#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Jun 16 23:54:47 2017
@author: vishal
"""
from HousingSpyder import loadin_housing_data
dataset = loadin_housing_data()
#print(dataset.head())
from sklearn.preprocessing import Imputer
# Missing value
imputer = Imputer(strategy='median')
# Imputer work on numeric col only so we need to extract numrric call only
dataset_num = dataset.drop('ocean_proximity', axis=1)
#print(dataset_num.head())
imputer.fit(dataset_num)
#print(imputer.statistics_)
#print(dataset_num.median().values)
X = imputer.transform(dataset_num)
import pandas as pd
@author: vishal
"""
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, Imputer, LabelBinarizer
from HousingSpyder import loadin_housing_data
from CoustomTransformation import CombinedAttributesAdder
from DataFrameSlector import DataFrameSelector
from sklearn.cross_validation import StratifiedShuffleSplit
import numpy as np
#print(dataset.head())
housing = loadin_housing_data()
housing["income_cat"] = np.ceil(housing["median_income"] / 1.5)
housing["income_cat"].where(housing["income_cat"] < 5, 5.0, inplace=True)
split = StratifiedShuffleSplit(housing["income_cat"], test_size=0.2)
train_indices, test_indices = next(iter(split))
strat_train_set = housing.loc[train_indices]
strat_test_set = housing.loc[test_indices]
housing = strat_train_set.drop("median_house_value", axis=1)
housing_labels = strat_train_set["median_house_value"].copy()
dataset = housing
dataset_num = dataset.drop('ocean_proximity', axis=1)