From 0a88f8792cf46eff813789057a871b1d6124a98d Mon Sep 17 00:00:00 2001
From: Xionghaoran <719929980@qq.com>
Date: Thu, 31 Oct 2024 17:22:06 +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 | 59 ++++++++++++++---------------------------------------
 1 file changed, 15 insertions(+), 44 deletions(-)

diff --git a/function.py b/function.py
index 7337ce1..87d09b9 100644
--- a/function.py
+++ b/function.py
@@ -1,4 +1,5 @@
 import numpy as np
+import pandas as pd
 from sklearn.impute import SimpleImputer
 from sklearn.feature_selection import SelectKBest, f_classif
 
@@ -6,52 +7,22 @@ from sklearn.feature_selection import SelectKBest, f_classif
 id = "202210423213"
 name = " 熊浩燃"
 
-def load_data(filepath, k_features=20):
+def load_data(filepath):
     """
-    从文件中加载数据并进行预处理，包括缺失值填充和特征选择。
-
-    Args:
-    - filepath (str): 数据文件路径。
-    - k_features (int): 选择的特征数量。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
+    从文件中加载数据，填充缺失值，并进行特征处理。
     """
-    data = []
-    labels = []
-    with open(filepath, 'r') as file:
-        for line in file:
-            line = line.strip().split()
-            if line:
-                features = []
-                for feature in line[:-1]:  # 最后一个元素是标签
-                    try:
-                        features.append(float(feature))
-                    except ValueError:
-                        features.append(np.nan)  # 用 NaN 表示缺失值
-                label = int(line[-1])
-                data.append(features)
-                labels.append(label)
-
-    # 转换为 numpy 数组
-    data = np.array(data)
-    labels = np.array(labels)
-
-    # 使用SimpleImputer填充NaN
-    imputer = SimpleImputer(strategy='mean')
-    data = imputer.fit_transform(data)
-
-    # 特征标准化，避免除零错误
-    mean = data.mean(axis=0)
-    std_dev = data.std(axis=0)
-    std_dev[std_dev == 0] = 1  # 如果标准差为0，将其设为1，避免除以零
-    data = (data - mean) / std_dev
-
-    # 特征选择
-    selector = SelectKBest(f_classif, k=k_features)
-    data = selector.fit_transform(data, labels)
-
+    # 使用pandas读取数据，处理缺失值
+    df = pd.read_csv(filepath, delim_whitespace=True, header=None)
+    # 将问号替换为NaN，并填充为0
+    df.replace('?', 0, inplace=True)
+    df = df.astype(float)  # 转换为浮点数类型
+    # 将最后一列设置为标签
+    labels = df.iloc[:, -1].values.astype(int)
+    labels[(labels == 2) | (labels == 3)] = 0  # 合并死亡和安乐死为0
+    # data = df.drop(columns=[2] + list(range(23, 28))).values  # 删除不相关特征
+    # 数据标准化
+    scaler = StandardScaler()
+    data = scaler.fit_transform(data)
     return data, labels
 
 def sigmoid(z):