Update app.py

app.py

@@ -1,5 +1,7 @@
 import gradio as gr
 import pandas as pd
+from slider import create_subset_ratios_tab
+from change_output import change_file
 import requests
 import os
 import shutil
@@ -7,41 +9,84 @@ import json
 import pandas as pd
 import subprocess
 import plotly.express as px
-def on_confirm(dataset_radio, num_parts_dropdown, token_counts_radio, line_counts_radio, cyclomatic_complexity_radio, problem_type_radio):
-   
+def on_confirm(dataset_radio, num_parts_dropdown, token_counts_radio, line_counts_radio, cyclomatic_complexity_radio, problem_type_checkbox):
+    # 根据用户选择的参数构建文件路径
     num_parts = num_parts_dropdown
-    token_counts_split = token_counts_radio
-    line_counts_split = line_counts_radio
-    cyclomatic_complexity_split = cyclomatic_complexity_radio
+    # token_counts_split = token_counts_radio
+    # line_counts_split = line_counts_radio
+    # cyclomatic_complexity_split = cyclomatic_complexity_radio
 
+
+    # 读取数据
     dataframes = []
-    if token_counts_split=="Equal Frequency Partitioning":
-        token_counts_df = pd.read_csv(f"/home/user/app/dividing_into_different_subsets/{num_parts}/QS/token_counts_QS.csv")
+    if token_counts_radio=="Equal Frequency Partitioning":#等频划分，每个子集数据点的数量基本一致
+        token_counts_df = pd.read_csv(f"E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num_parts}/QS/token_counts_QS.csv")
         dataframes.append(token_counts_df)
-
-    if line_counts_split=="Equal Frequency Partitioning":
-        line_counts_df = pd.read_csv(f"/home/user/app/dividing_into_different_subsets/{num_parts}/QS/line_counts_QS.csv")
+    if token_counts_radio=="Equal Interval Partitioning":
+        token_counts_df = pd.read_csv(f"E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num_parts}/EI/token_counts_EI.csv")
+        dataframes.append(token_counts_df)
+    if line_counts_radio=="Equal Frequency Partitioning":#等频划分，每个子集数据点的数量基本一致
+        line_counts_df = pd.read_csv(f"E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num_parts}/QS/line_counts_QS.csv")
         dataframes.append(line_counts_df)
+    if token_counts_radio=="Equal Interval Partitioning":
+        line_counts_df = pd.read_csv(f"E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num_parts}/EI/line_counts_EI.csv")
+        dataframes.append(line_counts_df)
+    if cyclomatic_complexity_radio=="Equal Frequency Partitioning":#等频划分，每个子集数据点的数量基本一致
+        CC_df = pd.read_csv(f"E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num_parts}/QS/CC_QS.csv")
+        dataframes.append(CC_df)
+    if token_counts_radio=="Equal Interval Partitioning":
+        CC_df = pd.read_csv(f"E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num_parts}/EI/CC_EI.csv")
+        dataframes.append(CC_df)
 
-    if cyclomatic_complexity_split=="Equal Frequency Partitioning":
-        cyclomatic_complexity_df = pd.read_csv(f"/home/user/app/dividing_into_different_subsets/{num_parts}/QS/CC_QS.csv")
-        dataframes.append(cyclomatic_complexity_df)
-    if dataset_radio=="MBPP":
-        dataframes="There are some minor bugs in the section showing MBPP data, which we are working on as soon as possible"
-        
-    
+
+
+    #以下改为直接从一个划分文件中读取即可
+    if problem_type_checkbox:
+        problem_type_df = pd.read_csv("E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/cata_result.csv")
+        dataframes.append(problem_type_df)
+
+    # 如果所有三个radio都有value，将三个文件中的所有行拼接
     if len(dataframes) > 0:
         combined_df = dataframes[0]
         for df in dataframes[1:]:
             combined_df = pd.merge(combined_df, df, left_index=True, right_index=True, suffixes=('', '_y'))
-            combined_df = combined_df.loc[:, ~combined_df.columns.str.endswith('_y')] 
+            combined_df = combined_df.loc[:, ~combined_df.columns.str.endswith('_y')]  # 去除重复的列
         return combined_df
     else:
         return pd.DataFrame()
 
 
 
-
+# 定义一个函数来返回数据
+# def show_data(line_counts, token_counts, cyclomatic_complexity, problem_type, show_high, show_medium, show_low):
+#     columns = ["Model"]
+#
+#     if token_counts:
+#         if show_high:
+#             columns.append("Token Counts.I")
+#
+#         if show_medium:
+#             columns.append("Token Counts.II")
+#         if show_low:
+#             columns.append("Token Counts.III")
+#     if line_counts:
+#         if show_high:
+#             columns.append("Line Counts.I")
+#         if show_medium:
+#             columns.append("Line Counts.II")
+#         if show_low:
+#             columns.append("Line Counts.III")
+#     if cyclomatic_complexity:
+#         if show_high:
+#             columns.append("Cyclomatic Complexity.I")
+#         if show_medium:
+#             columns.append("Cyclomatic Complexity.II")
+#         if show_low:
+#             columns.append("Cyclomatic Complexity.III")
+#     if problem_type:
+#         columns.extend(["Problem Type_String", "Problem Type_Math", "Problem Type_Array"])
+#     return data[columns]
+#用于更新数据文件的部分
 def execute_specified_python_files(directory_list, file_list):
     for directory in directory_list:
         for py_file in file_list:
@@ -49,42 +94,92 @@ def execute_specified_python_files(directory_list, file_list):
             if os.path.isfile(file_path) and py_file.endswith('.py'):
                 print(f"Executing {file_path}...")
                 try:
+                    # 使用subprocess执行Python文件
                     subprocess.run(['python', file_path], check=True)
                     print(f"{file_path} executed successfully.")
                 except subprocess.CalledProcessError as e:
                     print(f"Error executing {file_path}: {e}")
             else:
                 print(f"File {file_path} does not exist or is not a Python file.")
-
-
+# 定义一个函数来生成 CSS 样式
+def generate_css(line_counts, token_counts, cyclomatic_complexity, problem_type, show_high, show_medium, show_low):
+    css = """
+    #dataframe th {
+        background-color: #f2f2f2
+        
+    }
+    """
+    colors = ["#e6f7ff", "#ffeecc", "#e6ffe6", "#ffe6e6"]
+    categories = [line_counts, token_counts, cyclomatic_complexity]
+    category_index = 0
+    column_index = 1
+
+    for category in categories:
+        if category:
+            if show_high:
+                css += f"#dataframe td:nth-child({column_index + 1}) {{ background-color: {colors[category_index]}; }}\n"
+                column_index += 1
+            if show_medium:
+                css += f"#dataframe td:nth-child({column_index + 1}) {{ background-color: {colors[category_index]}; }}\n"
+                column_index += 1
+            if show_low:
+                css += f"#dataframe td:nth-child({column_index + 1}) {{ background-color: {colors[category_index]}; }}\n"
+                column_index += 1
+        category_index += 1
+
+    # 为 Problem Type 相关的三个子列设置固定颜色
+    if problem_type:
+        problem_type_color = "#d4f0fc"  # 你可以选择任何你喜欢的颜色
+        css += f"#dataframe td:nth-child({column_index + 1}) {{ background-color: {problem_type_color}; }}\n"
+        css += f"#dataframe td:nth-child({column_index + 2}) {{ background-color: {problem_type_color}; }}\n"
+        css += f"#dataframe td:nth-child({column_index + 3}) {{ background-color: {problem_type_color}; }}\n"
+
+    # 隐藏 "data" 标识
+    css += """
+    .gradio-container .dataframe-container::before {
+        content: none !important;
+    }
+    """
+
+    return css
+# def update_dataframe(line_counts, token_counts, cyclomatic_complexity, problem_type, show_high, show_medium,
+#                      show_low):
+#     df = show_data(line_counts, token_counts, cyclomatic_complexity, problem_type, show_high, show_medium, show_low)
+#     css = generate_css(line_counts, token_counts, cyclomatic_complexity, problem_type, show_high, show_medium,
+#                        show_low)
+#     return gr.update(value=df), gr.update(value=f"<style>{css}</style>")
 
 
 def generate_file(file_obj, user_string, user_number,dataset_choice):
     tmpdir = 'tmpdir'
 
-    
+    print('临时文件夹地址：{}'.format(tmpdir))
     FilePath = file_obj.name
+    print('上传文件的地址：{}'.format(file_obj.name))  # 输出上传后的文件在gradio中保存的绝对地址
 
+    # 将文件复制到临时目录中
     shutil.copy(file_obj.name, tmpdir)
 
-  
+    # 获取上传Gradio的文件名称
     FileName = os.path.basename(file_obj.name)
 
     print(FilePath)
-   
+    # 获取拷贝在临时目录的新的文件地址
+
+    # 打开复制到新路径后的文件
     with open(FilePath, 'r', encoding="utf-8") as file_obj:
-       
+        # 在本地电脑打开一个新的文件，并且将上传文件内容写入到新文件
         outputPath = os.path.join('F:/Desktop/test', FileName)
         data = json.load(file_obj)
         print("data:", data)
 
-        
+        # 将数据写入新的 JSON 文件
         with open(outputPath, 'w', encoding="utf-8") as w:
             json.dump(data, w, ensure_ascii=False, indent=4)
 
-       
-        file_content = json.dumps(data)  
-        url = "http://localhost:6222/submit" 
+        # 读取文件内容并上传到服务器
+        file_content = json.dumps(data)  # 将数据转换为 JSON 字符串
+        url = "http://localhost:6222/submit"  # 替换为你的后端服务器地址
         files = {'file': (FileName, file_content, 'application/json')}
         payload = {
             'user_string': user_string,
@@ -94,19 +189,21 @@ def generate_file(file_obj, user_string, user_number,dataset_choice):
 
         response = requests.post(url, files=files, data=payload)
         print(response)
-        
+        #返回服务器处理后的文件
         if response.status_code == 200:
-            
+            # 获取服务器返回的 JSON 数据
             output_data = response.json()
 
-            
-            output_file_path = os.path.join('E:/python-testn/pythonProject3/hh_1/evaluate_result', 'new-model.json')
+            # 保存 JSON 数据到本地
+            output_file_path = os.path.join('E:/python-testn/pythonProject3/hh_2/evaluate_result', 'new-model.json')
             with open(output_file_path, 'w', encoding="utf-8") as f:
                 json.dump(output_data, f, ensure_ascii=False, indent=4)
 
             print(f"File saved at: {output_file_path}")
-            directory_list = ['/path/to/directory1', '/path/to/directory2'] 
-            file_list = ['file1.py', 'file2.py', 'file3.py'] 
+
+            # 调用更新数据文件的函数
+            directory_list = ['E:\python-testn\pythonProject3\hh_2\dividing_into_different_subsets\5\QS']  # 替换为你的目录路径列表
+            file_list = ["calculate_humaneval_result.py"]  # 替换为你想要执行的Python文件列表
 
             execute_specified_python_files(directory_list, file_list)
 
@@ -114,53 +211,70 @@ def generate_file(file_obj, user_string, user_number,dataset_choice):
         else:
             return {"status": "error", "message": response.text}
 
+        # 返回服务器响应
     return {"status": "success", "message": response.text}
 
 def update_radio_options(token_counts, line_counts, cyclomatic_complexity, problem_type):
     options = []
     if token_counts:
-        options.append("Token Counts in Prompt")
+        options.append("The Number of Tokens in Problem Descriptions")
     if line_counts:
-        options.append("Line Counts in Prompt")
+        options.append("The Number of Lines in Problem Descriptions")
     if cyclomatic_complexity:
-        options.append("Cyclomatic Complexity")
+        options.append("The Complexity of Reference Code")
     if problem_type:
         options.append("Problem Type")
 
     return gr.update(choices=options)
 
 def plot_csv(radio,num):
-    if radio=="Line Counts in Prompt":
-        radio_choice="line_counts"
-        file_path = f'/home/user/app/dividing_into_different_subsets/{num}/QS/{radio_choice}_QS.csv'
-    elif radio=="Token Counts in Prompt":
+    # 读取本地的CSV文件
+    #token_counts_df = pd.read_csv(f"{num_parts}/QS/token_counts_QS.csv")
+    if radio=="The Number of Tokens in Problem Descriptions":
         radio_choice="token_counts"
-        file_path = f'/home/user/app/dividing_into_different_subsets/{num}/QS/{radio_choice}_QS.csv'
-    elif radio=="Cyclomatic Complexity":
+        file_path = f'E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num}/QS/{radio_choice}_QS.csv'
+    elif radio=="The Number of Lines in Problem Descriptions":
+        radio_choice="line_counts"
+        file_path = f'E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num}/QS/{radio_choice}_QS.csv'
+    elif radio=="The Complexity of Reference Code":
         radio_choice="CC"
-        file_path = f'/home/user/app/dividing_into_different_subsets/{num}/QS/{radio_choice}_QS.csv'
+        file_path = f'E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/{num}/QS/{radio_choice}_QS.csv'
     elif radio=="Problem Type":
         radio_choice="problem_type"
-        file_path = f'/home/user/app/dividing_into_different_subsets/cata_result.csv'
-    
+        file_path = f'E:/python-testn/pythonProject3/hh_2/dividing_into_different_subsets/cata_result.csv'
+    print("test!")
+
+    # file_path="E:/python-testn/pythonProject3/hh_1/dividing_into_different_subsets/3/QS/CC_QS.csv"
     df = pd.read_csv(file_path)
-   
+    # 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
 
+
+
+    # 创建 Gradio 界面
+import gradio as gr
+
 with gr.Blocks() as iface:
     gr.HTML("""
                <style>
+                   # body {
+                   #     max-width: 50%; /* 设置最大宽度为50% */
+                   #     margin: 0 auto; /* 将内容居中 */
+                   # }
                    .title {
                        text-align: center;
                        font-size: 3em;
@@ -173,7 +287,7 @@ with gr.Blocks() as iface:
                        margin-bottom: 1em;
                    }
                </style>
-               <div class="title">📊 Demo-Leaderboard 📊</div>
+               
            """)
 
     with gr.Tabs() as tabs:
@@ -184,43 +298,48 @@ with gr.Blocks() as iface:
                         with gr.Column():
                             dataset_radio = gr.Radio(["HumanEval", "MBPP"], label="Select Dataset ")
 
-                    with gr.Row():
-                        custom_css = """  
-                            <style>  
-                                .markdown-class {  
-                                    font-family: 'Helvetica', sans-serif;
-                                    font-size: 17px; 
-                                    font-weight: bold;  
-                                    color: #333; 
-                                }  
-                            </style>  
-                            """
-
-                        with gr.Column():
-                            gr.Markdown(
-                                f"{custom_css}<div class='markdown-class'> Choose Classification Perspective </div>")
+            with gr.Row():
+                custom_css = """  
+                    <style>  
+                        .markdown-class {  
+                            font-family: 'Helvetica', sans-serif;
+                            font-size: 20px; 
+                            font-weight: bold;  
+                            color: #333; 
+                        }  
+                    </style>  
+                    """
 
-                            token_counts_checkbox = gr.Checkbox(label="Token Counts in Prompt ")
-                            line_counts_checkbox = gr.Checkbox(label="Line Counts in Prompt ")
-                            cyclomatic_complexity_checkbox = gr.Checkbox(label="Cyclomatic Complexity ")
-                            problem_type_checkbox = gr.Checkbox(label="Problem Type ")
+                with gr.Column():
+                    gr.Markdown(
+                        f"{custom_css}<div class='markdown-class'> Choose Division Perspective </div>")
+
+                    token_counts_checkbox = gr.Checkbox(label="I-The Number of Tokens in Problem Descriptions")
+                    line_counts_checkbox = gr.Checkbox(label="II-The Number of Lines in Problem Descriptions")
+                    cyclomatic_complexity_checkbox = gr.Checkbox(label="III-The Complexity of Reference Code")
+                    problem_type_checkbox = gr.Checkbox(label="IV-Problem Types ")
+                css_code = """  
+                    .dropdown-container {  
+                        display: none;  
+                    }  
+                """
 
-                        with gr.Column():
-                            gr.Markdown("<div class='markdown-class'>Choose Subsets </div>")
-                            num_parts_dropdown = gr.Dropdown(choices=[3, 4, 5, 6, 7, 8], label="Number of Subsets")
+                with gr.Column():
+                    # gr.Markdown("<div class='markdown-class'>Choose Subsets </div>")
+                    num_parts_dropdown = gr.Dropdown(choices=[3, 4, 5, 6, 7, 8], label="Choose the Number of Subsets")
 
             with gr.Row():
                 with gr.Column():
                     token_counts_radio = gr.Radio(
-                        ["Equal Frequency Partitioning", "Equal Interval Partitioning"], label="Select Dataset",
+                        ["Equal Frequency Partitioning", "Equal Interval Partitioning"], label="Choose the Division Method for Perspective-I",
                         visible=False)
                 with gr.Column():
                     line_counts_radio = gr.Radio(
-                        ["Equal Frequency Partitioning", "Equal Interval Partitioning"], label="Select Dataset",
+                        ["Equal Frequency Partitioning", "Equal Interval Partitioning"], label="Choose the Division Method for Perspective-II",
                         visible=False)
                 with gr.Column():
                     cyclomatic_complexity_radio = gr.Radio(
-                        ["Equal Frequency Partitioning", "Equal Interval Partitioning"], label="Select Dataset",
+                        ["Equal Frequency Partitioning", "Equal Interval Partitioning"], label="Choose the Division Method for Perspective-III",
                         visible=False)
 
             token_counts_checkbox.change(fn=lambda x: toggle_radio(x, token_counts_radio),
@@ -232,16 +351,16 @@ with gr.Blocks() as iface:
                                                   outputs=cyclomatic_complexity_radio)
 
             with gr.Tabs() as inner_tabs:
-                with gr.TabItem("Leaderboard"):
+                with gr.TabItem("Ranking Table"):
                     dataframe_output = gr.Dataframe(elem_id="dataframe")
                     css_output = gr.HTML()
                     confirm_button = gr.Button("Confirm ")
                     confirm_button.click(fn=on_confirm, inputs=[dataset_radio, num_parts_dropdown, token_counts_radio,
-                                                                line_counts_radio, cyclomatic_complexity_radio],
+                                                                line_counts_radio, cyclomatic_complexity_radio,problem_type_checkbox],
                                          outputs=dataframe_output)
 
                 with gr.TabItem("Line chart"):
-                    select_radio = gr.Radio(choices=[])
+                    select_radio = gr.Radio(choices=[],label="Select One Perpective")
                     checkboxes = [token_counts_checkbox, line_counts_checkbox, cyclomatic_complexity_checkbox,
                                   problem_type_checkbox]
                     for checkbox in checkboxes:
@@ -249,13 +368,13 @@ with gr.Blocks() as iface:
                     select_radio.change(fn=plot_csv, inputs=[select_radio, num_parts_dropdown],
                                         outputs=gr.Plot(label="Line Plot "))
 
-        with gr.TabItem("Upload"):
+        with gr.TabItem("Upload Inference File"):
             gr.Markdown("Upload a JSON file")
             with gr.Row():
                 with gr.Column():
                     string_input = gr.Textbox(label="Enter the Model Name")
                     number_input = gr.Number(label="Select the Number of Samples")
-                    dataset_choice = gr.Dropdown(label="Select Dataset", choices=["humaneval", "mbpp"])
+                    dataset_choice = gr.Dropdown(label="Select Dataset", choices=["HumanEval", "MBPP"])
                 with gr.Column():
                     file_input = gr.File(label="Upload Generation Result in JSON file")
                     upload_button = gr.Button("Confirm and Upload")
@@ -266,26 +385,30 @@ with gr.Blocks() as iface:
                                 outputs=json_output)
 
 
-
+    # 定义事件处理函数
     def toggle_radio(checkbox, radio):
         return gr.update(visible=checkbox)
 
 
-
     css = """  
         #scale1 {  
     border: 1px solid rgba(0, 0, 0, 0.2); 
     padding: 10px;  
-    border-radius: 8px;   
-    background-color: #f9f9f9;  
-    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);  
+    border-radius: 8px; 
+    background-color: #f9f9f9; 
+    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1); 
 }  
         }  
         """
     gr.HTML(f"<style>{css}</style>")
 
 
+    # 初始化数据表格
+    # initial_df = show_data(False, False, False, False, False, False, False)
+    # initial_css = generate_css(False, False, False, False, True, False, False)
+    # dataframe_output.value = initial_df
+    # css_output.value = f"<style>{initial_css}</style>"
 
 
-
+# 启动界面
 iface.launch()