数据指标波动假设检验统计

eda/recommended_indexs/hypothesis_test.py

@@ -10,6 +10,8 @@ import smtplib
 from email.mime.text import MIMEText
 from email.utils import formataddr
 
+f=open('/srv/apps/ffm-baseline/eda/recommended_indexs/test.txt','w')
+
 #########推荐策略前后统计指标假设检验（t检验）###############
 
 #自动获取昨日日期
@@ -23,7 +25,7 @@ def get_yesterday_date():
 	yesterday = yesterday.strftime("%Y-%m-%d")
 	return yesterday
 yesterday=get_yesterday_date()
-print(yesterday)
+print("监测数据日期:{}".format(yesterday))
 #自动获取10日前的日期
 def get_somedate():
 	#自动获取10日前的日期,如"2018-07-28"
@@ -119,6 +121,7 @@ def t_test(x,y): #进行t检验
             print("\n")
         else:
             print("策略前后两组数据有显著性差异，即该指标获得显著提升，p_value:{}" .format(t_p_value))
+            print("\n")
     else: #认为数据方差不具有齐性，equal_var=false
         t_test = ttest_ind(x, y, equal_var=False)
         t_p_value = t_test[1]
@@ -128,6 +131,7 @@ def t_test(x,y): #进行t检验
             print("\n")
         else:
             print("策略前后两组数据有显著性差异，即该指标获得显著提升，p_value:{}" .format(t_p_value))
+            print("\n")
 #
 # ###假设检验，判断是否具有显著性
 #
@@ -233,8 +237,10 @@ def chi_cal(data):
     #查表发现阈值为3.84
     if X>3.84:
         print("数据波动较大，超出正常波动范围，95%可能性属于指标显著变化，请关注")
+        print("\n")
     else:
         print("数据波动较小，95%可能性属于正常波动范围")
+        print("\n")
 
 #老用户精准点击曝光数据（首页精选日记本列表on_click_diary_card）
 print("【1】（精准曝光）首页精选日记本列表老用户ctr数据波动假设检验结果：")
@@ -324,6 +330,7 @@ var_ctcvr_old=np.var(var_ctcvr_old_D)
 mean_var_ctcvr_old=np.mean(var_ctcvr_old_D)
 print("【1】老用户CT-CVR数据波动5日内方差检验结果：{}".format(var_ctcvr_old))
 print("老用户CT-CVR数据波动5日内均值:{}%".format(mean_var_ctcvr_old))
+print("\n")
 
 
 var_ctcvr_new_data=get_var_data1("diary_meigou_newUser","diary_exp_newUser","diary_meigou_crv",five_days)
@@ -332,6 +339,7 @@ var_ctcvr_new=np.var(var_ctcvr_new_D)
 mean_var_ctcvr_new=np.mean(var_ctcvr_new_D)
 print("【2】新用户CT-CVR数据波动5日内方差检验结果：{}".format(var_ctcvr_new))
 print("新用户CT-CVR数据波动5日内均值:{}%".format(mean_var_ctcvr_new))
+print("\n")
 
 var_cvr_old_data=get_var_data1("diary_meigou_oldUser","diary_clk_oldUser","diary_meigou_crv",five_days)
 var_cvr_old_D=collect_data(var_cvr_old_data)
@@ -339,6 +347,7 @@ var_cvr_old=np.var(var_cvr_old_D)
 mean_var_cvr_old=np.mean(var_cvr_old_D)
 print("【3】老用户CVR数据波动5日内方差检验结果：{}".format(var_cvr_old))
 print("老用户CVR数据波动5日内均值:{}%".format(mean_var_cvr_old))
+print("\n")
 
 #
 var_cvr_new_data=get_var_data1("diary_meigou_newUser","diary_clk_newUser","diary_meigou_crv",five_days)
@@ -347,6 +356,7 @@ var_cvr_new=np.var(var_cvr_new_D)
 mean_var_cvr_new=np.mean(var_cvr_new_D)
 print("【4】新用户CVR数据波动5日内方差检验结果：{}".format(var_cvr_new))
 print("新用户CVR数据波动5日内均值:{}%".format(mean_var_cvr_new))
+print("\n")
 
 var_ctr_old_data=get_var_data2("clk_count_oldUser_all_a","clk_count_oldUser_all_b","imp_count_oldUser_all","on_click_diary_card",five_days)
 var_ctr_old_D=collect_data(var_ctr_old_data)
@@ -354,6 +364,7 @@ var_ctr_old=np.var(var_cvr_old_D)
 mean_var_ctr_old=np.mean(var_ctr_old_D)
 print("【5】老用户CTR数据波动5日内方差检验结果：{}".format(var_ctr_old))
 print("老用户CTR数据波动5日内均值:{}%".format(mean_var_ctr_old))
+print("\n")
 
 var_ctr_new_data=get_var_data2("clk_count_newUser_all_a","clk_count_newUser_all_b","imp_count_newUser_all","on_click_diary_card",five_days)
 var_ctr_new_D=collect_data(var_ctr_new_data)
@@ -361,6 +372,7 @@ var_ctr_new=np.var(var_ctr_new_D)
 mean_var_ctr_new=np.mean(var_ctr_new_D)
 print("【6】新用户CTR数据波动5日内方差检验结果：{}".format(var_ctr_new))
 print("新用户CTR数据波动5日内均值:{}%".format(mean_var_ctr_new))
+print("\n")
 
 var_ctr_new_precise_data=get_var_data2("clk_count_newUser_all_a","clk_count_newUser_all_b","imp_count_newUser_all_precise","on_click_diary_card",five_days)
 var_ctr_new_precise_D=collect_data(var_ctr_new_precise_data)
@@ -368,6 +380,7 @@ var_ctr_new_precise=np.var(var_ctr_new_precise_D)
 mean_var_ctr_new_precise=np.mean(var_ctr_new_precise_D)
 print("【7】新用户精准曝光CTR数据波动5日内方差检验结果：{}".format(var_ctr_new_precise))
 print("新用户精准曝光CTR数据波动5日内均值:{}%".format(mean_var_ctr_new_precise))
+print("\n")
 
 var_ctr_old_precise_data=get_var_data2("clk_count_oldUser_all_a","clk_count_oldUser_all_b","imp_count_oldUser_all_precise","on_click_diary_card",five_days)
 var_ctr_old_precise_D=collect_data(var_ctr_old_precise_data)
@@ -375,38 +388,44 @@ var_ctr_old_precise=np.var(var_ctr_old_precise_D)
 mean_var_ctr_old_precise=np.mean(var_ctr_old_precise_D)
 print("【8】老用户精准曝光CTR数据波动5日内方差检验结果：{}".format(var_ctr_old_precise))
 print("老用户精准曝光CTR数据波动5日内均值:{}%".format(mean_var_ctr_old_precise))
+print("\n")
 
 
 
 # print(chi_ctr_precise_recently)
 # print(chi_ctr_precise_yesterday)
 print("============================分割线===================================")
+#保存文件
+
+
+
+
 ##发送邮件
 
-my_sender='gaoyazhe@igengmei.com'
-my_pass = 'VCrKTui99a7ALhiK'
-my_user1='wangzhiwei@igengmei.com'
-def mail():
-    ret = True
-    try:
-        text = "Hi!\nHow are you?\nHere is the link you wanted:\nhttp://www.baidu.com"
-        msg = MIMEText(text, 'plain', 'utf-8')
-        msg['From'] = formataddr(["王志伟", my_sender])
-        msg['To'] = my_user1
-        msg['Subject'] = str(datetime.date.today()) + "-esmm多目标模型训练指标统计"
-        server = smtplib.SMTP_SSL("smtp.exmail.qq.com", 465)
-        server.login(my_sender, my_pass)
-        server.sendmail(my_sender, [my_user1], msg.as_string())
-        server.quit()
-    except Exception:
-        ret=False
-    return ret
-
-ret=mail()
-if ret:
-    print("邮件发送成功")
-else:
-    print("邮件发送失败")
+# my_sender='gaoyazhe@igengmei.com'
+# my_pass = 'VCrKTui99a7ALhiK'
+# my_user1='wangzhiwei@igengmei.com'
+# def mail():
+#     ret = True
+#     try:
+#         text = "Hi!\nHow are you?\nHere is the link you wanted:\nhttp://www.baidu.com"
+#         msg = MIMEText(text, 'plain', 'utf-8')
+#         msg['From'] = formataddr(["王志伟", my_sender])
+#         msg['To'] = my_user1
+#         msg['Subject'] = str(datetime.date.today()) + "-esmm多目标模型训练指标统计"
+#         server = smtplib.SMTP_SSL("smtp.exmail.qq.com", 465)
+#         server.login(my_sender, my_pass)
+#         server.sendmail(my_sender, [my_user1], msg.as_string())
+#         server.quit()
+#     except Exception:
+#         ret=False
+#     return ret
+#
+# ret=mail()
+# if ret:
+#     print("邮件发送成功")
+# else:
+#     print("邮件发送失败")
 
 # chi_cvr_new=
 # chi_cvr_old=