仅通过标题tag 分析全部数据

main.py

@@ -44,7 +44,7 @@ class LightGBM(object):
         """
         df = pd.read_json(path)
         df = df.dropna(subset=['label'])  # 把 label 为空的删掉
-        df = df.drop(subset=['tag1', 'tag2', 'tag3', 'tag4'])  # 把 tag 为空的数据也删掉
+        df = df.dropna(subset=['tag1', 'tag2', 'tag3', 'tag4'])  # 把 tag 为空的数据也删掉
         labels = df['label']
         features = df.drop('label', axis=1)
         for key in self.str_columns: