有表头的预测

classify_server.py

@@ -18,8 +18,9 @@ class Classify(classify_pb2_grpc.classifyServicer):
 
 
     def Classify(self, request, context):
-        print('接收数据: ' + request.keyword)
-        res = self.predictorfac.predict(request.keyword)
+        dic_data = json.loads(request.keyword)
+        print(dic_data)
+        res = self.predictorfac.predict(dic_data)
         return classify_pb2.ClassifyReply(message='result {msg}'.format(msg=res))
 
     def fac_test_predic(self, data):

client/client.py

@@ -4,7 +4,8 @@ from protobuf import classify_pb2_grpc
 import pandas as pd
 import json
 def get_test_data():
-    df=pd.read_excel(r'C:\Users\ICHUNT\Desktop\bomlist\DZ0901_V1.4_BOM.xlsx',header=None)
+    df=pd.read_excel(r'C:\Users\ICHUNT\Desktop\bomlist\00 BSJ BMS合并-询价-珠海能源.xlsx', header=None)
+    print(df)
     df.fillna(' ', inplace=True)
     dic_dft = df.to_dict(orient='list')
     return json.dumps(dic_dft)

predic_fac.py

@@ -19,8 +19,7 @@ class PredictorFac():
         elif isinstance(data, dict):
             return self.dict_predictor
 
-    def predict(self, data):
-        dic_data = json.loads(data)
+    def predict(self, dic_data):
         predictor = self._get_predictor(dic_data)
         res = predictor.predict(dic_data)
         return res
@@ -40,5 +39,6 @@ if __name__ == "__main__":
 
     data = get_test_data()
     p = PredictorFac(model_config)
+    data = json.loads(data)
     res = p.predict(data)
     print(res)

predict/dict_predict.py

@@ -4,17 +4,17 @@ from predict.base_handler import BasePredictor
 
 # 可能的头部字段
 prob_fields = ["序号", "名称", "规格", "MPN", "用量(pcs)", "用量", "pcs", "位号", "描述", "值", "数量", "封装", "类别", "a面位置", "b面位置", "备注",
-               "需求数量",
+               "需求数量", "售价",
                "参考品牌", "品牌", "item", "厂商编码", "品牌/厂商", "参考料号", "参考供应商", "top面", "bottom面"]
 
 # 标准名和代名词的映射
 fields_map = {"序号": ["序号"],
               "类别": ["类别", "分类", "名称", "类别名称"],
               "参数": ["参数", "规格", "描述"],
-              "型号": ["型号", "参考料号", "料号", "MPN"],
+              "型号": ["型号", "参考料号", "料号", "MPN", "厂商编码"],
               "数量": ["数量", "用量(pcs)", "PCS", "用量", "用量(PCS)", "pcs"],
               "封装": ["封装", "封装规格"],
-              "品牌": ["品牌", "品牌/厂商", "参考品牌", "厂商编码", "参考供应商", "厂商", "参考供应商", "参考厂商"]}
+              "品牌": ["品牌", "品牌/厂商", "参考品牌", "参考供应商", "厂商", "参考供应商", "参考厂商"]}
 
 #
 order_list = ['序号']
@@ -28,14 +28,17 @@ def fun(seri):
 
 
 # 取前多少行
-HEAD_ROW = 5
+HEAD_ROW = 7
+# 空置率阈值
+NAN_RATE = 0.8
+
 
 
 class DicPredict(BasePredictor):
 
     def id_by_field(self, df_head):
         """
-        :param df_head: 传入接收数据的头部Dataframe(默认5行)
+        :param df_head: 传入接收数据的头部Dataframe(默认7行)
         :return li_res: 返回结果列表
         """
         series = df_head.apply(fun)
@@ -66,7 +69,7 @@ class DicPredict(BasePredictor):
             for item in v:
                 if not str(item).strip():
                     counter += 1
-            if counter / len(v) >= 0.8:
+            if counter / len(v) >= NAN_RATE:
                 continue
             columns.append(k)
             li_data.append(v)