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

# In[1]:


get_ipython().run_line_magic('reload_ext', 'autoreload')
get_ipython().run_line_magic('autoreload', '2')
get_ipython().run_line_magic('matplotlib', 'inline')
import os
os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID";
os.environ["CUDA_VISIBLE_DEVICES"]="0"; 

import urllib.request
import pandas as pd
import numpy as np
pd.set_option('display.max_columns', None)


# In[2]:


import ktrain
from ktrain import tabular


# # Predicting House Prices
# 
# In this notebook, we will predict the prices of houses from various house attributes.  The dataset [can be downloaded from Kaggle here](https://www.kaggle.com/c/house-prices-advanced-regression-techniques).

# ## STEP 1:  Load and Preprocess Data

# In[3]:


train_df = pd.read_csv('data/housing_price/train.csv', index_col=0)


# In[4]:


train_df.head()


# In[5]:


train_df.drop(['Alley','PoolQC','MiscFeature','Fence','FireplaceQu','Utilities'], 1, inplace=True)


# In[6]:


train_df.head()


# In[7]:


trn, val, preproc = tabular.tabular_from_df(train_df, is_regression=True, 
                                             label_columns='SalePrice', random_state=42)


# ## STEP 2: Create Model and Wrap in `Learner`

# In[8]:


model = tabular.tabular_regression_model('mlp', trn)
learner = ktrain.get_learner(model, train_data=trn, val_data=val, batch_size=128)


# ## STEP 3: Estimate LR
# 

# In[9]:


learner.lr_find(show_plot=True, max_epochs=16)


# ## STEP 4: Train

# In[10]:


learner.autofit(1e-1)


# ## Evaluate Model

# In[11]:


learner.evaluate(test_data=val)


# In[ ]: