修改测试文件

tensnsorflow/multi.py

@@ -18,15 +18,15 @@ def app_list_func(x,l):
     return ",".join([str(j) for j in e])
 
 def multi_hot(df,column,n):
-    df[column] = df[column].fillna("lost_na")
-    app_list_value = [i.split(",") for i in df[column].unique()]
+    df = df.select[column].fillna("lost_na")
+    app_list_value = [i.split(",") for i in df.select[column].unique()]
     app_list_unique = []
     for i in app_list_value:
         app_list_unique.extend(i)
     app_list_unique = list(set(app_list_unique))
     number = len(app_list_unique)
     app_list_map = dict(zip(app_list_unique, list(range(n, number + n))))
-    df[column] = df[column].apply(app_list_func, args=(app_list_map,))
+    df = df.select[column].apply(app_list_func, args=(app_list_map,))
     return number,app_list_map
 
 def feature_engineer():
@@ -75,11 +75,13 @@ def feature_engineer():
     hospital = spark.sql(sql)
 
     df = df.join(hospital,"diary_service_id","left_outer").fillna("na")
-    print(df.count())
     df = df.drop("level2").drop("diary_service_id")
     df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
                               "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"])
-    print(df.count())
+
+
+    multi_hot(df, "app_list", 1)
+