更新 function.py

function.py

@@ -28,7 +28,7 @@ name = "邓龙树"
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
-def sigmoid(intX):  #激活函数，逻辑回归中，将线性组合转换为概率
+def sigmoid(intX):  # 激活函数，逻辑回归中，将线性组合转换为概率
     return 1.0 / (1 + np.exp(-intX))
 
 def train_logreg(X, y, numIter=150):   # 训练逻辑回归模型的函数，使用梯度下降算法。
@@ -45,7 +45,6 @@ def train_logreg(X, y, numIter=150):   # 训练逻辑回归模型的函数，使
             del(dataIndex[randIndex])
     return weights
 
-
 def predict_logreg(X, weights):
     z = np.dot(X, weights)
     h = sigmoid(z)
@@ -55,8 +54,6 @@ def load_data(filepath):
     data = []
     labels = []
     with open(filepath, 'r') as f:
-        lines = f.readlines()
-        for line in lines:
         for line in f:
             line = line.strip().split()
             if len(line) >= 1 and line[-1].isdigit():
@@ -66,23 +63,17 @@ def load_data(filepath):
 
     data = np.array(data)
     labels = np.array(labels)
-    target_variable = labels
+    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
-    target_variable[np.logical_or(target_variable == 2, target_variable == 3)] = 0
     data = np.delete(data, [2] + list(range(23, 28)), axis=1)
     scaler = StandardScaler()
     data = scaler.fit_transform(data)
 
-    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
-
     return data, target_variable
 
-
 def accuracy(X, y, weights):
     predictions = predict_logreg(X, weights)
     return np.mean(predictions == y)
 
-if __name__ == '__main__':
-
 if __name__ == "__main__":
     X_train, y_train = load_data("./horse-colic.data")
     X_test, y_test = load_data("./horse-colic.test")
@@ -97,3 +88,4 @@ if __name__ == "__main__":
 
     final_accuracy = accuracy(X_test, y_test, final_weights)
     print(f"最终测试集的准确率: {final_accuracy:.4f}")
+