In [24]:

    

from sklearn import datasets as d
import numpy as np


    

In [25]:

    

d.*?


    

In [26]:

    

boston = d.load_boston()


    

In [27]:

    

boston.DESCR


    

    
Out[27]:





"Boston House Prices dataset\n\nNotes\n------\nData Set Characteristics:  \n\n    :Number of Instances: 506 \n\n    :Number of Attributes: 13 numeric/categorical predictive\n    \n    :Median Value (attribute 14) is usually the target\n\n    :Attribute Information (in order):\n        - CRIM     per capita crime rate by town\n        - ZN       proportion of residential land zoned for lots over 25,000 sq.ft.\n        - INDUS    proportion of non-retail business acres per town\n        - CHAS     Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)\n        - NOX      nitric oxides concentration (parts per 10 million)\n        - RM       average number of rooms per dwelling\n        - AGE      proportion of owner-occupied units built prior to 1940\n        - DIS      weighted distances to five Boston employment centres\n        - RAD      index of accessibility to radial highways\n        - TAX      full-value property-tax rate per $10,000\n        - PTRATIO  pupil-teacher ratio by town\n        - B        1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town\n        - LSTAT    % lower status of the population\n        - MEDV     Median value of owner-occupied homes in $1000's\n\n    :Missing Attribute Values: None\n\n    :Creator: Harrison, D. and Rubinfeld, D.L.\n\nThis is a copy of UCI ML housing dataset.\nhttp://archive.ics.uci.edu/ml/datasets/Housing\n\n\nThis dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.\n\nThe Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic\nprices and the demand for clean air', J. Environ. Economics & Management,\nvol.5, 81-102, 1978.   Used in Belsley, Kuh & Welsch, 'Regression diagnostics\n...', Wiley, 1980.   N.B. Various transformations are used in the table on\npages 244-261 of the latter.\n\nThe Boston house-price data has been used in many machine learning papers that address regression\nproblems.   \n     \n**References**\n\n   - Belsley, Kuh & Welsch, 'Regression diagnostics: Identifying Influential Data and Sources of Collinearity', Wiley, 1980. 244-261.\n   - 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.\n   - many more! (see http://archive.ics.uci.edu/ml/datasets/Housing)\n"

In [28]:

    

X, y = boston.data, boston.target


    

In [29]:

    

X.shape, y.shape


    

    
Out[29]:





((506, 13), (506,))

In [30]:

    

datasets.make_*?


    

In [31]:

    

reg_data = d.make_regression()
reg_data[0].shape


    

    
Out[31]:





(100, 100)

In [32]:

    

complex_reg_data = d.make_regression(1000, 10, 5, 2, 1.0)
complex_reg_data[0].shape


    

    
Out[32]:





(1000, 10)

In [33]:

    

classification_set = d.make_classification(weights=[0.1])
np.bincount(classification_set[1])


    

    
Out[33]:





array([10, 90])

In [45]:

    

blobs = d.make_blobs()
blobs[0].shape


    

    
Out[45]:





(100, 2)

In [38]:

    




    

In [39]:

    




    

In [42]:

    




    

In [ ]: