sklearn:LogisticRegression - predict_proba(X) - 计算

时间:2016-02-10 12:25:47

标签: scikit-learn logistic-regression

我想知道是否有人可以快速查看以下代码片段并指出我在计算模型中每个类的样本概率和相关代码错误时发现我的误解。我试图手动计算sklearn函数lm.predict_proba(X)提供的结果,遗憾的是结果不同,所以我犯了一个错误。

我认为该错误将在以下代码演练的“d”部分中进行。也许在数学中,但我不明白为什么。

a)创建和训练逻辑回归模型(工作正常)

lm = LogisticRegression(random_state=413, multi_class='multinomial', solver='newton-cg')
lm.fit(X, train_labels)

b)保存系数和偏差(工作正常)

W = lm.coef_
b = lm.intercept_

c)使用lm.predict_proba(X)(工作正常)

def reshape_single_element(x,num):
    singleElement = x[num]
    nx,ny = singleElement.shape
    return  singleElement.reshape((1,nx*ny))

select_image_number = 6 
X_select_image_data=reshape_single_element(train_dataset,select_image_number)
Y_probabilities =  lm.predict_proba(X_select_image_data)
Y_pandas_probabilities = pd.Series(Y_probabilities[0], index=['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j'])
print"estimate probabilities for each class: \n" ,Y_pandas_probabilities , "\n"
print"all probabilities by lm.predict_proba(..) sum up to ", np.sum(Y_probabilities) , "\n"

输出结果为:

estimate probabilities for each class: 
a 0.595426
b 0.019244
c 0.001343
d 0.004033
e 0.017185
f 0.004193
g 0.160380
h 0.158245
i 0.003093
j 0.036860
dtype: float64 
all probabilities by lm.predict_proba(..) sum up to 1.0

d)手动执行lm.predict_proba完成的计算(没有错误/警告,但结果不一样)

manual_calculated_probabilities = []
for select_class_k in range(0,10):  #a=0. b=1, c=3 ...
    z_for_class_k = (np.sum(W[select_class_k] *X_select_image_data) + b[select_class_k] )
    p_for_class_k = 1/ (1 + math.exp(-z_for_class_k))
    manual_calculated_probabilities.append(p_for_class_k)

print "formula: ", manual_calculated_probabilities , "\n"

def softmax(x):
    """Compute softmax values for each sets of scores in x."""
    e = np.exp(x)
    dist = e / np.sum(np.exp(x),axis=0)
    return dist

abc = softmax(manual_calculated_probabilities)
print "softmax:" , abc

输出结果为:

formula: [0.9667598370531315, 0.48453459121301334, 0.06154496922245115, 0.16456194859398865, 0.45634781280053394, 0.16999340794727547, 0.8867996361191054, 0.8854473986336552, 0.13124464656251109, 0.642913996162282]

softmax: [ 0.15329642 0.09464644 0.0620015 0.0687293 0.0920159 0.069103610.14151607 0.14132483 0.06647715 0.11088877]
由于github logistic.py

的评论,使用了Softmax
For a multi_class problem, if multi_class is set to be "multinomial" the softmax function is used to find the predicted probability of each class.

注意:

print "shape of X: " , X_select_image_data.shape
print "shape of W: " , W.shape
print "shape of b: " , b.shape

shape of X:  (1, 784)
shape of W:  (10, 784)
shape of b:  (10,)

我发现了一个非常相似的问题here,但遗憾的是我无法将其改编为我的代码,因此预测结果相同。我尝试了许多不同的组合来计算变量'z_for_class_k'和'p_for_class_k',但遗憾的是没有成功地从'predict_proba(X)'重现预测值。

3 个答案:

答案 0 :(得分:0)

我认为问题出在

p_for_class_k = 1 /(1 + math.exp(-z_for_class_k))

1 / (1 + exp(-logit))是一种简化,仅适用于二进制问题。

在简化之前,真实方程式如下:

p_for_classA = exp(logit_classA) / [1 + exp(logit_classA) + exp(logit_classB) ... + exp(logit_classC)]

换句话说,在计算特定类别的概率时,您必须将其他类别的所有权重和偏差也纳入公式中。

我没有数据可以验证这一点,但是希望这可以为您指明正确的方向。

答案 1 :(得分:0)

改变

p_for_class_k = 1/ (1 + math.exp(-z_for_class_k))
manual_calculated_probabilities.append(p_for_class_k)

manual_calculated_probabilities.append(z_for_class_k)

又名 softmax 的输入是“z”s 而不是“p”s,在你的符号中。 multinomial logistic

答案 2 :(得分:0)

通过执行以下操作,我能够复制方法 lr.predict_proba

>>> sigmoid = lambda x: 1/(1+np.exp(-x))
>>> sigmoid(lr.intercept_+np.sum(lr.coef_*X.values, axis=1))

假设 X 是一个 numpy 数组,lr 是一个来自 sklearn 的对象。