From 5ca6a5b4c677caa76c9fda4a389011dc8497f91b Mon Sep 17 00:00:00 2001
From: hao <19382120447@163.com>
Date: Sat, 2 Nov 2024 13:38:30 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 93 +++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 66 insertions(+), 27 deletions(-)

diff --git a/function.py b/function.py
index 91917c3..f145fdc 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,5 @@
 import numpy as np
 from sklearn.preprocessing import StandardScaler
-from sklearn.linear_model import LogisticRegression
 
 """
 实验说明:
@@ -26,37 +25,77 @@ id = "202210423228"
 name = "黎世浩"
 
 
+# 这里写自己的代码实现
+def train_logreg(X, y, other_params="114514"):
+    """
+    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。若需设置其它参数，必须设置其默认值，否则将**无法通过**自动评测，**成绩为零**。
+
+    Returns:
+    - numpy array: 训练得到的权重。
+    """
+
+
+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。
+    """
+
+
+# 这里也写自己的代码实现
 def load_data(filepath):
-    data = np.genfromtxt(filepath, delimiter=' ', dtype=float, missing_values='?')
-    X = data[:, :-1]
-    y = data[:, -1]
-    
-    # 将缺失值填充为每列的平均值
-    for i in range(X.shape[1]):
-        X[:, i] = np.where(np.isnan(X[:, i]), np.nanmean(X[:, i]), X[:, i])
-    
-    return X, y.astype(int)
+    """
+    从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
 
-def train_logreg(X, y):
+    Args:
+    - filepath (str): 数据文件路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
+    # 使用 np.genfromtxt 加载数据，处理缺失值 '?' 为 0
+    data = np.genfromtxt(filepath, delimiter=" ", missing_values="?", filling_values=-1)
+
+    # 分离特征标签
+    labels = data[:, -1].astype(int)
+    data = data[:, :-1]
+
+    # 合并死亡
+    labels = np.where((labels == 2) | (labels == 3), 0, labels)
+
+    # 删除无关值
+    data = np.delete(data, 2, axis=1)  # 删除第3列
+
+    # 数据标准化
     scaler = StandardScaler()
-    X_scaled = scaler.fit_transform(X)
-    
-    model = LogisticRegression(solver='liblinear')
-    model.fit(X_scaled, y)
-    
-    return model
+    data = scaler.fit_transform(data)
+
+    return data, labels
 
-def predict_logreg(model, inX):
-    prediction = model.predict(inX)
-    return prediction
 
 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")
+
+    # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
-    
-    model = train_logreg(X_train, y_train)
-    
-    # 测试模型
-    y_pred = predict_logreg(model, X_test)
-    accuracy = np.mean(y_pred == y_test)
-    print(f"Accuracy: {accuracy}")
\ No newline at end of file
+
+    # 训练对率回归模型
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+
+    # 测试单个数据
+    y_pred = predict_logreg(X_test[11], weights)
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
\ No newline at end of file