上传文件至 /

function.py

@@ -1,10 +1,14 @@
 import numpy as np
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.preprocessing import PolynomialFeatures, StandardScaler
+from sklearn.impute import SimpleImputer
+from sklearn.metrics import accuracy_score
+from sklearn.model_selection import train_test_split
 
 id = "202210423104"
 name = "张钦诚"
 
+
 def load_data(filepath):
     data = []
     with open(filepath, 'r') as file:
@@ -16,12 +20,14 @@ def load_data(filepath):
                 except ValueError as e:
                     print(f"Error processing line: {line}. Error: {e}")
     data = np.array(data)
-    data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))
+    imputer = SimpleImputer(strategy='mean')
+    data = imputer.fit_transform(data)
 
     X = data[:, :-1]  # 特征
-    y = data[:, -1]   # 标签
+    y = data[:, -1]  # 标签
     return X, y
 
+
 def preprocess_data(X):
     scaler = StandardScaler()
     X_standardized = scaler.fit_transform(X)
@@ -29,18 +35,33 @@ def preprocess_data(X):
     X_poly = poly.fit_transform(X_standardized)
     return X_poly
 
+
 def train_logreg(X, y):
     X_processed = preprocess_data(X)  # 预处理训练数据
-    model = RandomForestClassifier(n_estimators=200, max_depth=20, random_state=42)
+    model = RandomForestClassifier(n_estimators=200, max_depth=20, min_samples_split=5, random_state=42)
     model.fit(X_processed, y)
     return model  # 返回训练好的模型
 
+
 def predict_logreg(X, model):
-    # 确保输入数据是一个 numpy 数组
     if len(X.shape) == 1:
-        X = X.reshape(1, -1)  # 保持输入数据的形状为 (1, n)，符合模型的输入要求
+        X = X.reshape(1, -1)  # 保持输入数据的形状为 (1, n)
     X_processed = preprocess_data(X)  # 预处理测试数据
     return model.predict(X_processed)[0]  # 确保 model 是训练好的模型
 
+
 if __name__ == "__main__":
     X, y = load_data("./data/horse-colic.data")
+
+    # 划分训练集和测试集
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # 训练模型
+    model = train_logreg(X_train, y_train)
+
+    # 预测
+    y_pred = model.predict(preprocess_data(X_test))
+
+    # 计算准确率
+    accuracy = accuracy_score(y_test, y_pred)
+    print(f"Accuracy: {accuracy:.2f}")