按照用户去重应用列表样本

tensnsorflow/applist.py

@@ -34,7 +34,6 @@ def sort_app():
     df = df.rename(columns={0: "device_id", 1: "app_list",2:"stat_date"})
     print(df.shape)
     df = df.sort_values(by="stat_date",ascending=False)
-    print(df.head())
     df = df.drop("stat_date",axis=1)
     df = df.drop_duplicates("device_id")
     print(df.shape)
@@ -95,11 +94,11 @@ def sort_app():
     for i in range(0,df.shape[0],n):
         print(i)
         if i == 0:
-            temp = df.loc[0:n]
+            temp = df.iloc[0:n]
         elif i+n > df.shape[0]:
-            temp = df.loc[i+1:]
+            temp = df.iloc[i:]
         else:
-            temp = df.loc[i+1:i+n]
+            temp = df.loc[i:i+n]
         pd.io.sql.to_sql(temp, "app_list_sort", yconnect, schema='jerry_test', if_exists='append', index=False)
         print("insert done")