change test file

eda/esmm/Model_pipline/feature_engineering.py

@@ -76,40 +76,6 @@ def con_sql(db,sql):
     return df
 
 
-def train_yingshe(y):
-    tmp = []
-    for x in y:
-        i = (x[0], float(x[1]), float(x[2]), app_list_func(x[3], app_list_map), app_list_func(x[4], leve2_map),
-                       app_list_func(x[5], leve3_map), app_list_func(x[6], leve2_map), app_list_func(x[7], leve2_map),
-                       app_list_func(x[8], leve2_map), app_list_func(x[9], leve2_map), app_list_func(x[10], leve2_map),
-                       app_list_func(x[11], leve2_map), app_list_func(x[12], leve2_map),
-                       [value_map[x[0]], value_map[x[13]], value_map[x[14]], value_map[x[15]], value_map[x[16]],
-                        value_map[x[17]], value_map[x[18]], value_map[x[19]], value_map[x[20]], value_map[x[21]],
-                        value_map[x[22]], value_map[x[23]], value_map[x[24]], value_map[x[25]], value_map[x[26]]])
-        tmp.append(i)
-    return iter(tmp)
-
-def pre_yingshe(y):
-    tmp = []
-    for x in y:
-        i = (x[0], float(x[1]), float(x[2]), x[3], x[4], x[5],
-         app_list_func(x[6], app_list_map), app_list_func(x[7], leve2_map),
-         app_list_func(x[8], leve3_map), app_list_func(x[9], leve2_map),
-         app_list_func(x[10], leve2_map), app_list_func(x[11], leve2_map),
-         app_list_func(x[12], leve2_map), app_list_func(x[13], leve2_map),
-         app_list_func(x[14], leve2_map), app_list_func(x[15], leve2_map),
-         [value_map.get(validate_date, 1), value_map.get(x[16], 2),
-          value_map.get(x[17], 3), value_map.get(x[18], 4),
-          value_map.get(x[19], 5), value_map.get(x[20], 6),
-          value_map.get(x[21], 7), value_map.get(x[22], 8),
-          value_map.get(x[23], 9), value_map.get(x[24], 10),
-          value_map.get(x[25], 11), value_map.get(x[26], 12),
-          value_map.get(x[27], 13), value_map.get(x[28], 14),
-          value_map.get(x[29], 15)
-          ])
-        tmp.append(i)
-    return iter(tmp)
-
 def feature_engineer():
     apps_number, app_list_map, level2_number, leve2_map, level3_number, leve3_map = get_map()
     unique_values = []
@@ -238,6 +204,18 @@ def feature_engineer():
     #                [value_map[x[0]], value_map[x[13]], value_map[x[14]], value_map[x[15]], value_map[x[16]],
     #                 value_map[x[17]], value_map[x[18]], value_map[x[19]], value_map[x[20]], value_map[x[21]],
     #                 value_map[x[22]], value_map[x[23]], value_map[x[24]], value_map[x[25]], value_map[x[26]]]))
+    def train_yingshe(y):
+        tmp = []
+        for x in y:
+            i = (x[0], float(x[1]), float(x[2]), app_list_func(x[3], app_list_map), app_list_func(x[4], leve2_map),
+                 app_list_func(x[5], leve3_map), app_list_func(x[6], leve2_map), app_list_func(x[7], leve2_map),
+                 app_list_func(x[8], leve2_map), app_list_func(x[9], leve2_map), app_list_func(x[10], leve2_map),
+                 app_list_func(x[11], leve2_map), app_list_func(x[12], leve2_map),
+                 [value_map[x[0]], value_map[x[13]], value_map[x[14]], value_map[x[15]], value_map[x[16]],
+                  value_map[x[17]], value_map[x[18]], value_map[x[19]], value_map[x[20]], value_map[x[21]],
+                  value_map[x[22]], value_map[x[23]], value_map[x[24]], value_map[x[25]], value_map[x[26]]])
+            tmp.append(i)
+        return iter(tmp)
 
     rdd = df.select("stat_date", "y", "z", "app_list", "level2_ids", "level3_ids",
                     "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7",
@@ -331,7 +309,26 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
     #                                           value_map.get(x[27], 13), value_map.get(x[28], 14),
     #                                           value_map.get(x[29], 15)
     #                                           ]))
-
+    def pre_yingshe(y):
+        tmp = []
+        for x in y:
+            i = (x[0], float(x[1]), float(x[2]), x[3], x[4], x[5],
+                 app_list_func(x[6], app_list_map), app_list_func(x[7], leve2_map),
+                 app_list_func(x[8], leve3_map), app_list_func(x[9], leve2_map),
+                 app_list_func(x[10], leve2_map), app_list_func(x[11], leve2_map),
+                 app_list_func(x[12], leve2_map), app_list_func(x[13], leve2_map),
+                 app_list_func(x[14], leve2_map), app_list_func(x[15], leve2_map),
+                 [value_map.get(validate_date, 1), value_map.get(x[16], 2),
+                  value_map.get(x[17], 3), value_map.get(x[18], 4),
+                  value_map.get(x[19], 5), value_map.get(x[20], 6),
+                  value_map.get(x[21], 7), value_map.get(x[22], 8),
+                  value_map.get(x[23], 9), value_map.get(x[24], 10),
+                  value_map.get(x[25], 11), value_map.get(x[26], 12),
+                  value_map.get(x[27], 13), value_map.get(x[28], 14),
+                  value_map.get(x[29], 15)
+                  ])
+            tmp.append(i)
+        return iter(tmp)
     rdd = df.select("label", "y", "z", "ucity_id", "device_id", "cid_id", "app_list", "level2_ids", "level3_ids",
                     "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7",
                     "ucity_id", "ccity_name", "device_type", "manufacturer", "channel", "top", "time",