from sklearn import datasets from sklearn.linear_model import LinearRegression loaded_data = datasets.load_boston() data_X = loaded_data.data data_y = loaded_data.target model = LinearRegression() #train and prediect model.fit(data_X, data_y) Out[9]: LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False) data_X.min Out[10]: <function ndarray.min> data_X.min() Out[11]: 0.0 data_X.max() Out[12]: 711.0 model.predict(data_X[:4,:]) Out[13]: array([30.00821269, 25.0298606 , 30.5702317 , 28.60814055]) data_y[:4] Out[14]: array([24. , 21.6, 34.7, 33.4]) #参数和分数 model.coef_ Out[16]: array([-1.07170557e-01, 4.63952195e-02, 2.08602395e-02, 2.68856140e+00, -1.77957587e+01, 3.80475246e+00, 7.51061703e-04, -1.47575880e+00, 3.05655038e-01, -1.23293463e-02, -9.53463555e-01, 9.39251272e-03, -5.25466633e-01]) model.intercept_ Out[17]: 36.49110328036133 model.get_params Out[18]: <bound method BaseEstimator.get_params of LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)> #model score 可以对模型的经确定进行打分 model.score(data_X, data_y) Out[20]: 0.7406077428649428 import matplotlib.pyplot as plt Backend TkAgg is interactive backend. Turning interactive mode on. import pandas as pd import numpy as np loaded_data.keys Out[24]: <function Bunch.keys> loaded_data.keys() Out[25]: dict_keys(['data', 'target', 'feature_names', 'DESCR']) loaded_data Out[26]: {'data': array([[6.3200e-03, 1.8000e+01, 2.3100e+00, ..., 1.5300e+01, 3.9690e+02, 4.9800e+00], [2.7310e-02, 0.0000e+00, 7.0700e+00, ..., 1.7800e+01, 3.9690e+02, 9.1400e+00], [2.7290e-02, 0.0000e+00, 7.0700e+00, ..., 1.7800e+01, 3.9283e+02, 4.0300e+00], ..., [6.0760e-02, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 3.9690e+02, 5.6400e+00], [1.0959e-01, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 3.9345e+02, 6.4800e+00], [4.7410e-02, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 3.9690e+02, 7.8800e+00]]), 'target': array([24. , 21.6, 34.7, 33.4, 36.2, 28.7, 22.9, 27.1, 16.5, 18.9, 15. , 18.9, 21.7, 20.4, 18.2, 19.9, 23.1, 17.5, 20.2, 18.2, 13.6, 19.6, 15.2, 14.5, 15.6, 13.9, 16.6, 14.8, 18.4, 21. , 12.7, 14.5, 13.2, 13.1, 13.5, 18.9, 20. , 21. , 24.7, 30.8, 34.9, 26.6, 25.3, 24.7, 21.2, 19.3, 20. , 16.6, 14.4, 19.4, 19.7, 20.5, 25. , 23.4, 18.9, 35.4, 24.7, 31.6, 23.3, 19.6, 18.7, 16. , 22.2, 25. , 33. , 23.5, 19.4, 22. , 17.4, 20.9, 24.2, 21.7, 22.8, 23.4, 24.1, 21.4, 20. , 20.8, 21.2, 20.3, 28. , 23.9, 24.8, 22.9, 23.9, 26.6, 22.5, 22.2, 23.6, 28.7, 22.6, 22. , 22.9, 25. , 20.6, 28.4, 21.4, 38.7, 43.8, 33.2, 27.5, 26.5, 18.6, 19.3, 20.1, 19.5, 19.5, 20.4, 19.8, 19.4, 21.7, 22.8, 18.8, 18.7, 18.5, 18.3, 21.2, 19.2, 20.4, 19.3, 22. , 20.3, 20.5, 17.3, 18.8, 21.4, 15.7, 16.2, 18. , 14.3, 19.2, 19.6, 23. , 18.4, 15.6, 18.1, 17.4, 17.1, 13.3, 17.8, 14. , 14.4, 13.4, 15.6, 11.8, 13.8, 15.6, 14.6, 17.8, 15.4, 21.5, 19.6, 15.3, 19.4, 17. , 15.6, 13.1, 41.3, 24.3, 23.3, 27. , 50. , 50. , 50. , 22.7, 25. , 50. , 23.8, 23.8, 22.3, 17.4, 19.1, 23.1, 23.6, 22.6, 29.4, 23.2, 24.6, 29.9, 37.2, 39.8, 36.2, 37.9, 32.5, 26.4, 29.6, 50. , 32. , 29.8, 34.9, 37. , 30.5, 36.4, 31.1, 29.1, 50. , 33.3, 30.3, 34.6, 34.9, 32.9, 24.1, 42.3, 48.5, 50. , 22.6, 24.4, 22.5, 24.4, 20. , 21.7, 19.3, 22.4, 28.1, 23.7, 25. , 23.3, 28.7, 21.5, 23. , 26.7, 21.7, 27.5, 30.1, 44.8, 50. , 37.6, 31.6, 46.7, 31.5, 24.3, 31.7, 41.7, 48.3, 29. , 24. , 25.1, 31.5, 23.7, 23.3, 22. , 20.1, 22.2, 23.7, 17.6, 18.5, 24.3, 20.5, 24.5, 26.2, 24.4, 24.8, 29.6, 42.8, 21.9, 20.9, 44. , 50. , 36. , 30.1, 33.8, 43.1, 48.8, 31. , 36.5, 22.8, 30.7, 50. , 43.5, 20.7, 21.1, 25.2, 24.4, 35.2, 32.4, 32. , 33.2, 33.1, 29.1, 35.1, 45.4, 35.4, 46. , 50. , 32.2, 22. , 20.1, 23.2, 22.3, 24.8, 28.5, 37.3, 27.9, 23.9, 21.7, 28.6, 27.1, 20.3, 22.5, 29. , 24.8, 22. , 26.4, 33.1, 36.1, 28.4, 33.4, 28.2, 22.8, 20.3, 16.1, 22.1, 19.4, 21.6, 23.8, 16.2, 17.8, 19.8, 23.1, 21. , 23.8, 23.1, 20.4, 18.5, 25. , 24.6, 23. , 22.2, 19.3, 22.6, 19.8, 17.1, 19.4, 22.2, 20.7, 21.1, 19.5, 18.5, 20.6, 19. , 18.7, 32.7, 16.5, 23.9, 31.2, 17.5, 17.2, 23.1, 24.5, 26.6, 22.9, 24.1, 18.6, 30.1, 18.2, 20.6, 17.8, 21.7, 22.7, 22.6, 25. , 19.9, 20.8, 16.8, 21.9, 27.5, 21.9, 23.1, 50. , 50. , 50. , 50. , 50. , 13.8, 13.8, 15. , 13.9, 13.3, 13.1, 10.2, 10.4, 10.9, 11.3, 12.3, 8.8, 7.2, 10.5, 7.4, 10.2, 11.5, 15.1, 23.2, 9.7, 13.8, 12.7, 13.1, 12.5, 8.5, 5. , 6.3, 5.6, 7.2, 12.1, 8.3, 8.5, 5. , 11.9, 27.9, 17.2, 27.5, 15. , 17.2, 17.9, 16.3, 7. , 7.2, 7.5, 10.4, 8.8, 8.4, 16.7, 14.2, 20.8, 13.4, 11.7, 8.3, 10.2, 10.9, 11. , 9.5, 14.5, 14.1, 16.1, 14.3, 11.7, 13.4, 9.6, 8.7, 8.4, 12.8, 10.5, 17.1, 18.4, 15.4, 10.8, 11.8, 14.9, 12.6, 14.1, 13. , 13.4, 15.2, 16.1, 17.8, 14.9, 14.1, 12.7, 13.5, 14.9, 20. , 16.4, 17.7, 19.5, 20.2, 21.4, 19.9, 19. , 19.1, 19.1, 20.1, 19.9, 19.6, 23.2, 29.8, 13.8, 13.3, 16.7, 12. , 14.6, 21.4, 23. , 23.7, 25. , 21.8, 20.6, 21.2, 19.1, 20.6, 15.2, 7. , 8.1, 13.6, 20.1, 21.8, 24.5, 23.1, 19.7, 18.3, 21.2, 17.5, 16.8, 22.4, 20.6, 23.9, 22. , 11.9]), 'feature_names': array(['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT'], dtype='<U7'), '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) "} loaded_data.DESCR Out[27]: "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) " X = loaded_data.data[:, :2] #切片操作取loaded_data data部分506行， 13列中的前两行 X Out[34]: array([[6.3200e-03, 1.8000e+01], [2.7310e-02, 0.0000e+00], [2.7290e-02, 0.0000e+00], ..., [6.0760e-02, 0.0000e+00], [1.0959e-01, 0.0000e+00], [4.7410e-02, 0.0000e+00]]) X.shape Out[35]: (506, 2) plt.scatter(X[:,0], X[:, 1]) Out[36]: <matplotlib.collections.PathCollection at 0x1330f550> plt.hist(X[:,0]) Out[37]: (array([440., 43., 14., 1., 3., 2., 0., 1., 1., 1.]), array([6.3200000e-03, 8.9033080e+00, 1.7800296e+01, 2.6697284e+01, 3.5594272e+01, 4.4491260e+01, 5.3388248e+01, 6.2285236e+01, 7.1182224e+01, 8.0079212e+01, 8.8976200e+01]), <a list of 10 Patch objects>) #了解一下两维数组的切片操作 plt.scatter(X[:,0], loaded_data.target[:,0]) plt.scatter(X[:,0], loaded_data.target[:]) Out[42]: <matplotlib.collections.PathCollection at 0x131fb438> plt.plot(X[:,0], model.coef_[0][0]*X[:,0] + model.intercept_[0], '-r') plt.scatter(data_X[:,0], data_y[:]) Out[51]: <matplotlib.collections.PathCollection at 0x13a00fd0> plt.scatter(data_y[:], data_X[:, 0]) Out[52]: <matplotlib.collections.PathCollection at 0x13a00c50> plt.scatter(data_y[:], data_X[:, 0]) Out[53]: <matplotlib.collections.PathCollection at 0x13a16978> plt.plot(X[:,0], model.coef_[0]*X[:,0] + model.intercept_, '-r') Out[54]: [<matplotlib.lines.Line2D at 0x13a564a8>]