各判断方法改为类方法

predict/base_handler.py

@@ -6,17 +6,22 @@ from collections import Counter
 from utils.log_manager import get_logger
 from utils.robots import dd_send_msg
 import pandas as pd
+
 CATEGORY = ['二极管']
 RIGHT_LEVEL = 0.7
 SEQ_LEVEL = 0.5
 CATE_LEVEL = 0.5
 MULTI_SAME_LEVEL = 3
 
+
 class BasePredictor:
     '''
         预测类基类
     '''
 
+    # 占位符
+    PLACEHOLDER = '?'
+
     def __init__(self, name, extractor, classifier):
         self.name = name
         self.classifier = classifier
@@ -25,8 +30,6 @@ class BasePredictor:
         self.info = get_logger(self.name + '_info')
         self.robot_msg = dd_send_msg
         self.pd = pd
-        # 占位符
-        self.PLACEHOLDER = '?'
 
     def predict(self, key):
         raise NotImplementedError
@@ -47,42 +50,36 @@ class BasePredictor:
         dic_proba = {k: v for k, v in zip(classes, deal_list)}
         return predictions[0], dic_proba
 
-    def is_seq(self, data):
-        """
-        序号列预测
-        """
-        collect_seq = [int(kw) for kw in data if isinstance(kw, float) or isinstance(kw, int)]
-        if len(collect_seq) < 1 or not self.isIncrease(collect_seq, len(collect_seq)):
-            return False
-        else:
-            rate = round(len(collect_seq) / len(data), 3)
-            return True if rate >= SEQ_LEVEL else False
+    def valid_seq(self, data):
+        """取反"""
+        return not self.is_seq(data)
+
+    def valid_num(self, data):
+        return not self.is_num(data)
 
+    def valid_cate(self, data):
+        return not self.is_catecol(data)
+
+    @classmethod
     def is_num(self, data):
         """
         数量列预测
         """
-        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
 
-    def isIncrease(self, arr, size):
-        """
-        判断列表元素是否递增
-        """
-        if size == 1:
-            return True
-        return (arr[size - 1] >= arr[size - 2]) and self.isIncrease(arr, size - 1)
+        def isNumberCol(kw):
+            """
+            是否是数量列辅助函数
+            """
+            if isinstance(kw, str):
+                return re.match(r'(\d+)((K)|([\u4E00-\u9FA5]{1,3}))$', kw, re.M | re.I)
+            else:
+                return False
 
-    def isNumberCol(self, kw):
-        """
-        是否是数量列辅助函数
-        """
-        if isinstance(kw, str):
-            return re.match(r'(\d+)((K)|([\u4E00-\u9FA5]{1,3}))$', kw, re.M | re.I)
-        else:
-            return False
+        collect_num = [kw for kw in data if isinstance(kw, int) or isNumberCol(kw)]
+        rate = round(len(collect_num) / len(data), 3)
+        return True if rate >= RIGHT_LEVEL else False
 
+    @classmethod
     def is_catecol(self, data):
         cates = []
         for i in data:
@@ -92,18 +89,42 @@ class BasePredictor:
         rate = round(len(cates) / len(data), 3)
         return rate >= CATE_LEVEL
 
+    @classmethod
     def is_multi_same(self, data):
         no_null_data = list(filter(lambda x: x != self.PLACEHOLDER, data))
         result = Counter(no_null_data)
         li_sort = sorted(result.items(), key=lambda x: x[1], reverse=True)
         return li_sort[0][1] >= MULTI_SAME_LEVEL
 
-    def valid_seq(self, data):
-        """取反"""
-        return not self.is_seq(data)
+    @classmethod
+    def is_seq(self, data):
+        """
+        序号列预测
+        """
 
-    def valid_num(self, data):
-        return not self.is_num(data)
+        def isIncrease(arr, size):
+            """
+            判断列表元素是否递增
+            """
+            if size == 1:
+                return True
+            return (arr[size - 1] >= arr[size - 2]) and isIncrease(arr, size - 1)
 
-    def valid_cate(self, data):
-        return not self.is_catecol(data)
\ No newline at end of file
+        collect_seq = [int(kw) for kw in data if isinstance(kw, float) or isinstance(kw, int)]
+        if len(collect_seq) < 1 or not isIncrease(collect_seq, len(collect_seq)):
+            return False
+        else:
+            rate = round(len(collect_seq) / len(data), 3)
+            return True if rate >= SEQ_LEVEL else False
+
+
+if __name__ == "__main__":
+    li = ['?', 3400.0, 5920.0, 4849.0, 2544.0, 3270.0, 52751.0, 2031.0, 5302.0, 726.0, 1247.0, 2472.0, 689.0, 6049.0,
+          26796.0, 6164.0, 1605.0, 4346.0, 640.0, 960.0, 960.0, 320.0, 160.0, 860.0, 160.0, 320.0, 3183.0, 10151.0,
+          640.0, 130.0, 1237.0, 800.0, 960.0, 3740.0, 17701.0, 2146.0, 1280.0, 160.0, 1120.0, 160.0, 480.0, 960.0,
+          480.0, 160.0, 4717.0, 160.0, 160.0, 160.0, 640.0, 160.0, 320.0, 160.0, 160.0, 800.0, 800.0, 480.0, 1600.0,
+          155.0, 960.0, 320.0, 944.0, 160.0, 160.0, 1280.0, 1852.0, 7680.0, 7680.0, 2880.0, 160.0, 224.0, 480.0, 480.0,
+          640.0, 160.0, 640.0, 320.0, 1760.0, 640.0, 480.0, 960.0, 160.0, 160.0, 160.0, 160.0, 1920.0, 160.0, 5600.0,
+          480.0, 2560.0, 160.0, 160.0, 160.0, 160.0, 160.0, 1280.0, 160.0, 160.0, 160.0, 160.0, 160.0, 320.0, 0.0,
+          160.0, 160.0],
+    print(BasePredictor.is_num(li))