数据指标波动假设检验统计

eda/recommended_indexs/hypothesis_test.py

@@ -297,39 +297,79 @@ chi_cal(ctcvr_tst_new)
 # ###############数据波动大小检验##############
 print("============================分割线===================================")
 
-def get_var_data(x,y,z,t1):
+def get_var_data1(x,y,z,t1):
     sql_cid = "select {0}/{1} from {2} \
     where stat_date >= '{3}' ".format(x,y,z,t1)
     CVR_DATA_recently = con_sql(sql_cid)
     return CVR_DATA_recently
+
+def get_var_data2(x,y,z,q,t1):
+    sql_cid = "select ({0}+{1})/{2} from {3} \
+    where stat_date >= '{4}' ".format(x,y,z,q,t1)
+    CVR_DATA_recently = con_sql(sql_cid)
+    return CVR_DATA_recently
+
 def collect_data(data):
     tt = [float(data[i][0])*100 for i in range(len(data))]
     return tt
 
-var_ctcvr_old_data=get_var_data("diary_meigou_oldUser","diary_exp_oldUser","diary_meigou_crv",five_days)
+var_ctcvr_old_data=get_var_data1("diary_meigou_oldUser","diary_exp_oldUser","diary_meigou_crv",five_days)
 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))
+
 
-var_ctcvr_new_data=get_var_data("diary_meigou_newUser","diary_exp_newUser","diary_meigou_crv",five_days)
+var_ctcvr_new_data=get_var_data1("diary_meigou_newUser","diary_exp_newUser","diary_meigou_crv",five_days)
 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))
 
-var_cvr_old_data=get_var_data("diary_meigou_oldUser","diary_clk_oldUser","diary_meigou_crv",five_days)
+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))
+
 #
-var_cvr_new_data=get_var_data("diary_meigou_newUser","diary_clk_newUser","diary_meigou_crv",five_days)
+var_cvr_new_data=get_var_data1("diary_meigou_newUser","diary_clk_newUser","diary_meigou_crv",five_days)
 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))
+
+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))
+
+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))
+
+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))
 
-# var_ctr_new_data=get_var_data("diary_meigou_newUser","diary_clk_newUser","diary_meigou_crv",five_days)
-# var_cvr_new_D=collect_data(var_cvr_new_data)
-# var_cvr_new=np.var(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))
+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))