特征工程增加分享数据

eda/esmm/Model_pipline/feature_engineering.py

@@ -228,7 +228,7 @@ def feature_engineer():
                     "hospital_id", "treatment_method", "price_min", "price_max", "treatment_time",
                     "maintain_time", "recover_time", "search_tag2", "search_tag3","cid_id","device_id","s")\
         .rdd.repartition(200).map(
-        lambda x: (x[0], float(x[1]), float(x[2]), float(x[31]),app_list_func(x[3], app_list_map), app_list_func(x[4], leve2_map),
+        lambda x: (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),
@@ -237,7 +237,7 @@ def feature_engineer():
                     value_map.get(x[20], 9), value_map.get(x[21], 10),
                     value_map.get(x[22], 11), value_map.get(x[23], 12), value_map.get(x[24], 13),
                     value_map.get(x[25], 14), value_map.get(x[26], 15)],
-                   app_list_func(x[27], leve2_map), app_list_func(x[28], leve3_map),x[13],x[29],x[30]
+                   app_list_func(x[27], leve2_map), app_list_func(x[28], leve3_map),x[13],x[29],x[30],float(x[31])
                    ))