机器学习入门(五)——逻辑回归

一.逻辑回归简介

signoid函数：

import numpy as np
import matplotlib.pyplot as plt
def sigmoid(t):
    return 1. / (1. + np.exp(-t))
x = np.linspace(-10, 10, 500)
plt.plot(x, sigmoid(x))
plt.show()

二.损失函数

当y=1，则当p的值越接近1，损失函数就会越小，反之会无限大。

所求的梯度：

逻辑回归代码：

import numpy as np
from .metrics import accuracy_score
 
class LogisticRegression:
 
    def __init__(self):
        """初始化Logistic Regression模型"""
        self.coef_ = None
        self.intercept_ = None
        self._theta = None
 
    def _sigmoid(self, t):
        return 1. / (1. + np.exp(-t))
 
    def fit(self, X_train, y_train, eta=0.01, n_iters=1e4):
        """根据训练数据集X_train, y_train, 使用梯度下降法训练Logistic Regression模型"""
        assert X_train.shape[0] == y_train.shape[0], \
            "the size of X_train must be equal to the size of y_train"
 
        def J(theta, X_b, y):
            y_hat = self._sigmoid(X_b.dot(theta))
            try:
                return - np.sum(y*np.log(y_hat) + (1-y)*np.log(1-y_hat)) / len(y)
            except:
                return float('inf')
 
        def dJ(theta, X_b, y):
            return X_b.T.dot(self._sigmoid(X_b.dot(theta)) - y) / len(y)
 
        def gradient_descent(X_b, y, initial_theta, eta, n_iters=1e4, epsilon=1e-8):
 
            theta = initial_theta
            cur_iter = 0
 
            while cur_iter < n_iters:
                gradient = dJ(theta, X_b, y)
                last_theta = theta
                theta = theta - eta * gradient
                if (abs(J(theta, X_b, y) - J(last_theta, X_b, y)) < epsilon):
                    break
 
                cur_iter += 1
 
            return theta
 
        X_b = np.hstack([np.ones((len(X_train), 1)), X_train])
        initial_theta = np.zeros(X_b.shape[1])
        self._theta = gradient_descent(X_b, y_train, initial_theta, eta, n_iters)
 
        self.intercept_ = self._theta[0]
        self.coef_ = self._theta[1:]
 
        return self
 
    def predict_proba(self, X_predict):
        """给定待预测数据集X_predict，返回表示X_predict的结果概率向量"""
        assert self.intercept_ is not None and self.coef_ is not None, \
            "must fit before predict!"
        assert X_predict.shape[1] == len(self.coef_), \
            "the feature number of X_predict must be equal to X_train"
 
        X_b = np.hstack([np.ones((len(X_predict), 1)), X_predict])
        return self._sigmoid(X_b.dot(self._theta))
 
    def predict(self, X_predict):
        """给定待预测数据集X_predict，返回表示X_predict的结果向量"""
        assert self.intercept_ is not None and self.coef_ is not None, \
            "must fit before predict!"
        assert X_predict.shape[1] == len(self.coef_), \
            "the feature number of X_predict must be equal to X_train"
 
        proba = self.predict_proba(X_predict)
        return np.array(proba >= 0.5, dtype='int')
 
    def score(self, X_test, y_test):
        """根据测试数据集 X_test 和 y_test 确定当前模型的准确度"""
 
        y_predict = self.predict(X_test)
        return accuracy_score(y_test, y_predict)
 
    def __repr__(self):
        return "LogisticRegression()"

三.决策边界

测试数据集：

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
 
iris = datasets.load_iris()
 
X = iris.data
y = iris.target
 
X = X[y<2,:2]
y = y[y<2]
 
plt.scatter(X[y==0,0], X[y==0,1], color="red")
plt.scatter(X[y==1,0], X[y==1,1], color="blue")
plt.show()

导入自己的逻辑回归：

作图函数：

def plot_decision_boundary(model, axis):    
    x0, x1 = np.meshgrid(
        np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1),
        np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1),
    )
    X_new = np.c_[x0.ravel(), x1.ravel()]
    y_predict = model.predict(X_new)
    zz = y_predict.reshape(x0.shape)
    
    from matplotlib.colors import ListedColormap
    custom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])
    
    plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap)

plot_decision_boundary(log_reg, axis=[4, 7.5, 1.5, 4.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

kNN的决策边界:

from sklearn.neighbors import KNeighborsClassifier

knn_clf = KNeighborsClassifier()
knn_clf.fit(X_train,y_train)
plot_decision_boundary(knn_clf, axis=[4, 7.5, 1.5, 4.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

分成3类：

knn_clf_all = KNeighborsClassifier(n_neighbors=50)
knn_clf_all.fit(iris.data[:,:2], iris.target)

plot_decision_boundary(knn_clf_all, axis=[4, 8, 1.5, 4.5])
plt.scatter(iris.data[iris.target==0,0], iris.data[iris.target==0,1])
plt.scatter(iris.data[iris.target==1,0], iris.data[iris.target==1,1])
plt.scatter(iris.data[iris.target==2,0], iris.data[iris.target==2,1])
plt.show()

四.在逻辑回归中使用多项式特征

测试数据：

np.random.seed(666)
X = np.random.normal(0,1,size=(200,2))
y = np.array((X[:,0]**2+X[:,1]**2)<1.5,dtype='int')
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

逻辑回归是用一条直线来分割，会出现以下情况：

log_reg = LogisticRegression()
log_reg.fit(X,y)
plot_decision_boundary(log_reg, axis=[-4, 4, -4, 4])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

使用二次方程：

from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
 
def PolynomialLogisticRegression(degree):
    return Pipeline([
        ('poly', PolynomialFeatures(degree=degree)),
        ('std_scaler', StandardScaler()),
        ('log_reg', LogisticRegression())
    ])
poly_log_reg = PolynomialLogisticRegression(degree=2)
poly_log_reg.fit(X,y)
plot_decision_boundary(poly_log_reg, axis=[-4, 4, -4, 4])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

次数过高，会产生过拟合：

poly_log_reg = PolynomialLogisticRegression(degree=20)
poly_log_reg.fit(X,y)
plot_decision_boundary(poly_log_reg, axis=[-4, 4, -4, 4])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

五.scikit-learn中的逻辑回归

• 测试数据：

np.random.seed(666)
X = np.random.normal(0, 1, size=(200, 2))
y = np.array((X[:,0]**2+X[:,1])<1.5, dtype='int')
for _ in range(20):
    y[np.random.randint(200)] = 1
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

• 线性测试：

from sklearn.linear_model import LogisticRegression 
log_reg = LogisticRegression()
log_reg.fit(X_train, y_train)
log_reg.score(X_train, y_train)      #0.7933333333333333
log_reg.score(X_test, y_test)        #0.86

plot_decision_boundary(log_reg, axis=[-4, 4, -4, 4])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

• 二次测试（效果比较好）：

from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
 
def PolynomialLogisticRegression(degree):
    return Pipeline([
        ('poly', PolynomialFeatures(degree=degree)),
        ('std_scaler', StandardScaler()),
        ('log_reg', LogisticRegression())
    ])

poly_log_reg = PolynomialLogisticRegression(degree=2)
poly_log_reg.fit(X,y)
poly_log_reg.score(X_train, y_train)    #0.9133333333333333
poly_log_reg.score(X_test, y_test)      #0.94

plot_decision_boundary(poly_log_reg, axis=[-4, 4, -4, 4])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

• 二十次测试（发生过拟合）：

poly_log_reg2 = PolynomialLogisticRegression(degree=20)
poly_log_reg2.fit(X_train, y_train)
poly_log_reg2.score(X_train, y_train)    #0.94
poly_log_reg2.score(X_test, y_test)     #0.92

plot_decision_boundary(poly_log_reg2, axis=[-4, 4, -4, 4])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

• 加入参数C（默认penalty=‘l2’）

def PolynomialLogisticRegression(degree, C):
    return Pipeline([
        ('poly', PolynomialFeatures(degree=degree)),
        ('std_scaler', StandardScaler()),
        ('log_reg', LogisticRegression(C=C))
    ])
 
poly_log_reg3 = PolynomialLogisticRegression(degree=20, C=0.1)
poly_log_reg3.fit(X_train, y_train)
poly_log_reg3.score(X_train, y_train)    #0.84
poly_log_reg3.score(X_test, y_test)      #0.92

plot_decision_boundary(poly_log_reg3, axis=[-4, 4, -4, 4])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

• 采用正则 l1：

def PolynomialLogisticRegression(degree, C, penalty='l2'):
    return Pipeline([
        ('poly', PolynomialFeatures(degree=degree)),
        ('std_scaler', StandardScaler()),
        ('log_reg', LogisticRegression(C=C, penalty=penalty,solver='liblinear'))
    ])
 
poly_log_reg4 = PolynomialLogisticRegression(degree=20, C=0.1, penalty='l1')
poly_log_reg4.fit(X_train, y_train)
poly_log_reg4.score(X_train, y_train)   #0.8266666666666667
poly_log_reg4.score(X_test, y_test)     #0.9

plot_decision_boundary(poly_log_reg4, axis=[-4, 4, -4, 4])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

六.OvR与OvO

这种方法比ovr用的时间多，但其分类比较准确。

测试数据：

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
 
iris = datasets.load_iris()
 
X = iris.data[:,:2]
y = iris.target

Changed in version 0.22: Default changed from ‘ovr’ to ‘auto’ in 0.22.

有专门的类：

from sklearn.multiclass import OneVsRestClassifier
 
ovr = OneVsRestClassifier(log_reg)
ovr.fit(X_train, y_train)
ovr.score(X_test, y_test)

from sklearn.multiclass import OneVsOneClassifier
 
ovo = OneVsOneClassifier(log_reg)
ovo.fit(X_train, y_train)
ovo.score(X_test, y_test)