测试知识图谱的数据,测试3天

tensnsorflow/es/feature.py

@@ -32,7 +32,7 @@ def get_data():
     validate_date = con_sql(db, sql)[0].values.tolist()[0]
     print("validate_date:" + validate_date)
     temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
-    start = (temp - datetime.timedelta(days=300)).strftime("%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=3)).strftime("%Y-%m-%d")
     print(start)
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \
@@ -83,7 +83,8 @@ def get_data():
 
     unique_values = []
     features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date","hospital_id"]
+                "channel", "top", "time", "stat_date","hospital_id",
+                "method", "min", "max", "treatment_time", "maintain_time", "recover_time"]
     for i in features:
         df[i] = df[i].astype("str")
         df[i] = df[i].fillna("lost")
@@ -98,7 +99,8 @@ def get_data():
     train = df[df["stat_date"] != validate_date+"stat_date"]
     test = df[df["stat_date"] == validate_date+"stat_date"]
     for i in ["ucity_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date","hospital_id"]:
+                "channel", "top", "time", "stat_date","hospital_id",
+              "method", "min", "max", "treatment_time", "maintain_time", "recover_time"]:
         train[i] = train[i].map(value_map)
         test[i] = test[i].map(value_map)
 
@@ -139,16 +141,19 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map):
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select e.y,e.z,e.label,e.ucity_id,feat.level2_ids,e.ccity_name," \
           "u.device_type,u.manufacturer,u.channel,c.top,e.device_id,e.cid_id,cut.time," \
-          "dl.app_list,e.hospital_id,feat.level3_ids " \
+          "dl.app_list,e.hospital_id,feat.level3_ids,k.treatment_method,k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time " \
           "from esmm_pre_data e left join user_feature u on e.device_id = u.device_id " \
           "left join cid_type_top c on e.device_id = c.device_id " \
           "left join cid_time_cut cut on e.cid_id = cut.cid " \
           "left join device_app_list dl on e.device_id = dl.device_id " \
-          "left join diary_feat feat on e.cid_id = feat.diary_id limit 600"
+          "left join diary_feat feat on e.cid_id = feat.diary_id " \
+          "left join train_Knowledge_network_data k on feat.level2 = k.level2_id limit 600"
     df = con_sql(db, sql)
     df = df.rename(columns={0: "y", 1: "z", 2: "label", 3: "ucity_id", 4: "clevel2_id", 5: "ccity_name",
                             6: "device_type", 7: "manufacturer", 8: "channel", 9: "top",10: "device_id",
-                            11: "cid_id", 12: "time",13:"app_list",14:"hospital_id",15:"level3_ids"})
+                            11: "cid_id", 12: "time",13:"app_list",14:"hospital_id",15:"level3_ids",
+                            16: "method", 17: "min", 18: "max", 19: "treatment_time", 20: "maintain_time",
+                            21: "recover_time"})
 
     df["stat_date"] = date
     print(df.head(6))
@@ -164,7 +169,8 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map):
     df["uid"] = df["device_id"]
     df["city"] = df["ucity_id"]
     features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date","hospital_id"]
+                "channel", "top", "time", "stat_date","hospital_id",
+                "method", "min", "max", "treatment_time", "maintain_time", "recover_time"]
     for i in features:
         df[i] = df[i].astype("str")
         df[i] = df[i].fillna("lost")
@@ -176,7 +182,8 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map):
     nearby_pre = nearby_pre.drop("label", axis=1)
 
     for i in ["ucity_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date","hospital_id"]:
+                "channel", "top", "time", "stat_date","hospital_id",
+              "method", "min", "max", "treatment_time", "maintain_time", "recover_time"]:
         native_pre[i] = native_pre[i].map(value_map)
         # TODO 没有覆盖到的类别会处理成na，暂时用0填充，后续完善一下
         native_pre[i] = native_pre[i].fillna(0)