更新 function.py

function.py

@@ -1,7 +1,7 @@
 import numpy as np
+import pandas as pd
 from sklearn.impute import SimpleImputer
 from sklearn.preprocessing import StandardScaler
-import csv
 
 """
 实验说明:
@@ -27,7 +27,7 @@ id = "202210423219"
 name = "李燕如"
 
 
-# 这里写自己的代码实现
+
 def sigmoid(x):
     return 1 / (1 + np.exp(-x))
 
@@ -46,38 +46,6 @@ def predict_logreg(inX, weights):
     probability = sigmoid(linear_output)
     return 1 if probability > 0.5 else 0
 
-def load_data(filepath):
-    # 使用csv模块读取数据
-    data = []
-    with open(filepath, 'r') as file:
-        reader = csv.reader(file, delimiter=' ')
-        for row in reader:
-            if row:  # 确保行不为空
-                # 将非数值和空字符串转换为np.nan，并确保所有行具有相同的列数
-                row = [float(x) if x.replace('.', '', 1).isdigit() or x == '' else np.nan for x in row]
-                # 确保所有行具有相同的列数，可以通过填充缺失的列或截断多余的列来实现
-                while len(row) < 30:  # 假设数据集应该有30列
-                    row.append(np.nan)
-                while len(row) > 30:
-                    row.pop()
-                data.append(row)
-    
-    # 将列表转换为numpy数组
-    data = np.array(data, dtype=float)
-
-    # 使用SimpleImputer填充缺失值
-    imputer = SimpleImputer(missing_values=np.nan, strategy='constant', fill_value=0)
-    data = imputer.fit_transform(data)
-
-    # 分割特征和标签
-    X = data[:, :-1]
-    y = data[:, -1].astype(int)
-
-    # 预处理数据
-    X, y = preprocess_data(X, y)
-
-    return X, y
-
 def preprocess_data(X, y):
     # 合并目标变量的类别
     y[y == 2] = 0
@@ -89,11 +57,34 @@ def preprocess_data(X, y):
 
     return X, y
 
-# 确保其他函数（sigmoid, train_logreg, predict_logreg）保持不变
+def load_data(filepath):
+    # 使用Pandas读取数据，可以更好地处理缺失值和字符串
+    try:
+        data = pd.read_csv(filepath, header=None, sep=r'\s+', on_bad_lines='skip')
+    except pd.errors.ParserError as e:
+        print(f"Error parsing file: {e}")
+        return None, None
+
+    # 将'?'替换为np.nan
+    data.replace('?', np.nan, inplace=True)
+
+    # 使用SimpleImputer填充缺失值
+    imputer = SimpleImputer(missing_values=np.nan, strategy='constant', fill_value=0)
+    data.iloc[:, :-1] = imputer.fit_transform(data.iloc[:, :-1])
+
+    # 将所有列转换为数值类型
+    for col in data.columns[:-1]:
+        data[col] = pd.to_numeric(data[col], errors='coerce')
+
+    X = data.iloc[:, :-1].values
+    y = data.iloc[:, -1].values.astype(int)
+
+    # 预处理数据
+    X, y = preprocess_data(X, y)
+
+    return X, y
 
-# 确保其他函数（sigmoid, train_logreg, predict_logreg）保持不变
 def main():
-    # 更新文件路径以匹配实际位置
     X_train, y_train = load_data("C:/Users/HP/Desktop/机器学习/Experiment-LogReg/data/horse-colic.data")
     X_test, y_test = load_data("C:/Users/HP/Desktop/机器学习/Experiment-LogReg/data/horse-colic.test")