add hospital_id

tensnsorflow/ffm.py

@@ -146,32 +146,22 @@ def get_data():
     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,e.clevel1_id,e.ccity_name," \
-          "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,e.cid_id " \
+          "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,s.hospital_id " \
           "from esmm_train_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 on e.cid_id = cid_time.cid_id " \
+          "left join service_hospital on e.diary_service_id = s.id " \
           "where e.stat_date >= '{}'".format(start)
     df = con_sql(db, sql)
     print(df.shape)
     df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id",4: "clevel1_id", 5: "ccity_name",
-                            6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"time",11:"cid_id"})
+                            6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"time",11:"hospital_id"})
     print("esmm data ok")
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
-    sql = "select cid from diary_video"
-    diary_video = con_sql(db, sql)[0].values.tolist()
-    video_df = df.loc[df["cid_id"].isin(diary_video)]
-    print("video_df.shape")
-    print(video_df.shape)
-    video_df["video"] = "yes"
-    other_df = df.loc[~df["cid_id"].isin(diary_video)]
-    other_df["video"] = "no"
-    df =  video_df.append(other_df).sort_index()
-    print(df.shape)
-    df = df.drop("cid_id",axis=1)
     print(df.head(2))
-
-    category = ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top"]
+    features = 0
+    category = ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top","hospital_id"]
     for i in category:
         df[i] = df[i].fillna("na")
+        features = features + len(df[i].unique())
     df["time"] = df["time"].fillna(0.0)
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["y"] = df["y"].astype("str")
@@ -180,20 +170,12 @@ def get_data():
     df["y"] = df["stat_date"].str.cat([df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
     df = df.drop(["z","stat_date"], axis=1)
     print(df.head(2))
-    features = 0
-    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top"]:
-        features = features + len(df[i].unique())
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features))
     ccity_name = list(set(df["ccity_name"].values.tolist()))
     ucity_id = list(set(df["ucity_id"].values.tolist()))
     return df,validate_date,ucity_id,ccity_name
 
-def video_judge(cid,diary_video):
-    if cid in diary_video:
-        return "yes"
-    else:
-        return "no"
 
 def transform(a,validate_date):
     model = multiFFMFormatPandas()