Upload 71 files

dividing_into_different_subsets/3/EI/even.py

@@ -0,0 +1,32 @@
+import json
+
+# 读取 JSON 文件
+with open('humaneval_new.json', 'r') as file:
+    data = json.load(file)
+
+# 提取属性 A 的值
+values_of_A = [obj['line'] for obj in data]
+
+# 计算属性 A 的范围
+min_A = min(values_of_A)
+max_A = max(values_of_A)
+
+# 确定区间数量和宽度
+num_intervals = 3
+interval_width = (max_A - min_A) / num_intervals
+
+# 划分区间
+intervals = [(min_A + i * interval_width, min_A + (i + 1) * interval_width) for i in range(num_intervals)]
+
+# 将数据分配到各个区间
+subsets = [[] for _ in range(num_intervals)]
+
+for obj in data:
+    value_A = obj['line']
+    for i, (start, end) in enumerate(intervals):
+        if start <= value_A < end:
+            subsets[i].append(obj)
+            break
+
+with open('EI.json', 'w', encoding='utf-8') as file:
+    json.dump(data, file, ensure_ascii=False, indent=4)

dividing_into_different_subsets/3/QS/CC_QS.csv

@@ -0,0 +1,12 @@
+Model,CC_subset_1,CC_subset_2,CC_subset_3
+CodeFuse-DeepSeek-33b,80.0,77.78,72.73
+Nxcode-CQ-7B,88.18,85.37,88.27
+codegemma-2b,37.55,25.09,18.73
+codegemma-7b,51.64,37.96,29.73
+codegemma-7b-it,60.55,52.31,46.55
+deepseek-coder-1.3b-base,45.45,31.2,20.27
+deepseek-coder-6.7b-base,57.0,45.09,34.91
+deepseek_coder-6.7b-instruct,75.18,72.78,66.82
+deepseek_coder_33b-base,60.73,51.94,45.55
+deepseek_coder_33b-instruct,70.36,66.3,61.73
+codeqwen1.5-7b,58.73,51.76,43.64

dividing_into_different_subsets/3/QS/calculate_humaneval_result.py

@@ -0,0 +1,115 @@
+import json
+import os
+import csv
+# 定义文件所在的目录
+input_dir = 'E:\python-testn\pythonProject3\hh_1\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"])
+
+
+# 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"])
+
+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"])
+
+
+
+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
+
+    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
+
+
+        #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
+
+        #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
+
+
+
+    mean0=round(sum0/count0*100,2)
+
+    mean1=round(sum1/count1*100,2)
+    mean2=round(sum2/count2*100,2)
+    print("count_result!!")
+    print(count0,count1,count2)
+    print(mean0,mean1,mean2)
+    # 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])
+    with open("CC_QS.csv", mode='a', newline='', encoding='utf-8') as file:
+        writer = csv.writer(file)
+        writer.writerow([model_name,mean0,mean1,mean2])
+
+

dividing_into_different_subsets/3/QS/cata_result.csv

@@ -0,0 +1,12 @@
+Model,String,Math,Array,Sorting,Hash Table,Stack,Search,Matrix
+CodeFuse-DeepSeek-33b,78.57,72.84,77.78,72.41,83.33,100.0,78.26,100.0
+Nxcode-CQ-7B,87.29,86.54,87.06,88.28,74.17,85.0,83.91,20.0
+codegemma-2b,21.21,29.2,29.0,18.28,7.92,17.14,25.43,0.0
+codegemma-7b,34.86,41.91,41.39,29.83,27.5,23.57,32.61,0.0
+codegemma-7b-it,53.0,53.46,53.72,43.28,46.25,38.57,50.65,0.0
+deepseek-coder-1.3b-base,28.0,36.91,30.11,25.17,15.83,22.14,25.65,0.0
+deepseek-coder-6.7b-base,39.64,49.01,44.72,40.86,28.75,37.14,39.57,0.0
+deepseek_coder-6.7b-instruct,69.79,71.98,74.11,73.28,38.75,53.57,78.48,0.0
+deepseek_coder_33b-base,47.64,54.26,52.78,49.48,33.75,41.43,49.57,0.0
+deepseek_coder_33b-instruct,63.29,69.07,66.44,60.34,50.0,46.43,61.09,0.0
+codeqwen1.5-7b,47.64,55.0,50.67,45.69,35.0,45.71,43.91,0.0

dividing_into_different_subsets/3/QS/draw_line.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import pandas as pd
+import plotly.express as px
+
+
+def plot_csv(df):
+    # 将第一列作为索引
+    df.set_index('Model', inplace=True)
+
+    # 转置数据框，使得模型作为列，横轴作为行
+    df_transposed = df.T
+
+    # 使用plotly绘制折线图
+    fig = px.line(df_transposed, x=df_transposed.index, y=df_transposed.columns,
+                  title='Model Evaluation Results',
+                  labels={'value': 'Evaluation Score', 'index': 'Evaluation Metric'},
+                  color_discrete_sequence=px.colors.qualitative.Plotly)
+
+    # 设置悬停效果
+    fig.update_traces(hovertemplate='%{y}')
+
+    return fig
+
+
+# 读取本地的CSV文件
+file_path = 'line_counts_QS.csv'
+df = pd.read_csv(file_path)
+
+
+iface = gr.Interface(
+    fn=plot_csv,
+    inputs=gr.Dataframe(df),
+    outputs=gr.Plot(label="Line Plot"),
+    title="CSV to Line Plot",
+    description="Visualize the evaluation results as a line plot."
+)
+
+iface.launch()

dividing_into_different_subsets/3/QS/even.py

@@ -0,0 +1,53 @@
+import json
+with open("humaneval_new.json", "r", encoding="utf-8") as f:
+    data = json.load(f)
+line_counts=[33,33,34]
+line_counts_I=line_counts[0]*0.01*164
+line_counts_II=line_counts[1]*0.01*164
+line_counts_III=164-line_counts_I-line_counts_II
+
+token_counts=[33,33,34]
+token_counts_I=token_counts[0]*0.01*164
+token_counts_II=token_counts[1]*0.01*164
+token_counts_III=164-token_counts_I-token_counts_II
+
+cyclomatic_complexity=[33,33,34]
+cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*164
+cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*164
+cyclomatic_complexity_III=164-cyclomatic_complexity_II-cyclomatic_complexity_I
+
+
+
+data.sort(key=lambda x: x['line'])
+for i, item in enumerate(data):
+    if i < line_counts_I:
+        item['line_diff'] = 0
+    elif i <line_counts_I+line_counts_II:
+        item['line_diff'] = 1
+    else:
+        item['line_diff'] = 2
+
+data.sort(key=lambda x: x['token'])
+for i, item in enumerate(data):
+    if i < token_counts_I:
+        item['token_diff'] = 0
+    elif i < token_counts_I + token_counts_II:
+        item['token_diff'] = 1
+    else:
+        item['token_diff'] = 2
+
+data.sort(key=lambda x: x['cyclomatic_complexity'])
+for i, item in enumerate(data):
+    if i < cyclomatic_complexity_I:
+        item['CC_diff'] = 0
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II:
+        item['CC_diff'] = 1
+    else:
+        item['CC_diff'] = 2
+
+
+data.sort(key=lambda x: x['id'])
+# 将更新后的数据写回JSON文件
+with open('QS.json', 'w', encoding='utf-8') as file:
+    json.dump(data, file, ensure_ascii=False, indent=4)
+

dividing_into_different_subsets/3/QS/flagged/log.csv

@@ -0,0 +1,2 @@
+df,Line Plot,flag,username,timestamp
+"{""headers"": [""Model"", ""line_subset_1"", ""line_subset_2"", ""line_subset_3""], ""data"": [[""CodeFuse-DeepSeek-33b"", 81.82, 72.22, 76.36], [""Nxcode-CQ-7B"", 92.09, 88.33, 81.45], [""codegemma-2b"", 44.09, 17.5, 19.64], [""codegemma-7b"", 52.45, 35.19, 31.64], [""codegemma-7b-it"", 66.36, 49.26, 43.73], [""deepseek-coder-1.3b-base"", 47.45, 26.39, 23], [""deepseek-coder-6.7b-base"", 63.36, 39.35, 34.18], [""deepseek_coder-6.7b-instruct"", 85, 66.85, 62.82], [""deepseek_coder_33b-base"", 68, 48.89, 41.27], [""deepseek_coder_33b-instruct"", 82.09, 62.31, 53.91], [""codeqwen1.5-7b"", 59.73, 48.7, 45.64]], ""metadata"": null}",,,,2024-09-22 18:55:59.262701

dividing_into_different_subsets/3/QS/humaneval_with_cata.json

@@ -0,0 +1,658 @@
+[
+    {
+        "answer": "Array, Sorting",
+        "id": 0
+    },
+    {
+        "answer": "String, Stack",
+        "id": 1
+    },
+    {
+        "answer": "Math",
+        "id": 2
+    },
+    {
+        "answer": "Array, Math",
+        "id": 3
+    },
+    {
+        "answer": "Math, Array",
+        "id": 4
+    },
+    {
+        "answer": "Array",
+        "id": 5
+    },
+    {
+        "answer": "String, Stack",
+        "id": 6
+    },
+    {
+        "answer": "String, Array, Search",
+        "id": 7
+    },
+    {
+        "answer": "Math, Array",
+        "id": 8
+    },
+    {
+        "answer": "Array, Stack",
+        "id": 9
+    },
+    {
+        "answer": "String, Search",
+        "id": 10
+    },
+    {
+        "answer": "String, Math",
+        "id": 11
+    },
+    {
+        "answer": "String, Array",
+        "id": 12
+    },
+    {
+        "answer": "Math",
+        "id": 13
+    },
+    {
+        "answer": "String, Array",
+        "id": 14
+    },
+    {
+        "answer": "String, Math",
+        "id": 15
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 16
+    },
+    {
+        "answer": "String, Array",
+        "id": 17
+    },
+    {
+        "answer": "String, Search",
+        "id": 18
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 19
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 20
+    },
+    {
+        "answer": "Array, Math",
+        "id": 21
+    },
+    {
+        "answer": "Array, Search",
+        "id": 22
+    },
+    {
+        "answer": "String",
+        "id": 23
+    },
+    {
+        "answer": "Math",
+        "id": 24
+    },
+    {
+        "answer": "Math, Array",
+        "id": 25
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 26
+    },
+    {
+        "answer": "String",
+        "id": 27
+    },
+    {
+        "answer": "String",
+        "id": 28
+    },
+    {
+        "answer": "String, Array",
+        "id": 29
+    },
+    {
+        "answer": "Array",
+        "id": 30
+    },
+    {
+        "answer": "Math",
+        "id": 31
+    },
+    {
+        "answer": "Math, Search",
+        "id": 32
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 33
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 34
+    },
+    {
+        "answer": "Math, Array",
+        "id": 35
+    },
+    {
+        "answer": "Math, Search",
+        "id": 36
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 37
+    },
+    {
+        "answer": "String, Array",
+        "id": 38
+    },
+    {
+        "answer": "Math, Search",
+        "id": 39
+    },
+    {
+        "answer": "Array, Search",
+        "id": 40
+    },
+    {
+        "answer": "Math, Array",
+        "id": 41
+    },
+    {
+        "answer": "Array, Math",
+        "id": 42
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 43
+    },
+    {
+        "answer": "Math, String",
+        "id": 44
+    },
+    {
+        "answer": "Math",
+        "id": 45
+    },
+    {
+        "answer": "Math, Array",
+        "id": 46
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 47
+    },
+    {
+        "answer": "String",
+        "id": 48
+    },
+    {
+        "answer": "Math",
+        "id": 49
+    },
+    {
+        "answer": "String, Math",
+        "id": 50
+    },
+    {
+        "answer": "String",
+        "id": 51
+    },
+    {
+        "answer": "Array, Search",
+        "id": 52
+    },
+    {
+        "answer": "Math",
+        "id": 53
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 54
+    },
+    {
+        "answer": "Math",
+        "id": 55
+    },
+    {
+        "answer": "String, Stack",
+        "id": 56
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 57
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 58
+    },
+    {
+        "answer": "Math, Search",
+        "id": 59
+    },
+    {
+        "answer": "Math",
+        "id": 60
+    },
+    {
+        "answer": "String, Stack",
+        "id": 61
+    },
+    {
+        "answer": "Array, Math",
+        "id": 62
+    },
+    {
+        "answer": "Math, Array",
+        "id": 63
+    },
+    {
+        "answer": "String",
+        "id": 64
+    },
+    {
+        "answer": "String, Math",
+        "id": 65
+    },
+    {
+        "answer": "String, Math",
+        "id": 66
+    },
+    {
+        "answer": "String, Math",
+        "id": 67
+    },
+    {
+        "answer": "Array, Search",
+        "id": 68
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 69
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 70
+    },
+    {
+        "answer": "Math, Array",
+        "id": 71
+    },
+    {
+        "answer": "Array, Math",
+        "id": 72
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 73
+    },
+    {
+        "answer": "String, Array",
+        "id": 74
+    },
+    {
+        "answer": "Math, Hash table",
+        "id": 75
+    },
+    {
+        "answer": "Math",
+        "id": 76
+    },
+    {
+        "answer": "Math",
+        "id": 77
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 78
+    },
+    {
+        "answer": "String, Math",
+        "id": 79
+    },
+    {
+        "answer": "String, Search",
+        "id": 80
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 81
+    },
+    {
+        "answer": "String, Math",
+        "id": 82
+    },
+    {
+        "answer": "Math, Array",
+        "id": 83
+    },
+    {
+        "answer": "Math, String",
+        "id": 84
+    },
+    {
+        "answer": "Array, Math",
+        "id": 85
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 86
+    },
+    {
+        "answer": "Array, Search, Sorting",
+        "id": 87
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 88
+    },
+    {
+        "answer": "String, Math",
+        "id": 89
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 90
+    },
+    {
+        "answer": "String, Search",
+        "id": 91
+    },
+    {
+        "answer": "Math, Array",
+        "id": 92
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 93
+    },
+    {
+        "answer": "Array, Math",
+        "id": 94
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 95
+    },
+    {
+        "answer": "Math, Array",
+        "id": 96
+    },
+    {
+        "answer": "Math",
+        "id": 97
+    },
+    {
+        "answer": "String, Array",
+        "id": 98
+    },
+    {
+        "answer": "String, Math",
+        "id": 99
+    },
+    {
+        "answer": "Array, Math",
+        "id": 100
+    },
+    {
+        "answer": "String, Array",
+        "id": 101
+    },
+    {
+        "answer": "Math, Search",
+        "id": 102
+    },
+    {
+        "answer": "Math, String",
+        "id": 103
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 104
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 105
+    },
+    {
+        "answer": "Array, Math",
+        "id": 106
+    },
+    {
+        "answer": "Math, Search",
+        "id": 107
+    },
+    {
+        "answer": "Array, Math",
+        "id": 108
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 109
+    },
+    {
+        "answer": "Array, String",
+        "id": 110
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 111
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 112
+    },
+    {
+        "answer": "String, Array",
+        "id": 113
+    },
+    {
+        "answer": "Array, Math",
+        "id": 114
+    },
+    {
+        "answer": "Array, Math",
+        "id": 115
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 116
+    },
+    {
+        "answer": "String, Array",
+        "id": 117
+    },
+    {
+        "answer": "String, Search",
+        "id": 118
+    },
+    {
+        "answer": "String, Stack",
+        "id": 119
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 120
+    },
+    {
+        "answer": "Array, Math",
+        "id": 121
+    },
+    {
+        "answer": "Array, Math",
+        "id": 122
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 123
+    },
+    {
+        "answer": "String, Math",
+        "id": 124
+    },
+    {
+        "answer": "String, Math",
+        "id": 125
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 126
+    },
+    {
+        "answer": "Math, Array",
+        "id": 127
+    },
+    {
+        "answer": "Array, Math",
+        "id": 128
+    },
+    {
+        "answer": "Array, Search, Matrix",
+        "id": 129
+    },
+    {
+        "answer": "Math, Array",
+        "id": 130
+    },
+    {
+        "answer": "Math, String",
+        "id": 131
+    },
+    {
+        "answer": "String, Stack",
+        "id": 132
+    },
+    {
+        "answer": "Array, Math",
+        "id": 133
+    },
+    {
+        "answer": "String, Search",
+        "id": 134
+    },
+    {
+        "answer": "Array, Search",
+        "id": 135
+    },
+    {
+        "answer": "Array, Search",
+        "id": 136
+    },
+    {
+        "answer": "String, Math",
+        "id": 137
+    },
+    {
+        "answer": "Math",
+        "id": 138
+    },
+    {
+        "answer": "Math, Array",
+        "id": 139
+    },
+    {
+        "answer": "String, Array",
+        "id": 140
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 141
+    },
+    {
+        "answer": "Array, Math",
+        "id": 142
+    },
+    {
+        "answer": "String, Math",
+        "id": 143
+    },
+    {
+        "answer": "String, Math",
+        "id": 144
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 145
+    },
+    {
+        "answer": "Array, Math",
+        "id": 146
+    },
+    {
+        "answer": "Array, Math",
+        "id": 147
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 148
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 149
+    },
+    {
+        "answer": "Math, Search",
+        "id": 150
+    },
+    {
+        "answer": "Array, Math",
+        "id": 151
+    },
+    {
+        "answer": "Array, Math",
+        "id": 152
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 153
+    },
+    {
+        "answer": "String, Search",
+        "id": 154
+    },
+    {
+        "answer": "String, Math",
+        "id": 155
+    },
+    {
+        "answer": "String, Math",
+        "id": 156
+    },
+    {
+        "answer": "Math, Sorting",
+        "id": 157
+    },
+    {
+        "answer": "String, Array",
+        "id": 158
+    },
+    {
+        "answer": "Array, Math",
+        "id": 159
+    },
+    {
+        "answer": "String, Array, Math",
+        "id": 160
+    },
+    {
+        "answer": "String, Array",
+        "id": 161
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 162
+    },
+    {
+        "answer": "Array, Math",
+        "id": 163
+    }
+]

dividing_into_different_subsets/3/QS/line_counts_QS.csv

@@ -0,0 +1,12 @@
+Model,line_subset_1,line_subset_2,line_subset_3
+CodeFuse-DeepSeek-33b,81.82,72.22,76.36
+Nxcode-CQ-7B,92.09,88.33,81.45
+codegemma-2b,44.09,17.5,19.64
+codegemma-7b,52.45,35.19,31.64
+codegemma-7b-it,66.36,49.26,43.73
+deepseek-coder-1.3b-base,47.45,26.39,23.0
+deepseek-coder-6.7b-base,63.36,39.35,34.18
+deepseek_coder-6.7b-instruct,85.0,66.85,62.82
+deepseek_coder_33b-base,68.0,48.89,41.27
+deepseek_coder_33b-instruct,82.09,62.31,53.91
+codeqwen1.5-7b,59.73,48.7,45.64

dividing_into_different_subsets/3/QS/test.py

@@ -0,0 +1,100 @@
+import json
+import os
+import csv
+#用来计算数据集中不同问题种类对应的pass@k的平均值
+input_dir = 'E:\python-testn\pythonProject3\hh_1\evaluate_result'
+
+# 获取目录中的所有文件
+files = os.listdir(input_dir)
+
+with open("cata_result.csv", "w", newline='') as csvfile:
+    writer = csv.writer(csvfile)
+    writer.writerow(["Model", "String", "Math","Array","Sorting","Hash Table","Stack","Search","Matrix"])
+
+
+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("humaneval_with_cata.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
+    sum5=0
+    count5=0
+    sum6=0
+    count6=0
+    sum7=0
+    count7=0
+    for (item1,item2) in zip(data1["humaneval"]["pass@1"],data2):
+
+
+        if "String" in item2["answer"]:
+            index, value = item1
+            sum0=sum0+value
+            count0=count0+1
+
+        if "Math" in item2["answer"]:
+            index, value = item1
+            sum1=sum1+value
+            count1=count1+1
+
+        if "Array" in item2["answer"]:
+            index, value = item1
+            sum2=sum2+value
+            count2=count2+1
+        if "Sorting" in item2["answer"]:
+            index, value = item1
+            sum3=sum3+value
+            count3=count3+1
+        if "Hash table" in item2["answer"]:
+            index, value = item1
+            sum4 = sum4 + value
+            count4 = count4 + 1
+
+        if "Stack" in item2["answer"]:
+            index, value = item1
+            sum5=sum5+value
+            count5=count5+1
+
+        if "Search" in item2["answer"]:
+            index, value = item1
+            sum6=sum6+value
+            count6=count6+1
+
+        if "Matrix" in item2["answer"]:
+            index, value = item1
+            sum7=sum7+value
+            count7=count7+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)
+    mean5=round(sum5/count5*100,2)
+    mean6=round(sum6/count6*100,2)
+    mean7=round(sum7/count7*100,2)
+    print(count0,count1,count2,count3,count4,count5,count6,count7)
+    print(mean0,mean1,mean2,mean3,mean4,mean5,mean6,mean7)
+    with open("cata_result.csv", mode='a', newline='', encoding='utf-8') as file:
+        writer = csv.writer(file)
+        writer.writerow([model_name,mean0,mean1,mean2,mean3,mean4,mean5,mean6,mean7])
+
+

dividing_into_different_subsets/3/QS/token_counts_QS.csv

@@ -0,0 +1,12 @@
+Model,token_subset_1,token_subset_2,token_subset_3
+CodeFuse-DeepSeek-33b,72.73,88.89,69.09
+Nxcode-CQ-7B,90.73,87.04,84.09
+codegemma-2b,42.45,27.13,11.82
+codegemma-7b,54.18,39.81,25.36
+codegemma-7b-it,69.45,51.2,38.73
+deepseek-coder-1.3b-base,50.18,33.8,13.0
+deepseek-coder-6.7b-base,63.91,48.06,25.09
+deepseek_coder-6.7b-instruct,83.64,69.72,61.36
+deepseek_coder_33b-base,66.73,56.85,34.73
+deepseek_coder_33b-instruct,80.36,67.69,50.36
+codeqwen1.5-7b,65.0,51.76,37.36

dividing_into_different_subsets/4/QS/CC_QS.csv

@@ -0,0 +1,12 @@
+Model,CC_subset_1,CC_subset_2,CC_subset_3,CC_subset_4
+CodeFuse-DeepSeek-33b,85.37,78.05,75.61,68.29
+Nxcode-CQ-7B,89.51,80.49,90.24,88.9
+codegemma-2b,47.32,23.17,25.73,12.32
+codegemma-7b,59.02,37.2,42.32,20.61
+codegemma-7b-it,63.05,54.76,52.56,42.2
+deepseek-coder-1.3b-base,55.0,29.76,30.0,14.51
+deepseek-coder-6.7b-base,66.22,40.98,50.37,25.12
+deepseek_coder-6.7b-instruct,78.29,70.0,73.54,64.51
+deepseek_coder_33b-base,65.85,53.05,53.17,38.9
+deepseek_coder_33b-instruct,74.88,65.98,68.05,55.61
+codeqwen1.5-7b,65.24,47.8,54.51,37.93

dividing_into_different_subsets/4/QS/calculate_humaneval_result.py

@@ -0,0 +1,139 @@
+import json
+import os
+import csv
+# 定义文件所在的目录
+input_dir = 'E:\python-testn\pythonProject3\hh_1\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"])
+
+
+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"])
+#
+# 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"])
+
+
+
+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
+
+
+    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
+
+
+        #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
+
+        #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
+
+
+
+    mean0=round(sum0/count0*100,2)
+
+    mean1=round(sum1/count1*100,2)
+    mean2=round(sum2/count2*100,2)
+    mean3=round(sum3/count3*100,2)
+    print("count_result!!")
+    print(count0,count1,count2,count3)
+    print(mean0,mean1,mean2,mean3)
+    # 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])
+
+    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])
+
+    # 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])
+
+

dividing_into_different_subsets/4/QS/even.py

@@ -0,0 +1,65 @@
+import json
+with open("humaneval_new.json","r",encoding="utf-8") as f:
+    data = json.load(f)
+line_counts=[25,25,25,25]
+line_counts_I=line_counts[0]*0.01*164
+line_counts_II=line_counts[1]*0.01*164
+line_counts_III=line_counts[2]*0.01*164
+line_counts_IV=line_counts[3]*0.01*164
+
+token_counts=[25,25,25,25]
+token_counts_I=token_counts[0]*0.01*164
+token_counts_II=token_counts[1]*0.01*164
+token_counts_III=token_counts[2]*0.01*164
+token_counts_IV=token_counts[3]*0.01*164
+
+
+
+cyclomatic_complexity=[25,25,25,25]
+cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*164
+cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*164
+cyclomatic_complexity_III=cyclomatic_complexity[2]*0.01*164
+cyclomatic_complexity_IV=cyclomatic_complexity[3]*0.01*164
+
+
+data.sort(key=lambda x: x['line'])
+for i, item in enumerate(data):
+    if i < line_counts_I:
+        item['line_diff'] = 0
+    elif i <line_counts_I+line_counts_II:
+        item['line_diff'] = 1
+    elif i <line_counts_I+line_counts_II+line_counts_III:
+        item['line_diff'] = 2
+    else:
+        item["line_diff"]=3
+
+data.sort(key=lambda x: x['token'])
+for i, item in enumerate(data):
+    if i < token_counts_I:
+        item['token_diff'] = 0
+    elif i < token_counts_I + token_counts_II:
+        item['token_diff'] = 1
+    elif i < token_counts_I + token_counts_II+token_counts_III:
+        item['token_diff'] = 2
+    else:
+        item['token_diff'] = 3
+
+data.sort(key=lambda x: x['cyclomatic_complexity'])
+for i, item in enumerate(data):
+    if i < cyclomatic_complexity_I:
+        item['CC_diff'] = 0
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II:
+        item['CC_diff'] = 1
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III:
+        item['CC_diff'] = 2
+
+    else:
+        item['CC_diff'] = 3
+
+
+
+data.sort(key=lambda x: x['id'])
+# 将更新后的数据写回JSON文件
+with open('QS.json', 'w', encoding='utf-8') as file:
+    json.dump(data, file, ensure_ascii=False, indent=4)
+

dividing_into_different_subsets/4/QS/humaneval_with_cata.json

@@ -0,0 +1,658 @@
+[
+    {
+        "answer": "Array, Sorting",
+        "id": 0
+    },
+    {
+        "answer": "String, Stack",
+        "id": 1
+    },
+    {
+        "answer": "Math",
+        "id": 2
+    },
+    {
+        "answer": "Array, Math",
+        "id": 3
+    },
+    {
+        "answer": "Math, Array",
+        "id": 4
+    },
+    {
+        "answer": "Array",
+        "id": 5
+    },
+    {
+        "answer": "String, Stack",
+        "id": 6
+    },
+    {
+        "answer": "String, Array, Search",
+        "id": 7
+    },
+    {
+        "answer": "Math, Array",
+        "id": 8
+    },
+    {
+        "answer": "Array, Stack",
+        "id": 9
+    },
+    {
+        "answer": "String, Search",
+        "id": 10
+    },
+    {
+        "answer": "String, Math",
+        "id": 11
+    },
+    {
+        "answer": "String, Array",
+        "id": 12
+    },
+    {
+        "answer": "Math",
+        "id": 13
+    },
+    {
+        "answer": "String, Array",
+        "id": 14
+    },
+    {
+        "answer": "String, Math",
+        "id": 15
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 16
+    },
+    {
+        "answer": "String, Array",
+        "id": 17
+    },
+    {
+        "answer": "String, Search",
+        "id": 18
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 19
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 20
+    },
+    {
+        "answer": "Array, Math",
+        "id": 21
+    },
+    {
+        "answer": "Array, Search",
+        "id": 22
+    },
+    {
+        "answer": "String",
+        "id": 23
+    },
+    {
+        "answer": "Math",
+        "id": 24
+    },
+    {
+        "answer": "Math, Array",
+        "id": 25
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 26
+    },
+    {
+        "answer": "String",
+        "id": 27
+    },
+    {
+        "answer": "String",
+        "id": 28
+    },
+    {
+        "answer": "String, Array",
+        "id": 29
+    },
+    {
+        "answer": "Array",
+        "id": 30
+    },
+    {
+        "answer": "Math",
+        "id": 31
+    },
+    {
+        "answer": "Math, Search",
+        "id": 32
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 33
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 34
+    },
+    {
+        "answer": "Math, Array",
+        "id": 35
+    },
+    {
+        "answer": "Math, Search",
+        "id": 36
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 37
+    },
+    {
+        "answer": "String, Array",
+        "id": 38
+    },
+    {
+        "answer": "Math, Search",
+        "id": 39
+    },
+    {
+        "answer": "Array, Search",
+        "id": 40
+    },
+    {
+        "answer": "Math, Array",
+        "id": 41
+    },
+    {
+        "answer": "Array, Math",
+        "id": 42
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 43
+    },
+    {
+        "answer": "Math, String",
+        "id": 44
+    },
+    {
+        "answer": "Math",
+        "id": 45
+    },
+    {
+        "answer": "Math, Array",
+        "id": 46
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 47
+    },
+    {
+        "answer": "String",
+        "id": 48
+    },
+    {
+        "answer": "Math",
+        "id": 49
+    },
+    {
+        "answer": "String, Math",
+        "id": 50
+    },
+    {
+        "answer": "String",
+        "id": 51
+    },
+    {
+        "answer": "Array, Search",
+        "id": 52
+    },
+    {
+        "answer": "Math",
+        "id": 53
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 54
+    },
+    {
+        "answer": "Math",
+        "id": 55
+    },
+    {
+        "answer": "String, Stack",
+        "id": 56
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 57
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 58
+    },
+    {
+        "answer": "Math, Search",
+        "id": 59
+    },
+    {
+        "answer": "Math",
+        "id": 60
+    },
+    {
+        "answer": "String, Stack",
+        "id": 61
+    },
+    {
+        "answer": "Array, Math",
+        "id": 62
+    },
+    {
+        "answer": "Math, Array",
+        "id": 63
+    },
+    {
+        "answer": "String",
+        "id": 64
+    },
+    {
+        "answer": "String, Math",
+        "id": 65
+    },
+    {
+        "answer": "String, Math",
+        "id": 66
+    },
+    {
+        "answer": "String, Math",
+        "id": 67
+    },
+    {
+        "answer": "Array, Search",
+        "id": 68
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 69
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 70
+    },
+    {
+        "answer": "Math, Array",
+        "id": 71
+    },
+    {
+        "answer": "Array, Math",
+        "id": 72
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 73
+    },
+    {
+        "answer": "String, Array",
+        "id": 74
+    },
+    {
+        "answer": "Math, Hash table",
+        "id": 75
+    },
+    {
+        "answer": "Math",
+        "id": 76
+    },
+    {
+        "answer": "Math",
+        "id": 77
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 78
+    },
+    {
+        "answer": "String, Math",
+        "id": 79
+    },
+    {
+        "answer": "String, Search",
+        "id": 80
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 81
+    },
+    {
+        "answer": "String, Math",
+        "id": 82
+    },
+    {
+        "answer": "Math, Array",
+        "id": 83
+    },
+    {
+        "answer": "Math, String",
+        "id": 84
+    },
+    {
+        "answer": "Array, Math",
+        "id": 85
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 86
+    },
+    {
+        "answer": "Array, Search, Sorting",
+        "id": 87
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 88
+    },
+    {
+        "answer": "String, Math",
+        "id": 89
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 90
+    },
+    {
+        "answer": "String, Search",
+        "id": 91
+    },
+    {
+        "answer": "Math, Array",
+        "id": 92
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 93
+    },
+    {
+        "answer": "Array, Math",
+        "id": 94
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 95
+    },
+    {
+        "answer": "Math, Array",
+        "id": 96
+    },
+    {
+        "answer": "Math",
+        "id": 97
+    },
+    {
+        "answer": "String, Array",
+        "id": 98
+    },
+    {
+        "answer": "String, Math",
+        "id": 99
+    },
+    {
+        "answer": "Array, Math",
+        "id": 100
+    },
+    {
+        "answer": "String, Array",
+        "id": 101
+    },
+    {
+        "answer": "Math, Search",
+        "id": 102
+    },
+    {
+        "answer": "Math, String",
+        "id": 103
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 104
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 105
+    },
+    {
+        "answer": "Array, Math",
+        "id": 106
+    },
+    {
+        "answer": "Math, Search",
+        "id": 107
+    },
+    {
+        "answer": "Array, Math",
+        "id": 108
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 109
+    },
+    {
+        "answer": "Array, String",
+        "id": 110
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 111
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 112
+    },
+    {
+        "answer": "String, Array",
+        "id": 113
+    },
+    {
+        "answer": "Array, Math",
+        "id": 114
+    },
+    {
+        "answer": "Array, Math",
+        "id": 115
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 116
+    },
+    {
+        "answer": "String, Array",
+        "id": 117
+    },
+    {
+        "answer": "String, Search",
+        "id": 118
+    },
+    {
+        "answer": "String, Stack",
+        "id": 119
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 120
+    },
+    {
+        "answer": "Array, Math",
+        "id": 121
+    },
+    {
+        "answer": "Array, Math",
+        "id": 122
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 123
+    },
+    {
+        "answer": "String, Math",
+        "id": 124
+    },
+    {
+        "answer": "String, Math",
+        "id": 125
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 126
+    },
+    {
+        "answer": "Math, Array",
+        "id": 127
+    },
+    {
+        "answer": "Array, Math",
+        "id": 128
+    },
+    {
+        "answer": "Array, Search, Matrix",
+        "id": 129
+    },
+    {
+        "answer": "Math, Array",
+        "id": 130
+    },
+    {
+        "answer": "Math, String",
+        "id": 131
+    },
+    {
+        "answer": "String, Stack",
+        "id": 132
+    },
+    {
+        "answer": "Array, Math",
+        "id": 133
+    },
+    {
+        "answer": "String, Search",
+        "id": 134
+    },
+    {
+        "answer": "Array, Search",
+        "id": 135
+    },
+    {
+        "answer": "Array, Search",
+        "id": 136
+    },
+    {
+        "answer": "String, Math",
+        "id": 137
+    },
+    {
+        "answer": "Math",
+        "id": 138
+    },
+    {
+        "answer": "Math, Array",
+        "id": 139
+    },
+    {
+        "answer": "String, Array",
+        "id": 140
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 141
+    },
+    {
+        "answer": "Array, Math",
+        "id": 142
+    },
+    {
+        "answer": "String, Math",
+        "id": 143
+    },
+    {
+        "answer": "String, Math",
+        "id": 144
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 145
+    },
+    {
+        "answer": "Array, Math",
+        "id": 146
+    },
+    {
+        "answer": "Array, Math",
+        "id": 147
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 148
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 149
+    },
+    {
+        "answer": "Math, Search",
+        "id": 150
+    },
+    {
+        "answer": "Array, Math",
+        "id": 151
+    },
+    {
+        "answer": "Array, Math",
+        "id": 152
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 153
+    },
+    {
+        "answer": "String, Search",
+        "id": 154
+    },
+    {
+        "answer": "String, Math",
+        "id": 155
+    },
+    {
+        "answer": "String, Math",
+        "id": 156
+    },
+    {
+        "answer": "Math, Sorting",
+        "id": 157
+    },
+    {
+        "answer": "String, Array",
+        "id": 158
+    },
+    {
+        "answer": "Array, Math",
+        "id": 159
+    },
+    {
+        "answer": "String, Array, Math",
+        "id": 160
+    },
+    {
+        "answer": "String, Array",
+        "id": 161
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 162
+    },
+    {
+        "answer": "Array, Math",
+        "id": 163
+    }
+]

dividing_into_different_subsets/4/QS/line_counts_QS.csv

@@ -0,0 +1,12 @@
+Model,line_subset_1,line_subset_2,line_subset_3,line_subset_4
+CodeFuse-DeepSeek-33b,80.49,80.49,70.73,75.61
+Nxcode-CQ-7B,91.71,89.39,85.37,82.68
+codegemma-2b,49.39,23.78,16.83,18.54
+codegemma-7b,59.15,35.37,33.9,30.73
+codegemma-7b-it,72.32,49.76,49.88,40.61
+deepseek-coder-1.3b-base,50.98,29.76,26.34,22.2
+deepseek-coder-6.7b-base,68.29,46.71,33.41,34.27
+deepseek_coder-6.7b-instruct,81.1,81.34,64.51,59.39
+deepseek_coder_33b-base,75.0,50.0,47.2,38.78
+deepseek_coder_33b-instruct,84.15,69.27,59.15,51.95
+codeqwen1.5-7b,62.93,54.63,43.54,44.39

dividing_into_different_subsets/4/QS/token_counts_QS.csv

@@ -0,0 +1,12 @@
+Model,token_subset_1,token_subset_2,token_subset_3,token_subset_4
+CodeFuse-DeepSeek-33b,75.61,85.37,82.93,63.41
+Nxcode-CQ-7B,93.9,86.34,85.37,83.54
+codegemma-2b,43.05,37.68,19.76,8.05
+codegemma-7b,55.61,49.63,27.56,26.34
+codegemma-7b-it,69.76,63.9,37.07,41.83
+deepseek-coder-1.3b-base,49.39,46.59,20.98,12.32
+deepseek-coder-6.7b-base,68.29,54.15,36.34,23.9
+deepseek_coder-6.7b-instruct,85.98,71.22,72.8,56.34
+deepseek_coder_33b-base,69.02,66.83,42.32,32.8
+deepseek_coder_33b-instruct,82.93,73.05,62.44,46.1
+codeqwen1.5-7b,65.49,59.76,39.88,40.37

dividing_into_different_subsets/5/QS/CC_QS.csv

@@ -0,0 +1,12 @@
+Model,CC_subset_1,CC_subset_2,CC_subset_3,CC_subset_4,CC_subset_5
+CodeFuse-DeepSeek-33b,81.82,78.79,81.82,81.82,59.38
+Nxcode-CQ-7B,91.36,82.42,88.64,88.03,85.94
+codegemma-2b,49.85,21.67,24.24,29.24,10.16
+codegemma-7b,63.33,35.76,40.45,41.36,17.34
+codegemma-7b-it,66.67,51.82,53.18,57.88,35.62
+deepseek-coder-1.3b-base,59.24,28.94,28.33,32.58,11.88
+deepseek-coder-6.7b-base,70.91,38.79,46.36,51.82,19.69
+deepseek_coder-6.7b-instruct,84.7,66.06,69.39,79.24,58.13
+deepseek_coder_33b-base,72.12,44.24,54.09,60.0,32.66
+deepseek_coder_33b-instruct,80.15,59.55,64.85,76.52,49.06
+codeqwen1.5-7b,66.52,51.67,49.55,55.61,32.97

dividing_into_different_subsets/5/QS/calculate_humaneval_result.py

@@ -0,0 +1,157 @@
+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])
+
+

dividing_into_different_subsets/5/QS/draw_line.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import pandas as pd
+import plotly.express as px
+
+
+def plot_csv(df):
+    # 将第一列作为索引
+    df.set_index('Model', inplace=True)
+
+    # 转置数据框，使得模型作为列，横轴作为行
+    df_transposed = df.T
+
+    # 使用plotly绘制折线图
+    fig = px.line(df_transposed, x=df_transposed.index, y=df_transposed.columns,
+                  title='Model Evaluation Results',
+                  labels={'value': 'Evaluation Score', 'index': 'Evaluation Metric'},
+                  color_discrete_sequence=px.colors.qualitative.Plotly)
+
+    # 设置悬停效果
+    fig.update_traces(hovertemplate='%{y}')
+
+    return fig
+
+
+# 读取本地的CSV文件
+file_path = 'line_counts_QS.csv'
+df = pd.read_csv(file_path)
+
+
+iface = gr.Interface(
+    fn=plot_csv,
+    inputs=gr.Dataframe(df),
+    outputs=gr.Plot(label="Line Plot"),
+    title="CSV to Line Plot",
+    description="Visualize the evaluation results as a line plot."
+)
+
+iface.launch()

dividing_into_different_subsets/5/QS/even.py

@@ -0,0 +1,71 @@
+import json
+with open("humaneval_new.json", "r", encoding="utf-8") as f:
+    data = json.load(f)
+line_counts=[20,20,20,20,20]
+line_counts_I=line_counts[0]*0.01*164
+line_counts_II=line_counts[1]*0.01*164
+line_counts_III=line_counts[2]*0.01*164
+line_counts_IV=line_counts[3]*0.01*164
+line_counts_V=line_counts[4]*0.01*164
+
+token_counts=[20,20,20,20,20]
+token_counts_I=token_counts[0]*0.01*164
+token_counts_II=token_counts[1]*0.01*164
+token_counts_III=token_counts[2]*0.01*164
+token_counts_IV=token_counts[3]*0.01*164
+token_counts_V=token_counts[4]*0.01*164
+
+cyclomatic_complexity=[20,20,20,20,20]
+cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*164
+cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*164
+cyclomatic_complexity_III=cyclomatic_complexity[2]*0.01*164
+cyclomatic_complexity_IV=cyclomatic_complexity[3]*0.01*164
+cyclomatic_complexity_V=cyclomatic_complexity[4]*0.01*164
+
+
+data.sort(key=lambda x: x['line'])
+for i, item in enumerate(data):
+    if i < line_counts_I:
+        item['line_diff'] = 0
+    elif i <line_counts_I+line_counts_II:
+        item['line_diff'] = 1
+    elif i <line_counts_I+line_counts_II+line_counts_III:
+        item['line_diff'] = 2
+    elif i <line_counts_I+line_counts_II+line_counts_III+line_counts_IV:
+        item['line_diff'] = 3
+    else:
+        item['line_diff'] = 4
+
+data.sort(key=lambda x: x['token'])
+for i, item in enumerate(data):
+    if i < token_counts_I:
+        item['token_diff'] = 0
+    elif i < token_counts_I + token_counts_II:
+        item['token_diff'] = 1
+    elif i < token_counts_I + token_counts_II+token_counts_III:
+        item['token_diff'] = 2
+    elif i < token_counts_I + token_counts_II+token_counts_III+token_counts_IV:
+        item['token_diff'] = 3
+
+    else:
+        item['token_diff'] = 4
+
+data.sort(key=lambda x: x['cyclomatic_complexity'])
+for i, item in enumerate(data):
+    if i < cyclomatic_complexity_I:
+        item['CC_diff'] = 0
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II:
+        item['CC_diff'] = 1
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III:
+        item['CC_diff'] = 2
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III+cyclomatic_complexity_IV:
+        item['CC_diff'] = 3
+    else:
+        item['CC_diff'] = 4
+
+
+data.sort(key=lambda x: x['id'])
+# 将更新后的数据写回JSON文件
+with open('QS.json', 'w', encoding='utf-8') as file:
+    json.dump(data, file, ensure_ascii=False, indent=4)
+

dividing_into_different_subsets/5/QS/humaneval_with_cata.json

@@ -0,0 +1,658 @@
+[
+    {
+        "answer": "Array, Sorting",
+        "id": 0
+    },
+    {
+        "answer": "String, Stack",
+        "id": 1
+    },
+    {
+        "answer": "Math",
+        "id": 2
+    },
+    {
+        "answer": "Array, Math",
+        "id": 3
+    },
+    {
+        "answer": "Math, Array",
+        "id": 4
+    },
+    {
+        "answer": "Array",
+        "id": 5
+    },
+    {
+        "answer": "String, Stack",
+        "id": 6
+    },
+    {
+        "answer": "String, Array, Search",
+        "id": 7
+    },
+    {
+        "answer": "Math, Array",
+        "id": 8
+    },
+    {
+        "answer": "Array, Stack",
+        "id": 9
+    },
+    {
+        "answer": "String, Search",
+        "id": 10
+    },
+    {
+        "answer": "String, Math",
+        "id": 11
+    },
+    {
+        "answer": "String, Array",
+        "id": 12
+    },
+    {
+        "answer": "Math",
+        "id": 13
+    },
+    {
+        "answer": "String, Array",
+        "id": 14
+    },
+    {
+        "answer": "String, Math",
+        "id": 15
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 16
+    },
+    {
+        "answer": "String, Array",
+        "id": 17
+    },
+    {
+        "answer": "String, Search",
+        "id": 18
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 19
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 20
+    },
+    {
+        "answer": "Array, Math",
+        "id": 21
+    },
+    {
+        "answer": "Array, Search",
+        "id": 22
+    },
+    {
+        "answer": "String",
+        "id": 23
+    },
+    {
+        "answer": "Math",
+        "id": 24
+    },
+    {
+        "answer": "Math, Array",
+        "id": 25
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 26
+    },
+    {
+        "answer": "String",
+        "id": 27
+    },
+    {
+        "answer": "String",
+        "id": 28
+    },
+    {
+        "answer": "String, Array",
+        "id": 29
+    },
+    {
+        "answer": "Array",
+        "id": 30
+    },
+    {
+        "answer": "Math",
+        "id": 31
+    },
+    {
+        "answer": "Math, Search",
+        "id": 32
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 33
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 34
+    },
+    {
+        "answer": "Math, Array",
+        "id": 35
+    },
+    {
+        "answer": "Math, Search",
+        "id": 36
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 37
+    },
+    {
+        "answer": "String, Array",
+        "id": 38
+    },
+    {
+        "answer": "Math, Search",
+        "id": 39
+    },
+    {
+        "answer": "Array, Search",
+        "id": 40
+    },
+    {
+        "answer": "Math, Array",
+        "id": 41
+    },
+    {
+        "answer": "Array, Math",
+        "id": 42
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 43
+    },
+    {
+        "answer": "Math, String",
+        "id": 44
+    },
+    {
+        "answer": "Math",
+        "id": 45
+    },
+    {
+        "answer": "Math, Array",
+        "id": 46
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 47
+    },
+    {
+        "answer": "String",
+        "id": 48
+    },
+    {
+        "answer": "Math",
+        "id": 49
+    },
+    {
+        "answer": "String, Math",
+        "id": 50
+    },
+    {
+        "answer": "String",
+        "id": 51
+    },
+    {
+        "answer": "Array, Search",
+        "id": 52
+    },
+    {
+        "answer": "Math",
+        "id": 53
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 54
+    },
+    {
+        "answer": "Math",
+        "id": 55
+    },
+    {
+        "answer": "String, Stack",
+        "id": 56
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 57
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 58
+    },
+    {
+        "answer": "Math, Search",
+        "id": 59
+    },
+    {
+        "answer": "Math",
+        "id": 60
+    },
+    {
+        "answer": "String, Stack",
+        "id": 61
+    },
+    {
+        "answer": "Array, Math",
+        "id": 62
+    },
+    {
+        "answer": "Math, Array",
+        "id": 63
+    },
+    {
+        "answer": "String",
+        "id": 64
+    },
+    {
+        "answer": "String, Math",
+        "id": 65
+    },
+    {
+        "answer": "String, Math",
+        "id": 66
+    },
+    {
+        "answer": "String, Math",
+        "id": 67
+    },
+    {
+        "answer": "Array, Search",
+        "id": 68
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 69
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 70
+    },
+    {
+        "answer": "Math, Array",
+        "id": 71
+    },
+    {
+        "answer": "Array, Math",
+        "id": 72
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 73
+    },
+    {
+        "answer": "String, Array",
+        "id": 74
+    },
+    {
+        "answer": "Math, Hash table",
+        "id": 75
+    },
+    {
+        "answer": "Math",
+        "id": 76
+    },
+    {
+        "answer": "Math",
+        "id": 77
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 78
+    },
+    {
+        "answer": "String, Math",
+        "id": 79
+    },
+    {
+        "answer": "String, Search",
+        "id": 80
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 81
+    },
+    {
+        "answer": "String, Math",
+        "id": 82
+    },
+    {
+        "answer": "Math, Array",
+        "id": 83
+    },
+    {
+        "answer": "Math, String",
+        "id": 84
+    },
+    {
+        "answer": "Array, Math",
+        "id": 85
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 86
+    },
+    {
+        "answer": "Array, Search, Sorting",
+        "id": 87
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 88
+    },
+    {
+        "answer": "String, Math",
+        "id": 89
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 90
+    },
+    {
+        "answer": "String, Search",
+        "id": 91
+    },
+    {
+        "answer": "Math, Array",
+        "id": 92
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 93
+    },
+    {
+        "answer": "Array, Math",
+        "id": 94
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 95
+    },
+    {
+        "answer": "Math, Array",
+        "id": 96
+    },
+    {
+        "answer": "Math",
+        "id": 97
+    },
+    {
+        "answer": "String, Array",
+        "id": 98
+    },
+    {
+        "answer": "String, Math",
+        "id": 99
+    },
+    {
+        "answer": "Array, Math",
+        "id": 100
+    },
+    {
+        "answer": "String, Array",
+        "id": 101
+    },
+    {
+        "answer": "Math, Search",
+        "id": 102
+    },
+    {
+        "answer": "Math, String",
+        "id": 103
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 104
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 105
+    },
+    {
+        "answer": "Array, Math",
+        "id": 106
+    },
+    {
+        "answer": "Math, Search",
+        "id": 107
+    },
+    {
+        "answer": "Array, Math",
+        "id": 108
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 109
+    },
+    {
+        "answer": "Array, String",
+        "id": 110
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 111
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 112
+    },
+    {
+        "answer": "String, Array",
+        "id": 113
+    },
+    {
+        "answer": "Array, Math",
+        "id": 114
+    },
+    {
+        "answer": "Array, Math",
+        "id": 115
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 116
+    },
+    {
+        "answer": "String, Array",
+        "id": 117
+    },
+    {
+        "answer": "String, Search",
+        "id": 118
+    },
+    {
+        "answer": "String, Stack",
+        "id": 119
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 120
+    },
+    {
+        "answer": "Array, Math",
+        "id": 121
+    },
+    {
+        "answer": "Array, Math",
+        "id": 122
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 123
+    },
+    {
+        "answer": "String, Math",
+        "id": 124
+    },
+    {
+        "answer": "String, Math",
+        "id": 125
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 126
+    },
+    {
+        "answer": "Math, Array",
+        "id": 127
+    },
+    {
+        "answer": "Array, Math",
+        "id": 128
+    },
+    {
+        "answer": "Array, Search, Matrix",
+        "id": 129
+    },
+    {
+        "answer": "Math, Array",
+        "id": 130
+    },
+    {
+        "answer": "Math, String",
+        "id": 131
+    },
+    {
+        "answer": "String, Stack",
+        "id": 132
+    },
+    {
+        "answer": "Array, Math",
+        "id": 133
+    },
+    {
+        "answer": "String, Search",
+        "id": 134
+    },
+    {
+        "answer": "Array, Search",
+        "id": 135
+    },
+    {
+        "answer": "Array, Search",
+        "id": 136
+    },
+    {
+        "answer": "String, Math",
+        "id": 137
+    },
+    {
+        "answer": "Math",
+        "id": 138
+    },
+    {
+        "answer": "Math, Array",
+        "id": 139
+    },
+    {
+        "answer": "String, Array",
+        "id": 140
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 141
+    },
+    {
+        "answer": "Array, Math",
+        "id": 142
+    },
+    {
+        "answer": "String, Math",
+        "id": 143
+    },
+    {
+        "answer": "String, Math",
+        "id": 144
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 145
+    },
+    {
+        "answer": "Array, Math",
+        "id": 146
+    },
+    {
+        "answer": "Array, Math",
+        "id": 147
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 148
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 149
+    },
+    {
+        "answer": "Math, Search",
+        "id": 150
+    },
+    {
+        "answer": "Array, Math",
+        "id": 151
+    },
+    {
+        "answer": "Array, Math",
+        "id": 152
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 153
+    },
+    {
+        "answer": "String, Search",
+        "id": 154
+    },
+    {
+        "answer": "String, Math",
+        "id": 155
+    },
+    {
+        "answer": "String, Math",
+        "id": 156
+    },
+    {
+        "answer": "Math, Sorting",
+        "id": 157
+    },
+    {
+        "answer": "String, Array",
+        "id": 158
+    },
+    {
+        "answer": "Array, Math",
+        "id": 159
+    },
+    {
+        "answer": "String, Array, Math",
+        "id": 160
+    },
+    {
+        "answer": "String, Array",
+        "id": 161
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 162
+    },
+    {
+        "answer": "Array, Math",
+        "id": 163
+    }
+]

dividing_into_different_subsets/5/QS/line_counts_QS.csv

@@ -0,0 +1,12 @@
+Model,line_subset_1,line_subset_2,line_subset_3,line_subset_4,line_subset_5
+CodeFuse-DeepSeek-33b,75.76,84.85,78.79,66.67,78.12
+Nxcode-CQ-7B,92.27,87.27,91.21,87.12,78.28
+codegemma-2b,51.67,29.09,17.27,20.0,17.34
+codegemma-7b,60.45,38.64,38.18,32.88,28.44
+codegemma-7b-it,73.33,54.24,49.24,48.79,39.69
+deepseek-coder-1.3b-base,52.73,33.94,28.03,24.85,21.72
+deepseek-coder-6.7b-base,74.09,46.82,40.61,36.82,29.53
+deepseek_coder-6.7b-instruct,79.55,84.39,67.88,73.48,52.03
+deepseek_coder_33b-base,75.0,55.3,51.21,43.18,38.59
+deepseek_coder_33b-instruct,82.27,74.24,65.15,58.33,50.16
+codeqwen1.5-7b,63.18,55.76,49.55,46.36,41.72

dividing_into_different_subsets/5/QS/token_counts_QS.csv

@@ -0,0 +1,12 @@
+Model,token_subset_1,token_subset_2,token_subset_3,token_subset_4,token_subset_5
+CodeFuse-DeepSeek-33b,72.73,78.79,90.91,72.73,68.75
+Nxcode-CQ-7B,95.45,86.21,87.42,87.42,79.69
+codegemma-2b,46.97,38.48,28.03,16.21,5.31
+codegemma-7b,60.76,47.73,39.7,26.36,23.91
+codegemma-7b-it,74.39,64.09,50.3,37.27,39.22
+deepseek-coder-1.3b-base,54.85,45.61,34.09,15.45,10.94
+deepseek-coder-6.7b-base,74.09,54.24,44.24,33.79,21.25
+deepseek_coder-6.7b-instruct,87.88,76.36,65.0,76.36,51.72
+deepseek_coder_33b-base,73.18,63.79,54.09,42.27,29.69
+deepseek_coder_33b-instruct,87.12,73.48,65.45,64.7,39.06
+codeqwen1.5-7b,68.18,63.03,47.12,40.76,37.34

dividing_into_different_subsets/6/QS/CC_QS.csv

@@ -0,0 +1,13 @@
+Model,CC_subset_1,CC_subset_2,CC_subset_3,CC_subset_4,CC_subset_5,CC_subset_6
+CodeFuse-DeepSeek-33b,78.57,82.14,85.71,71.43,89.29,50.0
+Nxcode-CQ-7B,89.82,85.71,80.18,92.86,93.04,81.25
+codegemma-2b,48.93,24.82,33.04,22.86,27.32,2.29
+codegemma-7b,61.61,39.82,43.04,40.18,36.07,14.37
+codegemma-7b-it,65.36,54.46,56.25,53.21,53.39,33.33
+deepseek-coder-1.3b-base,55.54,33.75,37.86,30.18,26.25,6.67
+deepseek-coder-6.7b-base,69.64,42.32,48.57,49.11,46.07,13.75
+deepseek_coder-6.7b-instruct,81.96,68.75,70.0,78.04,73.75,54.58
+deepseek_coder_33b-base,70.71,50.18,56.79,52.32,54.11,28.96
+deepseek_coder_33b-instruct,80.18,61.61,68.04,66.79,71.79,45.42
+codeqwen1.5-7b,64.64,51.79,52.68,56.79,49.64,29.58
+new,65.36,54.46,56.25,53.21,53.39,33.33

dividing_into_different_subsets/6/QS/calculate_humaneval_result.py

@@ -0,0 +1,176 @@
+import json
+import os
+import csv
+# 定义文件所在的目录
+input_dir = 'E:/python-testn/pythonProject3/hh_1/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","token_subset_6"])
+
+
+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","line_subset_6"])
+
+# 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","CC_subset_6"])
+
+
+
+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
+    sum5 = 0
+    count5 = 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
+    #     if item2["token_diff"] ==5:
+    #         index, value = item1
+    #         print(item2["token_diff"], index, value)
+    #         sum5 = sum5 + value
+    #         count5 = count5 + 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
+        if item2["line_diff"] == 5:
+            index, value = item1
+            print(item2["line_diff"], index, value)
+            sum5 = sum5 + value
+            count5 = count5 + 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
+        # if item2["CC_diff"] == 5 :
+        #     index, value = item1
+        #     print(item2["CC_diff"], index, value)
+        #     sum5=sum5+value
+        #     count5=count5+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)
+    mean5 = round(sum5 / count5 * 100, 2)
+    print("count_result!!")
+    print(count0,count1,count2,count3,count4,count5)
+    print(mean0,mean1,mean2,mean3,count4,mean5)
+    # 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,mean5])
+
+    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,mean5])
+    #
+    # 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,mean5])
+    #
+

dividing_into_different_subsets/6/QS/even.py

@@ -0,0 +1,80 @@
+import json
+with open("humaneval_new.json", "r", encoding="utf-8") as f:
+    data = json.load(f)
+line_counts=[17,17,17,17,17,15]
+line_counts_I=line_counts[0]*0.01*164
+line_counts_II=line_counts[1]*0.01*164
+line_counts_III=line_counts[2]*0.01*164
+line_counts_IV=line_counts[3]*0.01*164
+line_counts_V=line_counts[4]*0.01*164
+line_counts_VI=line_counts[5]*0.01*164
+
+token_counts=[17,17,17,17,17,15]
+token_counts_I=token_counts[0]*0.01*164
+token_counts_II=token_counts[1]*0.01*164
+token_counts_III=token_counts[2]*0.01*164
+token_counts_IV=token_counts[3]*0.01*164
+token_counts_V=token_counts[4]*0.01*164
+token_counts_VI=token_counts[5]*0.01*164
+
+cyclomatic_complexity=[17,17,17,17,17,15]
+cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*164
+cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*164
+cyclomatic_complexity_III=cyclomatic_complexity[2]*0.01*164
+cyclomatic_complexity_IV=cyclomatic_complexity[3]*0.01*164
+cyclomatic_complexity_V=cyclomatic_complexity[4]*0.01*164
+cyclomatic_complexity_VI=cyclomatic_complexity[5]*0.01*164
+
+
+data.sort(key=lambda x: x['line'])
+for i, item in enumerate(data):
+    if i < line_counts_I:
+        item['line_diff'] = 0
+    elif i <line_counts_I+line_counts_II:
+        item['line_diff'] = 1
+    elif i <line_counts_I+line_counts_II+line_counts_III:
+        item['line_diff'] = 2
+    elif i <line_counts_I+line_counts_II+line_counts_III+line_counts_IV:
+        item['line_diff'] = 3
+    elif i <line_counts_I+line_counts_II+line_counts_III+line_counts_IV+line_counts_V:
+        item['line_diff'] = 4
+    else:
+        item['line_diff'] = 5
+
+data.sort(key=lambda x: x['token'])
+for i, item in enumerate(data):
+    if i < token_counts_I:
+        item['token_diff'] = 0
+    elif i < token_counts_I + token_counts_II:
+        item['token_diff'] = 1
+    elif i < token_counts_I + token_counts_II+token_counts_III:
+        item['token_diff'] = 2
+    elif i < token_counts_I + token_counts_II+token_counts_III+token_counts_IV:
+        item['token_diff'] = 3
+    elif i < token_counts_I + token_counts_II+token_counts_III+token_counts_IV+token_counts_V:
+        item['token_diff'] = 4
+
+    else:
+        item['token_diff'] = 5
+
+data.sort(key=lambda x: x['cyclomatic_complexity'])
+for i, item in enumerate(data):
+    if i < cyclomatic_complexity_I:
+        item['CC_diff'] = 0
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II:
+        item['CC_diff'] = 1
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III:
+        item['CC_diff'] = 2
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III+cyclomatic_complexity_IV:
+        item['CC_diff'] = 3
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III+cyclomatic_complexity_IV+cyclomatic_complexity_V:
+        item['CC_diff'] = 4
+    else:
+        item['CC_diff'] = 5
+
+
+data.sort(key=lambda x: x['id'])
+# 将更新后的数据写回JSON文件
+with open('QS.json', 'w', encoding='utf-8') as file:
+    json.dump(data, file, ensure_ascii=False, indent=4)
+

dividing_into_different_subsets/6/QS/humaneval_with_cata.json

@@ -0,0 +1,658 @@
+[
+    {
+        "answer": "Array, Sorting",
+        "id": 0
+    },
+    {
+        "answer": "String, Stack",
+        "id": 1
+    },
+    {
+        "answer": "Math",
+        "id": 2
+    },
+    {
+        "answer": "Array, Math",
+        "id": 3
+    },
+    {
+        "answer": "Math, Array",
+        "id": 4
+    },
+    {
+        "answer": "Array",
+        "id": 5
+    },
+    {
+        "answer": "String, Stack",
+        "id": 6
+    },
+    {
+        "answer": "String, Array, Search",
+        "id": 7
+    },
+    {
+        "answer": "Math, Array",
+        "id": 8
+    },
+    {
+        "answer": "Array, Stack",
+        "id": 9
+    },
+    {
+        "answer": "String, Search",
+        "id": 10
+    },
+    {
+        "answer": "String, Math",
+        "id": 11
+    },
+    {
+        "answer": "String, Array",
+        "id": 12
+    },
+    {
+        "answer": "Math",
+        "id": 13
+    },
+    {
+        "answer": "String, Array",
+        "id": 14
+    },
+    {
+        "answer": "String, Math",
+        "id": 15
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 16
+    },
+    {
+        "answer": "String, Array",
+        "id": 17
+    },
+    {
+        "answer": "String, Search",
+        "id": 18
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 19
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 20
+    },
+    {
+        "answer": "Array, Math",
+        "id": 21
+    },
+    {
+        "answer": "Array, Search",
+        "id": 22
+    },
+    {
+        "answer": "String",
+        "id": 23
+    },
+    {
+        "answer": "Math",
+        "id": 24
+    },
+    {
+        "answer": "Math, Array",
+        "id": 25
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 26
+    },
+    {
+        "answer": "String",
+        "id": 27
+    },
+    {
+        "answer": "String",
+        "id": 28
+    },
+    {
+        "answer": "String, Array",
+        "id": 29
+    },
+    {
+        "answer": "Array",
+        "id": 30
+    },
+    {
+        "answer": "Math",
+        "id": 31
+    },
+    {
+        "answer": "Math, Search",
+        "id": 32
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 33
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 34
+    },
+    {
+        "answer": "Math, Array",
+        "id": 35
+    },
+    {
+        "answer": "Math, Search",
+        "id": 36
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 37
+    },
+    {
+        "answer": "String, Array",
+        "id": 38
+    },
+    {
+        "answer": "Math, Search",
+        "id": 39
+    },
+    {
+        "answer": "Array, Search",
+        "id": 40
+    },
+    {
+        "answer": "Math, Array",
+        "id": 41
+    },
+    {
+        "answer": "Array, Math",
+        "id": 42
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 43
+    },
+    {
+        "answer": "Math, String",
+        "id": 44
+    },
+    {
+        "answer": "Math",
+        "id": 45
+    },
+    {
+        "answer": "Math, Array",
+        "id": 46
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 47
+    },
+    {
+        "answer": "String",
+        "id": 48
+    },
+    {
+        "answer": "Math",
+        "id": 49
+    },
+    {
+        "answer": "String, Math",
+        "id": 50
+    },
+    {
+        "answer": "String",
+        "id": 51
+    },
+    {
+        "answer": "Array, Search",
+        "id": 52
+    },
+    {
+        "answer": "Math",
+        "id": 53
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 54
+    },
+    {
+        "answer": "Math",
+        "id": 55
+    },
+    {
+        "answer": "String, Stack",
+        "id": 56
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 57
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 58
+    },
+    {
+        "answer": "Math, Search",
+        "id": 59
+    },
+    {
+        "answer": "Math",
+        "id": 60
+    },
+    {
+        "answer": "String, Stack",
+        "id": 61
+    },
+    {
+        "answer": "Array, Math",
+        "id": 62
+    },
+    {
+        "answer": "Math, Array",
+        "id": 63
+    },
+    {
+        "answer": "String",
+        "id": 64
+    },
+    {
+        "answer": "String, Math",
+        "id": 65
+    },
+    {
+        "answer": "String, Math",
+        "id": 66
+    },
+    {
+        "answer": "String, Math",
+        "id": 67
+    },
+    {
+        "answer": "Array, Search",
+        "id": 68
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 69
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 70
+    },
+    {
+        "answer": "Math, Array",
+        "id": 71
+    },
+    {
+        "answer": "Array, Math",
+        "id": 72
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 73
+    },
+    {
+        "answer": "String, Array",
+        "id": 74
+    },
+    {
+        "answer": "Math, Hash table",
+        "id": 75
+    },
+    {
+        "answer": "Math",
+        "id": 76
+    },
+    {
+        "answer": "Math",
+        "id": 77
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 78
+    },
+    {
+        "answer": "String, Math",
+        "id": 79
+    },
+    {
+        "answer": "String, Search",
+        "id": 80
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 81
+    },
+    {
+        "answer": "String, Math",
+        "id": 82
+    },
+    {
+        "answer": "Math, Array",
+        "id": 83
+    },
+    {
+        "answer": "Math, String",
+        "id": 84
+    },
+    {
+        "answer": "Array, Math",
+        "id": 85
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 86
+    },
+    {
+        "answer": "Array, Search, Sorting",
+        "id": 87
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 88
+    },
+    {
+        "answer": "String, Math",
+        "id": 89
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 90
+    },
+    {
+        "answer": "String, Search",
+        "id": 91
+    },
+    {
+        "answer": "Math, Array",
+        "id": 92
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 93
+    },
+    {
+        "answer": "Array, Math",
+        "id": 94
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 95
+    },
+    {
+        "answer": "Math, Array",
+        "id": 96
+    },
+    {
+        "answer": "Math",
+        "id": 97
+    },
+    {
+        "answer": "String, Array",
+        "id": 98
+    },
+    {
+        "answer": "String, Math",
+        "id": 99
+    },
+    {
+        "answer": "Array, Math",
+        "id": 100
+    },
+    {
+        "answer": "String, Array",
+        "id": 101
+    },
+    {
+        "answer": "Math, Search",
+        "id": 102
+    },
+    {
+        "answer": "Math, String",
+        "id": 103
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 104
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 105
+    },
+    {
+        "answer": "Array, Math",
+        "id": 106
+    },
+    {
+        "answer": "Math, Search",
+        "id": 107
+    },
+    {
+        "answer": "Array, Math",
+        "id": 108
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 109
+    },
+    {
+        "answer": "Array, String",
+        "id": 110
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 111
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 112
+    },
+    {
+        "answer": "String, Array",
+        "id": 113
+    },
+    {
+        "answer": "Array, Math",
+        "id": 114
+    },
+    {
+        "answer": "Array, Math",
+        "id": 115
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 116
+    },
+    {
+        "answer": "String, Array",
+        "id": 117
+    },
+    {
+        "answer": "String, Search",
+        "id": 118
+    },
+    {
+        "answer": "String, Stack",
+        "id": 119
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 120
+    },
+    {
+        "answer": "Array, Math",
+        "id": 121
+    },
+    {
+        "answer": "Array, Math",
+        "id": 122
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 123
+    },
+    {
+        "answer": "String, Math",
+        "id": 124
+    },
+    {
+        "answer": "String, Math",
+        "id": 125
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 126
+    },
+    {
+        "answer": "Math, Array",
+        "id": 127
+    },
+    {
+        "answer": "Array, Math",
+        "id": 128
+    },
+    {
+        "answer": "Array, Search, Matrix",
+        "id": 129
+    },
+    {
+        "answer": "Math, Array",
+        "id": 130
+    },
+    {
+        "answer": "Math, String",
+        "id": 131
+    },
+    {
+        "answer": "String, Stack",
+        "id": 132
+    },
+    {
+        "answer": "Array, Math",
+        "id": 133
+    },
+    {
+        "answer": "String, Search",
+        "id": 134
+    },
+    {
+        "answer": "Array, Search",
+        "id": 135
+    },
+    {
+        "answer": "Array, Search",
+        "id": 136
+    },
+    {
+        "answer": "String, Math",
+        "id": 137
+    },
+    {
+        "answer": "Math",
+        "id": 138
+    },
+    {
+        "answer": "Math, Array",
+        "id": 139
+    },
+    {
+        "answer": "String, Array",
+        "id": 140
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 141
+    },
+    {
+        "answer": "Array, Math",
+        "id": 142
+    },
+    {
+        "answer": "String, Math",
+        "id": 143
+    },
+    {
+        "answer": "String, Math",
+        "id": 144
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 145
+    },
+    {
+        "answer": "Array, Math",
+        "id": 146
+    },
+    {
+        "answer": "Array, Math",
+        "id": 147
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 148
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 149
+    },
+    {
+        "answer": "Math, Search",
+        "id": 150
+    },
+    {
+        "answer": "Array, Math",
+        "id": 151
+    },
+    {
+        "answer": "Array, Math",
+        "id": 152
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 153
+    },
+    {
+        "answer": "String, Search",
+        "id": 154
+    },
+    {
+        "answer": "String, Math",
+        "id": 155
+    },
+    {
+        "answer": "String, Math",
+        "id": 156
+    },
+    {
+        "answer": "Math, Sorting",
+        "id": 157
+    },
+    {
+        "answer": "String, Array",
+        "id": 158
+    },
+    {
+        "answer": "Array, Math",
+        "id": 159
+    },
+    {
+        "answer": "String, Array, Math",
+        "id": 160
+    },
+    {
+        "answer": "String, Array",
+        "id": 161
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 162
+    },
+    {
+        "answer": "Array, Math",
+        "id": 163
+    }
+]

dividing_into_different_subsets/6/QS/line_counts_QS.csv

@@ -0,0 +1,13 @@
+Model,line_subset_1,line_subset_2,line_subset_3,line_subset_4,line_subset_5,line_subset_6
+CodeFuse-DeepSeek-33b,75.0,85.71,82.14,67.86,71.43,79.17
+Nxcode-CQ-7B,92.68,91.79,87.86,89.29,85.71,74.58
+codegemma-2b,52.86,34.11,26.96,9.11,24.11,13.75
+codegemma-7b,62.32,42.68,39.64,30.18,35.0,27.08
+codegemma-7b-it,74.11,57.68,54.11,42.5,50.54,37.71
+deepseek-coder-1.3b-base,55.0,40.36,30.0,22.32,24.46,20.0
+deepseek-coder-6.7b-base,75.89,52.14,47.5,30.89,39.11,25.63
+deepseek_coder-6.7b-instruct,78.57,91.96,74.46,58.39,70.18,53.33
+deepseek_coder_33b-base,74.29,62.86,53.04,43.39,43.93,36.67
+deepseek_coder_33b-instruct,83.21,81.61,66.96,56.79,55.0,51.04
+codeqwen1.5-7b,65.18,54.64,59.46,37.86,53.21,35.62
+new,74.11,57.68,54.11,42.5,50.54,37.71

dividing_into_different_subsets/6/QS/token_counts_QS.csv

@@ -0,0 +1,13 @@
+Model,token_subset_1,token_subset_2,token_subset_3,token_subset_4,token_subset_5,token_subset_6
+CodeFuse-DeepSeek-33b,75.0,71.43,96.43,82.14,71.43,62.5
+Nxcode-CQ-7B,95.18,86.61,85.71,89.29,88.39,77.08
+codegemma-2b,46.96,36.43,34.82,20.36,19.29,1.25
+codegemma-7b,60.71,46.43,47.32,33.21,30.18,17.71
+codegemma-7b-it,75.89,61.79,58.93,43.21,40.36,36.25
+deepseek-coder-1.3b-base,57.14,41.43,41.96,24.11,19.82,5.62
+deepseek-coder-6.7b-base,73.04,52.5,53.75,42.68,31.79,16.04
+deepseek_coder-6.7b-instruct,85.71,82.14,65.89,72.5,73.04,46.67
+deepseek_coder_33b-base,73.57,60.18,67.14,46.79,39.46,25.42
+deepseek_coder_33b-instruct,86.25,75.18,70.54,63.57,57.86,39.58
+codeqwen1.5-7b,69.11,58.93,55.36,48.21,38.93,35.42
+new,75.89,61.79,58.93,43.21,40.36,36.25

dividing_into_different_subsets/7/QS/CC_QS.csv

@@ -0,0 +1,13 @@
+Model,CC_subset_1,CC_subset_2,CC_subset_3,CC_subset_4,CC_subset_5,CC_subset_6,CC_subset_7
+CodeFuse-DeepSeek-33b,73.91,86.96,78.26,91.3,65.22,92.0,50.0
+Nxcode-CQ-7B,91.3,85.65,81.09,88.04,91.3,92.2,81.25
+codegemma-2b,47.61,37.61,20.65,28.7,28.91,25.4,2.29
+codegemma-7b,57.61,53.26,35.87,44.78,40.22,34.0,14.37
+codegemma-7b-it,61.3,62.17,54.35,53.48,55.43,52.8,33.33
+deepseek-coder-1.3b-base,54.13,48.26,27.39,30.65,38.91,22.2,6.67
+deepseek-coder-6.7b-base,65.0,57.61,40.22,52.61,51.74,40.6,13.75
+deepseek_coder-6.7b-instruct,82.39,71.96,70.65,72.83,75.0,74.2,54.58
+deepseek_coder_33b-base,68.04,57.39,49.35,58.91,55.22,52.4,28.96
+deepseek_coder_33b-instruct,76.09,69.57,63.04,67.17,72.17,70.0,45.42
+codeqwen1.5-7b,64.78,57.83,52.61,55.87,51.3,48.8,29.58
+new,61.3,62.17,54.35,53.48,55.43,52.8,33.33

dividing_into_different_subsets/7/QS/calculate_humaneval_result.py

@@ -0,0 +1,195 @@
+import json
+import os
+import csv
+# 定义文件所在的目录
+input_dir = 'E:/python-testn/pythonProject3/hh_1/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","token_subset_6","token_subset_7"])
+#
+
+# 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","line_subset_6","line_subset_7"])
+
+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","CC_subset_6","CC_subset_7"])
+
+
+
+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
+    sum5 = 0
+    count5 = 0
+    sum6=0
+    count6=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
+    #     if item2["token_diff"] ==5:
+    #         index, value = item1
+    #         print(item2["token_diff"], index, value)
+    #         sum5 = sum5 + value
+    #         count5 = count5 + 1
+    #     if item2["token_diff"] ==6:
+    #         index, value = item1
+    #         print(item2["token_diff"], index, value)
+    #         sum6 = sum6 + value
+    #         count6 = count6 + 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
+        # if item2["line_diff"] == 5:
+        #     index, value = item1
+        #     print(item2["line_diff"], index, value)
+        #     sum5 = sum5 + value
+        #     count5 = count5 + 1
+        # if item2["line_diff"] == 6:
+        #     index, value = item1
+        #     print(item2["line_diff"], index, value)
+        #     sum6 = sum6 + value
+        #     count6 = count6 + 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
+        if item2["CC_diff"] == 5 :
+            index, value = item1
+            print(item2["CC_diff"], index, value)
+            sum5=sum5+value
+            count5=count5+1
+        if item2["CC_diff"] == 6 :
+            index, value = item1
+            print(item2["CC_diff"], index, value)
+            sum6=sum6+value
+            count6=count6+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)
+    mean5 = round(sum5 / count5 * 100, 2)
+    mean6=round(sum6/count6*100,2)
+    print("count_result!!")
+    print(count0,count1,count2,count3,count4,count5,count6)
+    print(mean0,mean1,mean2,mean3,count4,mean5,mean6)
+    # 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,mean5,mean6])
+
+    # 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,mean5,mean6])
+    #
+    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,mean5,mean6])
+
+

dividing_into_different_subsets/7/QS/even.py

@@ -0,0 +1,87 @@
+import json
+with open("humaneval_new.json", "r", encoding="utf-8") as f:
+    data = json.load(f)
+line_counts=[14, 14, 14, 14, 14, 15, 15]
+line_counts_I=line_counts[0]*0.01*164
+line_counts_II=line_counts[1]*0.01*164
+line_counts_III=line_counts[2]*0.01*164
+line_counts_IV=line_counts[3]*0.01*164
+line_counts_V=line_counts[4]*0.01*164
+line_counts_VI=line_counts[5]*0.01*164
+line_counts_VII=line_counts[6]*0.01*164
+
+token_counts=[14, 14, 14, 14, 14, 15, 15]
+token_counts_I=token_counts[0]*0.01*164
+token_counts_II=token_counts[1]*0.01*164
+token_counts_III=token_counts[2]*0.01*164
+token_counts_IV=token_counts[3]*0.01*164
+token_counts_V=token_counts[4]*0.01*164
+token_counts_VI=token_counts[5]*0.01*164
+token_counts_VII=token_counts[6]*0.01*164
+
+cyclomatic_complexity=[14, 14, 14, 14, 14, 15, 15]
+cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*164
+cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*164
+cyclomatic_complexity_III=cyclomatic_complexity[2]*0.01*164
+cyclomatic_complexity_IV=cyclomatic_complexity[3]*0.01*164
+cyclomatic_complexity_V=cyclomatic_complexity[4]*0.01*164
+cyclomatic_complexity_VI=cyclomatic_complexity[5]*0.01*164
+cyclomatic_complexity_VII=cyclomatic_complexity[6]*0.01*164
+
+data.sort(key=lambda x: x['line'])
+for i, item in enumerate(data):
+    if i < line_counts_I:
+        item['line_diff'] = 0
+    elif i <line_counts_I+line_counts_II:
+        item['line_diff'] = 1
+    elif i <line_counts_I+line_counts_II+line_counts_III:
+        item['line_diff'] = 2
+    elif i <line_counts_I+line_counts_II+line_counts_III+line_counts_IV:
+        item['line_diff'] = 3
+    elif i <line_counts_I+line_counts_II+line_counts_III+line_counts_IV+line_counts_V:
+        item['line_diff'] = 4
+    elif i <line_counts_I+line_counts_II+line_counts_III+line_counts_IV+line_counts_V+line_counts_VI:
+        item['line_diff'] = 5
+    else:
+        item['line_diff'] = 6
+
+data.sort(key=lambda x: x['token'])
+for i, item in enumerate(data):
+    if i < token_counts_I:
+        item['token_diff'] = 0
+    elif i < token_counts_I + token_counts_II:
+        item['token_diff'] = 1
+    elif i < token_counts_I + token_counts_II+token_counts_III:
+        item['token_diff'] = 2
+    elif i < token_counts_I + token_counts_II+token_counts_III+token_counts_IV:
+        item['token_diff'] = 3
+    elif i < token_counts_I + token_counts_II+token_counts_III+token_counts_IV+token_counts_V:
+        item['token_diff'] = 4
+    elif i < token_counts_I + token_counts_II + token_counts_III + token_counts_IV + token_counts_V+token_counts_VI:
+        item['token_diff'] = 5
+    else:
+        item['token_diff'] = 6
+
+data.sort(key=lambda x: x['cyclomatic_complexity'])
+for i, item in enumerate(data):
+    if i < cyclomatic_complexity_I:
+        item['CC_diff'] = 0
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II:
+        item['CC_diff'] = 1
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III:
+        item['CC_diff'] = 2
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III+cyclomatic_complexity_IV:
+        item['CC_diff'] = 3
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III+cyclomatic_complexity_IV+cyclomatic_complexity_V:
+        item['CC_diff'] = 4
+    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III+cyclomatic_complexity_IV+cyclomatic_complexity_V+cyclomatic_complexity_VI:
+        item['CC_diff'] = 5
+    else:
+        item['CC_diff'] = 6
+
+
+data.sort(key=lambda x: x['id'])
+# 将更新后的数据写回JSON文件
+with open('QS.json', 'w', encoding='utf-8') as file:
+    json.dump(data, file, ensure_ascii=False, indent=4)
+

dividing_into_different_subsets/7/QS/humaneval_with_cata.json

@@ -0,0 +1,658 @@
+[
+    {
+        "answer": "Array, Sorting",
+        "id": 0
+    },
+    {
+        "answer": "String, Stack",
+        "id": 1
+    },
+    {
+        "answer": "Math",
+        "id": 2
+    },
+    {
+        "answer": "Array, Math",
+        "id": 3
+    },
+    {
+        "answer": "Math, Array",
+        "id": 4
+    },
+    {
+        "answer": "Array",
+        "id": 5
+    },
+    {
+        "answer": "String, Stack",
+        "id": 6
+    },
+    {
+        "answer": "String, Array, Search",
+        "id": 7
+    },
+    {
+        "answer": "Math, Array",
+        "id": 8
+    },
+    {
+        "answer": "Array, Stack",
+        "id": 9
+    },
+    {
+        "answer": "String, Search",
+        "id": 10
+    },
+    {
+        "answer": "String, Math",
+        "id": 11
+    },
+    {
+        "answer": "String, Array",
+        "id": 12
+    },
+    {
+        "answer": "Math",
+        "id": 13
+    },
+    {
+        "answer": "String, Array",
+        "id": 14
+    },
+    {
+        "answer": "String, Math",
+        "id": 15
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 16
+    },
+    {
+        "answer": "String, Array",
+        "id": 17
+    },
+    {
+        "answer": "String, Search",
+        "id": 18
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 19
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 20
+    },
+    {
+        "answer": "Array, Math",
+        "id": 21
+    },
+    {
+        "answer": "Array, Search",
+        "id": 22
+    },
+    {
+        "answer": "String",
+        "id": 23
+    },
+    {
+        "answer": "Math",
+        "id": 24
+    },
+    {
+        "answer": "Math, Array",
+        "id": 25
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 26
+    },
+    {
+        "answer": "String",
+        "id": 27
+    },
+    {
+        "answer": "String",
+        "id": 28
+    },
+    {
+        "answer": "String, Array",
+        "id": 29
+    },
+    {
+        "answer": "Array",
+        "id": 30
+    },
+    {
+        "answer": "Math",
+        "id": 31
+    },
+    {
+        "answer": "Math, Search",
+        "id": 32
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 33
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 34
+    },
+    {
+        "answer": "Math, Array",
+        "id": 35
+    },
+    {
+        "answer": "Math, Search",
+        "id": 36
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 37
+    },
+    {
+        "answer": "String, Array",
+        "id": 38
+    },
+    {
+        "answer": "Math, Search",
+        "id": 39
+    },
+    {
+        "answer": "Array, Search",
+        "id": 40
+    },
+    {
+        "answer": "Math, Array",
+        "id": 41
+    },
+    {
+        "answer": "Array, Math",
+        "id": 42
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 43
+    },
+    {
+        "answer": "Math, String",
+        "id": 44
+    },
+    {
+        "answer": "Math",
+        "id": 45
+    },
+    {
+        "answer": "Math, Array",
+        "id": 46
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 47
+    },
+    {
+        "answer": "String",
+        "id": 48
+    },
+    {
+        "answer": "Math",
+        "id": 49
+    },
+    {
+        "answer": "String, Math",
+        "id": 50
+    },
+    {
+        "answer": "String",
+        "id": 51
+    },
+    {
+        "answer": "Array, Search",
+        "id": 52
+    },
+    {
+        "answer": "Math",
+        "id": 53
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 54
+    },
+    {
+        "answer": "Math",
+        "id": 55
+    },
+    {
+        "answer": "String, Stack",
+        "id": 56
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 57
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 58
+    },
+    {
+        "answer": "Math, Search",
+        "id": 59
+    },
+    {
+        "answer": "Math",
+        "id": 60
+    },
+    {
+        "answer": "String, Stack",
+        "id": 61
+    },
+    {
+        "answer": "Array, Math",
+        "id": 62
+    },
+    {
+        "answer": "Math, Array",
+        "id": 63
+    },
+    {
+        "answer": "String",
+        "id": 64
+    },
+    {
+        "answer": "String, Math",
+        "id": 65
+    },
+    {
+        "answer": "String, Math",
+        "id": 66
+    },
+    {
+        "answer": "String, Math",
+        "id": 67
+    },
+    {
+        "answer": "Array, Search",
+        "id": 68
+    },
+    {
+        "answer": "Array, Hash table",
+        "id": 69
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 70
+    },
+    {
+        "answer": "Math, Array",
+        "id": 71
+    },
+    {
+        "answer": "Array, Math",
+        "id": 72
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 73
+    },
+    {
+        "answer": "String, Array",
+        "id": 74
+    },
+    {
+        "answer": "Math, Hash table",
+        "id": 75
+    },
+    {
+        "answer": "Math",
+        "id": 76
+    },
+    {
+        "answer": "Math",
+        "id": 77
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 78
+    },
+    {
+        "answer": "String, Math",
+        "id": 79
+    },
+    {
+        "answer": "String, Search",
+        "id": 80
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 81
+    },
+    {
+        "answer": "String, Math",
+        "id": 82
+    },
+    {
+        "answer": "Math, Array",
+        "id": 83
+    },
+    {
+        "answer": "Math, String",
+        "id": 84
+    },
+    {
+        "answer": "Array, Math",
+        "id": 85
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 86
+    },
+    {
+        "answer": "Array, Search, Sorting",
+        "id": 87
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 88
+    },
+    {
+        "answer": "String, Math",
+        "id": 89
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 90
+    },
+    {
+        "answer": "String, Search",
+        "id": 91
+    },
+    {
+        "answer": "Math, Array",
+        "id": 92
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 93
+    },
+    {
+        "answer": "Array, Math",
+        "id": 94
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 95
+    },
+    {
+        "answer": "Math, Array",
+        "id": 96
+    },
+    {
+        "answer": "Math",
+        "id": 97
+    },
+    {
+        "answer": "String, Array",
+        "id": 98
+    },
+    {
+        "answer": "String, Math",
+        "id": 99
+    },
+    {
+        "answer": "Array, Math",
+        "id": 100
+    },
+    {
+        "answer": "String, Array",
+        "id": 101
+    },
+    {
+        "answer": "Math, Search",
+        "id": 102
+    },
+    {
+        "answer": "Math, String",
+        "id": 103
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 104
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 105
+    },
+    {
+        "answer": "Array, Math",
+        "id": 106
+    },
+    {
+        "answer": "Math, Search",
+        "id": 107
+    },
+    {
+        "answer": "Array, Math",
+        "id": 108
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 109
+    },
+    {
+        "answer": "Array, String",
+        "id": 110
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 111
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 112
+    },
+    {
+        "answer": "String, Array",
+        "id": 113
+    },
+    {
+        "answer": "Array, Math",
+        "id": 114
+    },
+    {
+        "answer": "Array, Math",
+        "id": 115
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 116
+    },
+    {
+        "answer": "String, Array",
+        "id": 117
+    },
+    {
+        "answer": "String, Search",
+        "id": 118
+    },
+    {
+        "answer": "String, Stack",
+        "id": 119
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 120
+    },
+    {
+        "answer": "Array, Math",
+        "id": 121
+    },
+    {
+        "answer": "Array, Math",
+        "id": 122
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 123
+    },
+    {
+        "answer": "String, Math",
+        "id": 124
+    },
+    {
+        "answer": "String, Math",
+        "id": 125
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 126
+    },
+    {
+        "answer": "Math, Array",
+        "id": 127
+    },
+    {
+        "answer": "Array, Math",
+        "id": 128
+    },
+    {
+        "answer": "Array, Search, Matrix",
+        "id": 129
+    },
+    {
+        "answer": "Math, Array",
+        "id": 130
+    },
+    {
+        "answer": "Math, String",
+        "id": 131
+    },
+    {
+        "answer": "String, Stack",
+        "id": 132
+    },
+    {
+        "answer": "Array, Math",
+        "id": 133
+    },
+    {
+        "answer": "String, Search",
+        "id": 134
+    },
+    {
+        "answer": "Array, Search",
+        "id": 135
+    },
+    {
+        "answer": "Array, Search",
+        "id": 136
+    },
+    {
+        "answer": "String, Math",
+        "id": 137
+    },
+    {
+        "answer": "Math",
+        "id": 138
+    },
+    {
+        "answer": "Math, Array",
+        "id": 139
+    },
+    {
+        "answer": "String, Array",
+        "id": 140
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 141
+    },
+    {
+        "answer": "Array, Math",
+        "id": 142
+    },
+    {
+        "answer": "String, Math",
+        "id": 143
+    },
+    {
+        "answer": "String, Math",
+        "id": 144
+    },
+    {
+        "answer": "Array, Sorting",
+        "id": 145
+    },
+    {
+        "answer": "Array, Math",
+        "id": 146
+    },
+    {
+        "answer": "Array, Math",
+        "id": 147
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 148
+    },
+    {
+        "answer": "String, Sorting",
+        "id": 149
+    },
+    {
+        "answer": "Math, Search",
+        "id": 150
+    },
+    {
+        "answer": "Array, Math",
+        "id": 151
+    },
+    {
+        "answer": "Array, Math",
+        "id": 152
+    },
+    {
+        "answer": "String, Array, Sorting",
+        "id": 153
+    },
+    {
+        "answer": "String, Search",
+        "id": 154
+    },
+    {
+        "answer": "String, Math",
+        "id": 155
+    },
+    {
+        "answer": "String, Math",
+        "id": 156
+    },
+    {
+        "answer": "Math, Sorting",
+        "id": 157
+    },
+    {
+        "answer": "String, Array",
+        "id": 158
+    },
+    {
+        "answer": "Array, Math",
+        "id": 159
+    },
+    {
+        "answer": "String, Array, Math",
+        "id": 160
+    },
+    {
+        "answer": "String, Array",
+        "id": 161
+    },
+    {
+        "answer": "String, Hash table",
+        "id": 162
+    },
+    {
+        "answer": "Array, Math",
+        "id": 163
+    }
+]

dividing_into_different_subsets/7/QS/line_counts_QS.csv

@@ -0,0 +1,13 @@
+Model,line_subset_1,line_subset_2,line_subset_3,line_subset_4,line_subset_5,line_subset_6,line_subset_7
+CodeFuse-DeepSeek-33b,82.61,73.91,86.96,78.26,69.57,68.0,79.17
+Nxcode-CQ-7B,95.43,85.65,89.57,87.39,95.22,84.0,74.58
+codegemma-2b,53.7,40.22,25.43,19.57,20.0,18.6,13.75
+codegemma-7b,68.26,43.48,36.09,41.09,32.83,31.0,27.08
+codegemma-7b-it,79.57,57.61,54.35,47.61,51.52,45.0,37.71
+deepseek-coder-1.3b-base,57.17,41.3,30.43,30.65,31.3,17.2,20.0
+deepseek-coder-6.7b-base,78.48,50.65,52.39,43.26,38.04,33.2,25.63
+deepseek_coder-6.7b-instruct,81.74,82.39,84.13,66.3,67.83,66.6,53.33
+deepseek_coder_33b-base,76.96,66.74,51.96,56.96,44.13,37.8,36.67
+deepseek_coder_33b-instruct,87.39,78.26,69.35,68.04,61.3,49.6,51.04
+codeqwen1.5-7b,68.26,53.04,55.43,54.13,46.52,47.6,35.62
+new,79.57,57.61,54.35,47.61,51.52,45.0,37.71

dividing_into_different_subsets/7/QS/token_counts_QS.csv

@@ -0,0 +1,13 @@
+Model,token_subset_1,token_subset_2,token_subset_3,token_subset_4,token_subset_5,token_subset_6,token_subset_7
+CodeFuse-DeepSeek-33b,69.57,82.61,78.26,91.3,82.61,72.0,62.5
+Nxcode-CQ-7B,94.13,92.17,85.22,84.13,91.74,87.0,77.08
+codegemma-2b,40.65,40.87,49.78,22.17,15.43,21.4,1.25
+codegemma-7b,59.13,48.26,56.96,34.78,29.35,33.8,17.71
+codegemma-7b-it,72.61,65.65,70.65,48.04,36.52,43.8,36.25
+deepseek-coder-1.3b-base,52.39,46.96,53.48,31.3,16.3,22.2,5.62
+deepseek-coder-6.7b-base,71.74,61.96,63.26,35.43,38.7,34.8,16.04
+deepseek_coder-6.7b-instruct,82.83,87.83,74.78,61.52,74.13,74.2,46.67
+deepseek_coder_33b-base,71.3,63.91,70.87,50.65,45.43,43.6,25.42
+deepseek_coder_33b-instruct,83.26,78.91,77.39,63.91,60.87,60.6,39.58
+codeqwen1.5-7b,66.09,66.09,64.78,38.7,50.43,39.8,35.42
+new,72.61,65.65,70.65,48.04,36.52,43.8,36.25

dividing_into_different_subsets/8/QS/CC_QS.csv

@@ -0,0 +1,13 @@
+Model,CC_subset_1,CC_subset_2,CC_subset_3,CC_subset_4,CC_subset_5,CC_subset_6,CC_subset_7,CC_subset_8
+CodeFuse-DeepSeek-33b,75.0,95.0,75.0,78.95,72.73,85.71,80.95,52.38
+Nxcode-CQ-7B,90.0,88.5,82.25,81.84,95.0,86.19,95.0,78.57
+codegemma-2b,49.75,47.0,18.0,30.53,12.95,37.38,21.67,2.38
+codegemma-7b,58.0,63.0,36.0,42.37,30.23,50.95,26.43,13.81
+codegemma-7b-it,60.5,68.5,53.75,58.95,42.05,61.19,51.19,31.19
+deepseek-coder-1.3b-base,56.5,56.25,22.75,35.53,20.91,40.95,20.71,7.62
+deepseek-coder-6.7b-base,63.75,72.0,36.0,47.63,40.45,58.57,37.14,11.9
+deepseek_coder-6.7b-instruct,84.75,75.75,67.0,70.0,67.5,82.38,74.29,51.67
+deepseek_coder_33b-base,71.5,63.25,47.5,59.74,44.77,61.43,47.38,28.57
+deepseek_coder_33b-instruct,77.75,74.75,62.0,67.63,57.95,81.67,61.19,47.38
+codeqwen1.5-7b,68.75,62.25,47.0,56.32,41.14,63.57,45.24,28.81
+new,60.5,68.5,53.75,58.95,42.05,61.19,51.19,31.19