【甘道夫】基于scikit-learn实现逻辑回归LogisticRegression

难得有不涉及机密，同时又有一定记录价值的收获，记录下来，以备查阅。

欢迎转载，请注明出处：
http://blog.csdn.net/u010967382/article/details/50225291
1.准备数据

***基础：LIBSVM数据格式***
数据文件格式如下：
<label> <index1>:<value1> <index2>:<value2> ...
其中
<label> 是训练数据集的目标值，对于分类，它是标识某类的整数(支持多个类)；对于回归，是任意实数。
<index> 是以1开始的整数。如果特征值为0，特征冒号前面的(姑且称做序号)可以不连续。如：-15 1:0.708 3:-0.3333；
<value>为实数，也就是我们常说的自变量。数据之间用空格隔开。

推荐使用该格式。
******

样本数据支持多种格式，这里用libsvm格式做示例：

1 1:1 2:175 3:75
0 1:1 2:175 3:50
1 1:1 2:170 3:65
0 1:1 2:180 3:60
1 1:0 2:165 3:50
1 1:0 2:160 3:45
0 1:0 2:168 3:40
0 1:0 2:170 3:42

这是一个虚构数据集，因变量Y是体重正常与否，自变量分别是性别（男1，女0）、身高、体重（公斤）

2.建模 & 预测

>>> from sklearn.datasets import load_svmlight_file #用于加载libsvm格式数据

>>> from sklearn.linear_model import LogisticRegression

>>> lrm= LogisticRegression() #使用默认参数创建逻辑回归模型实例

>>> x_train, y_train = load_svmlight_file("/sktest/sklearn_testdata") #加载libsvm训练数据

>>> lrm.fit(x_train,y_train) #训练模型

LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
verbose=0, warm_start=False)

"""至此，模型已训练完毕"""

>>> y= lrm.predict([1,174,50]) #预测 男性，174身高，50公里，体重是否正常

>>> print y

[ 0.]

>>> yp = lrm.predict_proba([1,174,50]) #当前样本属于各种因变量Y分类的概率，顺序参考lrm.classes_中的顺序

>>> print yp

[[ 0.74788311 0.25211689]]

>>> print lrm.classes_ #对应多个概率值顺序，[1,174,50]属于0的概率是0.74788311，属于1的概率是0.25211689
[ 0. 1.]

3.模型持久化和加载

真实场景下，模型训练往往耗时较长，不可能每次重启服务都训练一次模型，所以训练好的模型需要持久化。

scikit-learn提供了模型持久化和加载的库joblib，使用示例如下：

模型持久化：

from sklearn.externals import joblib

joblib.dump(lrm, "/sktest/lrm.m")
#将训练好的模型保存到/sktest/lrm.m文件中

下次再使用时，我们直接加载模型即可使用：

from sklearn.externals import joblib

lrm =joblib.load("/sktest/lrm.m")
#从/sktest/lrm.m文件中加载模型

y= lrm .predict([1,174,70])

print y

4.更多数据格式

除了以上使用的经典libsvm格式数据，常用数据格式还有iris鸢尾花数据格式：

>>> from sklearn.datasets import load_iris

>>> iris = load_iris()

>>> print iris
{'target_names': array(['setosa', 'versicolor', 'virginica'],
dtype='|S10'), 'data': array([[ 5.1, 3.5, 1.4, 0.2],
[ 4.9, 3. , 1.4, 0.2],
[ 4.7, 3.2, 1.3, 0.2],
[ 4.6, 3.1, 1.5, 0.2],
[ 5. , 3.6, 1.4, 0.2],
[ 5.4, 3.9, 1.7, 0.4],
[ 4.6, 3.4, 1.4, 0.3],
[ 5. , 3.4, 1.5, 0.2],
[ 4.4, 2.9, 1.4, 0.2],
[ 4.9, 3.1, 1.5, 0.1],
[ 5.4, 3.7, 1.5, 0.2],
[ 4.8, 3.4, 1.6, 0.2],
[ 4.8, 3. , 1.4, 0.1],
[ 4.3, 3. , 1.1, 0.1],
[ 5.8, 4. , 1.2, 0.2],
[ 5.7, 4.4, 1.5, 0.4],
[ 5.4, 3.9, 1.3, 0.4],
[ 5.1, 3.5, 1.4, 0.3],
[ 5.7, 3.8, 1.7, 0.3],
[ 5.1, 3.8, 1.5, 0.3],
[ 5.4, 3.4, 1.7, 0.2],
[ 5.1, 3.7, 1.5, 0.4],
[ 4.6, 3.6, 1. , 0.2],
[ 5.1, 3.3, 1.7, 0.5],
[ 4.8, 3.4, 1.9, 0.2],
[ 5. , 3. , 1.6, 0.2],
[ 5. , 3.4, 1.6, 0.4],
[ 5.2, 3.5, 1.5, 0.2],
[ 5.2, 3.4, 1.4, 0.2],
[ 4.7, 3.2, 1.6, 0.2],
[ 4.8, 3.1, 1.6, 0.2],
[ 5.4, 3.4, 1.5, 0.4],
[ 5.2, 4.1, 1.5, 0.1],
[ 5.5, 4.2, 1.4, 0.2],
[ 4.9, 3.1, 1.5, 0.1],
[ 5. , 3.2, 1.2, 0.2],
[ 5.5, 3.5, 1.3, 0.2],
[ 4.9, 3.1, 1.5, 0.1],
[ 4.4, 3. , 1.3, 0.2],
[ 5.1, 3.4, 1.5, 0.2],
[ 5. , 3.5, 1.3, 0.3],
[ 4.5, 2.3, 1.3, 0.3],
[ 4.4, 3.2, 1.3, 0.2],
[ 5. , 3.5, 1.6, 0.6],
[ 5.1, 3.8, 1.9, 0.4],
[ 4.8, 3. , 1.4, 0.3],
[ 5.1, 3.8, 1.6, 0.2],
[ 4.6, 3.2, 1.4, 0.2],
[ 5.3, 3.7, 1.5, 0.2],
[ 5. , 3.3, 1.4, 0.2],
[ 7. , 3.2, 4.7, 1.4],
[ 6.4, 3.2, 4.5, 1.5],
[ 6.9, 3.1, 4.9, 1.5],
[ 5.5, 2.3, 4. , 1.3],
[ 6.5, 2.8, 4.6, 1.5],
[ 5.7, 2.8, 4.5, 1.3],
[ 6.3, 3.3, 4.7, 1.6],
[ 4.9, 2.4, 3.3, 1. ],
[ 6.6, 2.9, 4.6, 1.3],
[ 5.2, 2.7, 3.9, 1.4],
[ 5. , 2. , 3.5, 1. ],
[ 5.9, 3. , 4.2, 1.5],
[ 6. , 2.2, 4. , 1. ],
[ 6.1, 2.9, 4.7, 1.4],
[ 5.6, 2.9, 3.6, 1.3],
[ 6.7, 3.1, 4.4, 1.4],
[ 5.6, 3. , 4.5, 1.5],
[ 5.8, 2.7, 4.1, 1. ],
[ 6.2, 2.2, 4.5, 1.5],
[ 5.6, 2.5, 3.9, 1.1],
[ 5.9, 3.2, 4.8, 1.8],
[ 6.1, 2.8, 4. , 1.3],
[ 6.3, 2.5, 4.9, 1.5],
[ 6.1, 2.8, 4.7, 1.2],
[ 6.4, 2.9, 4.3, 1.3],
[ 6.6, 3. , 4.4, 1.4],
[ 6.8, 2.8, 4.8, 1.4],
[ 6.7, 3. , 5. , 1.7],
[ 6. , 2.9, 4.5, 1.5],
[ 5.7, 2.6, 3.5, 1. ],
[ 5.5, 2.4, 3.8, 1.1],
[ 5.5, 2.4, 3.7, 1. ],
[ 5.8, 2.7, 3.9, 1.2],
[ 6. , 2.7, 5.1, 1.6],
[ 5.4, 3. , 4.5, 1.5],
[ 6. , 3.4, 4.5, 1.6],
[ 6.7, 3.1, 4.7, 1.5],
[ 6.3, 2.3, 4.4, 1.3],
[ 5.6, 3. , 4.1, 1.3],
[ 5.5, 2.5, 4. , 1.3],
[ 5.5, 2.6, 4.4, 1.2],
[ 6.1, 3. , 4.6, 1.4],
[ 5.8, 2.6, 4. , 1.2],
[ 5. , 2.3, 3.3, 1. ],
[ 5.6, 2.7, 4.2, 1.3],
[ 5.7, 3. , 4.2, 1.2],
[ 5.7, 2.9, 4.2, 1.3],
[ 6.2, 2.9, 4.3, 1.3],
[ 5.1, 2.5, 3. , 1.1],
[ 5.7, 2.8, 4.1, 1.3],
[ 6.3, 3.3, 6. , 2.5],
[ 5.8, 2.7, 5.1, 1.9],
[ 7.1, 3. , 5.9, 2.1],
[ 6.3, 2.9, 5.6, 1.8],
[ 6.5, 3. , 5.8, 2.2],
[ 7.6, 3. , 6.6, 2.1],
[ 4.9, 2.5, 4.5, 1.7],
[ 7.3, 2.9, 6.3, 1.8],
[ 6.7, 2.5, 5.8, 1.8],
[ 7.2, 3.6, 6.1, 2.5],
[ 6.5, 3.2, 5.1, 2. ],
[ 6.4, 2.7, 5.3, 1.9],
[ 6.8, 3. , 5.5, 2.1],
[ 5.7, 2.5, 5. , 2. ],
[ 5.8, 2.8, 5.1, 2.4],
[ 6.4, 3.2, 5.3, 2.3],
[ 6.5, 3. , 5.5, 1.8],
[ 7.7, 3.8, 6.7, 2.2],
[ 7.7, 2.6, 6.9, 2.3],
[ 6. , 2.2, 5. , 1.5],
[ 6.9, 3.2, 5.7, 2.3],
[ 5.6, 2.8, 4.9, 2. ],
[ 7.7, 2.8, 6.7, 2. ],
[ 6.3, 2.7, 4.9, 1.8],
[ 6.7, 3.3, 5.7, 2.1],
[ 7.2, 3.2, 6. , 1.8],
[ 6.2, 2.8, 4.8, 1.8],
[ 6.1, 3. , 4.9, 1.8],
[ 6.4, 2.8, 5.6, 2.1],
[ 7.2, 3. , 5.8, 1.6],
[ 7.4, 2.8, 6.1, 1.9],
[ 7.9, 3.8, 6.4, 2. ],
[ 6.4, 2.8, 5.6, 2.2],
[ 6.3, 2.8, 5.1, 1.5],
[ 6.1, 2.6, 5.6, 1.4],
[ 7.7, 3. , 6.1, 2.3],
[ 6.3, 3.4, 5.6, 2.4],
[ 6.4, 3.1, 5.5, 1.8],
[ 6. , 3. , 4.8, 1.8],
[ 6.9, 3.1, 5.4, 2.1],
[ 6.7, 3.1, 5.6, 2.4],
[ 6.9, 3.1, 5.1, 2.3],
[ 5.8, 2.7, 5.1, 1.9],
[ 6.8, 3.2, 5.9, 2.3],
[ 6.7, 3.3, 5.7, 2.5],
[ 6.7, 3. , 5.2, 2.3],
[ 6.3, 2.5, 5. , 1.9],
[ 6.5, 3. , 5.2, 2. ],
[ 6.2, 3.4, 5.4, 2.3],
[ 5.9, 3. , 5.1, 1.8]]), 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]), 'DESCR': 'Iris Plants Database\n\nNotes\n-----\nData Set Characteristics:\n :Number of Instances: 150 (50 in each of three classes)\n :Number of Attributes: 4 numeric, predictive attributes and the class\n
:Attribute Information:\n - sepal length in cm\n - sepal width in cm\n - petal length in cm\n - petal width in cm\n - class:\n - Iris-Setosa\n - Iris-Versicolour\n - Iris-Virginica\n
:Summary Statistics:\n\n ============== ==== ==== ======= ===== ====================\n Min Max Mean SD Class Correlation\n ============== ==== ==== ======= ===== ====================\n sepal length: 4.3 7.9 5.84
0.83 0.7826\n sepal width: 2.0 4.4 3.05 0.43 -0.4194\n petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)\n petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)\n ============== ==== ==== ======= ===== ====================\n\n
:Missing Attribute Values: None\n :Class Distribution: 33.3% for each of 3 classes.\n :Creator: R.A. Fisher\n :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n :Date: July, 1988\n\nThis is a copy of UCI ML iris datasets.\nhttp://archive.ics.uci.edu/ml/datasets/Iris\n\nThe
famous Iris database, first used by Sir R.A Fisher\n\nThis is perhaps the best known database to be found in the\npattern recognition literature. Fisher\'s paper is a classic in the field and\nis referenced frequently to this day. (See Duda & Hart, for example.)
The\ndata set contains 3 classes of 50 instances each, where each class refers to a\ntype of iris plant. One class is linearly separable from the other 2; the\nlatter are NOT linearly separable from each other.\n\nReferences\n----------\n - Fisher,R.A.
"The use of multiple measurements in taxonomic problems"\n Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to\n Mathematical Statistics" (John Wiley, NY, 1950).\n - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene
Analysis.\n (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.\n - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System\n Structure and Classification Rule for Recognition in Partially Exposed\n Environments". IEEE
Transactions on Pattern Analysis and Machine\n Intelligence, Vol. PAMI-2, No. 1, 67-71.\n - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions\n on Information Theory, May 1972, 431-433.\n - See also: 1988 MLC Proceedings,
54-64. Cheeseman et al"s AUTOCLASS II\n conceptual clustering system finds 3 classes in the data.\n - Many, many more ...\n', 'feature_names': ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']}

>>> samples = iris.data
>>> print samples
[[ 5.1 3.5 1.4 0.2]
[ 4.9 3. 1.4 0.2]
[ 4.7 3.2 1.3 0.2]
[ 4.6 3.1 1.5 0.2]
[ 5. 3.6 1.4 0.2]
[ 5.4 3.9 1.7 0.4]
[ 4.6 3.4 1.4 0.3]
[ 5. 3.4 1.5 0.2]
[ 4.4 2.9 1.4 0.2]
[ 4.9 3.1 1.5 0.1]
[ 5.4 3.7 1.5 0.2]
[ 4.8 3.4 1.6 0.2]
[ 4.8 3. 1.4 0.1]
[ 4.3 3. 1.1 0.1]
[ 5.8 4. 1.2 0.2]
[ 5.7 4.4 1.5 0.4]
[ 5.4 3.9 1.3 0.4]
[ 5.1 3.5 1.4 0.3]
[ 5.7 3.8 1.7 0.3]
[ 5.1 3.8 1.5 0.3]
[ 5.4 3.4 1.7 0.2]
[ 5.1 3.7 1.5 0.4]
[ 4.6 3.6 1. 0.2]
[ 5.1 3.3 1.7 0.5]
[ 4.8 3.4 1.9 0.2]
[ 5. 3. 1.6 0.2]
[ 5. 3.4 1.6 0.4]
[ 5.2 3.5 1.5 0.2]
[ 5.2 3.4 1.4 0.2]
[ 4.7 3.2 1.6 0.2]
[ 4.8 3.1 1.6 0.2]
[ 5.4 3.4 1.5 0.4]
[ 5.2 4.1 1.5 0.1]
[ 5.5 4.2 1.4 0.2]
[ 4.9 3.1 1.5 0.1]
[ 5. 3.2 1.2 0.2]
[ 5.5 3.5 1.3 0.2]
[ 4.9 3.1 1.5 0.1]
[ 4.4 3. 1.3 0.2]
[ 5.1 3.4 1.5 0.2]
[ 5. 3.5 1.3 0.3]
[ 4.5 2.3 1.3 0.3]
[ 4.4 3.2 1.3 0.2]
[ 5. 3.5 1.6 0.6]
[ 5.1 3.8 1.9 0.4]
[ 4.8 3. 1.4 0.3]
[ 5.1 3.8 1.6 0.2]
[ 4.6 3.2 1.4 0.2]
[ 5.3 3.7 1.5 0.2]
[ 5. 3.3 1.4 0.2]
[ 7. 3.2 4.7 1.4]
[ 6.4 3.2 4.5 1.5]
[ 6.9 3.1 4.9 1.5]
[ 5.5 2.3 4. 1.3]
[ 6.5 2.8 4.6 1.5]
[ 5.7 2.8 4.5 1.3]
[ 6.3 3.3 4.7 1.6]
[ 4.9 2.4 3.3 1. ]
[ 6.6 2.9 4.6 1.3]
[ 5.2 2.7 3.9 1.4]
[ 5. 2. 3.5 1. ]
[ 5.9 3. 4.2 1.5]
[ 6. 2.2 4. 1. ]
[ 6.1 2.9 4.7 1.4]
[ 5.6 2.9 3.6 1.3]
[ 6.7 3.1 4.4 1.4]
[ 5.6 3. 4.5 1.5]
[ 5.8 2.7 4.1 1. ]
[ 6.2 2.2 4.5 1.5]
[ 5.6 2.5 3.9 1.1]
[ 5.9 3.2 4.8 1.8]
[ 6.1 2.8 4. 1.3]
[ 6.3 2.5 4.9 1.5]
[ 6.1 2.8 4.7 1.2]
[ 6.4 2.9 4.3 1.3]
[ 6.6 3. 4.4 1.4]
[ 6.8 2.8 4.8 1.4]
[ 6.7 3. 5. 1.7]
[ 6. 2.9 4.5 1.5]
[ 5.7 2.6 3.5 1. ]
[ 5.5 2.4 3.8 1.1]
[ 5.5 2.4 3.7 1. ]
[ 5.8 2.7 3.9 1.2]
[ 6. 2.7 5.1 1.6]
[ 5.4 3. 4.5 1.5]
[ 6. 3.4 4.5 1.6]
[ 6.7 3.1 4.7 1.5]
[ 6.3 2.3 4.4 1.3]
[ 5.6 3. 4.1 1.3]
[ 5.5 2.5 4. 1.3]
[ 5.5 2.6 4.4 1.2]
[ 6.1 3. 4.6 1.4]
[ 5.8 2.6 4. 1.2]
[ 5. 2.3 3.3 1. ]
[ 5.6 2.7 4.2 1.3]
[ 5.7 3. 4.2 1.2]
[ 5.7 2.9 4.2 1.3]
[ 6.2 2.9 4.3 1.3]
[ 5.1 2.5 3. 1.1]
[ 5.7 2.8 4.1 1.3]
[ 6.3 3.3 6. 2.5]
[ 5.8 2.7 5.1 1.9]
[ 7.1 3. 5.9 2.1]
[ 6.3 2.9 5.6 1.8]
[ 6.5 3. 5.8 2.2]
[ 7.6 3. 6.6 2.1]
[ 4.9 2.5 4.5 1.7]
[ 7.3 2.9 6.3 1.8]
[ 6.7 2.5 5.8 1.8]
[ 7.2 3.6 6.1 2.5]
[ 6.5 3.2 5.1 2. ]
[ 6.4 2.7 5.3 1.9]
[ 6.8 3. 5.5 2.1]
[ 5.7 2.5 5. 2. ]
[ 5.8 2.8 5.1 2.4]
[ 6.4 3.2 5.3 2.3]
[ 6.5 3. 5.5 1.8]
[ 7.7 3.8 6.7 2.2]
[ 7.7 2.6 6.9 2.3]
[ 6. 2.2 5. 1.5]
[ 6.9 3.2 5.7 2.3]
[ 5.6 2.8 4.9 2. ]
[ 7.7 2.8 6.7 2. ]
[ 6.3 2.7 4.9 1.8]
[ 6.7 3.3 5.7 2.1]
[ 7.2 3.2 6. 1.8]
[ 6.2 2.8 4.8 1.8]
[ 6.1 3. 4.9 1.8]
[ 6.4 2.8 5.6 2.1]
[ 7.2 3. 5.8 1.6]
[ 7.4 2.8 6.1 1.9]
[ 7.9 3.8 6.4 2. ]
[ 6.4 2.8 5.6 2.2]
[ 6.3 2.8 5.1 1.5]
[ 6.1 2.6 5.6 1.4]
[ 7.7 3. 6.1 2.3]
[ 6.3 3.4 5.6 2.4]
[ 6.4 3.1 5.5 1.8]
[ 6. 3. 4.8 1.8]
[ 6.9 3.1 5.4 2.1]
[ 6.7 3.1 5.6 2.4]
[ 6.9 3.1 5.1 2.3]
[ 5.8 2.7 5.1 1.9]
[ 6.8 3.2 5.9 2.3]
[ 6.7 3.3 5.7 2.5]
[ 6.7 3. 5.2 2.3]
[ 6.3 2.5 5. 1.9]
[ 6.5 3. 5.2 2. ]
[ 6.2 3.4 5.4 2.3]
[ 5.9 3. 5.1 1.8]]
>>> target = iris.target
>>> print target
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2
2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
2 2]
>>> lrm.fit(samples, target) #使用iris格式数据训练LR模型