初步结果

pages/page1.py

@@ -15,18 +15,49 @@ from utils.hypergraph_drawer import draw_hypergraph
 def main():
     st.title("NIPS 论文数据集高斯混合聚类分析")
 
+    # 自动播放
+    slider_max = 10
+    if 'play_state' not in st.session_state:
+        st.session_state.play_state = False
+    if 'iteration' not in st.session_state:
+        st.session_state.iteration = 0
+    # 定义回调函数来切换播放状态
+    def toggle_play():
+        if not st.session_state.play_state and st.session_state.iteration == slider_max:
+            st.session_state.iteration = 0 # 重置迭代次数
+        st.session_state.play_state = not st.session_state.play_state
+
+    # 创建播放/暂停按钮
+    if st.session_state.play_state:
+        button_label = "暂停"
+    else:
+        button_label = "播放"
+    st.button(button_label, on_click=toggle_play, key="play_button")
+    # 播放速度
+    speed = st.slider("播放速度", min_value=0.1, max_value=2.0, value=1.0, step=0.1, key="speed_slider")
+    # 主页面布局
+
+    # 显示迭代次数滑条
+    iteration = st.slider("迭代步骤", min_value=1, max_value=slider_max, 
+                            value=st.session_state.iteration, step=1, 
+                            key="iteration_slider")
+    # st.write(f"当前迭代次数: {iteration}")
+    # print(st.session_state.iteration)
+
+
+    # 动态限制采样数量的最大值
+    df = load_data()
+
+    
     # 使用 sidebar 控制参数
     with st.sidebar:
         st.header("控制面板")
-        autoplay = st.button("自动播放")
-        if autoplay:
-            for i in range(1, 11):
-                with st.spinner(f"迭代 {i}"):
-                    time.sleep(1)
-                    st.session_state.iteration = i
-            st.session_state.autoplay = False
-            st.experimental_rerun()
+        max_samples = len(df)
+        num_samples = st.slider("选择采样论文数量", min_value=1, 
+                                max_value=min(100, max_samples), value=min(10, max_samples), step=1)
+
 
+        
         # 添加复选框选择显示 paper 的属性
         display_attribute = st.selectbox(
             "选择显示 paper 的属性",
@@ -39,37 +70,22 @@ def main():
         )
         # Top K Clusters
         if display_option == "Top K Clusters":
-            top_k = st.slider("选择 K 值", min_value=1, max_value=10, value=3, step=1)
+            max_k = 5
+            top_k = st.slider("选择 K 值", min_value=1, max_value=max_k, value=3, step=1)
             top_p = None
         else:
             top_k = None
             top_p = st.slider("选择 P 值", min_value=0.0, max_value=1.0, value=0.5, step=0.01)
 
-    # 主页面布局
-    if 'autoplay' not in st.session_state:
-        st.session_state.autoplay = True
-
-    if 'iteration' not in st.session_state:
-        st.session_state.iteration = 1
+        # 处理数据
+        sampled_df, probabilities, paper_attributes = process_data(df, iteration, num_samples)
+        # print(display_attribute) # 字符串
+        hyperedges = build_hyperedges(probabilities, paper_attributes, display_attribute, top_k=top_k, top_p=top_p)
+        # print(hyperedges)
 
-    if st.session_state.autoplay:
-        # 隐藏迭代次数滑条
-        iteration = st.session_state.iteration
-    else:
-        # 显示迭代次数滑条
-        iteration = st.slider("选择迭代次数", min_value=1, max_value=10, value=st.session_state.iteration, step=1)
 
-    # 动态限制采样数量的最大值
-    df = load_data()
-    max_samples = len(df)
-    num_samples = st.slider("选择采样论文数量", min_value=1, max_value=min(100, max_samples), value=min(10, max_samples), step=1)
-
-    # 处理数据
-    sampled_df, probabilities, paper_attributes = process_data(df, iteration, num_samples)
-    # print(display_attribute) # 字符串
-    hyperedges = build_hyperedges(probabilities, paper_attributes, display_attribute, top_k=top_k, top_p=top_p)
-    # print(hyperedges)
 
+    
     # 并排展示超图和高斯混合分布
     col1, col2 = st.columns(2)
     with col1:
@@ -89,4 +105,34 @@ def main():
     # 增加第二种可视化方式
     st.header("论文评分分布")
     fig_bar = visualize_ratings(sampled_df)
-    st.plotly_chart(fig_bar, use_container_width=True)
+    st.plotly_chart(fig_bar, use_container_width=True)
+
+
+    
+    # 自动播放功能
+    # print(st.session_state.play_state)
+    if st.session_state.play_state:
+        # 使用空容器来显示进度
+        progress_container = st.empty()
+        
+        with st.spinner("正在播放..."):
+            if st.session_state.iteration < slider_max:
+                # 增加滑动条值
+                st.session_state.iteration += 1
+                st.write(f"当前迭代次数: {st.session_state.iteration}")
+                # print(st.session_state.iteration)
+                # 等待一小段时间模拟滑动过程
+                time.sleep(1/speed)  # 根据速度调整等待时间
+                # 使用rerun来更新页面
+                st.rerun()
+            else:
+                # 到达最大值时停止播放
+                st.session_state.play_state = False
+
+
+    
+if __name__ == "__main__":
+    # 设置页面布局
+    st.set_page_config(layout="wide")
+    # 运行主函数
+    main()

pages/test.py

@@ -0,0 +1,42 @@
+import streamlit as st
+import time
+
+# 初始化会话状态
+if "slider_value" not in st.session_state:
+    st.session_state.slider_value = 0
+if "play_state" not in st.session_state:
+    st.session_state.play_state = False
+
+# 定义回调函数
+def toggle_play():
+    st.session_state.play_state = not st.session_state.play_state
+    if st.session_state.play_state:
+        st.session_state.slider_value = st.session_state.slider
+
+# 创建播放/暂停按钮
+button_label = "暂停" if st.session_state.play_state else "播放"
+st.button(button_label, on_click=toggle_play)
+
+# 创建滑动条，使用key参数将其与会话状态关联
+slider_max = 10
+slider = st.slider("进度", 0, slider_max, st.session_state.slider_value, key="slider")
+
+# 显示当前值
+st.write(f"当前值: {slider}")
+
+# 如果处于播放状态，自动增加滑动条的值
+if st.session_state.play_state:
+    # 使用空容器来显示进度
+    progress_container = st.empty()
+    
+    with st.spinner("正在播放..."):
+        if st.session_state.slider_value < slider_max:
+            # 增加滑动条值
+            st.session_state.slider_value += 1
+            # 等待一小段时间模拟滑动过程
+            time.sleep(0.1)
+            # 使用rerun来更新页面
+            st.rerun()
+        else:
+            # 到达最大值时停止播放
+            st.session_state.play_state = False

requirements.txt

@@ -0,0 +1,12 @@
+numpy>=1.21.0
+pandas>=1.3.0
+plotly>=6.0.0
+scipy>=1.7.0
+torch>=1.9.0
+scikit-learn>=1.0.0
+ipython>=8.0.0
+ipywidgets>=7.0.0
+nbformat>=5.0.0
+sympy>=1.8
+git+https://github.com/2catycm/pykan.git
+matplotlib

utils/data_processor.py

@@ -42,7 +42,8 @@ def build_hyperedges(
     for idx, (prob, paper_attr) in enumerate(zip(probabilities, paper_attributes)):
         if display_attribute_name == "index":
             display_attribute = f"Paper {idx}"
-        display_attribute: str = paper_attr[display_attribute_name]
+        else:
+            display_attribute: str = paper_attr[display_attribute_name]
         if top_k is not None:
             selected_indices = np.argsort(prob)[-top_k:][::-1]
         else: