数据预处理后从 Streamlit Web 应用程序下载数据帧时出错

Question

所需的任务是在 Streamlit 上部署数据预处理 Web 应用程序，用户可以在其中上传原始数据帧并下载处理后的数据帧。我正在尝试下载已完成数据预处理（例如缺失值插补）的文件，但出现如下错误：

RuntimeError: Invalid binary data format: <class 'pandas.core.frame.DataFrame'>

我不知道如何解决这个问题。请帮助我，因为我是 python 和 StreamLit 的新手。代码是

import streamlit as st
import pandas as pd
import os
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
temp='\\temp.csv'
path=os.getcwd()
path=path+temp

def upload_csv(zxc):
    if zxc:
        df=pd.read_csv(zxc)
        st.dataframe(df)
        df.to_csv(path,index=False)
        return df
    

def upload_xlsx(zxc):
    if zxc:
        df=pd.read_excel(zxc)
        st.dataframe(df)
        df.to_csv(path,index=False)
        return df

def mvt_mean(df):
    new_df=df.fillna(df.mean())
    new_df=new_df.fillna(df.select_dtypes(include='object').mode().iloc[0])
    st.dataframe(new_df)
    return new_df


def mvt_median(df):
    new_df=df.fillna(df.median())
    new_df=new_df.fillna(df.select_dtypes(include='object').mode().iloc[0])
    st.dataframe(new_df)
    return new_df

def mvt_mode(df):
    new_df=df.fillna(df.select_dtypes(include='object').mode().iloc[0])
    st.dataframe(new_df)
    return new_df

def export_data():
    with open('temp.csv','r+') as f:
        #contents=csv.reader(f)
        df=pd.read_csv(path)
        result=mvt_mean(df)
        result.to_csv(index=False)
        st.sidebar.download_button(label='Download CSV',data=result,mime='text/csv',file_name='Download.csv')
        return



st.title('Hello Streamlit Front end for Python ')
option = st.sidebar.selectbox('DSA Application',('Data-PreProcessing', 'Data-Visualization', 'Machine-Learning'))
st.sidebar.write('You selected:', option)
if option=='Data-PreProcessing':
    format_options=['csv','xlsx']
    a=st.sidebar.radio('Choose the file type',format_options)
    if a=='csv':
        b=st.sidebar.file_uploader("Choose a file",type='csv')
        if b :
            if st.sidebar.checkbox('Upload File'):
                df=upload_csv(b)
                #if st.sidebar.checkbox('Proceed for missing value treatment'):
                opt=st.sidebar.radio('Impute Missing Value using',('Mean','Median','Mode'))
                st.sidebar.write('You selected',opt)
                if opt=='Mean':
                    mvt_mean(df)
                    
                    
                    export_data()
                elif opt=='Median':
                    mvt_median(df)
                    #st.sidebar.download_button(label='Download CSV',data=d,mime='text/csv',file_name='Download.csv')
                    export_data()
                elif opt=='Mode':
                    mvt_mode(df)
                    #st.sidebar.download_button(label='Download CSV',data=d,mime='text/csv',file_name='Download.csv')
                    export_data()
    #elif a=='xlsx':
        #a=st.sidebar.file_uploader("Choose a file",type='xlsx')
        #b=st.sidebar.button('Upload File')
        #if b:
            #df=upload_xlsx(a)
            #st.dataframe(df)
        


        

Answer 1

我和你有同样的错误。我通过以下方式解决了它：

data_as_csv= data_to_csv.to_csv(index=False).encode("utf-8")
st.download_button(
    "Download data as CSV", 
    data_as_csv, 
    "benchmark-tools.csv",
    "text/csv",
    key="download-tools-csv",
)