From 6a308396d6f44705668e1ca97deb73a86ef3bdc0 Mon Sep 17 00:00:00 2001
From: dong <2938690875@qq.com>
Date: Fri, 1 Nov 2024 10:48:31 +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 | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/function.py b/function.py
index f87ddaa..19ce89c 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,6 @@
 import numpy as np
 import pandas as pd
-from sklearn.preprocessing import StandardScaler
+from sklearn.preprocessing import StandardScaler, PolynomialFeatures
 from sklearn.model_selection import train_test_split, GridSearchCV
 from sklearn.linear_model import LogisticRegression
 
@@ -68,15 +68,31 @@ def load_data(filepath):
                 else:
                     continue
                 values = [0 if np.isnan(v) else v for v in values]
-                data.append(values[:2] + values[3:23])
+                data.append(values[:2] + values[3:23])  # 根据数据结构选择特征
             except ValueError:
                 continue
 
     return np.array(data), np.array(labels)
 
 def preprocess_data(X):
+    # 标准化
     scaler = StandardScaler()
-    return scaler.fit_transform(X)
+    X_scaled = scaler.fit_transform(X)
+    
+    # 创建多项式特征
+    poly = PolynomialFeatures(degree=2, interaction_only=False, include_bias=False)
+    X_poly = poly.fit_transform(X_scaled)
+
+    # 例如，可以对某个特征进行分箱处理
+    # 假设 X_scaled[:, 0] 是一个连续特征，比如年龄
+    age_bins = pd.cut(X_scaled[:, 0], bins=[0, 30, 60, 100], labels=["年轻", "中年", "老年"])
+    # 将分箱结果转换为独热编码
+    age_dummies = pd.get_dummies(age_bins, drop_first=True)
+
+    # 将独热编码的结果与原特征组合
+    X_combined = np.hstack((X_poly, age_dummies.values))
+    
+    return X_combined
 
 if __name__ == "__main__":
     # 加载数据集