:


Y_TRAIN = np.array(TRAIN_BASE["Price"])
X_TRAIN = np.array(TRAIN_BASE[["Mileage","Year","EngineCapacity"]])


# In[4]:


MODEL = LinearRegression().fit(X_TRAIN,Y_TRAIN)


# ## DEV-0

# In[5]:


NAMES = ["Mileage","Year","Brand","EngineType","EngineCapacity"]
FILE_BASE = pd.read_csv("dev-0/in.tsv", sep ='\t', names=NAMES)


# In[6]:


X_TEST = np.array(FILE_BASE[["Mileage","Year","EngineCapacity"]])


# In[7]:


Y_TEST = MODEL.predict(X_TEST)


# In[8]:


VALUES = np.array2string(Y_TEST, precision=5, separator='\n',suppress_small=True)


# In[9]:


VALUES = VALUES.split(".\n")


# In[10]:


OUTFILE = open("dev-0/out.tsv", "w")


# In[11]:


for x in VALUES:
    RESULT = x.replace(" ","")
    RESULT = RESULT.replace("[","")
    RESULT = RESULT.replace("]","")
    OUTFILE.write(str(RESULT))


# In[12]:


OUTFILE.close()


# ## TEST A

# In[13]:


NAMES = ["Mileage","Year","Brand","EngineType","EngineCapacity"]
FILE_BASE = pd.read_csv("test-A/in.tsv", sep ='\t', names=NAMES)


# In[14]:


X_TEST = np.array(FILE_BASE[["Mileage","Year","EngineCapacity"]])


# In[15]:


Y_TEST = MODEL.predict(X_TEST)


# In[16]:


VALUES = np.array2string(Y_TEST, precision=5, separator='\n',suppress_small=True)


# In[17]:


VALUES = VALUES.split(".\n")


# In[18]:


OUTFILE = open("test-A/out.tsv", "w")


# In[19]:


for x in VALUES:
    RESULT = x.replace(" ","")
    RESULT = RESULT.replace("[","")
    RESULT = RESULT.replace("]","")
    OUTFILE.write(str(RESULT) )


# In[20]:


OUTFILE.close()


# In[ ]: