初始提交

classification_model/WaveSelect/Spa_acc.py

@@ -0,0 +1,111 @@
+import lightgbm as lgb
+import numpy as np
+from scipy.linalg import qr
+from progress.bar import Bar
+from matplotlib import pyplot as plt
+from sklearn.metrics import accuracy_score
+
+
+class SPA_acc:
+    def _projections_qr(self, X, k, M):
+        X_projected = X.copy()
+        norms = np.sum((X ** 2), axis=0)
+        norm_max = np.amax(norms)
+        X_projected.iloc[:, k] = X_projected.iloc[:, k] * 2 * norm_max / norms[k]
+        _, __, order = qr(X_projected.to_numpy(), 0, pivoting=True)
+        return order[:M].T
+
+    def _validation(self, Xcal, ycal, var_sel, Xval=None, yval=None):
+        train_data = lgb.Dataset(Xcal.iloc[:, var_sel], label=ycal)
+        params = {
+            'objective': 'multiclass',  # 多分类任务的目标函数
+            'boosting_type': 'gbdt',
+            'metric': 'multi_logloss',  # 使用多分类交叉熵损失
+            'device': 'gpu',  # 启用GPU加速
+            'verbosity': -1,
+            'num_class': len(np.unique(ycal))  # 设置类别数量
+        }
+
+        # LightGBM 模型训练
+        model = lgb.train(params, train_data, num_boost_round=100)
+
+        # 在验证集或训练集上进行预测
+        if Xval is not None and yval is not None:
+            yhat = model.predict(Xval.iloc[:, var_sel])
+            yhat = np.argmax(yhat, axis=1)  # 获取每个样本的最大概率类别
+            accuracy = accuracy_score(yval, yhat)
+        else:
+            yhat = model.predict(Xcal.iloc[:, var_sel])
+            yhat = np.argmax(yhat, axis=1)  # 获取每个样本的最大概率类别
+            accuracy = accuracy_score(ycal, yhat)
+
+        return yhat, accuracy
+
+    def spa(self, Xcal, ycal, m_min=1, m_max=None, Xval=None, yval=None, autoscaling=1, save_path=None):
+        N, K = Xcal.shape
+        m_max = min(N - 1, K) if m_max is None else m_max
+
+        normalization_factor = Xcal.std(ddof=1, axis=0) if autoscaling else np.ones(K)
+        Xcaln = (Xcal - Xcal.mean()) / normalization_factor
+
+        SEL = np.zeros((m_max, K))
+        with Bar('Projections :', max=K) as bar:
+            for k in range(K):
+                SEL[:, k] = self._projections_qr(Xcaln, k, m_max)
+                bar.next()
+
+        ACCURACY = np.full((m_max + 1, K), -np.inf)
+        with Bar('Evaluating subsets:', max=K * (m_max - m_min + 1)) as bar:
+            for k in range(K):
+                for m in range(m_min, m_max + 1):
+                    var_sel = SEL[:m, k].astype(int)
+                    _, accuracy = self._validation(Xcal, ycal, var_sel, Xval, yval)
+                    ACCURACY[m, k] = accuracy
+                    bar.next()
+
+        m_sel = np.argmax(ACCURACY, axis=0)
+        k_sel = np.argmax(np.max(ACCURACY, axis=0))
+        var_sel_phase2 = SEL[:m_sel[k_sel], k_sel].astype(int)
+
+        # Final LightGBM Training
+        Xcal2 = Xcal.iloc[:, var_sel_phase2]
+        train_data = lgb.Dataset(Xcal2, label=ycal)
+        params = {
+            'objective': 'multiclass',  # 多分类任务的目标函数
+            'boosting_type': 'gbdt',
+            'metric': 'multi_logloss',  # 使用多分类交叉熵损失
+            'device': 'gpu',  # 启用GPU加速
+            'verbosity': -1,
+            'num_class': len(np.unique(ycal))  # 设置类别数量
+        }
+        model = lgb.train(params, train_data, num_boost_round=100)
+        relev = model.feature_importance(importance_type='gain')
+
+        index_decreasing_relev = np.argsort(-relev)
+        ACCURACY_scree = np.empty(len(var_sel_phase2))
+        for i in range(len(var_sel_phase2)):
+            var_sel = var_sel_phase2[index_decreasing_relev[:i + 1]]
+            _, accuracy = self._validation(Xcal, ycal, var_sel, Xval, yval)
+            ACCURACY_scree[i] = accuracy
+
+        # 绘图
+        plt.figure()
+        plt.rcParams['font.sans-serif'] = ['Times New Roman']
+        plt.xlabel('Number of variables included in the model', fontsize=14)
+        plt.ylabel('Accuracy', fontsize=14)
+        plt.title(f'Final number of selected variables: {len(var_sel_phase2)} (Accuracy={ACCURACY_scree.max():.4f})', fontsize=16)
+        plt.plot(ACCURACY_scree, label='Accuracy Scree Plot')
+        plt.scatter(np.argmax(ACCURACY_scree), ACCURACY_scree.max(), color='r', marker='s', label='Selected Point')
+        plt.grid(True)
+        plt.legend()
+
+        if save_path:
+            plt.savefig(save_path, bbox_inches='tight', dpi=300)
+            print(f"图像已保存至: {save_path}")
+        else:
+            plt.show()
+
+        return var_sel_phase2, ACCURACY_scree
+
+    def __repr__(self):
+        return "SPA()"