File size: 5,427 Bytes
dfe37be |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 |
import json
import os
import csv
# 定义文件所在的目录
input_dir = '/evaluate_result'
# 获取目录中的所有文件
files = os.listdir(input_dir)
# with open("token_counts_QS.csv","w", newline='') as csvfile:
# writer = csv.writer(csvfile)
# writer.writerow(["Model", "token_subset_1", "token_subset_2","token_subset_3","token_subset_4","token_subset_5"])
#
# with open("line_counts_QS.csv","w", newline='') as csvfile:
# writer = csv.writer(csvfile)
# writer.writerow(["Model", "line_subset_1", "line_subset_2","line_subset_3","line_subset_4","line_subset_5"])
with open("CC_QS.csv", "w", newline='') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(["Model", "CC_subset_1", "CC_subset_2","CC_subset_3","CC_subset_4","CC_subset_5"])
for file_name in files:
# 构建完整的文件路径
input_file_path = os.path.join(input_dir, file_name)
first_underscore_index = file_name.find('_')
# 找到最后一个 - 的位置
last_dash_index = file_name.rfind('-')
model_name = file_name[first_underscore_index + 1:last_dash_index]
print(model_name)
with open(input_file_path,"r",encoding="utf-8") as file:
data1=json.load(file)
with open("QS.json", "r", encoding="utf-8") as file:
data2=json.load(file)
sum0=0
count0=0
sum1=0
count1=0
sum2=0
count2=0
sum3 = 0
count3 = 0
sum4=0
count4=0
for (item1,item2) in zip(data1["humaneval"]["pass@1"],data2):
# #按照token个数划分后的评估结果
# if item2["token_diff"] == 0:
# index, value = item1
# print(item2["token_diff"],index,value)
# sum0=sum0+value
# count0=count0+1
# if item2["token_diff"] == 1:
# index, value = item1
# print(item2["token_diff"], index, value)
# sum1=sum1+value
# count1=count1+1
# if item2["token_diff"] == 2:
# index, value = item1
# print(item2["token_diff"], index, value)
# sum2=sum2+value
# count2=count2+1
# if item2["token_diff"] == 3:
# index, value = item1
# print(item2["token_diff"], index, value)
# sum3=sum3+value
# count3=count3+1
# if item2["token_diff"] == 4:
# index, value = item1
# print(item2["token_diff"], index, value)
# sum4 = sum4 + value
# count4 = count4 + 1
#按照行数划分后的评估结果
# if item2["line_diff"] == 0:
# index, value = item1
# print(item2["line_diff"],index,value)
# sum0=sum0+value
# count0=count0+1
# if item2["line_diff"] == 1:
# index, value = item1
# print(item2["line_diff"], index, value)
# sum1=sum1+value
# count1=count1+1
# if item2["line_diff"] == 2:
# index, value = item1
# print(item2["line_diff"], index, value)
# sum2=sum2+value
# count2=count2+1
# if item2["line_diff"] == 3:
# index, value = item1
# print(item2["line_diff"], index, value)
# sum3=sum3+value
# count3=count3+1
# if item2["line_diff"] == 4:
# index, value = item1
# print(item2["line_diff"], index, value)
# sum4=sum4+value
# count4=count4+1
#按照圈复杂度划分后的评估结果
if item2["CC_diff"] == 0:
index, value = item1
print(item2["CC_diff"],index,value)
sum0=sum0+value
count0=count0+1
if item2["CC_diff"] == 1:
index, value = item1
print(item2["CC_diff"], index, value)
sum1=sum1+value
count1=count1+1
if item2["CC_diff"] == 2:
index, value = item1
print(item2["CC_diff"], index, value)
sum2=sum2+value
count2=count2+1
if item2["CC_diff"] == 3 :
index, value = item1
print(item2["CC_diff"], index, value)
sum3=sum3+value
count3=count3+1
if item2["CC_diff"] == 4 :
index, value = item1
print(item2["CC_diff"], index, value)
sum4=sum4+value
count4=count4+1
mean0=round(sum0/count0*100,2)
mean1=round(sum1/count1*100,2)
mean2=round(sum2/count2*100,2)
mean3=round(sum3/count3*100,2)
mean4=round(sum4/count4*100,2)
print("count_result!!")
print(count0,count1,count2,count3,count4)
print(mean0,mean1,mean2,mean3,count4)
# with open("token_counts_QS.csv", mode='a', newline='', encoding='utf-8') as file:
# writer = csv.writer(file)
# writer.writerow([model_name,mean0,mean1,mean2,mean3,mean4])
#
# with open("line_counts_QS.csv", mode='a', newline='', encoding='utf-8') as file:
# writer = csv.writer(file)
# writer.writerow([model_name,mean0,mean1,mean2,mean3,mean4])
#
with open("CC_QS.csv", mode='a', newline='', encoding='utf-8') as file:
writer = csv.writer(file)
writer.writerow([model_name,mean0,mean1,mean2,mean3,mean4])
|