generated from LufsX/Experiment-LogReg
This commit is contained in:
+9
-49
@@ -1,10 +1,5 @@
|
|||||||
import numpy as np
|
import numpy as np
|
||||||
|
|
||||||
"""
|
|
||||||
实验说明:
|
|
||||||
- 自行编写实现数据加载与预测病马死亡的对率回归算法。
|
|
||||||
"""
|
|
||||||
|
|
||||||
id = "202210423218"
|
id = "202210423218"
|
||||||
name = "唐一鸣"
|
name = "唐一鸣"
|
||||||
|
|
||||||
@@ -12,17 +7,6 @@ def sigmoid(z):
|
|||||||
return 1 / (1 + np.exp(-z))
|
return 1 / (1 + np.exp(-z))
|
||||||
|
|
||||||
def train_logreg(X, y, other_params=""):
|
def train_logreg(X, y, other_params=""):
|
||||||
"""
|
|
||||||
对率回归训练函数。
|
|
||||||
|
|
||||||
Args:
|
|
||||||
- X (numpy array): 特征数据。
|
|
||||||
- y (numpy array): 标签数据。
|
|
||||||
- other_params (str): 其它参数,可选设置。
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
- numpy array: 训练得到的权重。
|
|
||||||
"""
|
|
||||||
m, n = X.shape
|
m, n = X.shape
|
||||||
weights = np.zeros(n)
|
weights = np.zeros(n)
|
||||||
learning_rate = 0.01
|
learning_rate = 0.01
|
||||||
@@ -31,52 +15,32 @@ def train_logreg(X, y, other_params=""):
|
|||||||
for _ in range(num_iterations):
|
for _ in range(num_iterations):
|
||||||
linear_model = np.dot(X, weights)
|
linear_model = np.dot(X, weights)
|
||||||
y_predicted = sigmoid(linear_model)
|
y_predicted = sigmoid(linear_model)
|
||||||
|
|
||||||
# Gradient descent
|
|
||||||
gradient = np.dot(X.T, (y_predicted - y)) / m
|
gradient = np.dot(X.T, (y_predicted - y)) / m
|
||||||
weights -= learning_rate * gradient
|
weights -= learning_rate * gradient
|
||||||
|
|
||||||
return weights
|
return weights
|
||||||
|
|
||||||
def predict_logreg(inX, weights):
|
def predict_logreg(inX, weights):
|
||||||
"""
|
|
||||||
对率回归预测函数。
|
|
||||||
|
|
||||||
Args:
|
|
||||||
- inX (numpy array): 输入待分类的样本。
|
|
||||||
- weights (numpy array): 训练得到的权重。
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
- int: 预测的分类标签。
|
|
||||||
"""
|
|
||||||
prob = sigmoid(np.dot(inX, weights))
|
prob = sigmoid(np.dot(inX, weights))
|
||||||
return 1 if prob >= 0.5 else 0
|
return 1 if prob >= 0.5 else 0
|
||||||
|
|
||||||
def load_data(filepath):
|
def load_data(filepath):
|
||||||
"""
|
|
||||||
从文件中加载数据,处理缺失值。
|
|
||||||
|
|
||||||
Args:
|
|
||||||
- filepath (str): 数据文件路径。
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
- np.array: 特征数据。
|
|
||||||
- np.array: 标签数据。
|
|
||||||
"""
|
|
||||||
with open(filepath, 'r') as f:
|
with open(filepath, 'r') as f:
|
||||||
lines = f.readlines()
|
lines = f.readlines()
|
||||||
|
|
||||||
data = []
|
data = []
|
||||||
for line in lines:
|
for line in lines:
|
||||||
# 替换缺失值 '?' 为 np.nan
|
|
||||||
row = line.strip().split()
|
row = line.strip().split()
|
||||||
row = [float(x) if x != '?' else np.nan for x in row]
|
row = [float(x) if x != '?' else np.nan for x in row]
|
||||||
data.append(row)
|
data.append(row)
|
||||||
|
|
||||||
data = np.array(data)
|
data = np.array(data)
|
||||||
|
|
||||||
# 处理缺失值:用均值替代缺失值
|
# 用均值替代缺失值
|
||||||
data = np.where(np.isnan(data), np.nanmean(data, axis=0), data)
|
for i in range(data.shape[1] - 1): # 只处理特征列
|
||||||
|
if np.any(np.isnan(data[:, i])):
|
||||||
|
mean_value = np.nanmean(data[:, i])
|
||||||
|
data[:, i] = np.where(np.isnan(data[:, i]), mean_value, data[:, i])
|
||||||
|
|
||||||
# 特征为前n-1列,标签为最后一列
|
# 特征为前n-1列,标签为最后一列
|
||||||
X = data[:, :-1]
|
X = data[:, :-1]
|
||||||
@@ -84,19 +48,15 @@ def load_data(filepath):
|
|||||||
|
|
||||||
return X, y
|
return X, y
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
# 以下代码可用于测试,可自行随意修改
|
|
||||||
# 加载训练集
|
|
||||||
X_train, y_train = load_data("./data/horse-colic.data")
|
X_train, y_train = load_data("./data/horse-colic.data")
|
||||||
|
|
||||||
# 加载测试集
|
|
||||||
X_test, y_test = load_data("./data/horse-colic.test")
|
X_test, y_test = load_data("./data/horse-colic.test")
|
||||||
|
|
||||||
# 训练对率回归模型
|
|
||||||
weights = train_logreg(X_train, y_train)
|
weights = train_logreg(X_train, y_train)
|
||||||
|
|
||||||
# 测试单个数据
|
# 测试单个数据
|
||||||
y_pred = predict_logreg(X_test[11], weights)
|
test_index = 11 # 选择要测试的索引
|
||||||
print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
|
y_pred = predict_logreg(X_test[test_index], weights)
|
||||||
|
print(f"预测结果: {y_pred}, 实际结果: {y_test[test_index]}")
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user