# The Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic
# prices and the demand for clean air', J. Environ. Economics & Management,
# vol.5, 81-102, 1978.   Used in Belsley, Kuh & Welsch, 'Regression diagnostics
# ...', Wiley, 1980.   N.B. Various transformations are used in the table on
# pages 244-261 of the latter.
#
# Variables in order:
# CRIM     per capita crime rate by town
# ZN       proportion of residential land zoned for lots over 25,000 sq.ft.
# INDUS    proportion of non-retail business acres per town
# CHAS     Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)
# NOX      nitric oxides concentration (parts per 10 million)
# RM       average number of rooms per dwelling
# AGE      proportion of owner-occupied units built prior to 1940
# DIS      weighted distances to five Boston employment centres
# RAD      index of accessibility to radial highways
# TAX      full-value property-tax rate per $10,000
# PTRATIO  pupil-teacher ratio by town
# B        1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town
# LSTAT    % lower status of the population
# MEDV     Median value of owner-occupied homes in $1000's

from sklearn.datasets import load_boston
import pandas as pd

data = load_boston()

# import numpy as np

#data_url = "http://lib.stat.cmu.edu/datasets/boston"
#raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
#data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
#target = raw_df.values[1::2, 2]

print(data)

X = data.data
y = data.target

print("X = ", X)
print("y = ", y)


df = pd.DataFrame(X, columns = data.feature_names)

print("++++++++++++++++++++++++++++++++")
print("Feature names: ", data.feature_names)

print("++++++++++++++++++++++++++++++++")
print("Target: ", data.target)

print("++++++++++++++++++++++++++++++++")
print(df)

df["MEDV"] = y
n, m = df.shape # n: number of rows, m: number of columns