跑之前的数据

eda/esmm/Model_pipline/feature_engineering.py

@@ -155,7 +155,7 @@ def feature_engineer():
     print(start)
 
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC')
-    sql = "select doctor.hospital_id from jerry_test.esmm_train_data_dwell e " \
+    sql = "select distinct doctor.hospital_id from jerry_test.esmm_train_data_dwell e " \
           "left join eagle.src_zhengxing_api_service service on e.diary_service_id = service.id " \
           "left join eagle.src_zhengxing_api_doctor doctor on service.doctor_id = doctor.id " \
           "where e.stat_date >= '{}'".format(start)
@@ -212,9 +212,11 @@ def feature_engineer():
                    app_list_func(x[5], leve3_map), app_list_func(x[6], leve2_map), app_list_func(x[7], leve2_map),
                    app_list_func(x[8], leve2_map), app_list_func(x[9], leve2_map), app_list_func(x[10], leve2_map),
                    app_list_func(x[11], leve2_map), app_list_func(x[12], leve2_map),
-                   [value_map[x[0]], value_map[x[13]], value_map[x[14]], value_map[x[15]], value_map[x[16]],
-                    value_map[x[17]], value_map[x[18]], value_map[x[19]], value_map[x[20]], value_map[x[21]],
-                    value_map[x[22]], value_map[x[23]], value_map[x[24]], value_map[x[25]], value_map[x[26]]]))
+                   [value_map.get(x[0],1), value_map.get(x[13],2), value_map.get(x[14],3), value_map.get(x[15],4),
+                    value_map.get(x[16],5),value_map.get(x[17],6), value_map.get(x[18],7), value_map.get(x[19],8),
+                    value_map.get(x[20],9), value_map.get(x[21],10),
+                    value_map.get(x[22],11), value_map.get(x[23],12), value_map.get(x[24],13),
+                    value_map.get(x[25],14), value_map.get(x[26],15)]))
 
     rdd.persist(storageLevel= StorageLevel.MEMORY_ONLY_SER)