识别数量列

classify_server.py

@@ -43,6 +43,5 @@ def serve():
 if __name__ == '__main__':
     # serve()
     data = read_from_excel('DZ0901_V1.4_BOM.xlsx', 'DZ0901_V1.3BOM清单')
-    print(data)
     print(Classify().fac_test_predic(data))
 

predict/list_predict.py

 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
+import re
 from predict.base_handler import BasePredictor
-from utils.excel_manager import read_from_excel
 
 
-order_list = ['序号']
+RIGHT_LEVEL = 0.7
 
 
 class LiPredict(BasePredictor):
 
     def predict(self, key):
-        if len(key) > 0:
-            self.order_predict(key[0])
+        # if len(key) > 0:
+        #     self.order_predict(key[1])
+        for ix in key:
+            self.num_predict(key[ix])
         pass
 
+    """
+    序列预测
+    """
     def order_predict(self, data):
-        collect_num = [int(kw) for kw in data if isinstance(kw, float) or isinstance(kw, int)]
-        judge = self.IsIncrease(collect_num, len(collect_num))
+        collect_order = [int(kw) for kw in data if isinstance(kw, float) or isinstance(kw, int)]
+        judge = self.isIncrease(collect_order, len(collect_order)) if len(collect_order) > 0 else False
         print('judge: ' + str(judge))
         return judge
 
     """
+    数量预测
+    """
+    def num_predict(self, data):
+        collect_num = [kw for kw in data if isinstance(kw, int) or self.isNumberCol(kw)]
+        rate = round(len(collect_num) / len(data), 3)
+        return True if rate >= RIGHT_LEVEL else False
+
+    """
     判断列表元素是否递增
     """
-    def IsIncrease(self, arr, size):
+    def isIncrease(self, arr, size):
         if size == 1:
             return True
-        return (arr[size - 1] >= arr[size - 2]) and self.IsIncrease(arr, size - 1)
+        return (arr[size - 1] >= arr[size - 2]) and self.isIncrease(arr, size - 1)
+
+    """
+    判断是否数量列
+    """
+    def isNumberCol(self, kw):
+        if isinstance(kw, str):
+            return re.match(r'(\d+)((K)|([\u4E00-\u9FA5]{1,3}))$', kw, re.M | re.I)
+        else:
+            return False
+
 
 

utils/excel_manager.py

 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
-import xlwt
-import xlrd
+import pandas as pd
+
+
+# def read_from_excel(file_name, sheet_name):
+#     wb = xlrd.open_workbook(file_name)
+#     sheet = wb.sheet_by_name(sheet_name)
+#     row = sheet.nrows
+#     col = sheet.ncols
+#     result_dict = {}
+#     for i in range(col):
+#         col_list = []
+#         for j in range(row): col_list.append(sheet.cell_value(j, i))
+#         result_dict[i] = col_list
+#     return result_dict
 
 
 def read_from_excel(file_name, sheet_name):
-    wb = xlrd.open_workbook(file_name)
-    sheet = wb.sheet_by_name(sheet_name)
-    row = sheet.nrows
-    col = sheet.ncols
+    data = pd.read_excel(file_name, sheet_name=sheet_name, keep_default_na=False, header=-1)
     result_dict = {}
-    for i in range(col):
-        col_list = []
-        for j in range(row): col_list.append(sheet.cell_value(j, i))
-        result_dict[i] = col_list
+    count = 0
+    for index in data.columns:
+        result_dict[count] = data[index].tolist()
+        count += 1
+    print(result_dict)
     return result_dict
 
+