sklearn学习随笔1

快速入门：

加载数据集

In [1]: from sklearn import datasets

In [2]: iris = datasets.load_iris()

In [3]: digits = datasets.load_digits()

In [4]: print(digits.data)
[[  0.   0.   5. ...,   0.   0.   0.]
 [  0.   0.   0. ...,  10.   0.   0.]
 [  0.   0.   0. ...,  16.   9.   0.]
 ...,
 [  0.   0.   1. ...,   6.   0.   0.]
 [  0.   0.   2. ...,  12.   0.   0.]
 [  0.   0.  10. ...,  12.   1.   0.]]

In [5]: print (digits.target)
[0 1 2 ..., 8 9 8]

　　

In [6]: digits.images[1]
Out[6]:
array([[  0.,   0.,   0.,  12.,  13.,   5.,   0.,   0.],
       [  0.,   0.,   0.,  11.,  16.,   9.,   0.,   0.],
       [  0.,   0.,   3.,  15.,  16.,   6.,   0.,   0.],
       [  0.,   7.,  15.,  16.,  16.,   2.,   0.,   0.],
       [  0.,   0.,   1.,  16.,  16.,   3.,   0.,   0.],
       [  0.,   0.,   1.,  16.,  16.,   6.,   0.,   0.],
       [  0.,   0.,   1.,  16.,  16.,   6.,   0.,   0.],
       [  0.,   0.,   0.,  11.,  16.,  10.,   0.,   0.]])

　SVM小试牛刀：

In [9]: from sklearn import svm

In [10]: clf = svm.SVC(gamma=0.001,C = 50)

In [11]: clf.fit(digits.data[:-1],digits.target[:-1])
Out[11]:
SVC(C=50, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma=0.001, kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

In [12]: clf.predict(digits.data[-1:])
Out[12]: array([8])

模型持久化：

通过python的内置的持久化模型pickle讲模型保存在scikit中

In [13]: from sklearn import svm

In [14]: from sklearn import datasets

In [15]: clf = svm.SVC()

In [16]: iris = datasets.load_iris()

In [17]: X,y = iris.data,iris.target

In [18]: clf.fit(X,y)
Out[18]:
SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

In [19]: import pickle

In [20]: s = pickle.dumps(clf)

In [21]: clf2 = pickle.loads(s)

In [22]: clf2.predict(X[0:1])
Out[22]: array([0])

In [23]: y[0]
Out[23]: 0

　　pickle.dumps(clf)存储模型

　　pickle.loads()加载存储的模型

　　joblib替换pickle（joblib.dump＆joblib.load）可能会更有意思，这对大数据更有效，但只能腌制到磁盘而不是字符串：

　　

In [24]: from sklearn.externals import joblib

In [25]: joblib.dump(clf,'filename.pkl')


In [26]: joblib.dump(clf,'d:/clf.pkl')
Out[26]:
['d:/clf.pkl',
 'd:/clf.pkl_01.npy',
 'd:/clf.pkl_02.npy',
 'd:/clf.pkl_03.npy',
 'd:/clf.pkl_04.npy',
 'd:/clf.pkl_05.npy',
 'd:/clf.pkl_06.npy',
 'd:/clf.pkl_07.npy',
 'd:/clf.pkl_08.npy',
 'd:/clf.pkl_09.npy',
 'd:/clf.pkl_10.npy',
 'd:/clf.pkl_11.npy']

In [27]: clf = joblib.load('d:clf.pkl')