数据指标波动假设检验统计

eda/recommended_indexs/hypothesis_test.py

@@ -38,7 +38,7 @@ def get_somedate():
 	return someday
 ten_days=get_somedate()
 # print(ten_days)
-
+print("===========分割线，T检验最近10日指标与策略前10日指标是否获得显著提升============")
 #获取最近10天的数据
 def DATA_recently(x,y,z,q,t):
     ten_days = get_somedate()
@@ -117,20 +117,20 @@ def t_test(x,y): #进行t检验
         t_p_value=t_test[1]
         # print(t_p_value)
         if t_p_value>0.05:
-            print("策略前后两组数据无显著性差异，即该指标没有显著提升，p_value:{}" .format(t_p_value))
+            print("95%置信度认为策略前后两组数据无显著性差异，即该指标没有显著提升，p_value:{}" .format(t_p_value))
             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("95%置信度认为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]
         # print(t_p_value)
         if t_p_value > 0.05:
-            print("策略前后两组数据无显著性差异，即该指标没有显著提升，p_value:{}" .format(t_p_value))
+            print("95%置信度认为策略前后两组数据无显著性差异，即该指标没有显著提升，p_value:{}" .format(t_p_value))
             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("95%置信度认为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
@@ -165,7 +165,7 @@ print("【8】老用户CTR假设检验（on_click_diary_card）结果：")
 ctr_old_o_ttest=t_test(x_ctr_old_o,y_ctr_old_o)
 #
 # ###############推荐策略不变的情况下数据假设检验##############
-print("============================分割线===================================")
+print("===========分割线，卡方检验昨日指标与前5日指标均值是否显著变化============")
 # #1 计算每日指标卡方检验
 #
 # #自动获取5日前的日期
@@ -306,7 +306,7 @@ ctcvr_tst_new=data_cal(ctcvr_new,ctcvr_new2)
 chi_cal(ctcvr_tst_new)
 
 # ###############数据波动大小检验##############
-print("============================分割线===================================")
+print("============================分割线,开始检测各个指标的5日内的方差和均值===================================")
 
 def get_var_data1(x,y,z,t1):
     sql_cid = "select {0}/{1} from {2} \
@@ -328,8 +328,8 @@ var_ctcvr_old_data=get_var_data1("diary_meigou_oldUser","diary_exp_oldUser","dia
 var_ctcvr_old_D=collect_data(var_ctcvr_old_data)
 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("【1-1】老用户CT-CVR数据波动5日内方差检验结果：{}".format(var_ctcvr_old))
+print("【1-2】老用户CT-CVR数据波动5日内均值:{}%".format(mean_var_ctcvr_old))
 print("\n")
 
 
@@ -337,16 +337,16 @@ var_ctcvr_new_data=get_var_data1("diary_meigou_newUser","diary_exp_newUser","dia
 var_ctcvr_new_D=collect_data(var_ctcvr_new_data)
 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("【2-1】新用户CT-CVR数据波动5日内方差检验结果：{}".format(var_ctcvr_new))
+print("【2-2】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)
 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("【3-1】老用户CVR数据波动5日内方差检验结果：{}".format(var_cvr_old))
+print("【3-2】老用户CVR数据波动5日内均值:{}%".format(mean_var_cvr_old))
 print("\n")
 
 #
@@ -354,40 +354,40 @@ var_cvr_new_data=get_var_data1("diary_meigou_newUser","diary_clk_newUser","diary
 var_cvr_new_D=collect_data(var_cvr_new_data)
 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("【4-1】新用户CVR数据波动5日内方差检验结果：{}".format(var_cvr_new))
+print("【4-2】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)
 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("【5-1】老用户CTR数据波动5日内方差检验结果：{}".format(var_ctr_old))
+print("【5-2】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)
 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("【6-1】新用户CTR数据波动5日内方差检验结果：{}".format(var_ctr_new))
+print("【6-2】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)
 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("【7-1】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("【7-2】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)
 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("【8-1】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("【8-2】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")