Update app.py

app.py

@@ -2,59 +2,95 @@ import gradio as gr
 import pandas as pd
 import matplotlib.pyplot as plt
 
+import pandas as pd
+import matplotlib.pyplot as plt
+import gradio as gr
+import tempfile
+import warnings
+
+warnings.filterwarnings(action='ignore', category=UserWarning)
+
+# 设置中文字体和编码
+plt.rcParams['font.sans-serif'] = ['Arial Unicode MS']  # 选择合适的中文字体，这里使用宋体
+plt.rcParams['axes.unicode_minus'] = False  # 设置正常显示字符
+
 def process_file(file):
-    # 读取CSV文件并创建DataFrame
-    df = pd.read_csv(file.name)
+    # 读取CSV或Excel文件并创建DataFrame
+    if file.name.endswith('.csv'):
+        df = pd.read_csv(file.name)
+    elif file.name.endswith('.xlsx') or file.name.endswith('.xls'):
+        df = pd.read_excel(file.name)
+    else:
+        return "不支持的数据文件格式。"
+    
     columns = df.columns.tolist()
-    print("文件已上传，表头为：", columns)  # 调试信息
+    feature_columns = columns[:-1]
+    last_column = [columns[-1]]
     # 返回前5行数据，更新下拉列表选项，并使其他控件可见
-    return (df.head(),             
-            gr.update(choices=columns, visible=True), 
-            gr.update(choices=columns, visible=True), 
+    return (gr.update(choices=feature_columns, value=feature_columns[0], visible=True), 
+            gr.update(choices=last_column, value=last_column[-1], visible=True), 
+            gr.update(visible=True),
             gr.update(visible=True),
-            gr.update(visible=True))
+            df.head()
+            )
 
 def update_slider(choice):
-    print("选择框的值：", choice)  # 调试信息
     # 更新数轴控件的可见性
     return gr.update(visible=choice == "是")
 
-def generate_output(file, col1, col2, choice, number):
+def generate_output(file, column1, column2, choice, bins):
     df = pd.read_csv(file.name)
-    filtered_data = df[[col1, col2]].dropna()
+    data_x = df[column1]
+    data_y = df[column2]
 
-    plt.figure(figsize=(10, 6))
-    plt.scatter(filtered_data[col1], filtered_data[col2])
-    plt.xlabel(col1)
-    plt.ylabel(col2)
-    plt.title(f'Scatter plot of {col1} vs {col2}')
+    # 自动判断column1的数据类型
+    if choice == "是":
+        # 如果是连续值，则进行分组
+        data_x = pd.qcut(data_x, q=bins, duplicates='drop')
+    else:
+        # 如果是离散值，则直接使用
+        pass
     
+    # 统计每个身高分段中不同心血管疾病类别的数量
+    counts = pd.crosstab(data_x, data_y)
+    # 绘制分段柱形图
+    counts.plot(kind='bar')
+    # 设置画布大小
+    plt.figure(figsize=(bins*2, 6))
+    # 设置 x 轴刻度标签横向显示
+    plt.xticks(rotation=0)
+    plt.xlabel(column1, fontsize=12)
+    plt.ylabel(column2, fontsize=12)
+    # plt.legend(['不患病', '患病'])
+    plt.title(f'{column1}与{column2}的关系', fontsize=14)
+    # plt.show()   
+
     image_path = 'output.png'
     plt.savefig(image_path)
-    plt.close()
-
-    return filtered_data.head(), image_path
+    # plt.close()
 
+    return df.head(), gr.update(visible=True), image_path, gr.update(visible=True)
+    
 with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
-            file_input = gr.File(label="上传CSV文件", file_types=["csv"])
+            file_input = gr.File(label="上传表格文件（支持CSV、XLS、XLSX等格式", file_types=["csv", "xls", "xlsx"])
             col1_dropdown = gr.Dropdown(label="选择列1", visible=False)
             col2_dropdown = gr.Dropdown(label="选择列2", visible=False)
             choice_radio = gr.Radio(["是", "否"], label="是否选择", visible=False)
-            slider = gr.Slider(minimum=2, maximum=7, step=1, label="选择数字", visible=False)
+            slider = gr.Slider(minimum=3, maximum=7, step=1, label="选择数字", visible=False, value=4)
             submit_button = gr.Button("提交")
         with gr.Column():
             df_display = gr.Dataframe(visible=False)
             output_image = gr.Image(visible=False)
 
     # 文件上传后调用 process_file 函数
-    file_input.upload(process_file, inputs=file_input, outputs=[col1_dropdown, col2_dropdown, choice_radio, df_display])
+    file_input.upload(process_file, inputs=file_input, outputs=[col1_dropdown, col2_dropdown, choice_radio, df_display, df_display])
     
     # 选择框值改变时调用 update_slider 函数
     choice_radio.change(update_slider, inputs=choice_radio, outputs=slider)
     
     # 点击提交按钮时调用 generate_output 函数
-    submit_button.click(generate_output, inputs=[file_input, col1_dropdown, col2_dropdown, choice_radio, slider], outputs=[df_display, output_image])
+    submit_button.click(generate_output, inputs=[file_input, col1_dropdown, col2_dropdown, choice_radio, slider], outputs=[df_display, df_display, output_image, output_image])
 
-demo.launch()
+demo.launch(share=True)