更新 function.py

function.py

@@ -1,51 +1,86 @@
 import numpy as np
 
-def load_data(filepath):
+# 填写学号和姓名
-    for delimiter in [',', ' ', '\t']:
+id = "202210423118"
-        try:
+name = "刘国庆"
-            data = np.genfromtxt(filepath, delimiter=delimiter, missing_values='?', filling_values=np.nan)
-            if data.ndim < 2 or data.shape[1] < 2:
-                continue
-            data = data[~np.isnan(data).any(axis=1)]
-            if data.size == 0:
-                print(f"Error: No valid data after removing NaN rows in file '{filepath}'.")
-                return None, None
-            X = data[:, :-1]
-            y = data[:, -1]
-            if X.shape[0] != y.shape[0]:
-                print(f"Error: Feature and label count mismatch in file '{filepath}'")
-                return None, None
-            print(f"Loaded data from '{filepath}': {X.shape[0]} samples, {X.shape[1]} features.")
-            return X, y
-        except Exception as e:
-            print(f"Error loading data with delimiter '{delimiter}': {e}")
-    print(f"Error: File '{filepath}' may be empty or improperly formatted.")
-    return None, None
 
+# Sigmoid函数
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.01, epochs=1000):
+# 数据加载函数
-    X = np.c_[np.ones(X.shape[0]), X]
+def load_data(filepath):
-    weights = np.zeros(X.shape[1])
+    """
-    for epoch in range(epochs):
+    从文件中加载数据，处理缺失值，将 ? 替换为 NaN 并填充缺失值。
-        z = np.dot(X, weights)
+
-        predictions = sigmoid(z)
+    Args:
-        gradient = np.dot(X.T, (predictions - y)) / y.size
+    - filepath (str): 数据文件路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
+    data = np.genfromtxt(filepath, delimiter=' ', dtype=float, missing_values='?', filling_values=np.nan)
+    nan_columns = np.isnan(data)
+    col_means = np.nanmean(data, axis=0)
+    data[nan_columns] = np.take(col_means, np.where(nan_columns)[1])
+    
+    X = data[:, :-1]
+    y = data[:, -1]
+    return X, y
+
+# 对率回归训练函数
+def train_logreg(X, y, learning_rate=0.01, iterations=1000):
+    """
+    对率回归训练函数。
+
+    Args:
+    - X (np.array): 特征数据。
+    - y (np.array): 标签数据。
+    - learning_rate (float): 学习率。
+    - iterations (int): 迭代次数。
+
+    Returns:
+    - np.array: 训练得到的权重和偏置（合并为一个数组）。
+    """
+    n_samples, n_features = X.shape
+    X = np.c_[X, np.ones(n_samples)]  # 添加偏置项
+    weights = np.zeros(n_features + 1)
+
+    for _ in range(iterations):
+        y_pred = sigmoid(np.dot(X, weights))
+        gradient = np.dot(X.T, (y_pred - y)) / n_samples
         weights -= learning_rate * gradient
+
     return weights
 
+# 对率回归预测函数
 def predict_logreg(X, weights):
-    X = np.c_[np.ones(X.shape[0]), X]
+    """
-    probabilities = sigmoid(np.dot(X, weights))
+    对率回归预测函数，支持单个或多个样本。
-    return (probabilities >= 0.5).astype(int)
 
-# Load data and train model
+    Args:
-data_file_path = 'path_to_your_data/horse-colic.data'  # Update with your actual path
+    - X (np.array): 输入待分类的样本，可以是单个样本或样本集。
-X, y = load_data(data_file_path)
+    - weights (np.array): 训练得到的权重和偏置。
-if X is not None and y is not None:
-    weights = train_logreg(X, y)
-    predictions = predict_logreg(X, weights)
-    print("Weights:", weights)
-    print("Predictions:", predictions)
 
+    Returns:
+    - np.array: 预测的分类标签 (0 或 1)。
+    """
+    if X.ndim == 1:
+        X = X.reshape(1, -1)
+    X = np.c_[X, np.ones(X.shape[0])]
+    y_pred = sigmoid(np.dot(X, weights))
+    return (y_pred >= 0.5).astype(int)
+
+if __name__ == "__main__":
+    # 加载训练集和测试集
+    X_train, y_train = load_data("./data/horse-colic.data")
+    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, learning_rate=0.01, iterations=1000)
+
+    # 预测测试集并计算准确率
+    predictions = predict_logreg(X_test, weights)
+    accuracy = np.mean(predictions == y_test)
+    print(f"预测准确率: {accuracy * 100:.2f}%")