数据指标波动假设检验统计

eda/recommended_indexs/hypothesis_test.py

@@ -187,18 +187,6 @@ def data_cal(x,y):
     y_a=[y[0], y[1] - y[0]]
     a_df=pd.DataFrame({'原':x_a,'测':y_a})
     return a_df
-chi_ctr_precise_recently=chi_DATA_recently("clk_count_oldUser_all_a","clk_count_oldUser_all_b","imp_count_oldUser_all_precise","on_click_diary_card",five_days,yesterday)
-temp1=[float(str(Decimal(chi_ctr_precise_recently[i]).quantize(Decimal('0.0')))) for i in range(len(chi_ctr_precise_recently))]
-# print(temp1)
-chi_ctr_precise_yesterday=chi_DATA_yesterday("clk_count_oldUser_all_a","clk_count_oldUser_all_b","imp_count_oldUser_all_precise","on_click_diary_card",yesterday)
-temp2=[float(chi_ctr_precise_yesterday[i]) for i in range(len(chi_ctr_precise_yesterday))]
-# print(temp2)
-tst=data_cal(temp1,temp2)
-print(tst)
-
-
-# print(chi_ctr_precise_recently)
-# print(chi_ctr_precise_yesterday)
 
 def chi_cal(data):
     data['共计'] = data.apply(lambda x: x.sum(), axis=1)
@@ -231,6 +219,23 @@ def chi_cal(data):
     else:
         print("数据波动较小，95%可能性属于正常波动范围")
 
+
+chi_ctr_precise_recently=chi_DATA_recently("clk_count_oldUser_all_a","clk_count_oldUser_all_b","imp_count_oldUser_all_precise","on_click_diary_card",five_days,yesterday)
+temp1=[float(str(Decimal(chi_ctr_precise_recently[i]).quantize(Decimal('0.0')))) for i in range(len(chi_ctr_precise_recently))]
+# print(temp1)
+chi_ctr_precise_yesterday=chi_DATA_yesterday("clk_count_oldUser_all_a","clk_count_oldUser_all_b","imp_count_oldUser_all_precise","on_click_diary_card",yesterday)
+temp2=[float(chi_ctr_precise_yesterday[i]) for i in range(len(chi_ctr_precise_yesterday))]
+# print(temp2)
+tst=data_cal(temp1,temp2)
+print(tst)
+chi_cal(tst)
+
+
+# print(chi_ctr_precise_recently)
+# print(chi_ctr_precise_yesterday)
+
+
+
 # chi_cvr_new=
 # chi_cvr_old=
 #