diff --git a/function.py b/function.py index a979631..46d90e9 100644 --- a/function.py +++ b/function.py @@ -28,7 +28,24 @@ name = "董秋" # 这里写自己的代码实现 +import numpy as np +from sklearn.svm import SVC +from sklearn.model_selection import train_test_split +from sklearn.metrics import classification_report, accuracy_score +from sklearn.preprocessing import StandardScaler + +# 数据加载函数 def load_data(filepath): + """ + 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**。 + + Args: + - directory (str): 数据文件路径。 + + Returns: + - np.array: 特征数据。 + - np.array: 标签数据。 + """ data = [] labels = [] @@ -37,13 +54,13 @@ def load_data(filepath): fields = line.strip().split() # 处理缺失值,用0填充 - fields = [0 if f == '?' else float(f) for f in fields] + fields = [0 if f == '?' else float(f) for f in fields] - # 特征是除最后一列外的所有列 - features = np.array(fields[:-1], dtype=float) + # 标签是倒数第6列 + label = int(fields[-6]) - # 标签是最后一列 - label = int(fields[-1]) + # 特征为其他列(不包含倒数第6列标签) + features = np.array(fields[: -6] + fields[-5:], dtype=float) # 标签映射:将 1->0, 2->1, 3->2 if label == 1: @@ -61,53 +78,74 @@ def load_data(filepath): labels.append(label) # 转换为numpy数组 - labels = np.array(labels) data = np.array(data) - - # 检查标签的唯一值,确保只有 0, 1, 2 - unique_labels = np.unique(labels) + labels = np.array(labels) - if len(unique_labels) != 3: - print(f"错误:标签数据包含的类别不是3个,实际类别为:{unique_labels}") - raise ValueError("标签数量不为3,请确保标签未合并!") - return data, labels -def train_svm(X, y, learning_rate=0.01, iterations=1000, regularization_strength=0.01): - n_samples, n_features = X.shape - n_classes = len(np.unique(y)) - weights = np.zeros((n_classes, n_features)) + +def train_svm(X, y, other_params=None): + """ + 支持向量机训练函数。 + + 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: + - SVC: 训练好的SVM模型。 + """ + # 使用高斯核(RBF核)训练SVM + model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=42) + model.fit(X, y) - # 将标签转化为多类别(one-vs-rest)形式 - y_one_vs_rest = np.array([[1 if y[i] == c else -1 for c in range(n_classes)] for i in range(n_samples)]) - - for _ in range(iterations): - # 计算预测值 - margins = y_one_vs_rest * (X @ weights.T) - mask = margins < 1 - grad = -np.einsum('ij,ik->kj', y_one_vs_rest * mask, X) / n_samples - weights -= learning_rate * (grad + regularization_strength * weights) - - return weights - -def predict_svm(X, weights): - scores = X @ weights.T - return np.argmax(scores, axis=1) + return model +def predict_svm(inX, model): + """ + 支持向量机预测函数。 + + Args: + - inX (numpy array): 输入待分类的样本。 + - model (SVC): 训练得到的支持向量机模型。 + + Returns: + - int: 预测的分类标签。 + """ + return model.predict(inX.reshape(1, -1))[0] if __name__ == "__main__": - # 以下代码可用于测试,可自行随意修改 - # 加载训练集 + # 加载数据 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") + # 划分数据集 + X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.2, random_state=42, stratify=y_train) + + # 数据标准化 + scaler = StandardScaler() + X_train = scaler.fit_transform(X_train) + X_test = scaler.transform(X_test) + # 训练支持向量机模型 - weights = train_svm(X_train, y_train, learning_rate=0.01, iterations=1000) + print("正在训练支持向量机模型...") + svm_model = train_svm(X_train, y_train) + + # 预测测试集 + y_pred = svm_model.predict(X_test) + + # 输出评估结果 + print("\n分类报告:") + print(classification_report(y_test, y_pred, target_names=["存活", "安乐死", "死亡"])) + + # 输出准确率 + accuracy = accuracy_score(y_test, y_pred) + print(f"测试集准确率: {accuracy * 100:.2f}%") # 测试单个数据 - y_pred = predict_svm(X_test[11], weights) - print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}") + test_sample = X_test[11] # 选择第12个样本(从0开始计数) + y_pred_single = predict_svm(test_sample, svm_model) + print(f"\n单个样本预测结果: {y_pred_single}, 实际结果: {y_test[11]}")