generate label for mysql

main_spider.py

@@ -65,6 +65,9 @@ class LightGBM(object):
         df = pd.read_json(path)
         df = df.dropna(subset=['label'])
         labels = df['label']
+        temp = sorted(labels)
+        yc = temp[int(len(temp) * self.yc)]
+        labels = [0 if i < yc else 1 for i in labels]
         features = df.drop("label", axis=1)
         for key in self.float_columns:
             features[key] = pd.to_numeric(features[key], errors="coerce")