3逻辑回归二分类

3逻辑回归二分类

题目：根据学生的俩门学习成绩，预测该学生能否会被大学录取
数据集：ex2data1.txt

1. 数据可视化

# 读取文件
data = pd.read_csv("ex2data1.txt", sep=",", names=["exam1", "exam2", "accepted"])
print(data.head())
# 数据可视化
fig, ax = plt.subplots()
ax.scatter(data[data["accepted"] == 0]["exam1"], data[data["accepted"] == 0]["exam2"], c= "r", marker="x", label="y=0")
ax.scatter(data[data["accepted"] == 1]["exam1"], data[data["accepted"] == 1]["exam2"], c= "b", marker="o", label="y=1")
ax.legend()
ax.set(xlabel="exam1", ylabel= "exam2")
plt.show()

2. 数据集拆分（同以前，封装成一个函数）

def get_xy(data):
    data.insert(0, "ones", 1)
    X_ = data.iloc[:, 0:-1]
    X = X_.values
    y_ = data.iloc[:, -1]
    y = y_.values.reshape(len(y_), 1)
    return X, y


X, y = get_xy(data)
print(X.shape)      # (100,3)
print(y.shape)      # (100, 1)

3. sigmoid函数
   

def sigmoid(z):
    return 1 / (1 + np.exp(-z))

4 cost function

def cost_function(X, y, theta):
    A = sigmoid(X @ theta)
    first = y * np.log(A)
    second = (1-y) * np.log(1 - A)
    return -np.sum(first + second) / len(X)


theta = np.zeros((3, 1))
cost_init = cost_function(X, y, theta)
print(cost_init)    # 0.693

5. 梯度下降
   

def gradient_descent(X, y, theta, alpha, iters):
    costs = []
    for i in range(iters):
        A = sigmoid(X @ theta)
        theta = theta - (alpha / len(X)) * X.T @ (A - y)
        cost = cost_function(X, y, theta)
        costs.append(cost)
        # 抽取几个cost查看，避免太多
        if i % 10000 == 0:
            print(costs)
    return theta, costs


alpha = 0.004
iters = 200000
theta_final, costs = gradient_descent(X, y, theta, alpha, iters)

6. 判断正确率

def predict(X, theta):
    prob = sigmoid(X @ theta)
    return [1 if x >= 0.5 else 0 for x in prob]


y_ = np.array(predict(X,theta_final))
y_pre  = y_.reshape(len(y_), 1)
acc = np.mean(y_pre == y)
print(acc)

正确率达到了0.91

7. 绘制决策边界
   

coef1 = -theta_final[0, 0] / theta_final[2, 0]
coef2 = -theta_final[1, 0] / theta_final[2, 0]

x = np.linspace(20, 100, 100) # 20到100之间均匀生成100个点
f = coef1 + coef2 * x

fig, ax = plt.subplots()
ax.scatter(data[data["accepted"] == 0]["exam1"], data[data["accepted"] == 0]["exam2"], c= "r", marker="x", label="y=0")
ax.scatter(data[data["accepted"] == 1]["exam1"], data[data["accepted"] == 1]["exam2"], c= "b", marker="o", label="y=1")
ax.legend()
ax.set(xlabel="exam1", ylabel= "exam2")
ax.plot(x, f, c="g")
plt.show()