generate label for mysql

main_spider.py

@@ -65,7 +65,7 @@ class LightGBM(object):
         df = df.dropna(subset=['label'])
         labels = df['label']
         temp = sorted(labels)
-        yc = temp[int(len(temp) * self.yc)]
+        yc = temp[int(len(temp) * 0.7)]
         labels = [0 if i < yc else 1 for i in labels]
         features = df.drop("label", axis=1)
         for key in self.float_columns:
@@ -91,8 +91,14 @@ class LightGBM(object):
         }
 
         # 定义 RandomizedSearchCV
-        rsearch = RandomizedSearchCV(estimator=lgbm, param_distributions=param_dist, n_iter=100, cv=3,
-                                     scoring='roc_auc', random_state=42, verbose=2)
+        rsearch = RandomizedSearchCV(
+            estimator=lgbm,
+            param_distributions=param_dist,
+            n_iter=100,
+            cv=3,
+            scoring='roc_auc',
+            random_state=42, verbose=2
+        )
 
         # 开始搜索
         rsearch.fit(X_train, y_train)
@@ -210,9 +216,6 @@ if __name__ == "__main__":
         L = LightGBM(flag=f, dt=dt)
         L.evaluate_model()
         L.feature_importance()
-    # L = LightGBM("train", "whole")
-    # L.best_params()
-    # study = optuna.create_study(direction='maximize')
-    # study.optimize(L.bays_params, n_trials=100)
-    # print('Number of finished trials:', len(study.trials))
-    # print('Best trial:', study.best_trial.params)
+    elif i == 3:
+        L = LightGBM("train", "whole")
+        L.best_params()