In [1]:

    

import numpy as np
import pandas as pd
import sklearn
from sklearn import datasets 

%matplotlib inline
import matplotlib.pyplot as plt
from sklearn import datasets, linear_model

# load the dataset
boston = datasets.load_boston()

# see the description
print boston.DESCR


    

    




Boston House Prices dataset

Notes
------
Data Set Characteristics:  

    :Number of Instances: 506 

    :Number of Attributes: 13 numeric/categorical predictive
    
    :Median Value (attribute 14) is usually the target

    :Attribute Information (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

    :Missing Attribute Values: None

    :Creator: Harrison, D. and Rubinfeld, D.L.

This is a copy of UCI ML housing dataset.
http://archive.ics.uci.edu/ml/datasets/Housing


This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.

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.

The Boston house-price data has been used in many machine learning papers that address regression
problems.   
     
**References**

   - Belsley, Kuh & Welsch, 'Regression diagnostics: Identifying Influential Data and Sources of Collinearity', Wiley, 1980. 244-261.
   - Quinlan,R. (1993). Combining Instance-Based and Model-Based Learning. In Proceedings on the Tenth International Conference of Machine Learning, 236-243, University of Massachusetts, Amherst. Morgan Kaufmann.
   - many more! (see http://archive.ics.uci.edu/ml/datasets/Housing)







    




/Users/charilaostsarouchas/anaconda/lib/python2.7/site-packages/pytz/__init__.py:29: UserWarning: Module argparse was already imported from /Users/charilaostsarouchas/anaconda/lib/python2.7/argparse.pyc, but /Users/charilaostsarouchas/anaconda/lib/python2.7/site-packages is being added to sys.path
  from pkg_resources import resource_stream

In [12]:

    

# Lets explore a bit the Boston data:
print "boston keys: ", boston.keys()
print "boston feature names", boston.feature_names
# DESCR says "Median Value (attribute 14) is usually the target" 
# The MEDV is the boston.target

# get the df from boston data
boston_df = pd.DataFrame(boston.data, columns = boston.feature_names)

# add the target
boston_df["MEDV"] = boston.target
boston_df.head()


    

    




boston keys:  ['data', 'feature_names', 'DESCR', 'target']
boston feature names ['CRIM' 'ZN' 'INDUS' 'CHAS' 'NOX' 'RM' 'AGE' 'DIS' 'RAD' 'TAX' 'PTRATIO'
 'B' 'LSTAT']






    
Out[12]:






  

    

      

      
CRIM
      
ZN
      
INDUS
      
CHAS
      
NOX
      
RM
      
AGE
      
DIS
      
RAD
      
TAX
      
PTRATIO
      
B
      
LSTAT
      
MEDV
    
  
  

    

      
0
      
 0.00632
      
 18
      
 2.31
      
 0
      
 0.538
      
 6.575
      
 65.2
      
 4.0900
      
 1
      
 296
      
 15.3
      
 396.90
      
 4.98
      
 24.0
    
    

      
1
      
 0.02731
      
  0
      
 7.07
      
 0
      
 0.469
      
 6.421
      
 78.9
      
 4.9671
      
 2
      
 242
      
 17.8
      
 396.90
      
 9.14
      
 21.6
    
    

      
2
      
 0.02729
      
  0
      
 7.07
      
 0
      
 0.469
      
 7.185
      
 61.1
      
 4.9671
      
 2
      
 242
      
 17.8
      
 392.83
      
 4.03
      
 34.7
    
    

      
3
      
 0.03237
      
  0
      
 2.18
      
 0
      
 0.458
      
 6.998
      
 45.8
      
 6.0622
      
 3
      
 222
      
 18.7
      
 394.63
      
 2.94
      
 33.4
    
    

      
4
      
 0.06905
      
  0
      
 2.18
      
 0
      
 0.458
      
 7.147
      
 54.2
      
 6.0622
      
 3
      
 222
      
 18.7
      
 396.90
      
 5.33
      
 36.2
    
  

In [ ]: