更新 function.py
Gitea Actions Experiment Test / Experiment-Actions (push) Successful in 20s

This commit is contained in:
Wyy
2024-11-02 20:59:59 +08:00
parent b0c361f395
commit e52eb8eabe
+26 -28
View File
@@ -1,4 +1,5 @@
import numpy as np import numpy as np
from sklearn.preprocessing import StandardScaler
""" """
请在这里填写学号和姓名,不填写即成绩无效。 请在这里填写学号和姓名,不填写即成绩无效。
@@ -37,20 +38,20 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000):
return weights return weights
def predict_logreg(X, weights): def predict_logreg(inX, weights):
""" """
对率回归预测函数。 对率回归预测函数。
Args: Args:
- X (numpy array): 输入待分类的样本。 - inX (numpy array): 输入待分类的样本。
- weights (numpy array): 训练得到的权重。 - weights (numpy array): 训练得到的权重。
Returns: Returns:
- numpy array: 预测的分类标签。 - int: 预测的分类标签。
""" """
linear_model = np.dot(X, weights) linear_model = np.dot(inX, weights)
y_predicted = sigmoid(linear_model) y_predicted = sigmoid(linear_model)
return (y_predicted > 0.5).astype(int) return 1 if y_predicted > 0.5 else 0
def load_data(filepath): def load_data(filepath):
@@ -64,40 +65,37 @@ def load_data(filepath):
- X (np.array): 特征数据。 - X (np.array): 特征数据。
- y (np.array): 标签数据。 - y (np.array): 标签数据。
""" """
# 使用 np.genfromtxt 加载数据,并且忽略文件中不能转换为 float 的行 data = np.genfromtxt(filepath, delimiter=' ', dtype=float)
# 更新分隔符为逗号,根据实际格式来修改,通常csv用',',txt文件则可能用'\t'或者' '来分隔 X = data[:, :-1]
data = np.genfromtxt(filepath, delimiter=',', dtype=float, filling_values=np.nan) y = data[:, -1]
# 删除所有包含缺失值的行
data = data[~np.isnan(data).any(axis=1)]
# 确保数据的正确性: 不同于训练集的标签列
if data.ndim == 1:
data = np.array([data])
# 假设最后一列为标签
X = data[:, :-1] # 特征
y = data[:, -1] # 标签
return X, y return X, y
if __name__ == "__main__": def main():
# 加载训练集 # 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 # 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")
# 确保训练集和测试集特征数量匹配 # 标准化特征数据
if X_train.shape[1] != X_test.shape[1]: scaler = StandardScaler()
raise ValueError("训练集和测试集特征数量不匹配!") X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
# 训练对率回归模型 # 训练对率回归模型
weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000) weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
# 测试多个数据 # 测试单个数据
y_pred = predict_logreg(X_test, weights) correct_predictions = 0
for i in range(X_test.shape[0]):
y_pred = predict_logreg(X_test[i], weights)
if y_pred == y_test[i]:
correct_predictions += 1
# 输出部分预测结果 accuracy = correct_predictions / X_test.shape[0]
for i in range(min(10, len(y_pred))): # 只输出前10个预测结果 print(f"Accuracy: {accuracy:.2f}")
print(f"预测结果: {y_pred[i]}, 实际结果: {y_test[i]}")
if __name__ == "__main__":
main()