add test

tensnsorflow/applist.py

@@ -69,25 +69,31 @@ def sort_app():
                  }
     df["app_list"] = df["app_list"].apply(json_format)
     n = df.shape[0]
+    df["sum"] = 0
     for i in category.keys():
-        df[i] = df["app_list"].apply(lambda x: 1 if len(x & category[i]) > 0 else 2)
+        df[i] = df["app_list"].apply(lambda x: 1 if len(x & category[i]) > 0 else 0)
+        df["sum"] = df["sum"]+df[i]
         # print(i)
         # print(df.loc[df[i]==1].shape[0]/n)
     df = df.drop("app_list",axis=1)
-
-    yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
-    print(df.shape)
-    n = 200000
-    for i in range(0,df.shape[0],n):
+    for i in df["sum"].unique():
         print(i)
-        if i == 0:
-            temp = df.loc[0:n]
-        elif i+n > df.shape[0]:
-            temp = df.loc[i+1:]
-        else:
-            temp = df.loc[i+1:i+n]
-        pd.io.sql.to_sql(temp, "app_list_sort", yconnect, schema='jerry_test', if_exists='append', index=False)
-        print("insert done")
+        a = df.loc[df["sum"] == i].shape[0]/n
+        print(a)
+
+    # yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
+    # print(df.shape)
+    # n = 200000
+    # for i in range(0,df.shape[0],n):
+    #     print(i)
+    #     if i == 0:
+    #         temp = df.loc[0:n]
+    #     elif i+n > df.shape[0]:
+    #         temp = df.loc[i+1:]
+    #     else:
+    #         temp = df.loc[i+1:i+n]
+    #     pd.io.sql.to_sql(temp, "app_list_sort", yconnect, schema='jerry_test', if_exists='append', index=False)
+    #     print("insert done")