仅通过标题tag 分析全部数据

main.py

@@ -141,7 +141,7 @@ class LightGBM(object):
         y_pred = bst.predict(x, num_iteration=bst.best_iteration)
         pred_score_df = pd.DataFrame(list(y_pred), columns=['pred_score'])
         temp = sorted(list(y_pred))
-        yuzhi = temp[int(len(temp) * 0.75) - 1]
+        yuzhi = temp[int(len(temp) * 0.5) - 1]
         y_pred_binary = [0 if i <= yuzhi else 1 for i in list(y_pred)]
         pred_label_df = pd.DataFrame(list(y_pred_binary), columns=['pred_label'])
         score_list = []
@@ -179,7 +179,7 @@ class LightGBM(object):
         for name, imp in feature_importance:
             print(name, imp)
 
-# "cat summary_20240328.txt | awk -F "\t" '{print $1" "$3}'| /root/AUC/AUC/AUC"
+# "cat summary_20240326.txt | awk -F "\t" '{print $1" "$3}'| /root/AUC/AUC/AUC"
 """
  ossutil64 cp /root/luojunhui/alg/data/predict_data/spider_predict_result_20240330.xlsx oss://art-pubbucket/0temp/
 """