新增 requirements.txt

stratrgy/upLevel.py

@@ -0,0 +1,234 @@
+"""
+@author: luojunhui
+"""
+import json
+
+from pandas import DataFrame
+from datetime import datetime
+from applications import longArticlesMySQL
+
+lam = longArticlesMySQL()
+
+
+class articleLevelUp(object):
+    """
+    文章晋级
+    """
+    columns = [
+        "位置",
+        "粉丝量",
+        "阅读量",
+        "平均阅读量",
+        "头条阅读量",
+        "头条平均阅读量",
+        "阅读均值倍数",
+        "阅读率",
+        "小程序打开率",
+        "T+0裂变率",
+        "标题",
+        "链接"
+    ]
+    statMapThreeToEight = {
+        "阅读均值倍数": {
+            "mean": 1.1388723507368606,
+            "max": 62.50000000000001,
+            "min": 0.0,
+            "median": 0.8890469416785206,
+            "75%": 1.2617516081147946,
+            "80%": 1.37797320398902,
+            "90%": 1.8733429945338946,
+            "95%": 2.6455874825730517,
+            "99%": 6.252251764489181
+        },
+        "阅读率": {
+            "mean": 0.0006051220910642054,
+            "max": 0.06252537555826228,
+            "min": 0.0,
+            "median": 0.0002241206067691894,
+            "75%": 0.0005117154674215644,
+            "80%": 0.0006449975188817015,
+            "90%": 0.001255232384471895,
+            "95%": 0.002233845658277497,
+            "99%": 0.00633843067255787
+        },
+        "小程序打开率": {
+            "mean": 0.062085135696479415,
+            "max": 1.0,
+            "min": 0.0,
+            "median": 0.045454545454545456,
+            "75%": 0.08695652173913043,
+            "80%": 0.1,
+            "90%": 0.14285714285714285,
+            "95%": 0.18518518518518517,
+            "99%": 0.310463054187192
+        },
+        "T+0裂变率": {
+            "mean": 0.35277482885383377,
+            "max": 181.0,
+            "min": 0.0,
+            "median": 0.0,
+            "75%": 0.0,
+            "80%": 0.09090909090909091,
+            "90%": 0.6666666666666666,
+            "95%": 1.5,
+            "99%": 6.0
+        }
+    }
+    statMapTwoToOne = {
+        "阅读均值倍数": {
+            "mean": 1.0242728432910957,
+            "max": 4.921632060507756,
+            "min": 0.04236315118498048,
+            "median": 0.9604958720021857,
+            "75%": 1.237352622811623,
+            "80%": 1.3131587863024974,
+            "90%": 1.5778563945144477,
+            "95%": 1.8312064951656155,
+            "99%": 2.5125234834603165
+        },
+        "阅读率": {
+            "mean": 0.0073535037464145655,
+            "max": 0.05265662356955502,
+            "min": 0.00020895172629276676,
+            "median": 0.005941952332154309,
+            "75%": 0.009324205525316574,
+            "80%": 0.010420614811741105,
+            "90%": 0.013728137204835086,
+            "95%": 0.01704242661483454,
+            "99%": 0.02622215995438508
+        },
+        "小程序打开率": {
+            "mean": 0.14893695109764848,
+            "max": 2.5,
+            "min": 0.0,
+            "median": 0.1360318513603185,
+            "75%": 0.1875,
+            "80%": 0.20230028849345147,
+            "90%": 0.25449906489537877,
+            "95%": 0.3051369784478383,
+            "99%": 0.4016107123469446
+        },
+        "T+0裂变率": {
+            "mean": 0.6465295965706923,
+            "max": 12.804878048780488,
+            "min": 0.0,
+            "median": 0.48770491803278687,
+            "75%": 0.8011363636363636,
+            "80%": 0.9144722345551121,
+            "90%": 1.317362236032163,
+            "95%": 1.792137476827772,
+            "99%": 3.277849462365585
+        }
+    }
+
+    @classmethod
+    def getBaseData(cls):
+        """
+
+        :return:
+        """
+        # today = datetime.today().strftime("%Y%m%d")
+        sql = f"""
+        SELECT
+            position, fans, view_count, avg_view_count, first_view_count, first_avg_view_count, read_rate, read_fans_rate, first_read_rate, fission0_first_rate, title, link
+        FROM 
+            datastat_sort_strategy;
+        """
+        response = lam.select(sql)
+        df = DataFrame(response, columns=cls.columns)
+        return df
+
+    @classmethod
+    def analysisDF(cls, indexList):
+        """
+        分析 dataframe 中数据占比
+        :return:
+        """
+        DF = cls.getBaseData()
+        DF = DF[(DF["位置"].isin(indexList))]
+        print(len(DF))
+        avg_read_times = DF['阅读均值倍数'].sort_values(ascending=False)
+        read_rate = DF['阅读率'].sort_values(ascending=False)
+        mini_open_rate = DF['小程序打开率'].sort_values(ascending=False)
+        t_plus_0_fission = DF['T+0裂变率'].sort_values(ascending=False)
+        detail = {
+            "阅读均值倍数": {
+                "mean": avg_read_times.mean(),
+                "max": avg_read_times.max(),
+                "min": avg_read_times.min(),
+                "median": avg_read_times.median(),
+                "75%": avg_read_times.quantile(0.75),
+                "80%": avg_read_times.quantile(0.8),
+                "90%": avg_read_times.quantile(0.9),
+                "95%": avg_read_times.quantile(0.95),
+                "99%": avg_read_times.quantile(0.99)
+            },
+            "阅读率": {
+                "mean": read_rate.mean(),
+                "max": read_rate.max(),
+                "min": read_rate.min(),
+                "median": read_rate.median(),
+                "75%": read_rate.quantile(0.75),
+                "80%": read_rate.quantile(0.8),
+                "90%": read_rate.quantile(0.9),
+                "95%": read_rate.quantile(0.95),
+                "99%": read_rate.quantile(0.99)
+            },
+            "小程序打开率": {
+                "mean": mini_open_rate.mean(),
+                "max": mini_open_rate.max(),
+                "min": mini_open_rate.min(),
+                "median": mini_open_rate.median(),
+                "75%": mini_open_rate.quantile(0.75),
+                "80%": mini_open_rate.quantile(0.8),
+                "90%": mini_open_rate.quantile(0.9),
+                "95%": mini_open_rate.quantile(0.95),
+                "99%": mini_open_rate.quantile(0.99)
+            },
+            "T+0裂变率": {
+                "mean": t_plus_0_fission.mean(),
+                "max": t_plus_0_fission.max(),
+                "min": t_plus_0_fission.min(),
+                "median": t_plus_0_fission.median(),
+                "75%": t_plus_0_fission.quantile(0.75),
+                "80%": t_plus_0_fission.quantile(0.8),
+                "90%": t_plus_0_fission.quantile(0.9),
+                "95%": t_plus_0_fission.quantile(0.95),
+                "99%": t_plus_0_fission.quantile(0.99)
+            }
+        }
+        print(json.dumps(detail, ensure_ascii=False, indent=4))
+
+    @classmethod
+    def upLevel38To2(cls):
+        """
+        :return:
+        """
+        dataThreeToEight = cls.getBaseData()
+        dataThreeToEight = dataThreeToEight[dataThreeToEight['位置'].isin([3, 4, 5, 6, 7, 8])]
+        filter_data = dataThreeToEight[
+            (dataThreeToEight['T+0裂变率'] > cls.statMapThreeToEight['T+0裂变率']['95%'])
+            & (dataThreeToEight['阅读均值倍数'] > cls.statMapThreeToEight['阅读均值倍数']['95%'])
+            ]
+        return filter_data
+
+    @classmethod
+    def upLevel2To1(cls):
+        """
+        :return:
+        """
+        dataThreeToEight = cls.getBaseData()
+        dataThreeToEight = dataThreeToEight[dataThreeToEight['位置'].isin([2])]
+        filter_data = dataThreeToEight[
+            (dataThreeToEight['T+0裂变率'] > cls.statMapThreeToEight['T+0裂变率']['90%'])
+            & (dataThreeToEight['阅读均值倍数'] > cls.statMapThreeToEight['阅读均值倍数']['90%'])
+            ]
+        return filter_data
+
+
+U = articleLevelUp()
+f_d = U.upLevel2To1()
+for line in list(zip(f_d['标题'], f_d['链接'])):
+    print(line[0])
+    print(line[1])
+    print("\n")

updatePublishedMsgDaily.py

@@ -321,8 +321,6 @@ def updateJob():
             time.sleep(5)
         except Exception as e:
             print(e)
-    db_client.close()
-    print("服务号更新完成")
 
 
 def checkJob():
@@ -353,8 +351,6 @@ def checkJob():
         except Exception as e:
             print("Timeout Error: {}".format(e))
 
-    db_client.close()
-
 
 def job_with_thread(job_func):
     """
@@ -369,14 +365,14 @@ def job_with_thread(job_func):
 if __name__ == '__main__':
     schedule.every().day.at("20:50").do(job_with_thread, updateJob)
 
-    schedule.every().day.at("21:30").do(job_with_thread, checkJob)
+    schedule.every().day.at("21:45").do(job_with_thread, checkJob)
 
     while True:
         schedule.run_pending()
         time.sleep(1)
-        log(
-            task="updatePublishedMsgDaily",
-            function="main",
-            message="更新公众号文章信息任务正常执行"
-        )
+        # log(
+        #     task="updatePublishedMsgDaily",
+        #     function="main",
+        #     message="更新公众号文章信息任务正常执行"
+        # )