http://www.cnblogs.com/chaosimple/p/4153083.html

 

dummies 哑变量，将变量重新编码，便于二分类，例如男、女，变为0,1等

将哑变量变换后的新的属性列直接concat到原来的df中即可。

 dummies = pd.get_dummies(df['key'], prefix='key') predix加前缀

http://www.it165.net/pro/html/201405/14269.html

 

XGBoost模型调参、

http://www.2cto.com/kf/201607/528771.html

xgb和gbdt

http://blog.csdn.net/a819825294/article/details/51206410

http://blog.csdn.net/jasonding1354/article/details/50562513

 

XGBoost区别于GBDT的一些独特之处以及算法的R实现。

https://zhuanlan.zhihu.com/p/26154587

 

http://www.168seo.cn/python/1882.html

 

>>> import numpy as np  >>> import pandas as pd  Backend TkAgg is interactive backend. Turning interactive mode on.  >>> np.random.seed(1)  >>> df_test = pd.DataFrame(np.random.randn(4,4)* 4 + 3)  >>> df_test            0         1         2         3  0  9.497381  0.552974  0.887313 -1.291874  1  6.461631 -6.206155  9.979247 -0.044828  2  4.276156  2.002518  8.848432 -5.240563  3  1.710331  1.463783  7.535078 -1.399565  >>> df_test_1 = df_test  >>> df_test.apply(lambda x: (x - np.min(x)) / (np.max(x) - np.min(x)))  #方法一            0         1         2         3  0  1.000000  0.823413  0.000000  0.759986  1  0.610154  0.000000  1.000000  1.000000  2  0.329499  1.000000  0.875624  0.000000  3  0.000000  0.934370  0.731172  0.739260    >>> (df_test_1 - df_test_1.min()) / (df_test_1.max() - df_test_1.min())#方法二            0         1         2         3  0  1.000000  0.823413  0.000000  0.759986  1  0.610154  0.000000  1.000000  1.000000  2  0.329499  1.000000  0.875624  0.000000  3  0.000000  0.934370  0.731172  0.739260