LR代码:
import numpy as np
from sklearn.metrics import accuracy_score
class LogisticRegression(object):
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, alpha=0.01, n_iters=1e4):
"""使用梯度下降法训练LR模型"""
assert X_train.shape[0] == y_train.shape[0] #判断长度是否相等
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))
except:
return float('inf')
def dJ(theta, X_b, y):
#求导后公式
return X_b.T.dot(self.sigmoid(X_b.dot(theta)) - y) / len(y)
def gradient_descent(X_b, y, initial_theta, alpha, 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 - alpha * 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, alpha, n_iters)
#截距
self.intercept = self._theta[0]
#x_i前的参数
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
assert X_predict.shape[1] == len(self.coef)
# prob = self.predict_proba(X_predict)
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
assert X_predict.shape[1] == len(self.coef)
prob = self.predict_proba(X_predict)
return np.array(prob >= 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()"
训练:
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from LogisticRegression import LogisticRegression
#取鸢尾花数据集
iris = datasets.load_iris()
X = iris.data
y = iris.target
#筛选特征
X = X[y<2, :2]
y = y[y<2]
#绘制图像
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()
#切分数据集
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=666)
#调用自己写的逻辑回归函数
log_reg = LogisticRegression()
log_reg.fit(X_train, y_train)
print("final score is :%s" % log_reg.score(X_test, y_test))
print("actual prob is :", log_reg.predict_proba(X_test))