Template
64 lines
1.9 KiB
Python
64 lines
1.9 KiB
Python
import numpy as np
|
|
|
|
id = "202210423224"
|
|
name = "吴杨洋"
|
|
|
|
def sigmoid(z):
|
|
return 1 / (1 + np.exp(-np.clip(z, -500, 500)))
|
|
|
|
def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
|
|
m, n = X.shape
|
|
weights = np.zeros(n)
|
|
for j in range(numIter):
|
|
for i in range(m):
|
|
z = np.dot(X[i], weights)
|
|
h = sigmoid(z)
|
|
error = y[i] - h
|
|
gradient = X[i] * error
|
|
reg_term = lambda_reg * weights
|
|
gradient += reg_term
|
|
weights -= learning_rate * gradient
|
|
return weights
|
|
|
|
def predict_logreg(inX, weights):
|
|
z = np.dot(inX, weights)
|
|
prob = sigmoid(z)
|
|
return 1 if prob >= 0.5 else 0
|
|
|
|
def load_data(filepath):
|
|
file = open(filepath)
|
|
fr = file.readlines()
|
|
data_list = []
|
|
y = []
|
|
for data in fr:
|
|
data = data.strip()
|
|
data = data.split()
|
|
if len(data) < 26: # 确保每行数据有足够的元素
|
|
continue
|
|
y.append(1 if data[22] in ['2', '3'] else 0) # 假设标签是 '2' 或 '3' 为正类
|
|
data_25 = data[24]
|
|
data = [float(x) if x != '?' else 0 for x in data[:24] + data_25.split(',')] # 处理缺失值
|
|
data_list.append(data)
|
|
X = np.array(data_list)
|
|
return X, np.array(y)
|
|
|
|
def standardize(X):
|
|
mean = X.mean(axis=0)
|
|
std = X.std(axis=0)
|
|
return (X - mean) / std, mean, std
|
|
|
|
def main():
|
|
X_train, y_train = load_data("./data/horse-colic.data")
|
|
X_test, y_test = load_data("./data/horse-colic.test")
|
|
|
|
X_train, mean, std = standardize(X_train)
|
|
X_test = (X_test - mean) / std
|
|
|
|
weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01, lambda_reg=0.1)
|
|
|
|
y_pred_test = [predict_logreg(x, weights) for x in X_test]
|
|
accuracy_test = np.mean(y_pred_test == y_test)
|
|
print(f"Test Accuracy: {accuracy_test:.2f}")
|
|
|
|
if __name__.split("__main__"):
|
|
main() |